A Bioethical Computational Model for Integrating Relational Suffering into End-of-Life Clinical Decision-making

A Bioethical Computational Model for Integrating Relational Suffering into End-of-Life Clinical Decision-making | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article A Bioethical Computational Model for Integrating Relational Suffering into End-of-Life Clinical Decision-making ANDERSON DÍAZ PÉREZ This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7447403/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Background. End-of-life suffering in Latin America is a multidimensional phenomenon that includes physical, psychological, social, and spiritual domains, which remain insufficiently addressed within traditional biomedical models. Existing instruments fragment the experience, omit contextual variables (e.g., gender, inequities, regulation), and lack ethical justification for clinical decisions. Methods. We developed TEASUR (Ethical-Adaptive Framework of Relational Suffering), a Python-based prototype that calculates a Total Distress Index (TDI) using adaptive logarithmic logic and SHAP-based XAI. Structural modifiers such as gender, access to palliative care, and socioeconomic inequities were incorporated. Validation was performed exclusively on synthetic data (n = 300), with a representative subsample of 200 cases used for subgroup analyses. Monte Carlo simulations (n = 500) were conducted to assess stability under random perturbations. Results. We present TEASUR (Ethical Adaptive Framework of Relational Suffering), a Python-based system that quantifies multidimensional suffering and dynamically adjusts weightings using explainable artificial intelligence. Simulations with a synthetic cohort of 300 cases from five Latin American countries showed that TEASUR detected social and spiritual suffering with greater sensitivity than conventional scales. For subgroup comparisons, a representative subsample of 200 cases was analyzed. When the Total Distress Index (TDI) exceeded 7.0, the system activated narrative, spiritual, and community interventions, which reduced suffering below critical thresholds and prevented disproportionate measures such as immediate palliative sedation. Monte Carlo simulations (n=500) demonstrated high stability of the TDI under random perturbations. The adaptive logarithmic decision flow allowed proportionate and culturally situated responses, while explainable AI modules ensured transparency for ethical deliberation. Conclusions. TEASUR operationalizes suffering as a quantifiable, relational, and ethically traceable variable. By closing measurement gaps, incorporating structural barriers, and integrating spiritual dimensions, TEASUR provides a replicable framework for clinical decisión making in hospital and community palliative care. While validated only through simulations, TEASUR aligns with principles of trustworthy AI and demonstrates potential as a standardized bioethical decisión support tool pending clinical validation. Ethical AI Palliative Care Relational Suffering Computational Bioethics Relational Autonomy Latin America Explainable AI Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Figure 9 Introduction Suffering in palliative care cannot be reduced to physical pain alone; it encompasses psychological, social, spiritual, and cultural dimensions, shaping a complex ethical phenomenon. This comprehensive vision, formulated by Cicely Saunders under the concept of “total pain”, represented an epistemic shift toward the humanization of dying ( 1 ). Biomedical practice still privileges measurable and technical aspects over relational and subjective ones, producing what some authors call “ethical blindness” ( 2 , 3 ). End-of-life suffering is multidimensional, involving physical, psychological, social, and spiritual domains. Current instruments such as FACITSp and ESASR provide partial assessments but fail to integrate contextual and ethical factors into decisionmaking. This gap leads to fragmented care and, at times, morally unsatisfactory interventions. Moreover, none of these tools incorporate a deliberative computational framework or explainable ethical logic, leaving a critical gap that TEASUR seeks to address. These limitations highlight the urgent need for an ethicalcomputational framework capable of operationalizing multidimensional suffering (Fig. 1 ). Latin America illustrates these challenges vividly, with structural inequities, regulatory gaps, and limited access to palliative services. However, these issues are not exclusive to the region and reflect global shortcomings in measuring and addressing suffering. Although TEASUR was designed in response to Latin American realities, the structural gaps it addresses such as inequitable access, invisibilization of spiritual suffering, and lack of regulatory adaptation are universal, positioning the system as a transferable framework for global palliative care. TEASUR was developed to close these gaps. Unlike traditional tools, it integrates multidimensional suffering with ethical computation, contextual weighting, and explainable AI. Although designed from the Latin American context, TEASUR offers a replicable framework with potential global application (Fig. 1 ). Figure 1 Illustrates the global architecture of TEASUR, integrating clinical inputs, Contextual variables, dynamic ethical computation, and proportionate clinical outputs. The diagram shows how the system processes clinical data and contextual modifiers (such as gender, socioeconomic status, access, and advance planning) through a dynamic ethical algorithm. It then generates proportionate clinical decisions, traceable ethical reports, and interactive outputs. Structural barriers—such as inequality, spiritual neglect, and regulatory gaps are explicitly considered as ethical modifiers of the computation. From a clinical bioethics perspective, failing to recognize suffering in all its dimensions represents a systemic shortcoming that undermines fundamental principles such as beneficence, distributive justice, and relational autonomy ( 4 , 5 ). Although validated instruments exist to assess specific components of suffering—such as FACITSp for spirituality ( 6 ) or ESASR for physical symptoms ( 7 )—their systematic integration into clinical decisionmaking remains scarce ( 8 , 9 ). This results in fragmented, morally unsatisfactory, and potentially iatrogenic interventions ( 10 ) In the field of clinical software development, several tools have been proposed, such as Pallia10 ( 11 ), InterRAI Palliative Care ( 12 ), or digital adaptations of FACITSp ( 6 ) and ESASR ( 7 ). However, they present critical gaps: a. They do not integrate a deliberative computational approach. b. They fail to adapt suffering to cultural, regulatory, or relational conditions. c. They do not justify clinical decisions through an explainable ethical logic. d. They lack integration with narrative modules or AIassisted ethical deliberation. Table 1 compares these instruments with the proposed TEASUR (The EthicalAdaptive Framework of Relational Suffering). Unlike traditional tools such as FACITSp, ESASR, HADS, or DXplain ( 6 – 13 ), TEASUR integrates multiple dimensions of suffering, incorporates ethical weights adjustable to context (gender, poverty, spirituality, regulation), and applies explainable artificial intelligence (XAI) to justify clinical decisions. This adaptive and relational architecture positions TEASUR as the first computational framework to operationalize suffering as both a clinical and ethical unit, generating narrative reports with moral traceability. Table 1 Comparison of TEASUR with existing tools for assessing suffering across dimensions, adaptability, ethical justification, and use of explainable AI. Tool / Software Integrated dimensions Context adaptive Ethical justification Technology Narrative Report Explainable AI (XAI) Key limitations Ref. FACITSp Spirituality No No Paper/digital questionnaire No No Onedimensional, nonrelational ( 6 ) ESASR Physical and emotional symptoms No No Digital/paper No No It does not address spirituality or context ( 7 ) HADS Anxiety/Depression No No Clinical Questionnaire No No Not integrated with spirituality or clinical deliberation ( 8 ) SPIKES Communication Partial No Structured guide No No Focused only on the communicative act ( 9 ) Pallia10 Physical/emotional symptoms Partial (Europe) No Mobile app Partial No It does not include spirituality or ethical reasoning ( 11 ) InterRAI Palliative Care Functionality, clinical status Yes (modular) No Institutional software Partial No Poor integration of narrative or spirituality ( 12 ) DXplain Project Differential diagnosis Partial No Diagnostic AI No No It does not measure suffering; diseasefocused ( 13 ) TEASUR (current proposal) Physical, Psychological, Social, Spiritual Yes (gender, culture, poverty) Yes (relational bioethics) Python + SHAP + Streamlit Yes Yes Requires minimal adaptation; highly contextualizable — Source: Authors' elaboration based on Peterman et al. ( 6 ), Bruera et al. ( 7 ), Zigmond and Snaith ( 8 ), Baile et al. ( 9 ), SFAP ( 11 ), Hirdes et al. ( 12 ), Barnett et al. ( 13 ). The Table presents a summary comparison between the TEASUR model and seven clinicalpalliative tools widely used to assess suffering or related dimensions. The analysis shows that, unlike traditional instruments such as FACITSp, ESASR, HADS or DXplain, the TEASUR model integrates multiple dimensions of suffering (physical, psychological, social and spiritual), incorporates ethical weights adjustable to the context (such as gender, spirituality or inequality), and applies explainable artificial intelligence (XAI) technologies to justify clinical decisions. This adaptive and relational architecture makes TEASUR the first computational tool that operationalizes suffering as a clinical and ethical unit, offering narrative reports with moral traceability. Structural limitations in Latin America. The approach to end-of-life suffering in the region is profoundly shaped by structural barriers that constitute systemic health injustice. These include cultural, gender, economic, legal, and regulatory factors, which manifest in unequal access, invisibilization of spiritual suffering, lack of advance care planning, and insufficient bioethical frameworks ( 23 – 40 ). Table 2 summarizes these barriers in five Latin American countries (Colombia, Peru, Mexico, Chile, Brazil). Incorporating these factors into TEASUR as modifiers of the Total Distress Index (TDI) is one of its main innovations, enabling clinical decisions to be ethically adapted to the patient’s real context rather than relying solely on biomedical criteria. Table 2 Structural barriers to a multidimensional approach to suffering across five Latin American countries. Barrier Colombia Peru Mexico Chile Brazil Ref. Cultural Syncretic vision, religiosity prevents dialogue Suffering as punishment / resignation Death as a taboo in indigenous peoples Resistance in rural areas Ethnicreligious diversity ( 23 – 25 ) Gender Invisibility of caregivers Unpaid care and without psychosocial support Emotional Burden in Indigenous Women Most unsupported informal caregivers Gap in access to opioids and emotional support ( 24 , 26 – 29 ) Economic Regional inequality; Rurality without services High costs, scarce public coverage Insufficient public coverage Limited access outside capitals Lack of home services ( 30 – 34 ) Advance directive Law 1733 without clear application No specific regulation Partial legal recognition Regulation present, without community implementation Ambiguous norms and cultural barriers ( 31 , 35 – 37 ) Regulatory gaps Poor implementation of existing laws Lack of professional ethics training No clinicalethical committees Norms without territorial implementation Disconnection between federal law and local practice ( 35 , 38 – 40 ) Authors' elaboration from: Puchalski ( 23 ), Honorato ( 24 ), Fraser ( 25 ), CarrilloGonzález ( 26 ), Ghaemizade ( 27 ), LópezÁvila ( 28 ), DelgadoGuay ( 29 ), Pastrana ( 30 ), Sadiq ( 31 ), Knaul ( 32 ), Sepúlveda ( 33 ), Harding ( 34 ), Ley 1733 ( 35 ), Alvarado ( 36 ), Pathologies of Power ( 37 ), Moharra ( 38 ), DíazPérez ( 39 ), Pastrana & Knaul ( 40 ) These barriers are incorporated into the TEASUR model as modifiers of the Total Distress Index (TDI), making it possible to make conditions of inequity visible and ethically adapt the care route. Normative rationale: why it is ethically imperative to integrate multidimensional suffering Contemporary bioethics acknowledges suffering as a central ethical category rather than a peripheral phenomenon. From Hippocrates to modern frameworks of justice, autonomy, and beneficence, alleviating suffering has remained a guiding principle of medicine ( 4 , 5 ). Cassell described its omission as a form of moral iatrogenesis—harm produced by the system’s blindness to the deeper dimensions of human suffering ( 2 ). Nevertheless, currently available instruments for assessing suffering exhibit significant structural limitations. Tools such as FACITSp for spirituality ( 6 ) or ESASR for physical symptoms ( 7 ), along with questionnaires like HADS ( 8 ), structured communication guides such as SPIKES ( 9 ), and digital instruments including Pallia10 ( 11 ) and InterRAI Palliative Care ( 12 ), have provided partial contributions but share critical shortcomings: they fragment the experience, fail to proportionally integrate social and spiritual dimensions, lack explainable modules to justify clinical decisions, and do not adapt suffering to specific cultural or regulatory contexts. Even AIbased systems such as DXplain ( 13 ) are diseasefocused and do not treat suffering as an ethical variable. Reducing suffering to quantifiable measures reflects structural blindness privileging the technical over the spiritual and relational ( 14 ). Daniels, Balboni, and Nussbaum have argued that restricting access to comprehensive relief undermines patient dignity and agency ( 15 – 17 ). Evidence further shows that unaddressed spiritual suffering is linked to higher prevalence of anxiety, poorer quality of life, and extreme decisions such as euthanasia in the absence of physical pain ( 18 ). In response to these gaps, scholars such as Fraser and Honneth have advanced the concept of a justice of recognition that incorporates historically silenced spiritual and narrative voices ( 19 , 20 ). Fricker introduced the notion of epistemic injustice , which occurs when cognitive value is denied to the experience of spiritual suffering ( 21 ). Relational bioethics therefore advocates for a clinic oriented not only toward cure but also toward recognition and accompaniment ( 22 ). Within this perspective, TEASUR represents a computational advance: a situated framework that operationalizes suffering as a multidimensional variable, integrates it into ethical deliberation, and employs explainable AI to support clinical decisions that are proportional, culturally adapted, and ethically traceable. Implementation Overview and novelty. Existing tools (FACITSp, ESASR, HADS, Pallia10, InterRAI, DXplain) fragment suffering, lack explainable ethical integration, and are not contextadaptive. TEASUR introduces an adaptive, relational, and explainable architecture that operationalizes suffering to support proportionate, culturally situated clinical decisions. Architecture and modules. Implemented in Python with the following modules: Ingestion/Preprocessing (CSV/JSON; scale normalization to 0–1). Scoring engine (TDI) integrating seven dimensions: physical, psychological, social, spiritual, family support, educational level, and psychic component. Contextual weighting (national regulations, real access to care, gender, family/community support, spirituality). Adaptive decision flow (logarithmic algorithm) translating the (TDI) into proportionate clinical pathways (e.g., palliative sedation, withdrawal of futile treatments, referral to ethics/spiritual committee). XAI layer (SHAP) with global and local explanations by dimension and contextual modifiers. Narrative report generator (clinico-bioethical traceability). Clinical UI (interactive dashboard, forms, (TDI) and XAI visualizations). Persistence & audit (CSV/JSON exports; decision and rationale logging). Algorithm and formula. The (TDI) is a weighted sum: TDI=∑w i ⋅D i where D i are standardized scores from validated scales (ESASR, HADS, FACITSp) and w i are contextdriven weights. Weights were calibrated via interceptfree linear regression on 300 synthetic cases and validated with Monte Carlo simulations, showing stability and greater sensitivity than FACITSp and ESASR (quantitative results reported in Results ). Adaptive logarithmic decision flow. The (TDI) feeds a directed decision graph. Each node applies an adaptive logarithmic transform s = log(1 + β⋅x) (rescaled to (0,1)) with configurable thresholds. The system (i) computes the (TDI); (ii) propagates signals; (iii) activates/inhibits decisions by thresholds and modifiers; (iv) dynamically adjusts wiw_iwi (± 50% controlled linear learning); (v) logs full audit trails (TDI), weights, thresholds, activations, SHAP rationales). This is decision support, not automation. Data integration and validation. Two strategies: (a) international indicators to guide scenarios; (b) synthetic cohort (n = 300) across five Latin American countries (Colombia, Peru, Mexico, Chile, Brazil) using NumPy/Pandas. Variables included age, gender, residence, access, spirituality, education, and advance directives. This enabled direct comparison of (TDI) against FACITSp/ESASR and sensitivity to inequities. Ethical and systemic barriers as modifiers. Six structural barriers are encoded as algorithmic modifiers of the (TDI): economic inequality, gender/care roles, regulatory gaps, death culture/spirituality, absence of advance planning, and clinical bias. Rather than aseptic computation, TEASUR surfaces and adjusts for inequities to support proportionate decisions (Table 3 ). Table 3 Integration of ethical and contextual barriers into the TEASUR model as algorithmic modifiers of the TDI. Ethical/Operational Barrier Incorporation into the Model 1. Economic inequality Adjustment of wiw_iwi weights according to socioeconomic quintile and health coverage 2. Gender and care roles Algorithmic correction for the invisibilization of suffering in women caregivers 3. Regulatory gaps Triggering alerts by country in the absence of regulations on advance planning or palliatives 4. Culture of death and spirituality Validation of the spiritual axis with adapted tools such as Contextualized RCOPE Brief 5. Absent Advance Planning Initial bioethical screening in the absence of a formal document or expression of will 6. Medical imposition or clinical bias Incorporation of narrative module and detection of power imbalances between patient and clinician Source: Original development of the TEASUR model based on normative and bioethical analysis contextualized to Latin America. These barriers operate within the system as triggers of ethical adjustments, ensuring that the calculation of the (TDI) is not technically aseptic, but contextual, narrative and situated. Interoperability and deployment. I/O in CSV/JSON; optional FHIR mapping ( Observation , QuestionnaireResponse ); local or intranet deployment; offline mode for privacypreserving use. Reproducibility, testing, and audit. Deterministic seeds, unit tests for normalization/weights, and comprehensive audit logs (timestamps, inputs, (TDI), decisions, SHAP rationales). Validation notebooks are provided as supplementary material. Privacy, security, and ethical safeguards . No PHI by default; atrest encryption optional; rolebased controls in clinical deployments; guardrails requiring clinician confirmation for highstakes actions and mandatory rationale capture. User interface. Dashboard includes data capture, longitudinal (TDI) plots, SHAP barplots (global/local), radar of dimensions, proportionate alerts, and an exportable narrative report (PDF/CSV). Environment and dependencies (for “Availability and requirements”). Python ≥ 3.10; core packages: numpy, pandas, scikitlearn, shap, streamlit, networkx, matplotlib/plotly. Tested on Windows, Linux, macOS. Distributed via requirements.txt with install guide (see Availability ). License/repository/DOI to be specified in that section. Current limitations. Syntheticdata validation; need for multicenter clinical studies; risk of bias from mismeasured contextual variables; dependence on quality of underlying scales. Results Operational validation of the model. To evaluate the coherence and applicability of the TEASUR model, a simulation was generated with 300 synthetic clinical cases, designed under realistic epidemiological and bioethical parameters from Latin America. Each case integrated the four dimensions of suffering (physical, psychological, social, spiritual) along with structural variables such as: Country of origin (Colombia, Peru, Mexico, Chile, Brazil) Area of residence (urban or rural) Gender Presence or absence of access to palliative care Whether or not there is a registered advance directive The Total Distress Index (TDI) formula was applied to each case, as a quantifiable and ethical measure of the multidimensional burden of suffering. The (TDI) behaved in a way that was consistent with expectations, rural patients, without access to palliative care or without an advance directive showed higher levels of total suffering. Figure 2 shows the distribution of the average adjusted (TDI) by country, including 95% confidence intervals. It is observed that Mexico has the highest values, followed by Peru and Colombia, which reflects structural differences that affect the experience of suffering in each national context. Additionally, a sensitivity test using Monte Carlo simulations (500 iterations) demonstrated a narrow distribution of average (TDI) values, indicating that the model has high stability when exposed to random perturbations in dimensional weights (Fig. 3 ). Pooled Analysis of (TDI) by Key Variables The pooled results were organized into subgroups to identify systematic differences (Table 4 ). By country Colombia had the highest average (TDI) (6.40), followed by Chile (6.29) and Mexico (6.26). These values are consistent with reports describing inequities in access to comprehensive care across the region. By gender women exhibited higher psychological and spiritual suffering, particularly in rural areas, highlighting the importance of incorporating a gender perspective into clinical practice. By area of residence rural patients presented significantly higher (TDI) values than urban patients, largely due to barriers in access and limited social/community support. By access to palliative care patients without access consistently recorded higher (TDI) across all dimensions, with the greatest impact observed in the social and spiritual domains. By advance directive cases lacking advance care planning demonstrated greater burdens of spiritual, emotional, and ethical suffering. Taken together, the results indicate that Colombia, rural areas, women, patients without access to palliative care, and those without advance directives are the groups with the greatest suffering burden. This reinforces the need to ethically adapt clinical decisions to equity, gender, and social context factors. Although the synthetic cohort consisted of 300 simulated clinical cases, Table 4 reports a representative subsample of 200 cases. This subsample was selected to illustrate subgroup differences across contextual variables (country, gender, area of residence, access to palliative care, and advance directives). The remaining cases were reserved for additional robustness checks and sensitivity analyses. This strategy ensures both internal consistency and external interpretability of the comparative results. Table 4 Average TDI values by country, gender, area of residence, access to palliative care, and advance directives (subsample n = 200 from the total synthetic cohort of 300). Category Group Average STIs Standard deviation Cases Country Brazil 6.20 0.73 42 Chile 6.29 0.55 39 Colombia 6.40 0.52 44 Mexico 6.26 0.77 35 Peru 6.11 0.66 40 Gender Female 6.33 0.59 107 Male 6.20 0.68 93 Zone Urban 6.15 0.66 121 Rural 6.43 0.56 79 Access to Palliative Care Yes 6.01 0.59 83 No 6.44 0.61 117 Advance Directives Yes 6.10 0.62 73 No 6.41 0.62 127 Source: Algorithmic simulation of the TEASUR model. Parameters derived from the Global Atlas of Palliative Care (WHO, 2020) and The Lancet Commission on Palliative Care and Pain Relief (2025). The data presented here were generated by algorithmic simulation based on epidemiological and ethical parameters obtained from sources such as the Global Atlas of Palliative Care (WHO, 2020) and The Lancet Commission on Palliative Care (2025). The purpose is to demonstrate the functional coherence of the TEASUR model under realistic conditions in Latin America. No actual patient data were used. Comparison with traditional instruments and decisional flow Figure 4 . Comparison of suffering estimation methods: baseline TDI, TDI adjusted for structural barriers, and traditional FACITSp and ESASR scales. TEASUR produces broader and more sensitive distributions, whereas conventional tools underestimate suffering—especially in social and spiritual domains. The figure also visualizes the decisional flow of the TEASUR model. Figure 5 . Logarithmic structure of the TEASUR model, illustrating bioethical decisional dynamics based on the TDI and adjusted for structural conditions. This non-linear architecture allows for situated clinical deliberation, avoiding disproportionate decisions such as immediate sedation or the omission of spiritual suffering. In addition, it makes visible the importance of interdisciplinary interventions, such as spiritual accompaniment, the role of the ethics committee and community support, configuring a clinical route coherent with relational justice and narrative autonomy. Application of the TEASUR model in a simulated narrative clinical case A simulated case was developed to illustrate the operational behavior of the TEASUR computational framework. The case involved a 69yearold female patient from a rural area of the Colombian Caribbean, diagnosed with metastatic gastric adenocarcinoma. She lived with her daughter, who acted as her primary caregiver without additional support. The patient did not have a registered advance directive and had not received spiritual accompaniment. The local hospital lacked a formal palliative care unit, although basic pharmacological management had been provided. During the initial interview, she requested “to be put to sleep,” referring to palliative sedation, and expressed “unbearable suffering.” Initial clinical evaluation using TEASUR A multidimensional assessment of suffering was performed using validated clinical instruments, categorized into four dimensions: Physical suffering: 6.5 (moderate, partially controlled pain). Psychological suffering: 8.2 (hopelessness, anticipatory anxiety). Social suffering: 7.9 (isolation, feeling of family burden). Spiritual suffering: 9.0 (loss of meaning, dissociation with beliefs). The Total Distress Index (TDI) formula was applied as follows: TDI = (0.30⋅6.5) + (0.25⋅8.2) + (0.25⋅7.9) + (0.20⋅9.0) = 7.77 This value confirmed a level of critical suffering (> 7.0), activating the clinical logarithmic algorithm of the TEASUR model. Interventions applied according to the TEASUR algorithm Based on the ethicalclinical flow (Fig. 5 ), the following progressive actions were developed: 1. Day 1 – Initial evaluation: TDI > 7.0 are confirmed without advance directive or access to specialized palliatives. 2. Day 2 – Narrative and spiritual intervention: Extended clinical interview and existential evaluation are carried out. The patient expresses feelings of guilt, loss of faith, and fear of dying without saying goodbye to her community. A process of intensive spiritual accompaniment is activated. 3. Day 3 – Community ritual: With the authorization of the family and support of the health team, a symbolic closing ritual is facilitated with the presence of community and religious leaders, favoring spiritual reconciliation. 4. Day 4 – Ethical and clinical reevaluation of the TDI: The application of the formula to verify the evolution of the dimensions is repeated: TDI = (0.30⋅6.2) + (0.25⋅6.0) + (0.25⋅6.5) + (0.20⋅5.1) = 6.00 Timeline of the intervention and evolution of the (TDI) The clinical and ethical timeline presented in Table 5 summarizes the evolution of the simulated case after the application of the TEASUR model. It integrates the values of suffering in the four dimensions (physical, psychological, social and spiritual), as well as the calculation of the Total Suffering Index (TDI) at different key moments of the clinical process: On Day 1, an initial (TDI) of 7.77 is documented, confirming a critical level of multidimensional suffering. This result activates the adaptive decision logic of the TEASUR model, prioritizing an ethical and spiritual evaluation before considering irreversible interventions such as palliative sedation. During Day 2, a narrative interview was conducted and intensive spiritual accompaniment began, which produced a decrease in the (TDI) to 6.84, evidencing an immediate impact on the spiritual and emotional axis. On Day 3, a symbolic ritual of closure and spiritual reconciliation was facilitated, which was reflected in a sustained decline in the (TDI) to 6.34, highlighting the effectiveness of communityintegrated interventions and the patient's spiritual values. Finally, on Day 4, ethical and clinical reassessment showed an (TDI) of 6.00, confirming that suffering had been reduced to a level that did not warrant immediate sedation. Consequently, it was decided to maintain the adaptive intervention, with continuous monitoring and interdisciplinary accompaniment. This clinical progression confirms the usefulness of the TEASUR model to modulate complex decisions, avoiding both the omission of nonphysical suffering and the precipitation of irreversible clinical measures. Table 5 Timeline of clinical interventions and evolution of the TDI in a simulated TEASUR case. Stage Suf. Physics Suf. Psychological Suf. Social Suf. Spiritual TDI Day 1: Initial assessment (TDI) > 7.0) 6.5 8.2 7.9 9.0 7.77 Day 2: Narrative Interview and Spiritual Support 6.3 7.0 7.2 7.0 6.84 Day 3: Community ritual and existential accompaniment 6.2 6.5 6.8 5.8 6.34 Day 4: TDI Reassessment 6.2 6.0 6.5 5.1 6.00 This simulated clinical case illustrates the practical functionality of the TEASUR model in real clinical contexts with a high burden of suffering. Unlike traditional protocols, the model did not lead to immediate sedation, but rather allowed for a relational, narrative, and spiritual approach that significantly reduced (TDI). In addition, it made visible dimensions that are often excluded, such as existential suffering, social isolation and the absence of advance planning. The model proved to be operational, ethically sound and culturally competent, allowing for proportional and personalized deliberation, guided by the rate of suffering and contextualized to the values and realities of the Latin American environment. 5.4. Adaptive Dynamics of the EthicalComputational Algorithm To examine the adaptive behavior of the TEASUR computational framework, five iterations of the logarithmic decision algorithm were simulated. Each cycle included dynamic recalibration of contextual weights (w i ) and reassessment of the activation thresholds of critical clinical decisions. At every iteration, the Total Distress Index (TDI) was recalculated, reflecting the ethical feedback incorporated into the system. Figure 6 illustrates the simulated evolution of three critical decision nodes palliative sedation, suspension of futile treatments, and referral to the ethicalspiritual committee over five iterations. An upward trend in the activation scores was observed, aligned with higher (TDI) values. This behavior suggests that the algorithm is sensitive to contextual aggravation of suffering and progressively prioritizes ethically significant interventions. In parallel, Fig. 7 depicts the proportional growth of contextual weights (w i ) associated with structural variables such as inequality, limited access to care, and the absence of advance directives. This evolution demonstrates how the system dynamically increases the ethical relevance of these factors in successive simulations, thereby adjusting the interpretive value assigned to each dimension of suffering.. Table 6 summarizes the evolution of total (TDI) values across iterations. Although initial values were moderate, successive iterations showed an upward adjustment of the (TDI), reflecting the capacity of the algorithm to recalibrate ethical priorities under simulated structural constraints. Table 6 Evolution of total TDI values across successive iterations of the logarithmic adaptive model. Iteration TDI 1 6.878 2 7.325 3 7.803 4 8.313 5 8.857 Source: Results of the adaptive logarithmic script implemented in Python This adaptive behavior underscores the potential of TEASUR as a computational framework for ethically situated deliberation. By simulating contextual learning, the system avoids rigid thresholds and instead adjusts proportionally to inequities and unaddressed suffering. While these results are promising, they must be interpreted cautiously: the validation is based on synthetic data, and field studies are required to confirm applicability in realworld clinical contexts. Operational Implementation of the TEASUR System: Computational Functional Architecture and Ethics. Building upon the algorithmic design and simulation results, a prototype of the TEASUR system was developed as an operational digital platform. This prototype translates the conceptual framework into a functional software tool capable of supporting ethical clinical decisión making in real time, with particular attention to resource limited and communitybased contexts. The implementation emphasizes transparency, reproducibility, and adaptability, in line with international recommendations for ethically grounded health technologies. Functional modules of the TEASUR system The architecture of TEASUR is organized into modular components, each of which integrates bioethical principles with computational logic. Table 7 summarizes the main modules, their functions, and operational characteristics. Table 7 Functional modules of the TEASUR system, describing components, functions, and operational characteristics Module Main function Operational characteristics Clinical Data Entry Structured clinical and contextual profile capture Records age, sex, country, area, symptoms, spirituality, social support TDI Calculator Automatic calculation of the Total Distress Index (TDI) Apply the formula TDI = ∑w i ⋅Di, with dynamic weighting by dimension Adaptive Decision Engine Activation of clinical logarithmic flow Identifies critical nodes: advance directive, access to care, spiritual suffering Ethical Alerts Automatic alert generation It detects inequities, bad practices or decisions without informed consent Timeline dashTable Longitudinal followup of TDI Scheduled reevaluation every 48–72 hours with data and trajectory updates Community integration Activation of nonbiomedical pathways Liaison with spirituality, family network, community, or local ethics committee Automatic narrative report Personalized bioethicsclinical synthesis Generation of exportable or integrable PDF in the institutional electronic medical record Source: Own elaboration based on the functional design of the TEASUR system This modular structure ensures that the system can be flexibly adapted to hospital and community contexts, preserving traceability, ethical proportionality, and interdisciplinary collaboration Computational Architecture and Technologies The TEASUR model was implemented in a Python environment, chosen for its versatility and integration with stateoftheart libraries for data analysis, visualization, and explainable artificial intelligence (XAI). Table 8 describes the technical architecture and ethical purposes of each component. Table 8 Functional architecture of TEASUR in Python with integration of explainable AI (XAI). number System Component Python Technology Main Technical Function Ethicalpractical purpose Applied functional example 1 TDI Engine NumPy, Pandas Calculation of the Total Distress Index (TDI) with dynamic weights Ethical quantification of contextualized multidimensional suffering compute_ TDI (data, weights) 2 Adaptive logarithmic flow if/else, math.log, networkx Triggering Proportional Clinical Decisions Ethical hierarchy of interventions according to severity and context Conditional activation by TDI > 7.0 3 Interactive web interface Streamlit Clinical data entry and TDI visualization Usability and inclusion of the clinical and bioethical team st.slider(), st.dataframe() 4 Dynamic Visualization Matplotlib, Plotly, Altair TDI charts, time evolution, and method comparisons Realtime transparency, monitoring, and deliberation TDI Comparison Chart: TEASUR vs FACIT 5 Backend and connectivity FastAPI, PostgreSQL Connection to clinical databases and electronic records Systemic integration for traceability and decision auditing Clinical Data Upload/Download API 6 Explainable AI (XAI) SHAP, LIME, Sklearn Justification of clinical decisions based on (TDI) Understandability, Auditability and Algorithmic Nonmaleficence shap.waterfall_plot(shap_values(0)) 7 Automatic narrative report Jinja2, PDFKit, ReportLab Generation of personalized clinicalbioethical reports in PDF Transparent documentation and reasoning of ethical decisions made Case narrative export with TDI and ethical route Source: Authors' elaboration based on the executed code of the TEASUR model. Explainable AI (XAI) Integration with SHAP To reinforce transparency, auditability, and computational ethics, an XAI module was incorporated into the TEASUR system using the SHAP library. This integration provides a structured explanation of why certain dimensions of suffering have greater impact on clinical decisionmaking, which is fundamental for interdisciplinary teams and ethics committees. Specifically, the SHAP module enables: Justification of why a given dimension (e.g., spiritual suffering) outweighs others in the decision flow. Clarification of why a specific ethical alert was activated. Documentation and traceability of decisions for use in ethics committees and institutional audits. Accessibility of computational reasoning for nontechnical professionals, fostering interdisciplinary understanding. Clinical Simulated Use Cases Simulations with 200 synthetic patients demonstrated that the TEASUR system: Reduced the likelihood of immediate sedation decisions taken without a prior spiritual assessment. Increased detection of patients lacking advance directives. Made visible ethical burdens that are often overlooked by conventional biomedical scales. These findings suggest that TEASUR can act as a computational bioethics platform capable of supporting clinical and community practice in contexts with high vulnerability and inequity. Explanatory Contribution of Dimensions Figure 8 illustrates how each dimension contributed to the Total Distress Index (TDI) in a simulated scenario. Psychological suffering was the largest contributor (+ 0.19), followed by spiritual (+ 0.10), physical (+ 0.07), and social suffering (+ 0.05). The model predicted a total (TDI) of 7.56, which surpassed the predefined clinical threshold (> 7.0) and activated the adaptive pathway of the TEASUR model. This visualization confirms that the system not only quantifies suffering but also explains each computational step, favoring ethical deliberation in clinical committees and providing professionals with proportional and transparent reasoning From Prototype to Operational Architecture The integration of TEASUR within a Python environment, enhanced with adaptive visualization and explainable AI, transforms what was initially a conceptual model into a functional operating system for clinical bioethics. While still at the stage of simulation and prototype development, the system demonstrates potential to be applied in real clinical, rural, and community settings. As shown in Fig. 9 , the TEASUR system is implemented as a modular architecture that combines computational functions with ethical principles. Each module—from clinical data entry to narrative report generation—ensures transparency, traceability, and adaptability.. Discussion The development of the TEASUR framework (EthicalAdaptive Framework of Relational Suffering) addresses a critical gap in the Latin American context: overcoming the reductionist view of end-of-life suffering predominant in traditional biomedical models ( 1 – 3 ). Previous studies have shown that neglecting the integration of psychological, social, and spiritual dimensions into clinical decisionmaking often leads to fragmented, iatrogenic, and ethically unsatisfactory interventions ( 4 , 5 , 14 ). Unlike consolidated instruments such as FACITSp ( 6 ), ESASR ( 7 ), or HADS ( 8 ), TEASUR incorporates a relational and adaptive approach, weighting suffering according to contextual variables such as socioeconomic inequality, gender, culture of death, and regulatory gaps ( 19 – 21 , 23 , 24 , 31 , 35 ). This perspective is consistent with Fraser’s notion of recognition justice ( 19 ) and with relational autonomy, enabling the inclusion of historically silenced voices and experiences ( 20 , 21 ). Compared to existing decisionsupport systems such as DXplain ( 13 ) or InterRAI ( 12 ), TEASUR explicitly integrates computational ethics and Explainable Artificial Intelligence (XAI), ensuring transparency and traceability in each decision path. This design is aligned with international frameworks on trustworthy AI, which demand explainability, nonmaleficence, and respect for human dignity ( 15 , 16 ). Simulation with multicenter synthetic cases demonstrated that TEASUR detects social and spiritual suffering with greater sensitivity than conventional scales, and that its adaptive logarithmic flow helps prevent disproportionate interventions such as immediate palliative sedation ( 17 , 18 , 29 ). These results converge with prior findings that link the omission of spiritual care to poorer qualityoflife indicators and an increased frequency of euthanasia requests in the absence of physical pain ( 17 , 18 ). Finally, the modularity and multiplatform compatibility of TEASUR facilitate its integration into hospital and community settings with limited resources ( 34 , 38 ). However, field studies with real clinical data are still required to evaluate its impact across diverse populations and its adaptability to different national regulatory frameworks. Conclusions The TEASUR system demonstrates the feasibility of operationalizing multidimensional suffering as a quantifiable, relational, and ethically traceable construct in palliative care. Rooted in the Latin American context, TEASUR addresses the ethical blind spots of traditional biomedical models by integrating physical, psychological, social, and spiritual dimensions with structural modifiers such as gender, socioeconomic inequities, and regulatory barriers. Its adaptive logarithmic algorithm, implemented in Python and enhanced with SHAP-based explainable AI (XAI), enables ethically proportional and context-sensitive decision-making. Simulations across five Latin American countries confirmed that TEASUR outperforms conventional tools in sensitivity, particularly for social and spiritual domains, thereby promoting holistic and proportionate interventions that prevent premature or unnecessary measures such as immediate sedation. By design, TEASUR aligns with the principles of trustworthy AI—transparency, adaptability, and traceability. It mirrors the deliberative logic of clinical ethics committees, serving not only as a decision-support tool but also as a pedagogical resource for professional training. Looking ahead, TEASUR has the potential to evolve into a standardized bioethical platform for palliative care, scalable across hospital and community health settings. Future development should prioritize multicenter clinical validation, regulatory compliance, and external audits to ensure ethically robust deployment. In summary, TEASUR represents a significant advance in ethical AI for healthcare, combining computational precision, cultural competence, and moral responsibility to transform the way multidimensional suffering is recognized, measured, and addressed in palliative medicine. Developed entirely in Python, the TEASUR prototype demonstrates high applicability in clinical, community, and academic contexts. Its algorithmic and ethical robustness allows replication of deliberative processes typical of clinical ethics committees, while also supporting training for professionals facing complex decisions in contexts of multidimensional suffering. Core features include: Adaptive algorithmic logic for calculating the Total Distress Index (TDI). Structural barrier adjustment modules for context-sensitive weighting. Dynamic data visualization to facilitate rapid interpretation. Explainability modules (XAI/SHAP) ensuring ethical transparency and traceability. Future perspectives. Looking forward, TEASUR may complement general-purpose AI platforms such as Gemini, ChatGPT, or Amazon Bedrock by contributing a specialized module for clinical ethics and multidimensional suffering assessment. Unlike generic architectures, TEASUR provides: Traceable bioethical deliberation, integrating psychological, social, and spiritual dimensions often overlooked by conventional biomedical algorithms. Algorithmic explainability (XAI) as a standard for ethical auditing, reinforcing transparency in AI-driven clinical recommendations. Cultural and contextual adaptation, embedding situated frameworks of relational justice from Latin America with potential for global application. Interoperability via APIs, enabling seamless integration within hospital and community environments where general-purpose AI systems are deployed. Future development directions. Validation with real-world, multicenter clinical data. Adaptation to national and international regulatory frameworks. External ethical and technical audits. Development of secure web-based platforms for real-time deployment. Modular integration with general-purpose AI ecosystems, strengthening their ethical and clinical dimensions. Caution is required. TEASUR remains a prototype validated exclusively with synthetic data. It should be interpreted as a conceptual framework and not as a clinically tested instrument. Clinical validation through multicenter trials, integration with real-world patient data, and external ethical-technical audits are indispensable steps for its future adoption. Thus, TEASUR is projected not as a replacement but as a complementary bioethical software, contributing to the evolution of clinical AI that is transparent, context-sensitive, and morally responsible. Availability and Requirements Project name: TEASUR – Ethical Adaptive Model of Relational Suffering Format available: Python source code (.py) Operating system: Cross-platform (Windows, macOS, Linux) Repository: Zenodo (DOI: 10.5281/zenodo.16818469 ) Programming languages and libraries used. Python ≥ 3.8 Essential libraries: NumPy, Pandas, Matplotlib, Scikitlearn Optional libraries for advanced functionalities: SHAP (explainability), FPDF (PDF generation), NetworkX (logarithmic flow), TensorFlow (neural networks) Other requirements. Execution environment: onpremises or cloud runtime (Google Colab, Jupyter Notebook, or any IDE supporting Python ≥ 3.8). Input data: structured CSV file or automatic generation of synthetic cohorts. Restrictions for Non-academic Use The TEASUR code is available for academic, noncommercial clinical and research purposes, with prior authorization from the author. Any use for commercial purposes, integration into proprietary systems, or redistribution requires written consent. Abbreviations AI Artificial intelligence XAI Explainable Artificial Intelligence TDI Total Distress Index CSV CommaSeparated Values (data file format) API Application Programming Interface SHAP SHapley Additive exPlanations Declarations Data & materials. This study uses exclusively synthetic data generated by the TEASUR pipeline. The reproducible dataset, outputs, and code bundle are openly available at Zenodo (doi: https://doi.org/10.5281/zenodo.16818469). Ethical approval and consent to participate. Not applicable, as no real patient data were used. Consent for publication. Not applicable; no identifiable personal data are included. Availability of data and materials. The Python source code and the generated synthetic data are available as supplementary files. They are not hosted in public repositories. Academic access is granted upon request to the corresponding author. Protection of intellectual property. The TEASUR code is registered under the name of Anderson Díaz Pérez as an original and unpublished software work. Conflicts of interest. The author declares no conflicts of interest. Funding. No external funding was received for this study. Author contributions. Anderson Díaz Pérez developed, programmed, tested, and documented the entirety of the TEASUR code, as well as drafting and revising this manuscript. Acknowledgements. Not applicable. References Saunders C. The evolution of palliative care. Patient Educ Couns. 2000; 41(1):7–13. doi: 10.1016/s0738-3991(00)00110-5 Cassell EJ. The nature of suffering and the goals of medicine. N Engl J Med. 1982; 306(11):639–45. doi: 10.1056/NEJM198203183061104 Ferrell BR, Coyle N. The nature of suffering and the goals of nursing. Oncol Nurs Forum. 2008; 35(2):241–7. doi: 10.1188/08.ONF.241247 Beauchamp TL, Childress JF. Principles of Biomedical Ethics . 8th ed. Oxford University Press; 2019. ISBN: 9780190640873 Pellegrino ED, Thomasma DC. The virtues in medical practice. New York (NY): Oxford University Press; 1993. ISBN: 9780195082890. Peterman AH, Fitchett G, Brady MJ, Hernandez L, Cella D. Measuring spiritual wellbeing in people with cancer: the FACITSp. Ann Behav Med. 2002; 24(1):49–58. doi: 10.1207/S15324796ABM2401_06 Bruera E, Kuehn N, Miller MJ, Selmser P, Macmillan K. The Edmonton Symptom Assessment System (ESAS): a simple method for the assessment of palliative care patients. J Palliat Care. 1991 Summer; 7(2):6‑9. PMID: 1714502 Zigmond AS, Snaith RP. The Hospital Anxiety and Depression Scale. Acta Psychiatr Scand. 1983; 67(6):361–70. doi: 10.1111/j.1600-0447.1983.tb09716.x Baile WF, Buckman R, Lenzi R, Glober G, Beale EA, Kudelka AP. SPIKES — a six-step protocol for delivering bad news: application to the patient with cancer. Oncologist. 2000; 5(4):302–11. doi: 10.1634/theoncologist.5-4-302 Balboni TA, Paulk ME, Balboni MJ, et al. Provision of spiritual care to patients with advanced cancer: associations with medical care and quality of life near death. J Clin Oncol. 2010; 28(3):445–52. doi: 10.1200/JCO.2009.24.8005 Société Française d'Accompagnement et de Soins Palliatifs (SFAP). Outil Pallia10. Available from: https://sfap.org Hirdes JP, Ljunggren G, Morris JN, et al. Reliability of the interRAI suite of assessment instruments: a 12country study of an integrated health information system. BMC Health Serv Res. 2008;8:277. doi: 10.1186/1472-6963-8-277 Barnett GO, Cimino JJ, Hupp JA, Hoffer EP. DXplain: an evolving diagnostic decisionsupport system. JAMA. 1987; 258(1):67–74. doi: 10.1001/jama.258.1.67 Daniels N. Just health: meeting health needs fairly. Cambridge (UK): Cambridge University Press; 2008. ISBN: 9780521699983. Balboni TA, VanderWeele TJ, DoanSoares SD, et al. Spirituality in serious illness and health. JAMA. 2022; 328(2):184–97. doi: 10.1001/JAMA.2022.11086 Nussbaum MC. Frontiers of justice: disability, nationality, species membership. Cambridge (MA): Harvard University Press; 2006. ISBN: 9780674019170 DelgadoGuay MO, Hui D, Parsons HA, Govan K, De la Cruz M, Thorney S, et al. Spirituality, religiosity, and spiritual pain in advanced cancer patients. J Pain Symptom Manage. 2011; 41(6):986–94. doi: 10.1016/j.jpainsymman.2010.09.017 Mako C, Proulx PM, Galek K. Spiritual pain among patients with advanced cancer in palliative care. J Palliat Med. 2006; 9(5):1106–13. doi: 10.1089/JPM.2006.9.1106 Fraser N. Reframing justice in a globalizing world. New Left Rev. 2005; 36:69–88. Honneth A. The struggle for recognition: the moral grammar of social conflicts. Cambridge (UK): Polity Press; 1995. ISBN: 9780745615935. Fricker M. Epistemic injustice: power and the ethics of knowing. Oxford (UK): Oxford University Press; 2007. ISBN: 9780198237906 Charon R. Narrative medicine: honoring the stories of illness. New York (NY): Oxford University Press; 2006. ISBN: 9780195340227. Puchalski CM. The role of spirituality in health care. Proc Bayl Univ Med Cent. 2001; 14(4):352–7. doi: 10.1080/08998280.2001.11927788 Honorato MM, Oliveira NP de, Domingues RJ de S, Cremaschi RM de C, Coelho FMS, Silva JAC da. Bioethical Principle of Autonomy in Indigenous Health Care. Rev Bioét. 2022; 30:373–81. doi: 10.1590/198380422022302533EN Fraser BA, Powell RA, MwangiPowell FN, Namisango E, Hannon B, Zimmermann C, et al. Palliative Care Development in Africa: Lessons From Uganda and Kenya. J Glob Oncol. 2017; (4):1–10. doi: 10.1200/JGO.2017.010090 CarrilloGonzález GM, BarretoOsorio RV, Arboleda LB, GutiérrezLesmes OA, Melo BG, Ortiz VT. Competence to care at home for people with chronic disease and their caregivers in Colombia. Rev Fac Med. 2015; 63(4):665–75. Available from: https://www.redalyc.org/articulo.oa?id=576363526012 Ghaemizade Shushtari SS, Molavynejad S, Adineh M, Savaie M, Sharhani A. Effect of End-of-life nursing education on the knowledge and performance of nurses in the intensive care unit: a quasiexperimental study. BMC Nurs. 2022; 21(1):102. doi: 10.1186/s12912-022-00880-8 López Ávila A, Rivas Riveros E, Campillay Campillay M. Order of non-resuscitation and limitation of therapeutic effort: ethical challenges in healthcare teams in Chile. Salud Colectiva. 2024; 20:e4821. doi: 10.18294/sc.2024.4821 DelgadoGuay MO, Palma A, Duarte E, Grez M, Tupper L, Liu DD, et al. Association between Spirituality, Religiosity, Spiritual Pain, Symptom Distress, and Quality of Life among Latin American Patients with Advanced Cancer: A Multicenter Study. J Palliat Med. 2021; 24(11):1606–15. doi: 10.1089/JPM.2020.0776 Pastrana T, De Lima L. Palliative Care in Latin America: Are We Making Any Progress? Assessing Development Over Time Using Macro Indicators. J Pain Symptom Manage. 2022; 63(1):33–41. doi: 10.1016/j.jpainsymman.2021.07.020 Law 1733 of 2014 (Colombia). Consuelo Devis Law. Ministry of Health and Social Protection. Available from: https://www.funcionpublica.gov.co/eva/gestornormativo/norma.php?i=59379 Knaul FM, ArreolaOrnelas H, Kwete XJ, Bhadelia A, Rosa WE, Touchton M, et al. The evolution of serious healthrelated suffering from 1990 to 2021: an update to The Lancet Commission on global access to palliative care and pain relief. Lancet Glob Health. 2025; 13(3):E422–E436. doi: 10.1016/S2214-109X(24)00476-5 Sepúlveda C, Marlin A, Yoshida T, Ullrich A. Palliative care: the WHO global perspective. J Pain Symptom Manage. 2002; 24(2):91–6. doi: 10.1016/S0885-3924(02)00440-2 Harding R. Palliative care in resource-poor settings: fallacies and misapprehensions. J Pain Symptom Manage. 2008; 36(5):515–7. doi: 10.1016/j.jpainsymman.2008.04.019 Alp FY, Yucel SC. The effect of therapeutic touch on the comfort and anxiety of nursing home residents. J Relig Health. 2021;60(4):2037–50. doi: 10.1007/s10943-020-01025-4 Moharra M, Pons JMV, Almazán C, Quintana S, et al. Citizen participation in the institutional ethics committees of clinical and healthcare research in Catalonia. Acta Bioeth. 2018; 24(2):189–98. doi:10.4067/S1726569X2018000200189 Díaz-Pérez A, López ADJA, Oñoro LMM, Orozco SMR, Lubo AMM. Comparison of the methodology analysis of principles and ethical deliberation with the comprehensive methodology of ethicalclinical analysis: approach to an ethical dilemma in nursing. Gac Méd Caracas. 2024; 132(4). doi: 10.4067/S1726569X2024000200207 Sadiq FU, Yeh YL, Liao HE, Pranata MAE, Patnaik S, Shih YH. The benefits, barriers, and specific needs of palliative care for adults with cancer in sub-Saharan Africa: a systematic review. Glob Health Action. 2025; 18(1):2485742. doi: 10.1080/16549716.2025.2485742 Pastrana T, Knaul F. Serious healthrelated suffering in Latin America: a secondary analysis. Lancet Oncol. 2022;23 Suppl 1:S37. doi:10.1016/S14702045(22)004363 Farmer P. Pathologies of power: rethinking health and human rights. Am J Public Health. 1999 Oct; 89(10):1486-96. doi: 10.2105/ajph.89.10.1486. Additional Declarations No competing interests reported. Supplementary Files teasurreproducible.py TEASURdatasetsinteticoingles.xlsx Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7447403","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":512923024,"identity":"bf68ae28-6afc-4da7-92f8-5e25ce9414f3","order_by":0,"name":"ANDERSON DÍAZ PÉREZ","email":"data:image/png;base64,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","orcid":"","institution":"Universidad Simón Bolívar","correspondingAuthor":true,"prefix":"","firstName":"ANDERSON","middleName":"DÍAZ","lastName":"PÉREZ","suffix":""}],"badges":[],"createdAt":"2025-08-24 16:23:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7447403/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7447403/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91104810,"identity":"11368831-4ce2-4422-ab67-fff363febc94","added_by":"auto","created_at":"2025-09-11 15:21:44","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":70712,"visible":true,"origin":"","legend":"\u003cp\u003eGlobal architecture of TEASUR, showing the integration of clinical inputs, contextual variables, dynamic ethical computation, and proportionate clinical outputs.\u003c/p\u003e\n\u003cp\u003eThis diagram illustrates the global structure of the TEASUR system, which integrates clinical data, contextual variables (such as gender, socioeconomic status, and access), and advance planning into a central processing engine. Through a dynamic ethical algorithm, the system adjusts weightings and generates proportionate clinical decisions, traceable ethical reports, and interactive outputs. Structural barriers such as inequality, spiritual neglect, and regulatory gaps are explicitly considered as modifiers of ethical computation.\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-7447403/v1/9129c40f544b9618a99e5def.png"},{"id":91104322,"identity":"9b4776fa-1221-4a2d-a083-6eb523c82210","added_by":"auto","created_at":"2025-09-11 15:13:44","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":21213,"visible":true,"origin":"","legend":"\u003cp\u003eDistribution of the Total Distress Index (TDI) by country, adjusted for structural modifiers, with 95% confidence intervals.\u003c/p\u003e\n\u003cp\u003eAuthors' elaboration based on algorithmic simulation derived from data and structures from the \u003cem\u003eGlobal Atlas of Palliative Care (2020)\u003c/em\u003e and \u003cem\u003eThe Lancet Commission on Palliative Care and Pain Relief (2025)\u003c/em\u003e\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-7447403/v1/e57f85aa21228ba9416e1032.png"},{"id":91104809,"identity":"0faf8455-ddc4-472e-a2f8-4e97dbdd6558","added_by":"auto","created_at":"2025-09-11 15:21:43","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":24234,"visible":true,"origin":"","legend":"\u003cp\u003eSensitivity analysis of the Total Distress Index (TDI) using 500 Monte Carlo iterations, showing stability under random perturbations of weights.\u003c/p\u003e\n\u003cp\u003eAuthors' elaboration based on algorithmic simulation derived from data and structures from the \u003cem\u003eGlobal Atlas of Palliative Care (2020)\u003c/em\u003e and \u003cem\u003eThe Lancet Commission on Palliative Care and Pain Relief (2025)\u003c/em\u003e\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-7447403/v1/4558afe8c7976983595395eb.png"},{"id":91104346,"identity":"4aa18bfc-5f10-4684-abdd-244f0e0d8f7b","added_by":"auto","created_at":"2025-09-11 15:13:45","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":18322,"visible":true,"origin":"","legend":"\u003cp\u003eComparison of (TDI)estimated by different methods: baseline, with barriers, FACITSp and ESASR.\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-7447403/v1/57d473ff7ddd3586215110a2.png"},{"id":91104354,"identity":"be085f3a-27b2-4b69-a2c6-66b764d97082","added_by":"auto","created_at":"2025-09-11 15:13:45","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":175566,"visible":true,"origin":"","legend":"\u003cp\u003eAdaptive logarithmic clinical flowchart of the TEASUR model\u003c/p\u003e\n\u003cp\u003eThis diagram illustrates the nonlinear, ethically grounded decision-making structure of the TEASUR (Ethical Adaptive Model of Relational Suffering) system. The process begins with an initial clinical assessment, capturing multidimensional suffering—physical, psychological, social, and spiritual. Contextual weights are then adjusted according to variables such as gender, access to palliative care, and the presence of advance directives. Based on these inputs, the Total Distress Index (TDI) is calculated using a weighted algorithm. If the TDI exceeds the critical threshold of 7.0, an adaptive logarithmic decision architecture is triggered, prioritizing proportionate clinical interventions based on the ethical relevance of each domain. These may include narrative accompaniment, spiritual care, or referral to ethics committees and community networks. A reassessment occurs after 48–72 hours; if the TDI remains elevated, the system dynamically recalibrates the weights to guide a new iteration of care. This flowchart operationalizes relational justice and narrative autonomy, ensuring ethically situated, explainable, and proportionate responses to end-of-life suffering.\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-7447403/v1/10cfa4fb9f1ca28dd0632fd4.png"},{"id":91104301,"identity":"3cd61b39-f5bc-4efb-87f0-20190429ad52","added_by":"auto","created_at":"2025-09-11 15:13:43","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":30329,"visible":true,"origin":"","legend":"\u003cp\u003eEvolution of clinical decision scores (palliative sedation, withdrawal of futile treatments, ethical spiritual referral) across five adaptive iterations of the TEASUR model.\u003c/p\u003e\n\u003cp\u003eSource: Computational simulation of the TEASUR model. The figure illustrates the dynamic behavior of the activation scores corresponding to three critical clinical decisions: palliative sedation, suspension of futile treatments, and referral to the ethical and spiritual committee. Throughout five cycles of iteration of TEASUR's adaptive logarithmic model, an increasing trend in the activation of these decisions is observed, in correlation with high levels of the Total Suffering Index (TDI), which shows the ethical and progressive sensitivity of the system.\u003c/p\u003e","description":"","filename":"6.png","url":"https://assets-eu.researchsquare.com/files/rs-7447403/v1/cc331fed9ca02e361345edee.png"},{"id":91104811,"identity":"8d96053f-a098-4f46-b6e5-943b2f9bf17a","added_by":"auto","created_at":"2025-09-11 15:21:44","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":81261,"visible":true,"origin":"","legend":"\u003cp\u003eEvolution of contextual weights (wi) across adaptive iterations of the TEASUR model, highlighting the increasing ethical relevance of structural factors.\u003c/p\u003e\n\u003cp\u003eSource: Computational simulation of the TEASUR model. The figure represents how the weights assigned to each dimension of suffering (physical, psychological, social, spiritual, family support, educational level, psychic component) evolve over multiple iterations of the adaptive logarithmic algorithm of the TEASUR system. This dynamic illustrates the process of selfadjustment of the model in the face of simulated contextual conditions, reflecting ethicalcomputational algorithmic learning.\u003c/p\u003e","description":"","filename":"7.png","url":"https://assets-eu.researchsquare.com/files/rs-7447403/v1/fdafffd75d7efd2d65b506ff.png"},{"id":91104319,"identity":"7100fcd4-f311-435e-824f-db4d79811b27","added_by":"auto","created_at":"2025-09-11 15:13:44","extension":"png","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":41954,"visible":true,"origin":"","legend":"\u003cp\u003eContribution of each suffering dimension (physical, psychological, social, spiritual) to the TDI, explained using SHAP values\u003c/p\u003e\n\u003cp\u003eSource: Authors' elaboration based on computational simulation with SHAP in Python environment. Visualization generated by the SHAP (SHapley Additive exPlanations) library on a regression model based on RandomForest, applied to a set of simulated synthetic data within the framework of the TEASUR system. It shows how psychological, spiritual, physical and social suffering differentially impact the calculation of the Total Distress Index (TDI), providing an ethical and technical interpretation of each computational decision.\u003c/p\u003e","description":"","filename":"8.png","url":"https://assets-eu.researchsquare.com/files/rs-7447403/v1/8c5a964ad43e2eec2d032087.png"},{"id":91104826,"identity":"a9d036d9-c1f1-4104-a081-40e9e9527dbf","added_by":"auto","created_at":"2025-09-11 15:21:45","extension":"png","order_by":9,"title":"Figure 9","display":"","copyAsset":false,"role":"figure","size":205781,"visible":true,"origin":"","legend":"\u003cp\u003eFunctional computational architecture of TEASUR, from data entry to narrative report generation, integrating bioethical principles with explainable AI.\u003c/p\u003e\n\u003cp\u003eSource: Authors' elaboration based on modules of the TEASUR systemThis figure summarizes the modular structure of the TEASUR system, from the entry of clinical data to the generation of the narrative report. Each module represents a component of the ethicalcomputational system: the calculation of the Total Distress Index (TDI), the adaptive logarithmic flow, the generation of ethical alerts in the event of inequity or bad practices, and feedback through periodic reevaluations. This architecture allows the integration of the bioethical dimension with explainable artificial intelligence (XAI) tools, ensuring transparency, traceability and adaptability to highly vulnerable clinical contexts.\u003c/p\u003e","description":"","filename":"9.png","url":"https://assets-eu.researchsquare.com/files/rs-7447403/v1/30dd92f1dcc3f2f05c893795.png"},{"id":99316023,"identity":"8d03cffb-cca6-4f8b-95ca-d9b9b4052d66","added_by":"auto","created_at":"2025-12-31 16:27:34","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2280907,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7447403/v1/fdb40fea-6989-443f-8b01-ba47876fca8e.pdf"},{"id":91104304,"identity":"0143aafc-6f0a-4a1b-a171-fd251ae786ab","added_by":"auto","created_at":"2025-09-11 15:13:43","extension":"py","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":20844,"visible":true,"origin":"","legend":"","description":"","filename":"teasurreproducible.py","url":"https://assets-eu.researchsquare.com/files/rs-7447403/v1/d926e0878506def36172409c.py"},{"id":91104299,"identity":"8140c6e5-456b-4ec2-a9c2-6d5d89500793","added_by":"auto","created_at":"2025-09-11 15:13:43","extension":"xlsx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":35964,"visible":true,"origin":"","legend":"","description":"","filename":"TEASURdatasetsinteticoingles.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7447403/v1/088c9b514a890149e2ac37f4.xlsx"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Bioethical Computational Model for Integrating Relational Suffering into End-of-Life Clinical Decision-making","fulltext":[{"header":"Introduction","content":"\u003cp\u003eSuffering in palliative care cannot be reduced to physical pain alone; it encompasses psychological, social, spiritual, and cultural dimensions, shaping a complex ethical phenomenon. This comprehensive vision, formulated by Cicely Saunders under the concept of \u0026ldquo;total pain\u0026rdquo;, represented an epistemic shift toward the humanization of dying (\u003cspan class=\"CitationRef\"\u003e1\u003c/span\u003e). Biomedical practice still privileges measurable and technical aspects over relational and subjective ones, producing what some authors call \u0026ldquo;ethical blindness\u0026rdquo; (\u003cspan class=\"CitationRef\"\u003e2\u003c/span\u003e, \u003cspan class=\"CitationRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e\n\u003cp\u003eEnd-of-life suffering is multidimensional, involving physical, psychological, social, and spiritual domains. Current instruments such as FACITSp and ESASR provide partial assessments but fail to integrate contextual and ethical factors into decisionmaking. This gap leads to fragmented care and, at times, morally unsatisfactory interventions. Moreover, none of these tools incorporate a deliberative computational framework or explainable ethical logic, leaving a critical gap that TEASUR seeks to address. These limitations highlight the urgent need for an ethicalcomputational framework capable of operationalizing multidimensional suffering (Fig. \u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e).\u003c/p\u003e\n\u003cp\u003eLatin America illustrates these challenges vividly, with structural inequities, regulatory gaps, and limited access to palliative services. However, these issues are not exclusive to the region and reflect global shortcomings in measuring and addressing suffering. Although TEASUR was designed in response to Latin American realities, the structural gaps it addresses such as inequitable access, invisibilization of spiritual suffering, and lack of regulatory adaptation are universal, positioning the system as a transferable framework for global palliative care.\u003c/p\u003e\n\u003cp\u003eTEASUR was developed to close these gaps. Unlike traditional tools, it integrates multidimensional suffering with ethical computation, contextual weighting, and explainable AI. Although designed from the Latin American context, TEASUR offers a replicable framework with potential global application (Fig. \u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e).\u003c/p\u003e\n\u003cp\u003eFigure \u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e Illustrates the global architecture of TEASUR, integrating clinical inputs, Contextual variables, dynamic ethical computation, and proportionate clinical outputs. The diagram shows how the system processes clinical data and contextual modifiers (such as gender, socioeconomic status, access, and advance planning) through a dynamic ethical algorithm. It then generates proportionate clinical decisions, traceable ethical reports, and interactive outputs. Structural barriers\u0026mdash;such as inequality, spiritual neglect, and regulatory gaps are explicitly considered as ethical modifiers of the computation.\u003c/p\u003e\n\u003cp\u003eFrom a clinical bioethics perspective, failing to recognize suffering in all its dimensions represents a systemic shortcoming that undermines fundamental principles such as beneficence, distributive justice, and relational autonomy (\u003cspan class=\"CitationRef\"\u003e4\u003c/span\u003e, \u003cspan class=\"CitationRef\"\u003e5\u003c/span\u003e). Although validated instruments exist to assess specific components of suffering\u0026mdash;such as FACITSp for spirituality (\u003cspan class=\"CitationRef\"\u003e6\u003c/span\u003e) or ESASR for physical symptoms (\u003cspan class=\"CitationRef\"\u003e7\u003c/span\u003e)\u0026mdash;their systematic integration into clinical decisionmaking remains scarce (\u003cspan class=\"CitationRef\"\u003e8\u003c/span\u003e, \u003cspan class=\"CitationRef\"\u003e9\u003c/span\u003e). This results in fragmented, morally unsatisfactory, and potentially iatrogenic interventions (\u003cspan class=\"CitationRef\"\u003e10\u003c/span\u003e)\u003c/p\u003e\n\u003cp\u003eIn the field of clinical software development, several tools have been proposed, such as Pallia10 (\u003cspan class=\"CitationRef\"\u003e11\u003c/span\u003e), InterRAI Palliative Care (\u003cspan class=\"CitationRef\"\u003e12\u003c/span\u003e), or digital adaptations of FACITSp (\u003cspan class=\"CitationRef\"\u003e6\u003c/span\u003e) and ESASR (\u003cspan class=\"CitationRef\"\u003e7\u003c/span\u003e). However, they present critical gaps:\u003c/p\u003e\n\u003cp\u003e\u003cspan\u003e\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003ea. They do not integrate a deliberative computational approach.\u003c/p\u003e\u003cspan\u003e\n \u003cp\u003eb. They fail to adapt suffering to cultural, regulatory, or relational conditions.\u003c/p\u003e\n\u003c/span\u003e\u003cspan\u003e\n \u003cp\u003ec. They do not justify clinical decisions through an explainable ethical logic.\u003c/p\u003e\n\u003c/span\u003e\u003cspan\u003e\n \u003cp\u003ed. They lack integration with narrative modules or AIassisted ethical deliberation.\u003c/p\u003e\n\u003c/span\u003e\n\u003cp\u003eTable \u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e compares these instruments with the proposed TEASUR (The EthicalAdaptive Framework of Relational Suffering). Unlike traditional tools such as FACITSp, ESASR, HADS, or DXplain (\u003cspan class=\"CitationRef\"\u003e6\u003c/span\u003e\u0026ndash;\u003cspan class=\"CitationRef\"\u003e13\u003c/span\u003e), TEASUR integrates multiple dimensions of suffering, incorporates ethical weights adjustable to context (gender, poverty, spirituality, regulation), and applies explainable artificial intelligence (XAI) to justify clinical decisions. This adaptive and relational architecture positions TEASUR as the first computational framework to operationalize suffering as both a clinical and ethical unit, generating narrative reports with moral traceability.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n \u003ctable id=\"Tab1\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eComparison of TEASUR with existing tools for assessing suffering across dimensions, adaptability, ethical justification, and use of explainable AI.\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eTool / Software\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eIntegrated dimensions\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eContext adaptive\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eEthical justification\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eTechnology\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eNarrative Report\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eExplainable AI (XAI)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eKey limitations\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eRef.\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFACITSp\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSpirituality\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePaper/digital questionnaire\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eOnedimensional, nonrelational\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e(\u003cspan class=\"CitationRef\"\u003e6\u003c/span\u003e)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eESASR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePhysical and emotional symptoms\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDigital/paper\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eIt does not address spirituality or context\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e(\u003cspan class=\"CitationRef\"\u003e7\u003c/span\u003e)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eHADS\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAnxiety/Depression\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eClinical Questionnaire\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNot integrated with spirituality or clinical deliberation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e(\u003cspan class=\"CitationRef\"\u003e8\u003c/span\u003e)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSPIKES\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCommunication\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePartial\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eStructured guide\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFocused only on the communicative act\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e(\u003cspan class=\"CitationRef\"\u003e9\u003c/span\u003e)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePallia10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePhysical/emotional symptoms\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePartial (Europe)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMobile app\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePartial\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eIt does not include spirituality or ethical reasoning\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e(\u003cspan class=\"CitationRef\"\u003e11\u003c/span\u003e)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eInterRAI Palliative Care\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFunctionality, clinical status\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eYes (modular)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eInstitutional software\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePartial\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePoor integration of narrative or spirituality\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e(\u003cspan class=\"CitationRef\"\u003e12\u003c/span\u003e)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDXplain Project\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDifferential diagnosis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePartial\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDiagnostic AI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eIt does not measure suffering; diseasefocused\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e(\u003cspan class=\"CitationRef\"\u003e13\u003c/span\u003e)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eTEASUR (current proposal)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePhysical, Psychological, Social, Spiritual\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eYes (gender, culture, poverty)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eYes (relational bioethics)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePython\u0026thinsp;+\u0026thinsp;SHAP\u0026thinsp;+\u0026thinsp;Streamlit\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eRequires minimal adaptation; highly contextualizable\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u0026mdash;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003eSource: Authors\u0026apos; elaboration based on Peterman et al. (\u003cspan class=\"CitationRef\"\u003e6\u003c/span\u003e), Bruera et al. (\u003cspan class=\"CitationRef\"\u003e7\u003c/span\u003e), Zigmond and Snaith (\u003cspan class=\"CitationRef\"\u003e8\u003c/span\u003e), Baile et al. (\u003cspan class=\"CitationRef\"\u003e9\u003c/span\u003e), SFAP (\u003cspan class=\"CitationRef\"\u003e11\u003c/span\u003e), Hirdes et al. (\u003cspan class=\"CitationRef\"\u003e12\u003c/span\u003e), Barnett et al. (\u003cspan class=\"CitationRef\"\u003e13\u003c/span\u003e). The Table presents a summary comparison between the TEASUR model and seven clinicalpalliative tools widely used to assess suffering or related dimensions. The analysis shows that, unlike traditional instruments such as FACITSp, ESASR, HADS or DXplain, the TEASUR model integrates multiple dimensions of suffering (physical, psychological, social and spiritual), incorporates ethical weights adjustable to the context (such as gender, spirituality or inequality), and applies explainable artificial intelligence (XAI) technologies to justify clinical decisions. This adaptive and relational architecture makes TEASUR the first computational tool that operationalizes suffering as a clinical and ethical unit, offering narrative reports with moral traceability.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eStructural limitations in Latin America.\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe approach to end-of-life suffering in the region is profoundly shaped by structural barriers that constitute systemic health injustice. These include cultural, gender, economic, legal, and regulatory factors, which manifest in unequal access, invisibilization of spiritual suffering, lack of advance care planning, and insufficient bioethical frameworks (\u003cspan class=\"CitationRef\"\u003e23\u003c/span\u003e\u0026ndash;\u003cspan class=\"CitationRef\"\u003e40\u003c/span\u003e). Table \u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e summarizes these barriers in five Latin American countries (Colombia, Peru, Mexico, Chile, Brazil).\u003c/p\u003e\n\u003cp\u003eIncorporating these factors into TEASUR as modifiers of the Total Distress Index (TDI) is one of its main innovations, enabling clinical decisions to be ethically adapted to the patient\u0026rsquo;s real context rather than relying solely on biomedical criteria.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n \u003ctable id=\"Tab2\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eStructural barriers to a multidimensional approach to suffering across five Latin American countries.\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eBarrier\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eColombia\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003ePeru\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eMexico\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eChile\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" style=\"width: 13.8251%;\"\u003e\n \u003cp\u003eBrazil\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" style=\"width: 9.4114%;\"\u003e\n \u003cp\u003eRef.\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCultural\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSyncretic vision, religiosity prevents dialogue\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSuffering as punishment / resignation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDeath as a taboo in indigenous peoples\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eResistance in rural areas\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" style=\"width: 13.8251%;\"\u003e\n \u003cp\u003eEthnicreligious diversity\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" style=\"width: 9.4114%;\"\u003e\n \u003cp\u003e(\u003cspan class=\"CitationRef\"\u003e23\u003c/span\u003e\u0026ndash;\u003cspan class=\"CitationRef\"\u003e25\u003c/span\u003e)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eGender\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eInvisibility of caregivers\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eUnpaid care and without psychosocial support\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eEmotional Burden in Indigenous Women\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMost unsupported informal caregivers\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" style=\"width: 13.8251%;\"\u003e\n \u003cp\u003eGap in access to opioids and emotional support\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" style=\"width: 9.4114%;\"\u003e\n \u003cp\u003e(\u003cspan class=\"CitationRef\"\u003e24\u003c/span\u003e, \u003cspan class=\"CitationRef\"\u003e26\u003c/span\u003e\u0026ndash;\u003cspan class=\"CitationRef\"\u003e29\u003c/span\u003e)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eEconomic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eRegional inequality; Rurality without services\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eHigh costs, scarce public coverage\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eInsufficient public coverage\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLimited access outside capitals\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" style=\"width: 13.8251%;\"\u003e\n \u003cp\u003eLack of home services\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" style=\"width: 9.4114%;\"\u003e\n \u003cp\u003e(\u003cspan class=\"CitationRef\"\u003e30\u003c/span\u003e\u0026ndash;\u003cspan class=\"CitationRef\"\u003e34\u003c/span\u003e)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAdvance directive\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLaw 1733 without clear application\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo specific regulation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePartial legal recognition\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eRegulation present, without community implementation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" style=\"width: 13.8251%;\"\u003e\n \u003cp\u003eAmbiguous norms and cultural barriers\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" style=\"width: 9.4114%;\"\u003e\n \u003cp\u003e(\u003cspan class=\"CitationRef\"\u003e31\u003c/span\u003e, \u003cspan class=\"CitationRef\"\u003e35\u003c/span\u003e\u0026ndash;\u003cspan class=\"CitationRef\"\u003e37\u003c/span\u003e)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eRegulatory gaps\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePoor implementation of existing laws\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLack of professional ethics training\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo clinicalethical committees\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNorms without territorial implementation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" style=\"width: 13.8251%;\"\u003e\n \u003cp\u003eDisconnection between federal law and local practice\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" style=\"width: 9.4114%;\"\u003e\n \u003cp\u003e(\u003cspan class=\"CitationRef\"\u003e35\u003c/span\u003e, \u003cspan class=\"CitationRef\"\u003e38\u003c/span\u003e\u0026ndash;\u003cspan class=\"CitationRef\"\u003e40\u003c/span\u003e)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003ctfoot\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"7\"\u003eAuthors\u0026apos; elaboration from: Puchalski (\u003cspan class=\"CitationRef\"\u003e23\u003c/span\u003e), Honorato (\u003cspan class=\"CitationRef\"\u003e24\u003c/span\u003e), Fraser (\u003cspan class=\"CitationRef\"\u003e25\u003c/span\u003e), CarrilloGonz\u0026aacute;lez (\u003cspan class=\"CitationRef\"\u003e26\u003c/span\u003e), Ghaemizade (\u003cspan class=\"CitationRef\"\u003e27\u003c/span\u003e), L\u0026oacute;pez\u0026Aacute;vila (\u003cspan class=\"CitationRef\"\u003e28\u003c/span\u003e), DelgadoGuay (\u003cspan class=\"CitationRef\"\u003e29\u003c/span\u003e), Pastrana (\u003cspan class=\"CitationRef\"\u003e30\u003c/span\u003e), Sadiq (\u003cspan class=\"CitationRef\"\u003e31\u003c/span\u003e), Knaul (\u003cspan class=\"CitationRef\"\u003e32\u003c/span\u003e), Sep\u0026uacute;lveda (\u003cspan class=\"CitationRef\"\u003e33\u003c/span\u003e), Harding (\u003cspan class=\"CitationRef\"\u003e34\u003c/span\u003e), Ley 1733 (\u003cspan class=\"CitationRef\"\u003e35\u003c/span\u003e), Alvarado (\u003cspan class=\"CitationRef\"\u003e36\u003c/span\u003e), Pathologies of Power (\u003cspan class=\"CitationRef\"\u003e37\u003c/span\u003e), Moharra (\u003cspan class=\"CitationRef\"\u003e38\u003c/span\u003e), D\u0026iacute;azP\u0026eacute;rez (\u003cspan class=\"CitationRef\"\u003e39\u003c/span\u003e), Pastrana \u0026amp; Knaul (\u003cspan class=\"CitationRef\"\u003e40\u003c/span\u003e)\u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tfoot\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003eThese barriers are incorporated into the TEASUR model as modifiers of the Total Distress Index (TDI), making it possible to make conditions of inequity visible and ethically adapt the care route.\u003c/p\u003e\n\u003ch3\u003eNormative rationale: why it is ethically imperative to integrate multidimensional suffering\u003c/h3\u003e\n\u003cp\u003eContemporary bioethics acknowledges suffering as a central ethical category rather than a peripheral phenomenon. From Hippocrates to modern frameworks of justice, autonomy, and beneficence, alleviating suffering has remained a guiding principle of medicine (\u003cspan class=\"CitationRef\"\u003e4\u003c/span\u003e, \u003cspan class=\"CitationRef\"\u003e5\u003c/span\u003e). Cassell described its omission as a form of moral iatrogenesis\u0026mdash;harm produced by the system\u0026rsquo;s blindness to the deeper dimensions of human suffering (\u003cspan class=\"CitationRef\"\u003e2\u003c/span\u003e).\u003c/p\u003e\n\u003cp\u003eNevertheless, currently available instruments for assessing suffering exhibit significant structural limitations. Tools such as FACITSp for spirituality (\u003cspan class=\"CitationRef\"\u003e6\u003c/span\u003e) or ESASR for physical symptoms (\u003cspan class=\"CitationRef\"\u003e7\u003c/span\u003e), along with questionnaires like HADS (\u003cspan class=\"CitationRef\"\u003e8\u003c/span\u003e), structured communication guides such as SPIKES (\u003cspan class=\"CitationRef\"\u003e9\u003c/span\u003e), and digital instruments including Pallia10 (\u003cspan class=\"CitationRef\"\u003e11\u003c/span\u003e) and InterRAI Palliative Care (\u003cspan class=\"CitationRef\"\u003e12\u003c/span\u003e), have provided partial contributions but share critical shortcomings: they fragment the experience, fail to proportionally integrate social and spiritual dimensions, lack explainable modules to justify clinical decisions, and do not adapt suffering to specific cultural or regulatory contexts. Even AIbased systems such as DXplain (\u003cspan class=\"CitationRef\"\u003e13\u003c/span\u003e) are diseasefocused and do not treat suffering as an ethical variable.\u003c/p\u003e\n\u003cp\u003eReducing suffering to quantifiable measures reflects structural blindness privileging the technical over the spiritual and relational (\u003cspan class=\"CitationRef\"\u003e14\u003c/span\u003e). Daniels, Balboni, and Nussbaum have argued that restricting access to comprehensive relief undermines patient dignity and agency (\u003cspan class=\"CitationRef\"\u003e15\u003c/span\u003e\u0026ndash;\u003cspan class=\"CitationRef\"\u003e17\u003c/span\u003e). Evidence further shows that unaddressed spiritual suffering is linked to higher prevalence of anxiety, poorer quality of life, and extreme decisions such as euthanasia in the absence of physical pain (\u003cspan class=\"CitationRef\"\u003e18\u003c/span\u003e). In response to these gaps, scholars such as Fraser and Honneth have advanced the concept of a justice of recognition that incorporates historically silenced spiritual and narrative voices (\u003cspan class=\"CitationRef\"\u003e19\u003c/span\u003e, \u003cspan class=\"CitationRef\"\u003e20\u003c/span\u003e). Fricker introduced the notion of \u003cem\u003eepistemic injustice\u003c/em\u003e, which occurs when cognitive value is denied to the experience of spiritual suffering (\u003cspan class=\"CitationRef\"\u003e21\u003c/span\u003e). Relational bioethics therefore advocates for a clinic oriented not only toward cure but also toward recognition and accompaniment (\u003cspan class=\"CitationRef\"\u003e22\u003c/span\u003e). Within this perspective, TEASUR represents a computational advance: a situated framework that operationalizes suffering as a multidimensional variable, integrates it into ethical deliberation, and employs explainable AI to support clinical decisions that are proportional, culturally adapted, and ethically traceable.\u003c/p\u003e\n\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\n \u003ch2\u003eImplementation\u003c/h2\u003e\n \u003cp\u003e\u003cstrong\u003eOverview and novelty.\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003eExisting tools (FACITSp, ESASR, HADS, Pallia10, InterRAI, DXplain) fragment suffering, lack explainable ethical integration, and are not contextadaptive. TEASUR introduces an adaptive, relational, and explainable architecture that operationalizes suffering to support proportionate, culturally situated clinical decisions.\u003c/p\u003e\n \u003cp\u003eArchitecture and modules.\u003c/p\u003e\n \u003cp\u003eImplemented in Python with the following modules:\u003c/p\u003e\n \u003cul\u003e\n \u003cli\u003e\n \u003cp\u003eIngestion/Preprocessing (CSV/JSON; scale normalization to 0\u0026ndash;1).\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eScoring engine (TDI) integrating seven dimensions: physical, psychological, social, spiritual, family support, educational level, and psychic component.\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eContextual weighting (national regulations, real access to care, gender, family/community support, spirituality).\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eAdaptive decision flow (logarithmic algorithm) translating the (TDI) into proportionate clinical pathways (e.g., palliative sedation, withdrawal of futile treatments, referral to ethics/spiritual committee).\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eXAI layer (SHAP) with global and local explanations by dimension and contextual modifiers.\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eNarrative report generator (clinico-bioethical traceability).\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eClinical UI (interactive dashboard, forms, (TDI) and XAI visualizations).\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003ePersistence \u0026amp; audit (CSV/JSON exports; decision and rationale logging).\u003c/p\u003e\n \u003c/li\u003e\n \u003c/ul\u003e\n \u003cp\u003e\u003cstrong\u003eAlgorithm and formula.\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003eThe (TDI) is a weighted sum:\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eTDI=\u0026sum;w\u003c/strong\u003e\u003cstrong\u003ei\u003c/strong\u003e\u003cstrong\u003e\u0026sdot;D\u003c/strong\u003e\u003cstrong\u003ei\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003ewhere D\u003cem\u003ei\u003c/em\u003e are standardized scores from validated scales (ESASR, HADS, FACITSp) and w\u003cem\u003ei\u003c/em\u003e are contextdriven weights. Weights were calibrated via interceptfree linear regression on 300 synthetic cases and validated with Monte Carlo simulations, showing stability and greater sensitivity than FACITSp and ESASR (quantitative results reported in \u003cem\u003eResults\u003c/em\u003e).\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eAdaptive logarithmic decision flow.\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003eThe (TDI) feeds a directed decision graph. Each node applies an adaptive logarithmic transform s\u0026thinsp;=\u0026thinsp;log(1\u0026thinsp;+\u0026thinsp;\u0026beta;\u0026sdot;x) (rescaled to (0,1)) with configurable thresholds.\u003c/p\u003e\n \u003cp\u003eThe system (i) computes the (TDI); (ii) propagates signals; (iii) activates/inhibits decisions by thresholds and modifiers; (iv) dynamically adjusts wiw_iwi (\u0026plusmn;\u0026thinsp;50% controlled linear learning); (v) logs full audit trails (TDI), weights, thresholds, activations, SHAP rationales). This is decision support, not automation.\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eData integration and validation.\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003eTwo strategies: (a) international indicators to guide scenarios; (b) synthetic cohort (n\u0026thinsp;=\u0026thinsp;300) across five Latin American countries (Colombia, Peru, Mexico, Chile, Brazil) using NumPy/Pandas. Variables included age, gender, residence, access, spirituality, education, and advance directives. This enabled direct comparison of (TDI) against FACITSp/ESASR and sensitivity to inequities.\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eEthical and systemic barriers as modifiers.\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003eSix structural barriers are encoded as algorithmic modifiers of the (TDI): economic inequality, gender/care roles, regulatory gaps, death culture/spirituality, absence of advance planning, and clinical bias. Rather than aseptic computation, TEASUR surfaces and adjusts for inequities to support proportionate decisions (Table \u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e\n \u003cdiv class=\"gridtable\"\u003e\n \u003ctable id=\"Tab3\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eIntegration of ethical and contextual barriers into the TEASUR model as algorithmic modifiers of the TDI.\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eEthical/Operational Barrier\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eIncorporation into the Model\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1. Economic inequality\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAdjustment of wiw_iwi weights according to socioeconomic quintile and health coverage\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2. Gender and care roles\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAlgorithmic correction for the invisibilization of suffering in women caregivers\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3. Regulatory gaps\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eTriggering alerts by country in the absence of regulations on advance planning or palliatives\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e4. Culture of death and spirituality\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eValidation of the spiritual axis with adapted tools such as Contextualized RCOPE Brief\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5. Absent Advance Planning\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eInitial bioethical screening in the absence of a formal document or expression of will\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6. Medical imposition or clinical bias\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eIncorporation of narrative module and detection of power imbalances between patient and clinician\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n \u003c/div\u003e\n \u003cp\u003eSource: Original development of the TEASUR model based on normative and bioethical analysis contextualized to Latin America. These barriers operate within the system as triggers of ethical adjustments, ensuring that the calculation of the (TDI) is not technically aseptic, but contextual, narrative and situated.\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eInteroperability and deployment.\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003eI/O in CSV/JSON; optional FHIR mapping (\u003cem\u003eObservation\u003c/em\u003e, \u003cem\u003eQuestionnaireResponse\u003c/em\u003e); local or intranet deployment; offline mode for privacypreserving use.\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eReproducibility, testing, and audit.\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003eDeterministic seeds, unit tests for normalization/weights, and comprehensive audit logs (timestamps, inputs, (TDI), decisions, SHAP rationales). Validation notebooks are provided as supplementary material.\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003ePrivacy, security, and ethical safeguards\u003c/strong\u003e.\u003c/p\u003e\n \u003cp\u003eNo PHI by default; atrest encryption optional; rolebased controls in clinical deployments; guardrails requiring clinician confirmation for highstakes actions and mandatory rationale capture.\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eUser interface.\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003eDashboard includes data capture, longitudinal (TDI) plots, SHAP barplots (global/local), radar of dimensions, proportionate alerts, and an exportable narrative report (PDF/CSV).\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eEnvironment and dependencies (for \u0026ldquo;Availability and requirements\u0026rdquo;).\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003ePython\u0026thinsp;\u0026ge;\u0026thinsp;3.10; core packages: numpy, pandas, scikitlearn, shap, streamlit, networkx, matplotlib/plotly. Tested on Windows, Linux, macOS. Distributed via requirements.txt with install guide (see \u003cem\u003eAvailability\u003c/em\u003e).\u003c/p\u003e\n \u003cp\u003eLicense/repository/DOI to be specified in that section.\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eCurrent limitations.\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003eSyntheticdata validation; need for multicenter clinical studies; risk of bias from mismeasured contextual variables; dependence on quality of underlying scales.\u003c/p\u003e\n\u003c/div\u003e"},{"header":"Results","content":"\u003cp\u003e\u003cstrong\u003eOperational validation of the model.\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eTo evaluate the coherence and applicability of the TEASUR model, a simulation was generated with 300 synthetic clinical cases, designed under realistic epidemiological and bioethical parameters from Latin America. Each case integrated the four dimensions of suffering (physical, psychological, social, spiritual) along with structural variables such as:\u003c/p\u003e\n\u003cul\u003e\n \u003cli\u003e\n \u003cp\u003eCountry of origin (Colombia, Peru, Mexico, Chile, Brazil)\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eArea of residence (urban or rural)\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eGender\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003ePresence or absence of access to palliative care\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eWhether or not there is a registered advance directive\u003c/p\u003e\n \u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eThe Total Distress Index (TDI) formula was applied to each case, as a quantifiable and ethical measure of the multidimensional burden of suffering. The (TDI) behaved in a way that was consistent with expectations, rural patients, without access to palliative care or without an advance directive showed higher levels of total suffering.\u003c/p\u003e\n\u003cp\u003eFigure \u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e shows the distribution of the average adjusted (TDI) by country, including 95% confidence intervals. It is observed that Mexico has the highest values, followed by Peru and Colombia, which reflects structural differences that affect the experience of suffering in each national context.\u003c/p\u003e\n\u003cp\u003eAdditionally, a sensitivity test using Monte Carlo simulations (500 iterations) demonstrated a narrow distribution of average (TDI) values, indicating that the model has high stability when exposed to random perturbations in dimensional weights (Fig. \u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e\n\u003ch3\u003ePooled Analysis of (TDI) by Key Variables\u003c/h3\u003e\n\u003cul\u003e\n \u003cli\u003e\n \u003cp\u003eThe pooled results were organized into subgroups to identify systematic differences (Table \u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003e).\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eBy country\u003c/p\u003e\n \u003cul\u003e\n \u003cli\u003e\n \u003cp\u003eColombia had the highest average (TDI) (6.40), followed by Chile (6.29) and Mexico (6.26). These values are consistent with reports describing inequities in access to comprehensive care across the region.\u003c/p\u003e\n \u003c/li\u003e\n \u003c/ul\u003e\n \u003cp\u003e\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eBy gender\u003c/p\u003e\n \u003cul\u003e\n \u003cli\u003e\n \u003cp\u003ewomen exhibited higher psychological and spiritual suffering, particularly in rural areas, highlighting the importance of incorporating a gender perspective into clinical practice.\u003c/p\u003e\n \u003c/li\u003e\n \u003c/ul\u003e\n \u003cp\u003e\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eBy area of residence\u003c/p\u003e\n \u003cul\u003e\n \u003cli\u003e\n \u003cp\u003erural patients presented significantly higher (TDI) values than urban patients, largely due to barriers in access and limited social/community support.\u003c/p\u003e\n \u003c/li\u003e\n \u003c/ul\u003e\n \u003cp\u003e\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eBy access to palliative care\u003c/p\u003e\n \u003cul\u003e\n \u003cli\u003e\n \u003cp\u003epatients without access consistently recorded higher (TDI) across all dimensions, with the greatest impact observed in the social and spiritual domains.\u003c/p\u003e\n \u003c/li\u003e\n \u003c/ul\u003e\n \u003cp\u003e\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eBy advance directive\u003c/p\u003e\n \u003cul\u003e\n \u003cli\u003e\n \u003cp\u003ecases lacking advance care planning demonstrated greater burdens of spiritual, emotional, and ethical suffering.\u003c/p\u003e\n \u003c/li\u003e\n \u003c/ul\u003e\n \u003cp\u003e\u003c/p\u003e\n \u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eTaken together, the results indicate that Colombia, rural areas, women, patients without access to palliative care, and those without advance directives are the groups with the greatest suffering burden. This reinforces the need to ethically adapt clinical decisions to equity, gender, and social context factors.\u003c/p\u003e\n\u003cp\u003eAlthough the synthetic cohort consisted of 300 simulated clinical cases, Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003e reports a representative subsample of 200 cases. This subsample was selected to illustrate subgroup differences across contextual variables (country, gender, area of residence, access to palliative care, and advance directives). The remaining cases were reserved for additional robustness checks and sensitivity analyses. This strategy ensures both internal consistency and external interpretability of the comparative results.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n \u003ctable id=\"Tab4\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eAverage TDI values by country, gender, area of residence, access to palliative care, and advance directives (subsample n\u0026thinsp;=\u0026thinsp;200 from the total synthetic cohort of 300).\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eCategory\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eGroup\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eAverage STIs\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eStandard deviation\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eCases\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"5\"\u003e\n \u003cp\u003eCountry\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eBrazil\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.20\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.73\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e42\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eChile\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.29\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.55\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e39\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eColombia\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.40\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.52\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e44\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMexico\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.26\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.77\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e35\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePeru\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.66\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e40\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003eGender\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFemale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.33\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.59\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e107\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.20\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.68\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e93\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003eZone\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eUrban\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.15\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.66\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e121\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eRural\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.43\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.56\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e79\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003eAccess to Palliative Care\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.01\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.59\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e83\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.44\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.61\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e117\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003eAdvance Directives\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.62\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e73\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.41\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.62\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e127\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003eSource: Algorithmic simulation of the TEASUR model. Parameters derived from the \u003cem\u003eGlobal Atlas of Palliative Care\u003c/em\u003e (WHO, 2020) and \u003cem\u003eThe Lancet Commission on Palliative Care and Pain Relief\u003c/em\u003e (2025). The data presented here were generated by algorithmic simulation based on epidemiological and ethical parameters obtained from sources such as the Global Atlas of Palliative Care (WHO, 2020) and The Lancet Commission on Palliative Care (2025). The purpose is to demonstrate the functional coherence of the TEASUR model under realistic conditions in Latin America. No actual patient data were used.\u003c/p\u003e\n\u003ch3\u003eComparison with traditional instruments and decisional flow\u003c/h3\u003e\n\u003cp\u003eFigure \u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003e. Comparison of suffering estimation methods: baseline TDI, TDI adjusted for structural barriers, and traditional FACITSp and ESASR scales. TEASUR produces broader and more sensitive distributions, whereas conventional tools underestimate suffering\u0026mdash;especially in social and spiritual domains. The figure also visualizes the decisional flow of the TEASUR model.\u003c/p\u003e\n\u003cp\u003eFigure \u003cspan class=\"InternalRef\"\u003e5\u003c/span\u003e. Logarithmic structure of the TEASUR model, illustrating bioethical decisional dynamics based on the TDI and adjusted for structural conditions. This non-linear architecture allows for situated clinical deliberation, avoiding disproportionate decisions such as immediate sedation or the omission of spiritual suffering. In addition, it makes visible the importance of interdisciplinary interventions, such as spiritual accompaniment, the role of the ethics committee and community support, configuring a clinical route coherent with relational justice and narrative autonomy.\u003c/p\u003e\n\u003ch3\u003eApplication of the TEASUR model in a simulated narrative clinical case\u003c/h3\u003e\n\u003cp\u003eA simulated case was developed to illustrate the operational behavior of the TEASUR computational framework. The case involved a 69yearold female patient from a rural area of the Colombian Caribbean, diagnosed with metastatic gastric adenocarcinoma. She lived with her daughter, who acted as her primary caregiver without additional support. The patient did not have a registered advance directive and had not received spiritual accompaniment. The local hospital lacked a formal palliative care unit, although basic pharmacological management had been provided. During the initial interview, she requested \u0026ldquo;to be put to sleep,\u0026rdquo; referring to palliative sedation, and expressed \u0026ldquo;unbearable suffering.\u0026rdquo;\u003c/p\u003e\n\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\n \u003ch2\u003eInitial clinical evaluation using TEASUR\u003c/h2\u003e\n \u003cp\u003eA multidimensional assessment of suffering was performed using validated clinical instruments, categorized into four dimensions:\u003c/p\u003e\n \u003cul\u003e\n \u003cli\u003e\n \u003cp\u003ePhysical suffering: 6.5 (moderate, partially controlled pain).\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003ePsychological suffering: 8.2 (hopelessness, anticipatory anxiety).\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eSocial suffering: 7.9 (isolation, feeling of family burden).\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eSpiritual suffering: 9.0 (loss of meaning, dissociation with beliefs).\u003c/p\u003e\n \u003c/li\u003e\n \u003c/ul\u003e\n \u003cp\u003eThe Total Distress Index (TDI) formula was applied as follows:\u003c/p\u003e\n\u003c/div\u003e\n\u003ch3\u003eTDI = (0.30\u0026sdot;6.5) + (0.25\u0026sdot;8.2) + (0.25\u0026sdot;7.9) + (0.20\u0026sdot;9.0)\u0026thinsp;=\u0026thinsp;7.77\u003c/h3\u003e\n\u003cp\u003eThis value confirmed a level of critical suffering (\u0026gt;\u0026thinsp;7.0), activating the clinical logarithmic algorithm of the TEASUR model.\u003c/p\u003e\n\u003ch3\u003eInterventions applied according to the TEASUR algorithm\u003c/h3\u003e\n\u003cp\u003eBased on the ethicalclinical flow (Fig. \u003cspan class=\"InternalRef\"\u003e5\u003c/span\u003e), the following progressive actions were developed:\u003c/p\u003e\n\u003cp\u003e\u003cspan\u003e\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003e1. Day 1 \u0026ndash; Initial evaluation: TDI\u0026thinsp;\u0026gt;\u0026thinsp;7.0 are confirmed without advance directive or access to specialized palliatives.\u003c/p\u003e\u003cspan\u003e\n \u003cp\u003e2. Day 2 \u0026ndash; Narrative and spiritual intervention: Extended clinical interview and existential evaluation are carried out. The patient expresses feelings of guilt, loss of faith, and fear of dying without saying goodbye to her community. A process of intensive spiritual accompaniment is activated.\u003c/p\u003e\n\u003c/span\u003e\u003cspan\u003e\n \u003cp\u003e3. Day 3 \u0026ndash; Community ritual: With the authorization of the family and support of the health team, a symbolic closing ritual is facilitated with the presence of community and religious leaders, favoring spiritual reconciliation.\u003c/p\u003e\n\u003c/span\u003e\u003cspan\u003e\n \u003cp\u003e4. Day 4 \u0026ndash; Ethical and clinical reevaluation of the TDI: The application of the formula to verify the evolution of the dimensions is repeated:\u003c/p\u003e\n\u003c/span\u003e\n\u003cp\u003e\u003c/p\u003e\n\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e\n \u003ch2\u003eTDI = (0.30\u0026sdot;6.2) + (0.25\u0026sdot;6.0) + (0.25\u0026sdot;6.5) + (0.20\u0026sdot;5.1)\u0026thinsp;=\u0026thinsp;6.00\u003c/h2\u003e\n \u003cp\u003e\u003cstrong\u003eTimeline of the intervention and evolution of the\u003c/strong\u003e (TDI)\u003c/p\u003e\n \u003cp\u003eThe clinical and ethical timeline presented in Table \u003cspan class=\"InternalRef\"\u003e5\u003c/span\u003e summarizes the evolution of the simulated case after the application of the TEASUR model. It integrates the values of suffering in the four dimensions (physical, psychological, social and spiritual), as well as the calculation of the Total Suffering Index (TDI) at different key moments of the clinical process:\u003c/p\u003e\n \u003cul\u003e\n \u003cli\u003e\n \u003cp\u003eOn Day 1, an initial (TDI) of 7.77 is documented, confirming a critical level of multidimensional suffering. This result activates the adaptive decision logic of the TEASUR model, prioritizing an ethical and spiritual evaluation before considering irreversible interventions such as palliative sedation.\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eDuring Day 2, a narrative interview was conducted and intensive spiritual accompaniment began, which produced a decrease in the (TDI) to 6.84, evidencing an immediate impact on the spiritual and emotional axis.\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eOn Day 3, a symbolic ritual of closure and spiritual reconciliation was facilitated, which was reflected in a sustained decline in the (TDI) to 6.34, highlighting the effectiveness of communityintegrated interventions and the patient\u0026apos;s spiritual values.\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eFinally, on Day 4, ethical and clinical reassessment showed an (TDI) of 6.00, confirming that suffering had been reduced to a level that did not warrant immediate sedation. Consequently, it was decided to maintain the adaptive intervention, with continuous monitoring and interdisciplinary accompaniment.\u003c/p\u003e\n \u003c/li\u003e\n \u003c/ul\u003e\n \u003cp\u003eThis clinical progression confirms the usefulness of the TEASUR model to modulate complex decisions, avoiding both the omission of nonphysical suffering and the precipitation of irreversible clinical measures.\u003c/p\u003e\n \u003cdiv class=\"gridtable\"\u003e\n \u003ctable id=\"Tab5\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 5\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eTimeline of clinical interventions and evolution of the TDI in a simulated TEASUR case.\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eStage\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eSuf. Physics\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eSuf. Psychological\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eSuf. Social\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eSuf. Spiritual\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eTDI\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDay 1: Initial assessment (TDI)\u0026thinsp;\u0026gt;\u0026thinsp;7.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e8.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e7.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e9.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e7.77\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDay 2: Narrative Interview and Spiritual Support\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e7.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e7.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e7.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.84\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDay 3: Community ritual and existential accompaniment\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e5.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.34\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDay 4: TDI Reassessment\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e5.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.00\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n \u003c/div\u003e\n \u003cp\u003eThis simulated clinical case illustrates the practical functionality of the TEASUR model in real clinical contexts with a high burden of suffering. Unlike traditional protocols, the model did not lead to immediate sedation, but rather allowed for a relational, narrative, and spiritual approach that significantly reduced (TDI). In addition, it made visible dimensions that are often excluded, such as existential suffering, social isolation and the absence of advance planning.\u003c/p\u003e\n \u003cp\u003eThe model proved to be operational, ethically sound and culturally competent, allowing for proportional and personalized deliberation, guided by the rate of suffering and contextualized to the values and realities of the Latin American environment.\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e5.4. Adaptive Dynamics of the EthicalComputational Algorithm\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003eTo examine the adaptive behavior of the TEASUR computational framework, five iterations of the logarithmic decision algorithm were simulated. Each cycle included dynamic recalibration of contextual weights (w\u003cem\u003ei\u003c/em\u003e) and reassessment of the activation thresholds of critical clinical decisions. At every iteration, the Total Distress Index (TDI) was recalculated, reflecting the ethical feedback incorporated into the system.\u003c/p\u003e\n \u003cp\u003eFigure \u003cspan class=\"InternalRef\"\u003e6\u003c/span\u003e illustrates the simulated evolution of three critical decision nodes palliative sedation, suspension of futile treatments, and referral to the ethicalspiritual committee over five iterations. An upward trend in the activation scores was observed, aligned with higher (TDI) values. This behavior suggests that the algorithm is sensitive to contextual aggravation of suffering and progressively prioritizes ethically significant interventions.\u003c/p\u003e\n \u003cp\u003eIn parallel, Fig. \u003cspan class=\"InternalRef\"\u003e7\u003c/span\u003e depicts the proportional growth of contextual weights (w\u003cem\u003ei\u003c/em\u003e) associated with structural variables such as inequality, limited access to care, and the absence of advance directives. This evolution demonstrates how the system dynamically increases the ethical relevance of these factors in successive simulations, thereby adjusting the interpretive value assigned to each dimension of suffering..\u003c/p\u003e\n \u003cp\u003eTable\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e6\u003c/span\u003e summarizes the evolution of total (TDI) values across iterations. Although initial values were moderate, successive iterations showed an upward adjustment of the (TDI), reflecting the capacity of the algorithm to recalibrate ethical priorities under simulated structural constraints.\u003c/p\u003e\n \u003cdiv class=\"gridtable\"\u003e\n \u003cdiv align=\"char\" class=\"colspec\"\u003e\u003cbr\u003e\u003c/div\u003e\n \u003ctable id=\"Tab6\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 6\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eEvolution of total TDI values across successive iterations of the logarithmic adaptive model.\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eIteration\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eTDI\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e6.878\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e7.325\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e7.803\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e8.313\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e8.857\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n \u003c/div\u003e\n \u003cp\u003eSource: Results of the adaptive logarithmic script implemented in Python\u003c/p\u003e\n \u003cp\u003eThis adaptive behavior underscores the potential of TEASUR as a computational framework for ethically situated deliberation. By simulating contextual learning, the system avoids rigid thresholds and instead adjusts proportionally to inequities and unaddressed suffering. While these results are promising, they must be interpreted cautiously: the validation is based on synthetic data, and field studies are required to confirm applicability in realworld clinical contexts.\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eOperational Implementation of the TEASUR System: Computational Functional Architecture and Ethics.\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003eBuilding upon the algorithmic design and simulation results, a prototype of the TEASUR system was developed as an operational digital platform. This prototype translates the conceptual framework into a functional software tool capable of supporting ethical clinical decisi\u0026oacute;n making in real time, with particular attention to resource limited and communitybased contexts. The implementation emphasizes transparency, reproducibility, and adaptability, in line with international recommendations for ethically grounded health technologies.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\n \u003ch2\u003eFunctional modules of the TEASUR system\u003c/h2\u003e\n \u003cp\u003eThe architecture of TEASUR is organized into modular components, each of which integrates bioethical principles with computational logic. Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e7\u003c/span\u003e summarizes the main modules, their functions, and operational characteristics.\u003c/p\u003e\n \u003cdiv class=\"gridtable\"\u003e\n \u003ctable id=\"Tab7\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 7\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eFunctional modules of the TEASUR system, describing components, functions, and operational characteristics\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eModule\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eMain function\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eOperational characteristics\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eClinical Data Entry\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eStructured clinical and contextual profile capture\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eRecords age, sex, country, area, symptoms, spirituality, social support\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eTDI Calculator\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAutomatic calculation of the Total Distress Index (TDI)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eApply the formula TDI = \u0026sum;w\u003cem\u003ei\u003c/em\u003e\u0026sdot;Di, with dynamic weighting by dimension\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAdaptive Decision Engine\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eActivation of clinical logarithmic flow\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eIdentifies critical nodes: advance directive, access to care, spiritual suffering\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eEthical Alerts\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAutomatic alert generation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eIt detects inequities, bad practices or decisions without informed consent\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eTimeline dashTable\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLongitudinal followup of TDI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eScheduled reevaluation every 48\u0026ndash;72 hours with data and trajectory updates\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCommunity integration\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eActivation of nonbiomedical pathways\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLiaison with spirituality, family network, community, or local ethics committee\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAutomatic narrative report\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePersonalized bioethicsclinical synthesis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eGeneration of exportable or integrable PDF in the institutional electronic medical record\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n \u003c/div\u003e\n \u003cp\u003eSource: Own elaboration based on the functional design of the TEASUR system\u003c/p\u003e\n \u003cp\u003eThis modular structure ensures that the system can be flexibly adapted to hospital and community contexts, preserving traceability, ethical proportionality, and interdisciplinary collaboration\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec13\" class=\"Section2\"\u003e\n \u003ch2\u003eComputational Architecture and Technologies\u003c/h2\u003e\n \u003cp\u003eThe TEASUR model was implemented in a Python environment, chosen for its versatility and integration with stateoftheart libraries for data analysis, visualization, and explainable artificial intelligence (XAI). Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e8\u003c/span\u003e describes the technical architecture and ethical purposes of each component.\u003c/p\u003e\n \u003cdiv class=\"gridtable\"\u003e\n \u003ctable id=\"Tab8\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 8\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eFunctional architecture of TEASUR in Python with integration of explainable AI (XAI).\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003enumber\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eSystem Component\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003ePython Technology\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eMain Technical Function\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eEthicalpractical purpose\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eApplied functional example\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eTDI Engine\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNumPy, Pandas\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCalculation of the Total Distress Index (TDI) with dynamic weights\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eEthical quantification of contextualized multidimensional suffering\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ecompute_ TDI (data, weights)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAdaptive logarithmic flow\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eif/else, math.log, networkx\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eTriggering Proportional Clinical Decisions\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eEthical hierarchy of interventions according to severity and context\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eConditional activation by TDI\u0026thinsp;\u0026gt;\u0026thinsp;7.0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eInteractive web interface\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eStreamlit\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eClinical data entry and TDI visualization\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eUsability and inclusion of the clinical and bioethical team\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003est.slider(), st.dataframe()\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDynamic Visualization\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMatplotlib, Plotly, Altair\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eTDI charts, time evolution, and method comparisons\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eRealtime transparency, monitoring, and deliberation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eTDI Comparison Chart: TEASUR vs FACIT\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eBackend and connectivity\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFastAPI, PostgreSQL\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eConnection to clinical databases and electronic records\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSystemic integration for traceability and decision auditing\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eClinical Data Upload/Download API\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eExplainable AI (XAI)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSHAP, LIME, Sklearn\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eJustification of clinical decisions based on (TDI)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eUnderstandability, Auditability and Algorithmic Nonmaleficence\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eshap.waterfall_plot(shap_values(0))\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAutomatic narrative report\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eJinja2, PDFKit, ReportLab\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eGeneration of personalized clinicalbioethical reports in PDF\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eTransparent documentation and reasoning of ethical decisions made\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCase narrative export with TDI and ethical route\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n \u003c/div\u003e\n \u003cp\u003eSource: Authors\u0026apos; elaboration based on the executed code of the TEASUR model.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec14\" class=\"Section2\"\u003e\n \u003ch2\u003eExplainable AI (XAI) Integration with SHAP\u003c/h2\u003e\n \u003cp\u003eTo reinforce transparency, auditability, and computational ethics, an XAI module was incorporated into the TEASUR system using the SHAP library. This integration provides a structured explanation of why certain dimensions of suffering have greater impact on clinical decisionmaking, which is fundamental for interdisciplinary teams and ethics committees.\u003c/p\u003e\n \u003cp\u003eSpecifically, the SHAP module enables:\u003c/p\u003e\n \u003cul\u003e\n \u003cli\u003e\n \u003cp\u003eJustification of why a given dimension (e.g., spiritual suffering) outweighs others in the decision flow.\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eClarification of why a specific ethical alert was activated.\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eDocumentation and traceability of decisions for use in ethics committees and institutional audits.\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eAccessibility of computational reasoning for nontechnical professionals, fostering interdisciplinary understanding.\u003c/p\u003e\n \u003c/li\u003e\n \u003c/ul\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec15\" class=\"Section2\"\u003e\n \u003ch2\u003eClinical Simulated Use Cases\u003c/h2\u003e\n \u003cp\u003eSimulations with 200 synthetic patients demonstrated that the TEASUR system:\u003c/p\u003e\n \u003cul\u003e\n \u003cli\u003e\n \u003cp\u003eReduced the likelihood of immediate sedation decisions taken without a prior spiritual assessment.\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eIncreased detection of patients lacking advance directives.\u003c/p\u003e\n \u003c/li\u003e\n \u003cli\u003e\n \u003cp\u003eMade visible ethical burdens that are often overlooked by conventional biomedical scales.\u003c/p\u003e\n \u003c/li\u003e\n \u003c/ul\u003e\n \u003cp\u003eThese findings suggest that TEASUR can act as a computational bioethics platform capable of supporting clinical and community practice in contexts with high vulnerability and inequity.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec16\" class=\"Section2\"\u003e\n \u003ch2\u003eExplanatory Contribution of Dimensions\u003c/h2\u003e\n \u003cp\u003eFigure \u003cspan class=\"InternalRef\"\u003e8\u003c/span\u003e illustrates how each dimension contributed to the Total Distress Index (TDI) in a simulated scenario. Psychological suffering was the largest contributor (+\u0026thinsp;0.19), followed by spiritual (+\u0026thinsp;0.10), physical (+\u0026thinsp;0.07), and social suffering (+\u0026thinsp;0.05). The model predicted a total (TDI) of 7.56, which surpassed the predefined clinical threshold (\u0026gt;\u0026thinsp;7.0) and activated the adaptive pathway of the TEASUR model. This visualization confirms that the system not only quantifies suffering but also explains each computational step, favoring ethical deliberation in clinical committees and providing professionals with proportional and transparent reasoning\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec17\" class=\"Section2\"\u003e\n \u003ch2\u003eFrom Prototype to Operational Architecture\u003c/h2\u003e\n \u003cp\u003eThe integration of TEASUR within a Python environment, enhanced with adaptive visualization and explainable AI, transforms what was initially a conceptual model into a functional operating system for clinical bioethics. While still at the stage of simulation and prototype development, the system demonstrates potential to be applied in real clinical, rural, and community settings.\u003c/p\u003e\n \u003cp\u003eAs shown in Fig. \u003cspan class=\"InternalRef\"\u003e9\u003c/span\u003e, the TEASUR system is implemented as a modular architecture that combines computational functions with ethical principles. Each module\u0026mdash;from clinical data entry to narrative report generation\u0026mdash;ensures transparency, traceability, and adaptability..\u003c/p\u003e\n\u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eThe development of the TEASUR framework (EthicalAdaptive Framework of Relational Suffering) addresses a critical gap in the Latin American context: overcoming the reductionist view of end-of-life suffering predominant in traditional biomedical models (\u003cspan additionalcitationids=\"CR2\" citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e). Previous studies have shown that neglecting the integration of psychological, social, and spiritual dimensions into clinical decisionmaking often leads to fragmented, iatrogenic, and ethically unsatisfactory interventions (\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e, \u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e, \u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eUnlike consolidated instruments such as FACITSp (\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e), ESASR (\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e), or HADS (\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e), TEASUR incorporates a relational and adaptive approach, weighting suffering according to contextual variables such as socioeconomic inequality, gender, culture of death, and regulatory gaps (\u003cspan additionalcitationids=\"CR20\" citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e, \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e, \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e, \u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e, \u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e). This perspective is consistent with Fraser\u0026rsquo;s notion of recognition justice (\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e) and with relational autonomy, enabling the inclusion of historically silenced voices and experiences (\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e, \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e). Compared to existing decisionsupport systems such as DXplain (\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e) or InterRAI (\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e), TEASUR explicitly integrates computational ethics and Explainable Artificial Intelligence (XAI), ensuring transparency and traceability in each decision path. This design is aligned with international frameworks on trustworthy AI, which demand explainability, nonmaleficence, and respect for human dignity (\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e, \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eSimulation with multicenter synthetic cases demonstrated that TEASUR detects social and spiritual suffering with greater sensitivity than conventional scales, and that its adaptive logarithmic flow helps prevent disproportionate interventions such as immediate palliative sedation (\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e, \u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e, \u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e). These results converge with prior findings that link the omission of spiritual care to poorer qualityoflife indicators and an increased frequency of euthanasia requests in the absence of physical pain (\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e, \u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eFinally, the modularity and multiplatform compatibility of TEASUR facilitate its integration into hospital and community settings with limited resources (\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e, \u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e). However, field studies with real clinical data are still required to evaluate its impact across diverse populations and its adaptability to different national regulatory frameworks.\u003c/p\u003e"},{"header":"Conclusions","content":"\u003cp\u003eThe TEASUR system demonstrates the feasibility of operationalizing multidimensional suffering as a quantifiable, relational, and ethically traceable construct in palliative care. Rooted in the Latin American context, TEASUR addresses the ethical blind spots of traditional biomedical models by integrating physical, psychological, social, and spiritual dimensions with structural modifiers such as gender, socioeconomic inequities, and regulatory barriers.\u003c/p\u003e\u003cp\u003eIts adaptive logarithmic algorithm, implemented in Python and enhanced with SHAP-based explainable AI (XAI), enables ethically proportional and context-sensitive decision-making. Simulations across five Latin American countries confirmed that TEASUR outperforms conventional tools in sensitivity, particularly for social and spiritual domains, thereby promoting holistic and proportionate interventions that prevent premature or unnecessary measures such as immediate sedation.\u003c/p\u003e\u003cp\u003eBy design, TEASUR aligns with the principles of trustworthy AI\u0026mdash;transparency, adaptability, and traceability. It mirrors the deliberative logic of clinical ethics committees, serving not only as a decision-support tool but also as a pedagogical resource for professional training. Looking ahead, TEASUR has the potential to evolve into a standardized bioethical platform for palliative care, scalable across hospital and community health settings. Future development should prioritize multicenter clinical validation, regulatory compliance, and external audits to ensure ethically robust deployment.\u003c/p\u003e\u003cp\u003eIn summary, TEASUR represents a significant advance in ethical AI for healthcare, combining computational precision, cultural competence, and moral responsibility to transform the way multidimensional suffering is recognized, measured, and addressed in palliative medicine.\u003c/p\u003e\u003cp\u003eDeveloped entirely in Python, the TEASUR prototype demonstrates high applicability in clinical, community, and academic contexts. Its algorithmic and ethical robustness allows replication of deliberative processes typical of clinical ethics committees, while also supporting training for professionals facing complex decisions in contexts of multidimensional suffering.\u003c/p\u003e\u003cdiv id=\"Sec20\" class=\"Section2\"\u003e\u003ch2\u003eCore features include:\u003c/h2\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003eAdaptive algorithmic logic for calculating the Total Distress Index (TDI).\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eStructural barrier adjustment modules for context-sensitive weighting.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eDynamic data visualization to facilitate rapid interpretation.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eExplainability modules (XAI/SHAP) ensuring ethical transparency and traceability.\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003cp\u003e\u003cb\u003eFuture perspectives.\u003c/b\u003e\u003c/p\u003e\u003cp\u003eLooking forward, TEASUR may complement general-purpose AI platforms such as Gemini, ChatGPT, or Amazon Bedrock by contributing a specialized module for clinical ethics and multidimensional suffering assessment. Unlike generic architectures, TEASUR provides:\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003eTraceable bioethical deliberation, integrating psychological, social, and spiritual dimensions often overlooked by conventional biomedical algorithms.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eAlgorithmic explainability (XAI) as a standard for ethical auditing, reinforcing transparency in AI-driven clinical recommendations.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eCultural and contextual adaptation, embedding situated frameworks of relational justice from Latin America with potential for global application.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eInteroperability via APIs, enabling seamless integration within hospital and community environments where general-purpose AI systems are deployed.\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003cp\u003e\u003cb\u003eFuture development directions.\u003c/b\u003e\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003eValidation with real-world, multicenter clinical data.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eAdaptation to national and international regulatory frameworks.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eExternal ethical and technical audits.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eDevelopment of secure web-based platforms for real-time deployment.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eModular integration with general-purpose AI ecosystems, strengthening their ethical and clinical dimensions.\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003cp\u003e\u003cb\u003eCaution is required.\u003c/b\u003e\u003c/p\u003e\u003cp\u003eTEASUR remains a prototype validated exclusively with synthetic data. It should be interpreted as a conceptual framework and not as a clinically tested instrument. Clinical validation through multicenter trials, integration with real-world patient data, and external ethical-technical audits are indispensable steps for its future adoption.\u003c/p\u003e\u003cp\u003eThus, TEASUR is projected not as a replacement but as a complementary bioethical software, contributing to the evolution of clinical AI that is transparent, context-sensitive, and morally responsible.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec21\" class=\"Section2\"\u003e\u003ch2\u003eAvailability and Requirements\u003c/h2\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003eProject name: TEASUR \u0026ndash; Ethical Adaptive Model of Relational Suffering\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eFormat available: Python source code (.py)\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eOperating system: Cross-platform (Windows, macOS, Linux)\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eRepository: Zenodo (DOI: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.5281/zenodo.16818469\u003c/span\u003e\u003cspan address=\"10.5281/zenodo.16818469\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e)\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003cp\u003e\u003cb\u003eProgramming languages and libraries used.\u003c/b\u003e\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003ePython\u0026thinsp;\u0026ge;\u0026thinsp;3.8\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eEssential libraries: NumPy, Pandas, Matplotlib, Scikitlearn\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eOptional libraries for advanced functionalities: SHAP (explainability), FPDF (PDF generation), NetworkX (logarithmic flow), TensorFlow (neural networks)\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003cp\u003e\u003cb\u003eOther requirements.\u003c/b\u003e\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003eExecution environment: onpremises or cloud runtime (Google Colab, Jupyter Notebook, or any IDE supporting Python\u0026thinsp;\u0026ge;\u0026thinsp;3.8).\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eInput data: structured CSV file or automatic generation of synthetic cohorts.\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec22\" class=\"Section2\"\u003e\u003ch2\u003eRestrictions for Non-academic Use\u003c/h2\u003e\u003cp\u003eThe TEASUR code is available for academic, noncommercial clinical and research purposes, with prior authorization from the author. Any use for commercial purposes, integration into proprietary systems, or redistribution requires written consent.\u003c/p\u003e\u003c/div\u003e"},{"header":"Abbreviations","content":"\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eAI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eArtificial intelligence\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eXAI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eExplainable Artificial Intelligence\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eTDI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eTotal Distress Index\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eCSV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eCommaSeparated Values (data file format)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eAPI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eApplication Programming Interface\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eSHAP\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eSHapley Additive exPlanations\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e"},{"header":"Declarations","content":"\u003cul\u003e\n \u003cli\u003e\u003cstrong\u003eData \u0026amp; materials.\u0026nbsp;\u003c/strong\u003eThis study uses exclusively synthetic data generated by the TEASUR pipeline. The reproducible dataset, outputs, and code bundle are openly available at Zenodo (doi: https://doi.org/10.5281/zenodo.16818469).\u003c/li\u003e\n \u003cli\u003e\u003cstrong\u003eEthical approval and consent to participate.\u0026nbsp;\u003c/strong\u003eNot applicable, as no real patient data were used.\u003c/li\u003e\n \u003cli\u003e\u003cstrong\u003eConsent for publication.\u0026nbsp;\u003c/strong\u003eNot applicable; no identifiable personal data are included.\u003c/li\u003e\n \u003cli\u003e\u003cstrong\u003eAvailability of data and materials. \u0026nbsp;\u003c/strong\u003eThe Python source code and the generated synthetic data are available as supplementary files. They are not hosted in public repositories. Academic access is granted upon request to the corresponding author.\u003c/li\u003e\n \u003cli\u003e\u003cstrong\u003eProtection of intellectual property.\u0026nbsp;\u003c/strong\u003eThe TEASUR code is registered under the name of Anderson D\u0026iacute;az P\u0026eacute;rez as an original and unpublished software work.\u0026nbsp;\u003c/li\u003e\n \u003cli\u003e\u003cstrong\u003eConflicts of interest.\u0026nbsp;\u003c/strong\u003eThe author declares no conflicts of interest.\u0026nbsp;\u003c/li\u003e\n \u003cli\u003e\u003cstrong\u003eFunding.\u0026nbsp;\u003c/strong\u003eNo external funding was received for this study.\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor contributions.\u0026nbsp;\u003c/strong\u003eAnderson D\u0026iacute;az P\u0026eacute;rez developed, programmed, tested, and documented the entirety of the TEASUR code, as well as drafting and revising this manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgements.\u0026nbsp;\u003c/strong\u003eNot applicable.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eSaunders C. The evolution of palliative care. Patient Educ Couns. 2000; 41(1):7\u0026ndash;13. doi: 10.1016/s0738-3991(00)00110-5\u003c/li\u003e\n\u003cli\u003eCassell EJ. The nature of suffering and the goals of medicine. N Engl J Med. 1982; 306(11):639\u0026ndash;45. doi: 10.1056/NEJM198203183061104 \u003c/li\u003e\n\u003cli\u003eFerrell BR, Coyle N. The nature of suffering and the goals of nursing. Oncol Nurs Forum. 2008; 35(2):241\u0026ndash;7. doi: 10.1188/08.ONF.241247\u003c/li\u003e\n\u003cli\u003eBeauchamp TL, Childress JF. \u003cem\u003ePrinciples of Biomedical Ethics\u003c/em\u003e. 8th ed. Oxford University Press; 2019. ISBN: 9780190640873\u003c/li\u003e\n\u003cli\u003ePellegrino ED, Thomasma DC. The virtues in medical practice. New York (NY): Oxford University Press; 1993. ISBN: 9780195082890. \u003c/li\u003e\n\u003cli\u003ePeterman AH, Fitchett G, Brady MJ, Hernandez L, Cella D. Measuring spiritual wellbeing in people with cancer: the FACITSp. Ann Behav Med. 2002; 24(1):49\u0026ndash;58. doi: 10.1207/S15324796ABM2401_06\u003c/li\u003e\n\u003cli\u003eBruera E, Kuehn N, Miller MJ, Selmser P, Macmillan K. The Edmonton Symptom Assessment System (ESAS): a simple method for the assessment of palliative care patients. J Palliat Care. 1991 Summer; 7(2):6‑9. PMID: 1714502\u003c/li\u003e\n\u003cli\u003eZigmond AS, Snaith RP. The Hospital Anxiety and Depression Scale. Acta Psychiatr Scand. 1983; 67(6):361\u0026ndash;70. doi: 10.1111/j.1600-0447.1983.tb09716.x\u003c/li\u003e\n\u003cli\u003eBaile WF, Buckman R, Lenzi R, Glober G, Beale EA, Kudelka AP. SPIKES \u0026mdash; a six-step protocol for delivering bad news: application to the patient with cancer. Oncologist. 2000; 5(4):302\u0026ndash;11. doi: 10.1634/theoncologist.5-4-302\u003c/li\u003e\n\u003cli\u003eBalboni TA, Paulk ME, Balboni MJ, et al. Provision of spiritual care to patients with advanced cancer: associations with medical care and quality of life near death. J Clin Oncol. 2010; 28(3):445\u0026ndash;52. doi: 10.1200/JCO.2009.24.8005\u003c/li\u003e\n\u003cli\u003eSoci\u0026eacute;t\u0026eacute; Fran\u0026ccedil;aise d\u0026apos;Accompagnement et de Soins Palliatifs (SFAP). Outil Pallia10. Available from: https://sfap.org\u003c/li\u003e\n\u003cli\u003eHirdes JP, Ljunggren G, Morris JN, et al. Reliability of the interRAI suite of assessment instruments: a 12country study of an integrated health information system. BMC Health Serv Res. 2008;8:277. doi: 10.1186/1472-6963-8-277\u003c/li\u003e\n\u003cli\u003eBarnett GO, Cimino JJ, Hupp JA, Hoffer EP. DXplain: an evolving diagnostic decisionsupport system. JAMA. 1987; 258(1):67\u0026ndash;74. doi: 10.1001/jama.258.1.67\u003c/li\u003e\n\u003cli\u003eDaniels N. Just health: meeting health needs fairly. Cambridge (UK): Cambridge University Press; 2008. ISBN: 9780521699983. \u003c/li\u003e\n\u003cli\u003eBalboni TA, VanderWeele TJ, DoanSoares SD, et al. Spirituality in serious illness and health. JAMA. 2022; 328(2):184\u0026ndash;97. doi: 10.1001/JAMA.2022.11086\u003c/li\u003e\n\u003cli\u003eNussbaum MC. Frontiers of justice: disability, nationality, species membership. Cambridge (MA): Harvard University Press; 2006. ISBN: 9780674019170 \u003c/li\u003e\n\u003cli\u003eDelgadoGuay MO, Hui D, Parsons HA, Govan K, De la Cruz M, Thorney S, et al. Spirituality, religiosity, and spiritual pain in advanced cancer patients. J Pain Symptom Manage. 2011; 41(6):986\u0026ndash;94. doi: 10.1016/j.jpainsymman.2010.09.017\u003c/li\u003e\n\u003cli\u003eMako C, Proulx PM, Galek K. Spiritual pain among patients with advanced cancer in palliative care. J Palliat Med. 2006; 9(5):1106\u0026ndash;13. doi: 10.1089/JPM.2006.9.1106\u003c/li\u003e\n\u003cli\u003eFraser N. Reframing justice in a globalizing world. New Left Rev. 2005; 36:69\u0026ndash;88. \u003c/li\u003e\n\u003cli\u003eHonneth A. The struggle for recognition: the moral grammar of social conflicts. Cambridge (UK): Polity Press; 1995. ISBN: 9780745615935. \u003c/li\u003e\n\u003cli\u003eFricker M. Epistemic injustice: power and the ethics of knowing. Oxford (UK): Oxford University Press; 2007. ISBN: 9780198237906\u003c/li\u003e\n\u003cli\u003eCharon R. Narrative medicine: honoring the stories of illness. New York (NY): Oxford University Press; 2006. ISBN: 9780195340227. \u003c/li\u003e\n\u003cli\u003ePuchalski CM. The role of spirituality in health care. Proc Bayl Univ Med Cent. 2001; 14(4):352\u0026ndash;7. doi: 10.1080/08998280.2001.11927788\u003c/li\u003e\n\u003cli\u003eHonorato MM, Oliveira NP de, Domingues RJ de S, Cremaschi RM de C, Coelho FMS, Silva JAC da. Bioethical Principle of Autonomy in Indigenous Health Care. Rev Bio\u0026eacute;t. 2022; 30:373\u0026ndash;81. doi: 10.1590/198380422022302533EN \u003c/li\u003e\n\u003cli\u003eFraser BA, Powell RA, MwangiPowell FN, Namisango E, Hannon B, Zimmermann C, et al. Palliative Care Development in Africa: Lessons From Uganda and Kenya. J Glob Oncol. 2017; (4):1\u0026ndash;10. doi: 10.1200/JGO.2017.010090\u003c/li\u003e\n\u003cli\u003eCarrilloGonz\u0026aacute;lez GM, BarretoOsorio RV, Arboleda LB, Guti\u0026eacute;rrezLesmes OA, Melo BG, Ortiz VT. Competence to care at home for people with chronic disease and their caregivers in Colombia. Rev Fac Med. 2015; 63(4):665\u0026ndash;75. Available from: https://www.redalyc.org/articulo.oa?id=576363526012\u003c/li\u003e\n\u003cli\u003eGhaemizade Shushtari SS, Molavynejad S, Adineh M, Savaie M, Sharhani A. Effect of End-of-life nursing education on the knowledge and performance of nurses in the intensive care unit: a quasiexperimental study. BMC Nurs. 2022; 21(1):102. doi: 10.1186/s12912-022-00880-8\u003c/li\u003e\n\u003cli\u003eL\u0026oacute;pez \u0026Aacute;vila A, Rivas Riveros E, Campillay Campillay M. Order of non-resuscitation and limitation of therapeutic effort: ethical challenges in healthcare teams in Chile. Salud Colectiva. 2024; 20:e4821. doi: 10.18294/sc.2024.4821\u003c/li\u003e\n\u003cli\u003eDelgadoGuay MO, Palma A, Duarte E, Grez M, Tupper L, Liu DD, et al. Association between Spirituality, Religiosity, Spiritual Pain, Symptom Distress, and Quality of Life among Latin American Patients with Advanced Cancer: A Multicenter Study. J Palliat Med. 2021; 24(11):1606\u0026ndash;15. doi: 10.1089/JPM.2020.0776\u003c/li\u003e\n\u003cli\u003ePastrana T, De Lima L. Palliative Care in Latin America: Are We Making Any Progress? Assessing Development Over Time Using Macro Indicators. J Pain Symptom Manage. 2022; 63(1):33\u0026ndash;41. doi: 10.1016/j.jpainsymman.2021.07.020\u003c/li\u003e\n\u003cli\u003eLaw 1733 of 2014 (Colombia). Consuelo Devis Law. Ministry of Health and Social Protection. Available from: https://www.funcionpublica.gov.co/eva/gestornormativo/norma.php?i=59379 \u003c/li\u003e\n\u003cli\u003eKnaul FM, ArreolaOrnelas H, Kwete XJ, Bhadelia A, Rosa WE, Touchton M, et al. The evolution of serious healthrelated suffering from 1990 to 2021: an update to The Lancet Commission on global access to palliative care and pain relief. Lancet Glob Health. 2025; 13(3):E422\u0026ndash;E436. doi: 10.1016/S2214-109X(24)00476-5\u003c/li\u003e\n\u003cli\u003eSep\u0026uacute;lveda C, Marlin A, Yoshida T, Ullrich A. Palliative care: the WHO global perspective. J Pain Symptom Manage. 2002; 24(2):91\u0026ndash;6. doi: 10.1016/S0885-3924(02)00440-2\u003c/li\u003e\n\u003cli\u003eHarding R. Palliative care in resource-poor settings: fallacies and misapprehensions. J Pain Symptom Manage. 2008; 36(5):515\u0026ndash;7. doi: 10.1016/j.jpainsymman.2008.04.019\u003c/li\u003e\n\u003cli\u003eAlp FY, Yucel SC. The effect of therapeutic touch on the comfort and anxiety of nursing home residents. J Relig Health. 2021;60(4):2037\u0026ndash;50. doi: 10.1007/s10943-020-01025-4\u003c/li\u003e\n\u003cli\u003eMoharra M, Pons JMV, Almaz\u0026aacute;n C, Quintana S, et al. Citizen participation in the institutional ethics committees of clinical and healthcare research in Catalonia. Acta Bioeth. 2018; 24(2):189\u0026ndash;98. doi:10.4067/S1726569X2018000200189\u003c/li\u003e\n\u003cli\u003eD\u0026iacute;az-P\u0026eacute;rez A, L\u0026oacute;pez ADJA, O\u0026ntilde;oro LMM, Orozco SMR, Lubo AMM. Comparison of the methodology analysis of principles and ethical deliberation with the comprehensive methodology of ethicalclinical analysis: approach to an ethical dilemma in nursing. Gac M\u0026eacute;d Caracas. 2024; 132(4). doi: 10.4067/S1726569X2024000200207\u003c/li\u003e\n\u003cli\u003eSadiq FU, Yeh YL, Liao HE, Pranata MAE, Patnaik S, Shih YH. The benefits, barriers, and specific needs of palliative care for adults with cancer in sub-Saharan Africa: a systematic review. Glob Health Action. 2025; 18(1):2485742. doi: 10.1080/16549716.2025.2485742\u003c/li\u003e\n\u003cli\u003ePastrana T, Knaul F. Serious healthrelated suffering in Latin America: a secondary analysis. Lancet Oncol. 2022;23 Suppl 1:S37. doi:10.1016/S14702045(22)004363\u003c/li\u003e\n\u003cli\u003eFarmer P. Pathologies of power: rethinking health and human rights. Am J Public Health. 1999 Oct; 89(10):1486-96. doi: 10.2105/ajph.89.10.1486. \u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Ethical AI, Palliative Care, Relational Suffering, Computational Bioethics, Relational Autonomy, Latin America, Explainable AI","lastPublishedDoi":"10.21203/rs.3.rs-7447403/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7447403/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground.\u003c/strong\u003e End-of-life suffering in Latin America is a multidimensional phenomenon that includes physical, psychological, social, and spiritual domains, which remain insufficiently addressed within traditional biomedical models. Existing instruments fragment the experience, omit contextual variables (e.g., gender, inequities, regulation), and lack ethical justification for clinical decisions.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods.\u003c/strong\u003e We developed TEASUR (Ethical-Adaptive Framework of Relational Suffering), a Python-based prototype that calculates a Total Distress Index (TDI) using adaptive logarithmic logic and SHAP-based XAI. Structural modifiers such as gender, access to palliative care, and socioeconomic inequities were incorporated. Validation was performed exclusively on synthetic data (n = 300), with a representative subsample of 200 cases used for subgroup analyses. Monte Carlo simulations (n = 500) were conducted to assess stability under random perturbations.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults.\u003c/strong\u003e We present TEASUR (Ethical Adaptive Framework of Relational Suffering), a Python-based system that quantifies multidimensional suffering and dynamically adjusts weightings using explainable artificial intelligence. Simulations with a synthetic cohort of 300 cases from five Latin American countries showed that TEASUR detected social and spiritual suffering with greater sensitivity than conventional scales. For subgroup comparisons, a representative subsample of 200 cases was analyzed. When the Total Distress Index (TDI) exceeded 7.0, the system activated narrative, spiritual, and community interventions, which reduced suffering below critical thresholds and prevented disproportionate measures such as immediate palliative sedation. Monte Carlo simulations (n=500) demonstrated high stability of the TDI under random perturbations. The adaptive logarithmic decision flow allowed proportionate and culturally situated responses, while explainable AI modules ensured transparency for ethical deliberation.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusions.\u003c/strong\u003e TEASUR operationalizes suffering as a quantifiable, relational, and ethically traceable variable. By closing measurement gaps, incorporating structural barriers, and integrating spiritual dimensions, TEASUR provides a replicable framework for clinical decisión making in hospital and community palliative care. While validated only through simulations, TEASUR aligns with principles of trustworthy AI and demonstrates potential as a standardized bioethical decisión support tool pending clinical validation.\u003c/p\u003e","manuscriptTitle":"A Bioethical Computational Model for Integrating Relational Suffering into End-of-Life Clinical Decision-making","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-11 15:13:38","doi":"10.21203/rs.3.rs-7447403/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"2e9f20fc-1b97-4b0c-8eb0-8066760fe7d0","owner":[],"postedDate":"September 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-12-29T14:09:29+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-11 15:13:38","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7447403","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7447403","identity":"rs-7447403","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}