SEapp versus MIMIC score for predicting spontaneous ureteral stone passage

SEapp versus MIMIC score for predicting spontaneous ureteral stone passage | 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 SEapp versus MIMIC score for predicting spontaneous ureteral stone passage Riccardo Lombardo, Marta Santioni, Antonio Nacchia, Giorgia Tema, and 9 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9233651/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 PURPOSE - A generative artificial intelligence–based clinical decision-support tool (Spontaneous Expulsion app; SEapp) was developed and prospectively validated to estimate spontaneous stone passage (SSP) in patients with ureteral lithiasis. The secondary objective was to compare its predictive performance with the MIMIC score. METHODS - SEapp was developed using a standardized large language model (LLM)-based architecture powered by ChatGPT (OpenAI). A fixed structured prompt template incorporating predefined clinical, laboratory, and radiological variables was used to generate a probability estimate of SSP. In a second phase, a prospective, single-center, non-interventional cohort study was conducted to evaluate predictive performance. Discrimination was assessed using receiver operating characteristic (ROC) curves and area under the curve (AUC), and clinical utility was evaluated through decision curve analysis (DCA). RESULTS - A consecutive series of 115 adult patients diagnosed with renal colic and radiologically confirmed ureteral lithiasis were prospectively enrolled. On univariable logistic regression analysis, stone location, stone density, maximum stone length, and neutrophil count were significantly associated with SSP (all p < 0.01). Sex, hydronephrosis, hydroureter, number of stones, and serum creatinine were not significantly associated with the outcome. SEapp demonstrated good discriminative performance with an AUC of 0.806 (95% CI 0.719–0.893), outperforming the MIMIC score (AUC 0.772; 95% CI 0.682–0.863) in the estimation of SSP. Decision curve analysis showed a consistently higher net clinical benefit for SEapp across clinically relevant probability thresholds (10–40%). CONCLUSIONS - In this prospective cohort, SEapp demonstrated higher discriminative performance and clinical utility than the MIMIC score. External validation and controlled clinical integration are needed before widespread adoption. stone passage decision-support tool large language models urolithiasis AI Figures Figure 1 Figure 2 Figure 3 Introduction Urolithiasis is one of the most prevalent urological conditions and its initial clinical management remains challenging due to the difficulty in accurately predicting which patients will experience spontaneous stone passage (SSP) and which will require active intervention [ 1 ]. Clinical decision-making is typically based on a heterogeneous combination of anatomical, laboratory, and radiological parameters, whose individual prognostic value is not always clear and is rarely integrated into standardized, user-friendly predictive tools [ 1 ]. In recent years, artificial intelligence (AI) applications in urology have demonstrated significant potential in supporting and optimizing clinical decision-making processes: advanced large language models (LLMs), such as ChatGPT, have shown promising capabilities in processing complex clinical information and generating personalized decision-support outputs [ 2 – 6 ]. Based on these premises, the present study aimed to develop and prospectively validate a generative AI–based clinical decision-support tool, the Spontaneous Expulsion app (SEapp), designed to estimate the probability of SSP using predefined, readily available clinical variables. The secondary objective was to assess the discriminative accuracy and clinical utility of this model by comparing its performance with the MIMIC score proposed by Shah et al [ 7 , 8 ], in a consecutive cohort of patients with ureteral lithiasis. Material & Methods Study Design The study was conducted in two sequential phases: (1) development of an AI–based clinical decision-support tool – the Spontaneous Expulsion app (SEapp), and (2) prospective clinical validation with comparison to the MIMIC score. The study was approved by the local ethics committee and conducted in accordance with the Declaration of Helsinki. Phase 1: Development of the Spontaneous Expulsion app (SEapp) SEapp was developed as a large language model (LLM)–based clinical decision-support tool powered by ChatGPT (OpenAI). Its primary objective was to estimate the probability of SSP in adult patients with ureteral stones by integrating predefined clinical, laboratory, and radiological parameters. Model development was informed by previously published multivariate predictive models, incorporating established prognostic factors for SSP, including stone size, ureteral location (proximal, mid, distal), neutrophil-to-lymphocyte ratio (NLR), degree of hydronephrosis, stone density measured in Hounsfield Units (HU), and urinary inflammatory markers[ 9 – 15 ]. Additional evidence from recent studies on ureteral wall thickness (UWT) and AI-based predictive systems was also integrated [ 11 , 16 ]. These variables were incorporated into a fixed structured and semi-structured prompt template (e.g., “8-mm distal ureteral stone, 600 HU, moderate hydronephrosis, NLR 3.5”). For each case, predefined variables were entered into SEapp using the standardized template and the model generated a probabilistic estimate (0–100%) of SSP. The interface was intentionally designed for educational and decision-support purposes only, avoiding therapeutic recommendations and consistently encouraging specialist urological evaluation. SEapp works as a clinical decision support system (CDSS) rather than a diagnostic device. Probability estimates are derived from probabilistic extrapolation of published evidence rather than supervised machine-learning training on proprietary clinical datasets. The model is accessible online at the following link: https://urology.moretti.cc/ . Phase 2: Prospective Validation and Comparison with the MIMIC Score A prospective, single-center, non-interventional cohort study was conducted. Consecutive adult patients presenting to the emergency department with renal colic and radiologically confirmed ureteral lithiasis were enrolled between December 2024 and November 2025. Eligibility Criteria Inclusion criteria: Age ≥ 18 years Ureteral stone confirmed by non-contrast computed tomography (NCCT) Availability for a 30-day follow-up Exclusion criteria: Active urinary tract infection Fever or signs of sepsis Renal impairment requiring urgent drainage Recent urological intervention (< 6 months) Patient Management All patients received medical expulsive therapy (MET) with an alpha-blocker (tamsulosin), in accordance with current international guidelines [ 17 – 19 ]. Nonsteroidal anti-inflammatory drugs (NSAIDs) were administered for pain control as clinically indicated. SEapp predictions were generated independently and did not guide treatment decisions. Variables The variables collected and processed by SEapp were: number of stones, maximum stone length, ureteral stone location, stone density (HU), presence of hydronephrosis and hydroureter, serum creatinine levels, neutrophil count. MIMIC Score Calculation The MIMIC score, developed by the BURST Urology collaborative, was calculated for each patient using sex, neutrophil count, hydronephrosis, hydroureter, MET use, stone size, stone location, and NSAID administration to estimate SSP probability [ 7 ]. Statistical Analysis Continuous variables were reported as mean ± standard deviation or median (IQR), as appropriate. Group comparisons were performed using Student’s t-test or Mann–Whitney U test for continuous variables and χ² or Fisher’s exact test for categorical variables. Univariable logistic regression was performed to evaluate the association between predefined clinical variables and SSP. SEapp and MIMIC scores were evaluated separately as predictive tools. Discrimination was assessed using receiver operating characteristic (ROC) curves and the area under the curve (AUC). Clinical utility was evaluated through decision curve analysis (DCA), comparing net benefit across probability thresholds against “treat-all” and “treat-none” strategies. Statistical analyses were performed using SPSS version 27 (IBM Corp., Armonk, NY, USA). A two-sided p-value < 0.05 was considered statistically significant. No missing data were observed for variables included in the analysis. Results A consecutive series of 115 patients were enrolled, including 69 men (60%) and 46 women (40%). Patient’s characteristics are enlisted in Table 1 . All patients received medical expulsive therapy with an alpha-blocker at diagnosis. Hydronephrosis was documented in 77/115 patients (67%). Regarding stone burden, 100 patients (87%) had a single stone, 5 (4.3%) had two stones, 9 (7.8%) had three stones, and 1 (0.9%) had four stones. Stone location was juxtavesical in 20 patients (17.4%), distal ureter in 45 (39.1%), mid ureter in 21 (18.3%), and proximal ureter in 29 (25.2%). Spontaneous stone passage (SSP) occurred in 38 patients (33%) within 30 days. The morphological and laboratory characteristics of stones and patients are summarized as follows: the median stone density was 761 (500–1000) HU, while the maximum length had a median of 6 (5–8) mm. Median creatinine serum was 1 (0.8–1.1) mg/dL; median neutrophil count was 6.7 (4.4–9.5) x10 3 µL. Median SEapp score was 35 (20–50) %, and median MIMIC score was 63 (43–72) %. Baseline characteristics stratified by SSP are presented in Table 2 . Patients who achieved SSP had significantly smaller stones, lower stone density, and higher neutrophil counts compared with those who did not. No significant differences were observed in sex, hydronephrosis, hydroureter, number of stones, or serum creatinine levels. On univariable logistic regression analysis, stone location, stone density, maximum stone length, neutrophil, SEapp probability, and MIMIC score count were significantly associated with SSP (all p < 0.01) (Table 3 ). Specifically: Stone location (OR 0.503; 95% CI 0.328–0.769; p < 0.001): probability of expulsion decreased with increasing distance from the ureterovesical junction. Stone density (OR 0.996; 95% CI 0.994–0.997; p < 0.001): higher HU values were associated with lower probability of SSP. Stone length (OR 0.602; 95% CI 0.471–0.767; p < 0.001): increasing size was associated with reduced likelihood of expulsion. SEapp score (OR = 1.071; 95% CI: 1.041–1.102; p < 0.001): an increase in SEapp score is positively associated with expulsion. MIMIC score (OR = 1.058; 95% CI: 1.032–1.085; p < 0.001): an increase in MIMIC score is associated with favourable outcome. Neutrophil count (OR 1.153; 95% CI 1.007–1.320; p = 0.009). Increased neutrophil counts were associated with a greater likelihood of expulsion. Sex, hydronephrosis, hydroureter, number of stones, and serum creatinine were not significantly associated with SSP (Table 3 ). SEapp demonstrated good discriminative ability, with an AUC of 0.806 (95% CI 0.719–0.893). The MIMIC score showed an AUC of 0.772 (95% CI 0.682–0.863) (Fig. 1 ). Decision curve analysis demonstrated consistently higher net clinical benefit for SEapp compared with the MIMIC score across clinically relevant probability thresholds (10–40%) (Fig. 2 , Fig. 3 ). Discussion The present study represents one of the first prospective clinical evaluations of a generative AI–based clinical decision-support tool for predicting spontaneous stone passage (SSP) in ureteral lithiasis. SEapp was designed to generate individualized probability estimates by integrating routinely available clinical, laboratory, and radiological variables. Unlike traditional static predictive scores, such as the MIMIC score [ 7 ], SEapp operates within a flexible LLM framework capable of synthesizing structured inputs into a continuous probability output, through an intuitive conversational interface, potentially improving clinical usability and applicability in real-world settings. In this prospective cohort, SEapp demonstrated good discriminative ability (AUC 0.806) and superior clinical utility compared with the MIMIC score. Decision curve analysis showed consistently greater net benefit across clinically relevant probability thresholds, particularly between 10% and 40%. This range represents a critical decision zone in routine practice, where clinicians must balance continued conservative management against early intervention. These findings suggest that SEapp may support risk stratification, particularly in scenarios characterized by therapeutic uncertainty. A recent external validation of the MIMIC score was conducted by Milton et al at the Royal Adelaide Hospital in Australia [ 20 ]. This retrospective study included 399 patients with acute ureteral colic managed conservatively over two years [ 20 ]. Results showed that the area under the receiver operating characteristic curve (AUC) of the MIMIC score was 0.68 (95% CI: 0.60–0.77), indicating moderate discriminatory ability [ 20 ]. The model tended to underestimate the probability of spontaneous expulsion in low-risk patients: in the quintile with a mean predicted probability of 46%, the observed rate of SSP was 74% (95% CI: 63–83%) [ 20 ]. However, in the quintile with the highest predicted probability (mean 90%), the observed rate of SSP was 92% (95% CI: 84–97%), suggesting good predictive accuracy in high-risk patients [ 20 ]. One of the major strengths of this study lies in its prospective design and homogeneous patient management. The cohort included 115 consecutive patients with symptomatic ureteral stones, all treated with standardized medical expulsive therapy and systematically evaluated with radiological follow-up at 30 days. This approach enhances the internal validity of the findings and reflects real-world clinical practice. In addition, the integration and comparison with a validated predictive model such as the MIMIC score [ 7 , 20 ] allowed an objective evaluation of SEapp performance under clinically relevant conditions. The higher AUC observed for SEapp supports its strong discriminatory capacity and highlights the potential advantages of AI-driven predictive systems in complex clinical scenarios. Regarding individual predictors, our findings are consistent with existing literature, suggesting that the characteristics of the study cohort are aligned with previously reported clinical patterns of spontaneous stone passage. Stone location was significantly associated with spontaneous expulsion, with distal ureteral stones demonstrating significantly higher success rates compared to mid or proximal stones [ 9 ]. This observation reinforces previous evidence and confirms the importance of anatomical assessment in the initial evaluation of renal colic. Stone size was likewise confirmed as a key determinant of conservative management success. Increasing stone length was associated with a substantial increase in the risk of expulsion failure, supporting the need for accurate measurement of maximum stone diameter on computed tomography and its integration into decision-making processes [ 10 ]. Stone density, expressed as Hounsfield units, further contributed to outcome prediction. In line with previous studies, higher HU values were inversely associated with spontaneous expulsion, reflecting the reduced friability and mobility of denser stones [ 11 ]. The association between HU and SSP supports the relevance of quantitative radiological parameters within predictive tools such as SEapp, beyond stone size and location alone. An additional and clinically relevant finding of the present study is the role of systemic inflammation. The role of absolute neutrophilia in predicting SSP remains controversial. Some studies have reported an increased likelihood of SSP in patients with elevated neutrophil counts, whereas others have found higher passage rates in patients with normal neutrophil levels [ 12 , 13 , 15 ]. In our cohort, higher neutrophil counts were associated with an increased likelihood of expulsion. This finding is consistent with the original MIMIC study, in which neutrophil count was positively associated with SSP in univariable analysis [ 7 ]. The heterogeneity of these findings may reflect differences in patient selection, timing of laboratory assessment, and the complex, potentially bidirectional role of inflammation. On one hand, a migrating stone may induce ureteral wall inflammation and trigger a systemic inflammatory response, resulting in elevated neutrophil counts. On the other hand, a sustained inflammatory response may reflect persistent ureteral irritation, edema, spasm, and obstruction, potentially hindering stone passage. Although inflammatory markers are not specific to stone disease, their integration into predictive models may provide incremental prognostic information and deserve further investigation in larger, multicenter cohorts. The spontaneous expulsion rate observed in this study was lower than that reported in large multicenter series [ 7 ]. This difference can be explained by the specific clinical characteristics of our cohort, which included a higher proportion of patients with larger stones and mid-to-proximal ureteral location. While this supports the robustness of the model in a more challenging population, it also represents an important limitation. The predictive performance of SEapp may not be directly generalizable to populations with different baseline characteristics, and external validation in broader and more heterogeneous cohorts is therefore required. The introduction of generative AI into predictive medicine represents a promising but still evolving frontier. Large language models such as ChatGPT offer the ability to synthesize complex and potentially nonlinear clinical data and to present predictions through an accessible and intuitive interface [ 4 , 21 ]. In our study, these capabilities enabled rapid and personalized estimation of expulsion probability, with potential applications in both emergency and outpatient settings. However, several limitations inherent to this technology must be acknowledged. First, SEapp does not account for dynamic clinical variables such as symptom progression, response to therapy, patient comorbidities, or clinician expertise, which remain central to individualized medical decision-making. Second, variability in AI-generated outputs and dependence on underlying training data raise concerns regarding reproducibility and standardization, which are essential prerequisites for clinical implementation [ 22 ]. Third, imperfect adherence to clinical guidelines in complex scenarios has been reported, emphasizing the need for supervised, continuously updated, and clinically controlled AI systems [ 23 , 24 ]. Despite these limitations, AI-based tools should be regarded as decision-support systems rather than replacements for clinical judgment. Their primary value lies in improving risk stratification, supporting consistency in decision-making, and assisting physicians in managing complex clinical scenarios involving multiple interacting variables. From this perspective, SEapp represents a proof-of-concept for the responsible integration of generative AI into urological practice. Future developments should focus on external multicenter validation, integration with dynamically updated clinical data, and close collaboration between clinicians and data scientists. Conclusions In this prospective cohort, SEapp demonstrated good discriminative performance and higher clinical utility than the MIMIC score in predicting spontaneous ureteral stone passage. Established predictors such as stone location, size, and density were confirmed, while neutrophil count emerged as an additional associated factor. Generative AI–based tools may support risk stratification when used as clinical decision-support systems rather than replacements for physician judgment. External validation and calibration assessment are required before routine clinical implementation. Declarations Competing interests The authors declare no competing interests. Funding No funding was received to assist with the preparation of this manuscript. Author Contribution Conceptualization: R:L., A.N.; Methodology: A.C, A.M.; Formal analysis and investigation: R.L, A.F; Writing - original draft preparation: M.S., E.P., M.N.; Writing - review and editing: A.C., G.T, B.T; Supervision: C.D.N., A.T. Data Availability The datasets generated and/or analyzed during the current study are not publicly available due to institutional and privacy restrictions but are available from the corresponding author on reasonable request. References Sorokin I, Mamoulakis C, Miyazawa K, Rodgers A, Talati J, Lotan Y (2017) Epidemiology of stone disease across the world. World J Urol 35(9):1301–1320. 10.1007/s00345-017-2008-6 PubMed PMID: 28213860 Ravi D, Wong C, Deligianni F, Berthelot M, Andreu-Perez J, Lo B et al (2017) Deep Learning for Health Informatics. IEEE J Biomed Health Inf 21(1):4–21. 10.1109/JBHI.2016.2636665 PubMed PMID: 28055930 Mitchell TM (1997) Machine Learning. McGraw-Hill, p 414 Khene ZE, Bigot P, Mathieu R, Rouprêt M, Bensalah K (2024) Development of a Personalized Chat Model Based on the European Association of Urology Oncology Guidelines: Harnessing the Power of Generative Artificial Intelligence in Clinical Practice. Eur Urol Oncol 7(1):160–162. 10.1016/j.euo.2023.06 .009 PubMed PMID: 37474402 Hershenhouse JS, Mokhtar D, Eppler MB, Rodler S, Ramacciotti LS, Ganjavi C et al Accuracy, readability, and understandability of large language models for prostate cancer information to the public. Clin Res. 10.1038/s41391-024-00826-y Tun HM, Naing L, Malik OA, Rahman HA (2025) Artificial Intelligence (AI)-based tools in the diagnosis and management of prostate cancer: a systematic review and meta-analysis. Prostate Cancer Prostatic Dis 2025 1–15. 10.1038/s41391-025-01060-w Shah TT, Gao C, Peters M, Manning T, Cashman S, Nambiar A et al (2019) Factors associated with spontaneous stone passage in a contemporary cohort of patients presenting with acute ureteric colic: results from the Multi-centre cohort study evaluating the role of Inflammatory Markers In patients presenting with acute ureteric…. BJU Int 124(3):504–513. 10.1111/bju.14777 PubMed PMID: 31001912 Gao C, Peters M, Kurver P, Anbarasan T, Jayaraajan K, Manning T et al (2022) Nomogram predicting the probability of spontaneous stone passage in patients presenting with acute ureteric colic. BJU Int 130(6):823–831. 10.1111/bju.15839 PubMed PMID: 35762278 Coll DM, Varanelli MJ, Smith RC (2002) Relationship of spontaneous passage of ureteral calculi to stone size and location as revealed by unenhanced helical CT. AJR Am J Roentgenol 178(1):101–103. 10.2214/ajr.178.1.1780101 PubMed PMID: 11756098 Miller OF, Kane CJ (1999) Time to stone passage for observed ureteral calculi: a guide for patient education. J Urol 162(3 Pt 1):688–691. 10.1097/00005392-199909010 -00014 PubMed PMID: 10458343 Kadırhan Ö, Aydın S, Keskin E, Kantarcı M (2026) Role of ureteral wall thickness and computed tomography imaging in predicting spontaneous passage of ureteral stones. Diagn Interventional Radiol 32(2):139. 10.4274/dir.2025.253304 PubMed PMID: 40626708 Aldaqadossi HA (2013) Stone expulsion rate of small distal ureteric calculi could be predicted with plasma C-reactive protein. Urolithiasis 41(3):235–239. 10.1007/s00240-013-0551-1 PubMed PMID: 23468212 Park CH, Ha JY, Park CH, Kim C, Il, Kim KS, Kim BH (2013) Relationship Between Spontaneous Passage Rates of Ureteral Stones Less Than 8 mm and Serum C-Reactive Protein Levels and Neutrophil Percentages. Korean J Urol 54(9):615–618. 10.4111/kju.2013.54 .9.615 PubMed PMID: 24044096 Ahmad A, Mahmood K, Kumar N, Sharma RR, Ranjan N, Anand RK et al (2024) Predictive Value of C-reactive Protein in the Spontaneous Passage of Lower Ureteric Stones: A Prospective Single-Centre Study. Cureus 16(6):e62669. 10.7759/cureus.62669 PubMed PMID: 39036228 Sfoungaristos S, Kavouras A, Katafigiotis I, Perimenis P (2012) Role of white blood cell and neutrophil counts in predicting spontaneous stone passage in patients with renal colic. BJU Int 110:E339–E345 (8 Pt B). 10.1111/j.1464-410x.2012 Yoshida T, Inoue T, Taguchi M, Omura N, Kinoshita H, Matsuda T (2019) Ureteral wall thickness as a significant factor in predicting spontaneous passage of ureteral stones of ≤ 10 mm: a preliminary report. World J Urol 37(5):913–919. 10.1007/s00345-018-2461-x PubMed PMID: 30155728 Jung H, Do, Cho KS, Jun DY, Jeong JY, Moon YJ, Chung DY et al (2022) Silodosin versus Tamsulosin for Medical Expulsive Therapy of Ureteral Stones: An Updated Systematic Review and Meta-Analysis of Randomized Controlled Trials. Med (Lithuania) 58(12). 10.3390/medicina58121794 PubMed PMID: 36556996 Ramanah M, Banerjee I, Nunkoo S, Robinson J, Krissheeven M, Banerjee I (2025) The Comparative Effectiveness of PDE5 Inhibitors and β3 Agonists Versus α-Blockers in Medical Expulsive Therapy for Distal Ureteric Stones: A Systematic Review and Meta-Analysis of Randomized Controlled Trials. Cureus 17(11). 10.7759/cureus.96637 PubMed PMID: 41393662 Yilmaz E, Batislam E, Basar MM, Tuglu D, Ferhat M, Basar H (2005) The comparison and efficacy of 3 different alpha1-adrenergic blockers for distal ureteral stones. J Urol 173(6):2010–2012. 10.1097/01.ju.0000158453.60029.0 a PubMed PMID: 15879806 Milton TM, Noll DN, Stapleton PS, Zhang PZ, Chieng JC, Chow JC et al (2025) Validating the MIMIC score as a predictor of successful spontaneous stone passage in patients managed conservatively for ureteric colic. ANZ J Surg 95(4):773–777. 10.1111/ans.70033 PubMed PMID: 39963984 Kung TH, Cheatham M, Medenilla A, Sillos C, De Leon L, Elepaño C et al (2023) Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models. PLOS Digit health 2(2). 10.1371/journal.pdig.0000198 PubMed PMID: 36812645 Dave T, Athaluri SA, Singh S (2023) ChatGPT in medicine: an overview of its applications, advantages, limitations, future prospects, and ethical considerations. Front Artif Intell 6. 10.3389/frai.2023.1169595 PubMed PMID: 37215063 Zhou Z, Wang X, Li X, Liao L (2023) Is ChatGPT an Evidence-based Doctor? Eur Urol 84(3):355–356. 10.1016/j.eururo.2023.03 .037 PubMed PMID: 37061445 Lombardo R, Gallo G, Stira J, Turchi B, Santoro G, Riolo S et al (2025) Quality of information and appropriateness of Open AI outputs for prostate cancer. Prostate Cancer Prostatic Dis 28(1):229–231. 10.1038/s41391-024-00789-0 PubMed PMID: 38228809 Tables Table 1 Patient’s characteristics Variables Results n (%), median [IQR] Sex (M/F) 69/46 MET 1 115/115 (100%) Hydronephrosis 77/115 (88,5%) Stones number 1 110/115 (87%) 2 5/115 (4,3%) 3 9/115 (7,8%) 4 1/115 (0,9%) Stone location juxtavesical 20/115 (17,4%) distal 45/115 (39,1%) mid 21/115 (18,3) proximal 29/115 (25,2%) SSP 2 38/115 (33%) Stone density (HU) 761 [500–1000] Maximum length (mm) 6 [ 5 – 8 ] Creatinine (mg/dL) 1 [0,8 − 1,1] Neutrophils (×10³/µL) 6,7 [ 4 , 4 – 9 , 5 ] SEapp 3 score (%) 35 [20–50] MIMIC score (%) 63 [43–72] 1 MET: Medical Expulsive Therapy; 2 SSP: Spontaneous Stone Passage; 3 SEapp: Spontaneous Expulsion app. Table 2 Comparison between patients with or without spontaneous stone expulsion Variable No SSP (n = 77) Yes SSP (n = 38) p Sex M (69) 47 (61%) 22 (58%) 0.746 F (46) 30 (39%) 16 (42%) MET 1 77 (100%) 38 (100%) 1.000 Hydronephrosis Yes 52 (68) 25 (66) 0.639 No 25 (32%) 13 (34) Hydroureter 0.188 Yes 36 (47%) 19 (50%) No 41 (53%) 19 (50%) Number of stones 0.535 1 68 (88%) 32 (84%) 2 2 (3%) 3 (8%) 3 6 (8%) 3 (8%) 4 1 (1%) 0 Stone location < 0.001 Juxtavesical 3 (4%) 17 (45%) Distal 39 (50%) 6 (16%) Mid 10 (13%) 11 (29%) Proximal 25 (33%) 4 (10%) Stone density (HU) 900 [700–1101] 500 [400–703] < 0.001 Maximum length (mm) 7 [ 6 – 10 ] 5 [ 3 – 6 ] < 0.001 Creatinine (mg/dL) 1.0 [0.89–1.17] 1.0 [0.77–1.18] 0.471 Neutrophils (×10³/µL) 5.8 [4.1–8.7] 8.2 [6.8–10.4] 0.009 SEapp 2 score (%) 30 [20–40] 52.5 [39–61] < 0.001 MIMIC score (%) 52 [38–69] 72 [55–90] < 0.001 1 MET: Medical Expulsive Therapy; 2 SEapp: Spontaneous Expulsion app Table 3 Univariable Logistic Regression Variable OR (95% CI) p Sex 0.878 (0.398–1.934) 0.746 Hydronephrosis 1.059 (0.573–1.956) 0.639 Hydroureter 2.243 (0.66–7.61) 0.188 Number of stones 1.042 (0.56–1.93) 0.535 Stone location 0.503 (0.328–0.769) 0.001 Stone density 0.996 (0.994–0.997) 0.001 Maximum length 0.602 (0.471–0.767) 0.001 Creatinine 0.773 (0.201–2.969) 0.471 Neutrophils 1.153 (1.007–1.320) 0.009 SEapp 1 score 1.071 (1.041–1.102) 0.001 MIMIC score 1.058 (1.032–1.085) 0.001 1 SEapp: Spontaneous Expulsion app Additional Declarations No competing interests reported. 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-9233651","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":614415546,"identity":"a409b477-b874-4b53-bfd3-8f76a5a12d4b","order_by":0,"name":"Riccardo Lombardo","email":"","orcid":"","institution":"Sapienza University of Rome","correspondingAuthor":false,"prefix":"","firstName":"Riccardo","middleName":"","lastName":"Lombardo","suffix":""},{"id":614415548,"identity":"24d3da3b-cae6-4b34-8098-3eaeaa45374d","order_by":1,"name":"Marta Santioni","email":"","orcid":"","institution":"Sapienza University of Rome","correspondingAuthor":false,"prefix":"","firstName":"Marta","middleName":"","lastName":"Santioni","suffix":""},{"id":614415551,"identity":"35c822a8-8a8f-42ea-b79d-68f238edd929","order_by":2,"name":"Antonio Nacchia","email":"","orcid":"","institution":"Sapienza University of Rome","correspondingAuthor":false,"prefix":"","firstName":"Antonio","middleName":"","lastName":"Nacchia","suffix":""},{"id":614415555,"identity":"be5208b8-ca58-4499-8d61-39043437b351","order_by":3,"name":"Giorgia Tema","email":"","orcid":"","institution":"Sapienza University of Rome","correspondingAuthor":false,"prefix":"","firstName":"Giorgia","middleName":"","lastName":"Tema","suffix":""},{"id":614415557,"identity":"98e672bf-663a-4af1-9e23-a83b0c440304","order_by":4,"name":"Beatrice Turchi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCUlEQVRIiWNgGAWjYBACAySSgYGxQUIORILYPAzMOLUAVYC0sEG0GMO0yDAwY9djAFMB1cKQ2ACVsWHAYY05e/PzxxUFdnIM8j1mH37usEjfcLu57cPHHDseBnb+A9i0WPYcM2w8Y5BszMDGYzyz94xE7oY7B5tnztyWzIPTYTcSDBsbDA4kNgC1MDO2AbXcSGxm5t3GjFvL/ecfQVrqYVrSDSBa6vHYwgO2JYEBqiUBquUwTi2WPTmFMxsMkg3b2NKKGXvbJAxnArUwztx2nIeNmdkAmxZz9uMbPjb8sZPnZz68meFnW5083430xwwft1Xb8/MffIDVGhhgI0JkFIyCUTAKRgGxAADLl1VFDAHJEQAAAABJRU5ErkJggg==","orcid":"","institution":"Sapienza University of Rome","correspondingAuthor":true,"prefix":"","firstName":"Beatrice","middleName":"","lastName":"Turchi","suffix":""},{"id":614415560,"identity":"31c73afd-431c-4880-a2bc-603f273f7738","order_by":5,"name":"Antonio Franco","email":"","orcid":"","institution":"Sapienza University of Rome","correspondingAuthor":false,"prefix":"","firstName":"Antonio","middleName":"","lastName":"Franco","suffix":""},{"id":614415562,"identity":"81d0b686-a91e-428d-be5f-6af227eb3a0d","order_by":6,"name":"Antonio Cicione","email":"","orcid":"","institution":"Sapienza University of Rome","correspondingAuthor":false,"prefix":"","firstName":"Antonio","middleName":"","lastName":"Cicione","suffix":""},{"id":614415568,"identity":"fb93c580-beb2-4302-8fc3-750b691b5f3b","order_by":7,"name":"Emanuele Pillitteri","email":"","orcid":"","institution":"Sapienza University of Rome","correspondingAuthor":false,"prefix":"","firstName":"Emanuele","middleName":"","lastName":"Pillitteri","suffix":""},{"id":614415570,"identity":"f2917459-c392-49cc-8a88-ce20e41d7e7a","order_by":8,"name":"Miriam Nichiri","email":"","orcid":"","institution":"Sapienza University of Rome","correspondingAuthor":false,"prefix":"","firstName":"Miriam","middleName":"","lastName":"Nichiri","suffix":""},{"id":614415571,"identity":"ddc950a1-8109-4112-8690-525e8f6f2590","order_by":9,"name":"Antonio Cavaliere","email":"","orcid":"","institution":"Sapienza University of Rome","correspondingAuthor":false,"prefix":"","firstName":"Antonio","middleName":"","lastName":"Cavaliere","suffix":""},{"id":614415572,"identity":"bcc76620-df23-4eee-b1c2-5847e309e18b","order_by":10,"name":"Alessandro Moretti","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Alessandro","middleName":"","lastName":"Moretti","suffix":""},{"id":614415573,"identity":"5152d264-2a51-4211-9950-ef8aa9eb7ad6","order_by":11,"name":"Andrea Tubaro","email":"","orcid":"","institution":"Sapienza University of Rome","correspondingAuthor":false,"prefix":"","firstName":"Andrea","middleName":"","lastName":"Tubaro","suffix":""},{"id":614415574,"identity":"cfd6e2b3-e1db-4073-9f3c-2b828bda5ccf","order_by":12,"name":"Cosimo De Nunzio","email":"","orcid":"","institution":"Sapienza University of Rome","correspondingAuthor":false,"prefix":"","firstName":"Cosimo","middleName":"","lastName":"De Nunzio","suffix":""}],"badges":[],"createdAt":"2026-03-26 11:41:13","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9233651/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9233651/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105885796,"identity":"4dcabd8f-5764-4c98-b9a0-e2d2b6210724","added_by":"auto","created_at":"2026-04-01 07:27:42","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":21545,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSEapp e MIMIC score ROC Curves\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-9233651/v1/f321b80749e1c92461cb40fd.png"},{"id":105885770,"identity":"cff22376-b0b3-4c8d-a696-240c5010d6a4","added_by":"auto","created_at":"2026-04-01 07:27:37","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":32437,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eDecision curve analysis for SEapp\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-9233651/v1/b4710c9672f33bcff6dee537.png"},{"id":105885749,"identity":"7a5206f7-38f6-4361-bc30-c9cf2ce3eb27","added_by":"auto","created_at":"2026-04-01 07:27:27","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":27914,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eDecision curve analysis for MIMIC score\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-9233651/v1/4c21d1b380a120cae0999813.png"},{"id":108181904,"identity":"4a16bbe5-05e0-41ef-8b38-a48171157787","added_by":"auto","created_at":"2026-04-30 08:59:00","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":404061,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9233651/v1/07ca5f7c-2542-4a1d-81d9-0697f0781009.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"SEapp versus MIMIC score for predicting spontaneous ureteral stone passage","fulltext":[{"header":"Introduction","content":"\u003cp\u003eUrolithiasis is one of the most prevalent urological conditions and its initial clinical management remains challenging due to the difficulty in accurately predicting which patients will experience spontaneous stone passage (SSP) and which will require active intervention [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Clinical decision-making is typically based on a heterogeneous combination of anatomical, laboratory, and radiological parameters, whose individual prognostic value is not always clear and is rarely integrated into standardized, user-friendly predictive tools [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eIn recent years, artificial intelligence (AI) applications in urology have demonstrated significant potential in supporting and optimizing clinical decision-making processes: advanced large language models (LLMs), such as ChatGPT, have shown promising capabilities in processing complex clinical information and generating personalized decision-support outputs [\u003cspan additionalcitationids=\"CR3 CR4 CR5\" citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eBased on these premises, the present study aimed to develop and prospectively validate a generative AI\u0026ndash;based clinical decision-support tool, the Spontaneous Expulsion app (SEapp), designed to estimate the probability of SSP using predefined, readily available clinical variables.\u003c/p\u003e \u003cp\u003eThe secondary objective was to assess the discriminative accuracy and clinical utility of this model by comparing its performance with the MIMIC score proposed by Shah et al [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e], in a consecutive cohort of patients with ureteral lithiasis.\u003c/p\u003e"},{"header":"Material \u0026 Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\n\u003ch2\u003eStudy Design\u003c/h2\u003e\n\u003cp\u003eThe study was conducted in two sequential phases: (1) development of an AI\u0026ndash;based clinical decision-support tool \u0026ndash; the Spontaneous Expulsion app (SEapp), and (2) prospective clinical validation with comparison to the MIMIC score. The study was approved by the local ethics committee and conducted in accordance with the Declaration of Helsinki.\u003c/p\u003e\n\u003c/div\u003e\n\u003ch3\u003ePhase 1: Development of the Spontaneous Expulsion app (SEapp)\u003c/h3\u003e\n\u003cp\u003eSEapp was developed as a large language model (LLM)\u0026ndash;based clinical decision-support tool powered by ChatGPT (OpenAI). Its primary objective was to estimate the probability of SSP in adult patients with ureteral stones by integrating predefined clinical, laboratory, and radiological parameters.\u003c/p\u003e\n\u003cp\u003eModel development was informed by previously published multivariate predictive models, incorporating established prognostic factors for SSP, including stone size, ureteral location (proximal, mid, distal), neutrophil-to-lymphocyte ratio (NLR), degree of hydronephrosis, stone density measured in Hounsfield Units (HU), and urinary inflammatory markers[\u003cspan class=\"CitationRef\"\u003e9\u003c/span\u003e\u0026ndash;\u003cspan class=\"CitationRef\"\u003e15\u003c/span\u003e]. Additional evidence from recent studies on ureteral wall thickness (UWT) and AI-based predictive systems was also integrated [\u003cspan class=\"CitationRef\"\u003e11\u003c/span\u003e, \u003cspan class=\"CitationRef\"\u003e16\u003c/span\u003e].\u003c/p\u003e\n\u003cp\u003eThese variables were incorporated into a fixed structured and semi-structured prompt template (e.g., \u0026ldquo;8-mm distal ureteral stone, 600 HU, moderate hydronephrosis, NLR 3.5\u0026rdquo;). For each case, predefined variables were entered into SEapp using the standardized template and the model generated a probabilistic estimate (0\u0026ndash;100%) of SSP. The interface was intentionally designed for educational and decision-support purposes only, avoiding therapeutic recommendations and consistently encouraging specialist urological evaluation.\u003c/p\u003e\n\u003cp\u003eSEapp works as a clinical decision support system (CDSS) rather than a diagnostic device. Probability estimates are derived from probabilistic extrapolation of published evidence rather than supervised machine-learning training on proprietary clinical datasets. The model is accessible online at the following link: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://urology.moretti.cc/\u003c/span\u003e\u003c/span\u003e.\u003c/p\u003e\n\u003ch3\u003ePhase 2: Prospective Validation and Comparison with the MIMIC Score\u003c/h3\u003e\n\u003cp\u003eA prospective, single-center, non-interventional cohort study was conducted. Consecutive adult patients presenting to the emergency department with renal colic and radiologically confirmed ureteral lithiasis were enrolled between December 2024 and November 2025.\u003c/p\u003e\n\u003ch3\u003eEligibility Criteria\u003c/h3\u003e\n\u003cp\u003eInclusion criteria:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003eAge\u0026thinsp;\u0026ge;\u0026thinsp;18 years\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eUreteral stone confirmed by non-contrast computed tomography (NCCT)\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eAvailability for a 30-day follow-up\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eExclusion criteria:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003eActive urinary tract infection\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eFever or signs of sepsis\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eRenal impairment requiring urgent drainage\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eRecent urological intervention (\u0026lt;\u0026thinsp;6 months)\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003ePatient Management\u003c/h3\u003e\n\u003cp\u003eAll patients received medical expulsive therapy (MET) with an alpha-blocker (tamsulosin), in accordance with current international guidelines [\u003cspan class=\"CitationRef\"\u003e17\u003c/span\u003e\u0026ndash;\u003cspan class=\"CitationRef\"\u003e19\u003c/span\u003e]. Nonsteroidal anti-inflammatory drugs (NSAIDs) were administered for pain control as clinically indicated. SEapp predictions were generated independently and did not guide treatment decisions.\u003c/p\u003e\n\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\n\u003ch2\u003eVariables\u003c/h2\u003e\n\u003cp\u003eThe variables collected and processed by SEapp were: number of stones, maximum stone length, ureteral stone location, stone density (HU), presence of hydronephrosis and hydroureter, serum creatinine levels, neutrophil count.\u003c/p\u003e\n\u003c/div\u003e\n\u003ch3\u003eMIMIC Score Calculation\u003c/h3\u003e\n\u003cp\u003eThe MIMIC score, developed by the BURST Urology collaborative, was calculated for each patient using sex, neutrophil count, hydronephrosis, hydroureter, MET use, stone size, stone location, and NSAID administration to estimate SSP probability [\u003cspan class=\"CitationRef\"\u003e7\u003c/span\u003e].\u003c/p\u003e\n\u003cdiv id=\"Sec10\" class=\"Section2\"\u003e\n\u003ch2\u003eStatistical Analysis\u003c/h2\u003e\n\u003cp\u003eContinuous variables were reported as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation or median (IQR), as appropriate. Group comparisons were performed using Student\u0026rsquo;s t-test or Mann\u0026ndash;Whitney U test for continuous variables and \u0026chi;\u0026sup2; or Fisher\u0026rsquo;s exact test for categorical variables. Univariable logistic regression was performed to evaluate the association between predefined clinical variables and SSP. SEapp and MIMIC scores were evaluated separately as predictive tools. Discrimination was assessed using receiver operating characteristic (ROC) curves and the area under the curve (AUC). Clinical utility was evaluated through decision curve analysis (DCA), comparing net benefit across probability thresholds against \u0026ldquo;treat-all\u0026rdquo; and \u0026ldquo;treat-none\u0026rdquo; strategies. Statistical analyses were performed using SPSS version 27 (IBM Corp., Armonk, NY, USA). A two-sided p-value\u0026thinsp;\u0026lt;\u0026thinsp;0.05 was considered statistically significant. No missing data were observed for variables included in the analysis.\u003c/p\u003e\n\u003c/div\u003e"},{"header":"Results","content":"\u003cp\u003eA consecutive series of 115 patients were enrolled, including 69 men (60%) and 46 women (40%). Patient\u0026rsquo;s characteristics are enlisted in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. All patients received medical expulsive therapy with an alpha-blocker at diagnosis. Hydronephrosis was documented in 77/115 patients (67%). Regarding stone burden, 100 patients (87%) had a single stone, 5 (4.3%) had two stones, 9 (7.8%) had three stones, and 1 (0.9%) had four stones. Stone location was juxtavesical in 20 patients (17.4%), distal ureter in 45 (39.1%), mid ureter in 21 (18.3%), and proximal ureter in 29 (25.2%). Spontaneous stone passage (SSP) occurred in 38 patients (33%) within 30 days. The morphological and laboratory characteristics of stones and patients are summarized as follows: the median stone density was 761 (500\u0026ndash;1000) HU, while the maximum length had a median of 6 (5\u0026ndash;8) mm. Median creatinine serum was 1 (0.8\u0026ndash;1.1) mg/dL; median neutrophil count was 6.7 (4.4\u0026ndash;9.5) x10\u003csup\u003e3\u003c/sup\u003e \u0026micro;L. Median SEapp score was 35 (20\u0026ndash;50) %, and median MIMIC score was 63 (43\u0026ndash;72) %. Baseline characteristics stratified by SSP are presented in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. Patients who achieved SSP had significantly smaller stones, lower stone density, and higher neutrophil counts compared with those who did not. No significant differences were observed in sex, hydronephrosis, hydroureter, number of stones, or serum creatinine levels.\u003c/p\u003e \u003cp\u003eOn univariable logistic regression analysis, stone location, stone density, maximum stone length, neutrophil, SEapp probability, and MIMIC score count were significantly associated with SSP (all p\u0026thinsp;\u0026lt;\u0026thinsp;0.01) (Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eSpecifically:\u003c/p\u003e \u003cp\u003e \u003cul\u003e \u003cli\u003e \u003cp\u003eStone location (OR 0.503; 95% CI 0.328\u0026ndash;0.769; p\u0026thinsp;\u0026lt;\u0026thinsp;0.001): probability of expulsion decreased with increasing distance from the ureterovesical junction.\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eStone density (OR 0.996; 95% CI 0.994\u0026ndash;0.997; p\u0026thinsp;\u0026lt;\u0026thinsp;0.001): higher HU values were associated with lower probability of SSP.\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eStone length (OR 0.602; 95% CI 0.471\u0026ndash;0.767; p\u0026thinsp;\u0026lt;\u0026thinsp;0.001): increasing size was associated with reduced likelihood of expulsion.\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eSEapp score (OR\u0026thinsp;=\u0026thinsp;1.071; 95% CI: 1.041\u0026ndash;1.102; p\u0026thinsp;\u0026lt;\u0026thinsp;0.001): an increase in SEapp score is positively associated with expulsion.\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eMIMIC score (OR\u0026thinsp;=\u0026thinsp;1.058; 95% CI: 1.032\u0026ndash;1.085; p\u0026thinsp;\u0026lt;\u0026thinsp;0.001): an increase in MIMIC score is associated with favourable outcome.\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eNeutrophil count (OR 1.153; 95% CI 1.007\u0026ndash;1.320; p\u0026thinsp;=\u0026thinsp;0.009). Increased neutrophil counts were associated with a greater likelihood of expulsion.\u003c/p\u003e \u003c/li\u003e \u003c/ul\u003e \u003c/p\u003e \u003cp\u003eSex, hydronephrosis, hydroureter, number of stones, and serum creatinine were not significantly associated with SSP (Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eSEapp demonstrated good discriminative ability, with an AUC of 0.806 (95% CI 0.719\u0026ndash;0.893). The MIMIC score showed an AUC of 0.772 (95% CI 0.682\u0026ndash;0.863) (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eDecision curve analysis demonstrated consistently higher net clinical benefit for SEapp compared with the MIMIC score across clinically relevant probability thresholds (10\u0026ndash;40%) (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e, Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e "},{"header":"Discussion","content":"\u003cp\u003eThe present study represents one of the first prospective clinical evaluations of a generative AI\u0026ndash;based clinical decision-support tool for predicting spontaneous stone passage (SSP) in ureteral lithiasis. SEapp was designed to generate individualized probability estimates by integrating routinely available clinical, laboratory, and radiological variables. Unlike traditional static predictive scores, such as the MIMIC score [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e], SEapp operates within a flexible LLM framework capable of synthesizing structured inputs into a continuous probability output, through an intuitive conversational interface, potentially improving clinical usability and applicability in real-world settings.\u003c/p\u003e \u003cp\u003eIn this prospective cohort, SEapp demonstrated good discriminative ability (AUC 0.806) and superior clinical utility compared with the MIMIC score. Decision curve analysis showed consistently greater net benefit across clinically relevant probability thresholds, particularly between 10% and 40%. This range represents a critical decision zone in routine practice, where clinicians must balance continued conservative management against early intervention. These findings suggest that SEapp may support risk stratification, particularly in scenarios characterized by therapeutic uncertainty. A recent external validation of the MIMIC score was conducted by Milton et al at the Royal Adelaide Hospital in Australia [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. This retrospective study included 399 patients with acute ureteral colic managed conservatively over two years [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. Results showed that the area under the receiver operating characteristic curve (AUC) of the MIMIC score was 0.68 (95% CI: 0.60\u0026ndash;0.77), indicating moderate discriminatory ability [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. The model tended to underestimate the probability of spontaneous expulsion in low-risk patients: in the quintile with a mean predicted probability of 46%, the observed rate of SSP was 74% (95% CI: 63\u0026ndash;83%) [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. However, in the quintile with the highest predicted probability (mean 90%), the observed rate of SSP was 92% (95% CI: 84\u0026ndash;97%), suggesting good predictive accuracy in high-risk patients [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. One of the major strengths of this study lies in its prospective design and homogeneous patient management. The cohort included 115 consecutive patients with symptomatic ureteral stones, all treated with standardized medical expulsive therapy and systematically evaluated with radiological follow-up at 30 days. This approach enhances the internal validity of the findings and reflects real-world clinical practice. In addition, the integration and comparison with a validated predictive model such as the MIMIC score [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e, \u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e] allowed an objective evaluation of SEapp performance under clinically relevant conditions. The higher AUC observed for SEapp supports its strong discriminatory capacity and highlights the potential advantages of AI-driven predictive systems in complex clinical scenarios. Regarding individual predictors, our findings are consistent with existing literature, suggesting that the characteristics of the study cohort are aligned with previously reported clinical patterns of spontaneous stone passage. Stone location was significantly associated with spontaneous expulsion, with distal ureteral stones demonstrating significantly higher success rates compared to mid or proximal stones [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. This observation reinforces previous evidence and confirms the importance of anatomical assessment in the initial evaluation of renal colic. Stone size was likewise confirmed as a key determinant of conservative management success. Increasing stone length was associated with a substantial increase in the risk of expulsion failure, supporting the need for accurate measurement of maximum stone diameter on computed tomography and its integration into decision-making processes [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eStone density, expressed as Hounsfield units, further contributed to outcome prediction. In line with previous studies, higher HU values were inversely associated with spontaneous expulsion, reflecting the reduced friability and mobility of denser stones [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. The association between HU and SSP supports the relevance of quantitative radiological parameters within predictive tools such as SEapp, beyond stone size and location alone.\u003c/p\u003e \u003cp\u003eAn additional and clinically relevant finding of the present study is the role of systemic inflammation. The role of absolute neutrophilia in predicting SSP remains controversial. Some studies have reported an increased likelihood of SSP in patients with elevated neutrophil counts, whereas others have found higher passage rates in patients with normal neutrophil levels [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e, \u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e, \u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e]. In our cohort, higher neutrophil counts were associated with an increased likelihood of expulsion. This finding is consistent with the original MIMIC study, in which neutrophil count was positively associated with SSP in univariable analysis [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. The heterogeneity of these findings may reflect differences in patient selection, timing of laboratory assessment, and the complex, potentially bidirectional role of inflammation. On one hand, a migrating stone may induce ureteral wall inflammation and trigger a systemic inflammatory response, resulting in elevated neutrophil counts. On the other hand, a sustained inflammatory response may reflect persistent ureteral irritation, edema, spasm, and obstruction, potentially hindering stone passage. Although inflammatory markers are not specific to stone disease, their integration into predictive models may provide incremental prognostic information and deserve further investigation in larger, multicenter cohorts.\u003c/p\u003e \u003cp\u003eThe spontaneous expulsion rate observed in this study was lower than that reported in large multicenter series [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. This difference can be explained by the specific clinical characteristics of our cohort, which included a higher proportion of patients with larger stones and mid-to-proximal ureteral location. While this supports the robustness of the model in a more challenging population, it also represents an important limitation. The predictive performance of SEapp may not be directly generalizable to populations with different baseline characteristics, and external validation in broader and more heterogeneous cohorts is therefore required.\u003c/p\u003e \u003cp\u003eThe introduction of generative AI into predictive medicine represents a promising but still evolving frontier. Large language models such as ChatGPT offer the ability to synthesize complex and potentially nonlinear clinical data and to present predictions through an accessible and intuitive interface [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e, \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. In our study, these capabilities enabled rapid and personalized estimation of expulsion probability, with potential applications in both emergency and outpatient settings. However, several limitations inherent to this technology must be acknowledged.\u003c/p\u003e \u003cp\u003eFirst, SEapp does not account for dynamic clinical variables such as symptom progression, response to therapy, patient comorbidities, or clinician expertise, which remain central to individualized medical decision-making. Second, variability in AI-generated outputs and dependence on underlying training data raise concerns regarding reproducibility and standardization, which are essential prerequisites for clinical implementation [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]. Third, imperfect adherence to clinical guidelines in complex scenarios has been reported, emphasizing the need for supervised, continuously updated, and clinically controlled AI systems [\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e, \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eDespite these limitations, AI-based tools should be regarded as decision-support systems rather than replacements for clinical judgment. Their primary value lies in improving risk stratification, supporting consistency in decision-making, and assisting physicians in managing complex clinical scenarios involving multiple interacting variables. From this perspective, SEapp represents a proof-of-concept for the responsible integration of generative AI into urological practice. Future developments should focus on external multicenter validation, integration with dynamically updated clinical data, and close collaboration between clinicians and data scientists.\u003c/p\u003e"},{"header":"Conclusions","content":"\u003cp\u003eIn this prospective cohort, SEapp demonstrated good discriminative performance and higher clinical utility than the MIMIC score in predicting spontaneous ureteral stone passage. Established predictors such as stone location, size, and density were confirmed, while neutrophil count emerged as an additional associated factor. Generative AI\u0026ndash;based tools may support risk stratification when used as clinical decision-support systems rather than replacements for physician judgment. External validation and calibration assessment are required before routine clinical implementation.\u003c/p\u003e"},{"header":"Declarations","content":" \u003cp\u003e \u003cstrong\u003eCompeting interests\u003c/strong\u003e \u003cp\u003eThe authors declare no competing interests.\u003c/p\u003e \u003c/p\u003e\u003ch2\u003eFunding\u003c/h2\u003e \u003cp\u003eNo funding was received to assist with the preparation of this manuscript.\u003c/p\u003e\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eConceptualization: R:L., A.N.; Methodology: A.C, A.M.; Formal analysis and investigation: R.L, A.F; Writing - original draft preparation: M.S., E.P., M.N.; Writing - review and editing: A.C., G.T, B.T; Supervision: C.D.N., A.T.\u003c/p\u003e\u003ch2\u003eData Availability\u003c/h2\u003e\u003cp\u003eThe datasets generated and/or analyzed during the current study are not publicly available due to institutional and privacy restrictions but are available from the corresponding author on reasonable request.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eSorokin I, Mamoulakis C, Miyazawa K, Rodgers A, Talati J, Lotan Y (2017) Epidemiology of stone disease across the world. World J Urol 35(9):1301\u0026ndash;1320. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1007/s00345-017-2008-6\u003c/span\u003e\u003cspan address=\"10.1007/s00345-017-2008-6\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003ePubMed PMID: 28213860\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRavi D, Wong C, Deligianni F, Berthelot M, Andreu-Perez J, Lo B et al (2017) Deep Learning for Health Informatics. IEEE J Biomed Health Inf 21(1):4\u0026ndash;21. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1109/JBHI.2016.2636665\u003c/span\u003e\u003cspan address=\"10.1109/JBHI.2016.2636665\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003ePubMed PMID: 28055930\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMitchell TM (1997) Machine Learning. McGraw-Hill, p 414\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKhene ZE, Bigot P, Mathieu R, Roupr\u0026ecirc;t M, Bensalah K (2024) Development of a Personalized Chat Model Based on the European Association of Urology Oncology Guidelines: Harnessing the Power of Generative Artificial Intelligence in Clinical Practice. Eur Urol Oncol 7(1):160\u0026ndash;162. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.euo.2023.06\u003c/span\u003e\u003cspan address=\"10.1016/j.euo.2023.06\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.009 PubMed PMID: 37474402\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHershenhouse JS, Mokhtar D, Eppler MB, Rodler S, Ramacciotti LS, Ganjavi C et al Accuracy, readability, and understandability of large language models for prostate cancer information to the public. Clin Res. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/s41391-024-00826-y\u003c/span\u003e\u003cspan address=\"10.1038/s41391-024-00826-y\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTun HM, Naing L, Malik OA, Rahman HA (2025) Artificial Intelligence (AI)-based tools in the diagnosis and management of prostate cancer: a systematic review and meta-analysis. Prostate Cancer Prostatic Dis 2025 1\u0026ndash;15. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/s41391-025-01060-w\u003c/span\u003e\u003cspan address=\"10.1038/s41391-025-01060-w\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShah TT, Gao C, Peters M, Manning T, Cashman S, Nambiar A et al (2019) Factors associated with spontaneous stone passage in a contemporary cohort of patients presenting with acute ureteric colic: results from the Multi-centre cohort study evaluating the role of Inflammatory Markers In patients presenting with acute ureteric\u0026hellip;. BJU Int 124(3):504\u0026ndash;513. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/bju.14777\u003c/span\u003e\u003cspan address=\"10.1111/bju.14777\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003ePubMed PMID: 31001912\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGao C, Peters M, Kurver P, Anbarasan T, Jayaraajan K, Manning T et al (2022) Nomogram predicting the probability of spontaneous stone passage in patients presenting with acute ureteric colic. BJU Int 130(6):823\u0026ndash;831. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/bju.15839\u003c/span\u003e\u003cspan address=\"10.1111/bju.15839\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003ePubMed PMID: 35762278\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eColl DM, Varanelli MJ, Smith RC (2002) Relationship of spontaneous passage of ureteral calculi to stone size and location as revealed by unenhanced helical CT. AJR Am J Roentgenol 178(1):101\u0026ndash;103. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.2214/ajr.178.1.1780101\u003c/span\u003e\u003cspan address=\"10.2214/ajr.178.1.1780101\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003ePubMed PMID: 11756098\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMiller OF, Kane CJ (1999) Time to stone passage for observed ureteral calculi: a guide for patient education. J Urol 162(3 Pt 1):688\u0026ndash;691. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1097/00005392-199909010\u003c/span\u003e\u003cspan address=\"10.1097/00005392-199909010\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e-00014 PubMed PMID: 10458343\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKadırhan \u0026Ouml;, Aydın S, Keskin E, Kantarcı M (2026) Role of ureteral wall thickness and computed tomography imaging in predicting spontaneous passage of ureteral stones. Diagn Interventional Radiol 32(2):139. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.4274/dir.2025.253304\u003c/span\u003e\u003cspan address=\"10.4274/dir.2025.253304\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003ePubMed PMID: 40626708\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAldaqadossi HA (2013) Stone expulsion rate of small distal ureteric calculi could be predicted with plasma C-reactive protein. Urolithiasis 41(3):235\u0026ndash;239. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1007/s00240-013-0551-1\u003c/span\u003e\u003cspan address=\"10.1007/s00240-013-0551-1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003ePubMed PMID: 23468212\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePark CH, Ha JY, Park CH, Kim C, Il, Kim KS, Kim BH (2013) Relationship Between Spontaneous Passage Rates of Ureteral Stones Less Than 8 mm and Serum C-Reactive Protein Levels and Neutrophil Percentages. Korean J Urol 54(9):615\u0026ndash;618. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.4111/kju.2013.54\u003c/span\u003e\u003cspan address=\"10.4111/kju.2013.54\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.9.615 PubMed PMID: 24044096\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAhmad A, Mahmood K, Kumar N, Sharma RR, Ranjan N, Anand RK et al (2024) Predictive Value of C-reactive Protein in the Spontaneous Passage of Lower Ureteric Stones: A Prospective Single-Centre Study. Cureus 16(6):e62669. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.7759/cureus.62669\u003c/span\u003e\u003cspan address=\"10.7759/cureus.62669\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003ePubMed PMID: 39036228\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSfoungaristos S, Kavouras A, Katafigiotis I, Perimenis P (2012) Role of white blood cell and neutrophil counts in predicting spontaneous stone passage in patients with renal colic. BJU Int 110:E339\u0026ndash;E345 (8 Pt B). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/j.1464-410x.2012\u003c/span\u003e\u003cspan address=\"10.1111/j.1464-410x.2012\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYoshida T, Inoue T, Taguchi M, Omura N, Kinoshita H, Matsuda T (2019) Ureteral wall thickness as a significant factor in predicting spontaneous passage of ureteral stones of \u0026le;\u0026thinsp;10 mm: a preliminary report. World J Urol 37(5):913\u0026ndash;919. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1007/s00345-018-2461-x\u003c/span\u003e\u003cspan address=\"10.1007/s00345-018-2461-x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003ePubMed PMID: 30155728\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJung H, Do, Cho KS, Jun DY, Jeong JY, Moon YJ, Chung DY et al (2022) Silodosin versus Tamsulosin for Medical Expulsive Therapy of Ureteral Stones: An Updated Systematic Review and Meta-Analysis of Randomized Controlled Trials. Med (Lithuania) 58(12). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/medicina58121794\u003c/span\u003e\u003cspan address=\"10.3390/medicina58121794\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003ePubMed PMID: 36556996\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRamanah M, Banerjee I, Nunkoo S, Robinson J, Krissheeven M, Banerjee I (2025) The Comparative Effectiveness of PDE5 Inhibitors and β3 Agonists Versus α-Blockers in Medical Expulsive Therapy for Distal Ureteric Stones: A Systematic Review and Meta-Analysis of Randomized Controlled Trials. Cureus 17(11). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.7759/cureus.96637\u003c/span\u003e\u003cspan address=\"10.7759/cureus.96637\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003ePubMed PMID: 41393662\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYilmaz E, Batislam E, Basar MM, Tuglu D, Ferhat M, Basar H (2005) The comparison and efficacy of 3 different alpha1-adrenergic blockers for distal ureteral stones. J Urol 173(6):2010\u0026ndash;2012. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1097/01.ju.0000158453.60029.0\u003c/span\u003e\u003cspan address=\"10.1097/01.ju.0000158453.60029.0\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003ea PubMed PMID: 15879806\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMilton TM, Noll DN, Stapleton PS, Zhang PZ, Chieng JC, Chow JC et al (2025) Validating the MIMIC score as a predictor of successful spontaneous stone passage in patients managed conservatively for ureteric colic. ANZ J Surg 95(4):773\u0026ndash;777. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/ans.70033\u003c/span\u003e\u003cspan address=\"10.1111/ans.70033\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003ePubMed PMID: 39963984\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKung TH, Cheatham M, Medenilla A, Sillos C, De Leon L, Elepa\u0026ntilde;o C et al (2023) Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models. PLOS Digit health 2(2). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1371/journal.pdig.0000198\u003c/span\u003e\u003cspan address=\"10.1371/journal.pdig.0000198\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003ePubMed PMID: 36812645\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDave T, Athaluri SA, Singh S (2023) ChatGPT in medicine: an overview of its applications, advantages, limitations, future prospects, and ethical considerations. Front Artif Intell 6. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/frai.2023.1169595\u003c/span\u003e\u003cspan address=\"10.3389/frai.2023.1169595\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003ePubMed PMID: 37215063\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhou Z, Wang X, Li X, Liao L (2023) Is ChatGPT an Evidence-based Doctor? Eur Urol 84(3):355\u0026ndash;356. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.eururo.2023.03\u003c/span\u003e\u003cspan address=\"10.1016/j.eururo.2023.03\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.037 PubMed PMID: 37061445\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLombardo R, Gallo G, Stira J, Turchi B, Santoro G, Riolo S et al (2025) Quality of information and appropriateness of Open AI outputs for prostate cancer. Prostate Cancer Prostatic Dis 28(1):229\u0026ndash;231. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/s41391-024-00789-0\u003c/span\u003e\u003cspan address=\"10.1038/s41391-024-00789-0\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003ePubMed PMID: 38228809\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"},{"header":"Tables","content":"\u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003ePatient\u0026rsquo;s characteristics\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"2\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVariables\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eResults n (%), median [IQR]\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eSex (M/F)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e69/46\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMET\u003c/b\u003e\u003csup\u003e\u003cb\u003e1\u003c/b\u003e\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e115/115 (100%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eHydronephrosis\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e77/115 (88,5%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eStones number\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003e1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e110/115 (87%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003e2\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e5/115 (4,3%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003e3\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e9/115 (7,8%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003e4\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1/115 (0,9%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eStone location\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003ejuxtavesical\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e20/115 (17,4%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003edistal\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e45/115 (39,1%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003emid\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e21/115 (18,3)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eproximal\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e29/115 (25,2%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eSSP\u003c/b\u003e\u003csup\u003e\u003cb\u003e2\u003c/b\u003e\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e38/115 (33%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eStone density (HU)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e761 [500\u0026ndash;1000]\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMaximum length (mm)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6 [\u003cspan additionalcitationids=\"CR6 CR7\" citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eCreatinine (mg/dL)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1 [0,8\u0026thinsp;\u0026minus;\u0026thinsp;1,1]\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eNeutrophils (\u0026times;10\u0026sup3;/\u0026micro;L)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6,7 [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e, \u003cspan additionalcitationids=\"CR5 CR6 CR7 CR8\" citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e, \u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eSEapp\u003c/b\u003e\u003csup\u003e\u003cb\u003e3\u003c/b\u003e\u003c/sup\u003e \u003cb\u003escore (%)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e35 [20\u0026ndash;50]\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMIMIC score (%)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e63 [43\u0026ndash;72]\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003csup\u003e1\u003c/sup\u003eMET: Medical Expulsive Therapy; \u003csup\u003e2\u003c/sup\u003eSSP: Spontaneous Stone Passage; \u003csup\u003e3\u003c/sup\u003eSEapp: Spontaneous Expulsion app.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eComparison between patients with or without spontaneous stone expulsion\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVariable\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNo SSP (n\u0026thinsp;=\u0026thinsp;77)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eYes SSP (n\u0026thinsp;=\u0026thinsp;38)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003ep\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSex\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eM (69)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e47 (61%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e22 (58%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e0.746\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eF (46)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e30 (39%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e16 (42%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMET\u003c/b\u003e\u003csup\u003e\u003cb\u003e1\u003c/b\u003e\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e77 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e38 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eHydronephrosis\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eYes\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e52 (68)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e25 (66)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e0.639\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eNo\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e25 (32%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e13 (34)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eHydroureter\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e0.188\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eYes\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e36 (47%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e19 (50%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eNo\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e41 (53%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e19 (50%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eNumber of stones\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\" morerows=\"4\" rowspan=\"5\"\u003e \u003cp\u003e0.535\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003e1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e68 (88%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e32 (84%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003e2\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (3%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3 (8%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003e3\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6 (8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3 (8%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003e4\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1 (1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eStone location\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eJuxtavesical\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3 (4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e17 (45%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eDistal\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e39 (50%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6 (16%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMid\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10 (13%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e11 (29%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eProximal\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e25 (33%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (10%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eStone density (HU)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e900 [700\u0026ndash;1101]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e500 [400\u0026ndash;703]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMaximum length (mm)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7 [\u003cspan additionalcitationids=\"CR7 CR8 CR9\" citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5 [\u003cspan additionalcitationids=\"CR4 CR5\" citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eCreatinine (mg/dL)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.0 [0.89\u0026ndash;1.17]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.0 [0.77\u0026ndash;1.18]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.471\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eNeutrophils (\u0026times;10\u0026sup3;/\u0026micro;L)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e5.8 [4.1\u0026ndash;8.7]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e8.2 [6.8\u0026ndash;10.4]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.009\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eSEapp\u003c/b\u003e\u003csup\u003e\u003cb\u003e2\u003c/b\u003e\u003c/sup\u003e \u003cb\u003escore (%)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e30 [20\u0026ndash;40]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e52.5 [39\u0026ndash;61]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMIMIC score (%)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e52 [38\u0026ndash;69]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e72 [55\u0026ndash;90]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"4\"\u003e\u003csup\u003e1\u003c/sup\u003eMET: Medical Expulsive Therapy; \u003csup\u003e2\u003c/sup\u003eSEapp: Spontaneous Expulsion app\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eUnivariable Logistic Regression\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVariable\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOR (95% CI)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003ep\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eSex\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.878 (0.398\u0026ndash;1.934)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.746\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eHydronephrosis\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.059 (0.573\u0026ndash;1.956)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.639\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eHydroureter\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2.243 (0.66\u0026ndash;7.61)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.188\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eNumber of stones\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.042 (0.56\u0026ndash;1.93)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.535\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eStone location\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.503 (0.328\u0026ndash;0.769)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eStone density\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.996 (0.994\u0026ndash;0.997)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMaximum length\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.602 (0.471\u0026ndash;0.767)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eCreatinine\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.773 (0.201\u0026ndash;2.969)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.471\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eNeutrophils\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.153 (1.007\u0026ndash;1.320)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.009\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eSEapp\u003c/b\u003e\u003csup\u003e\u003cb\u003e1\u003c/b\u003e\u003c/sup\u003e \u003cb\u003escore\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.071 (1.041\u0026ndash;1.102)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMIMIC score\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.058 (1.032\u0026ndash;1.085)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"3\"\u003e\u003csup\u003e1\u003c/sup\u003eSEapp: Spontaneous Expulsion app\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\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":"stone passage, decision-support tool, large language models, urolithiasis, AI","lastPublishedDoi":"10.21203/rs.3.rs-9233651/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9233651/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003ePURPOSE\u003c/strong\u003e - A generative artificial intelligence–based clinical decision-support tool (Spontaneous Expulsion app; SEapp) was developed and prospectively validated to estimate spontaneous stone passage (SSP) in patients with ureteral lithiasis. The secondary objective was to compare its predictive performance with the MIMIC score.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMETHODS\u003c/strong\u003e - SEapp was developed using a standardized large language model (LLM)-based architecture powered by ChatGPT (OpenAI). A fixed structured prompt template incorporating predefined clinical, laboratory, and radiological variables was used to generate a probability estimate of SSP. In a second phase, a prospective, single-center, non-interventional cohort study was conducted to evaluate predictive performance. Discrimination was assessed using receiver operating characteristic (ROC) curves and area under the curve (AUC), and clinical utility was evaluated through decision curve analysis (DCA).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eRESULTS\u003c/strong\u003e - A consecutive series of 115 adult patients diagnosed with renal colic and radiologically confirmed ureteral lithiasis were prospectively enrolled. On univariable logistic regression analysis, stone location, stone density, maximum stone length, and neutrophil count were significantly associated with SSP (all p \u0026lt; 0.01). Sex, hydronephrosis, hydroureter, number of stones, and serum creatinine were not significantly associated with the outcome. SEapp demonstrated good discriminative performance with an AUC of 0.806 (95% CI 0.719–0.893), outperforming the MIMIC score (AUC 0.772; 95% CI 0.682–0.863) in the estimation of SSP. Decision curve analysis showed a consistently higher net clinical benefit for SEapp across clinically relevant probability thresholds (10–40%).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCONCLUSIONS\u003c/strong\u003e - In this prospective cohort, SEapp demonstrated higher discriminative performance and clinical utility than the MIMIC score. External validation and controlled clinical integration are needed before widespread adoption.\u003c/p\u003e","manuscriptTitle":"SEapp versus MIMIC score for predicting spontaneous ureteral stone passage","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-01 07:23:16","doi":"10.21203/rs.3.rs-9233651/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":"a60e9513-3abe-4c32-a198-3089e42024ea","owner":[],"postedDate":"April 1st, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-29T04:24:39+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-01 07:23:16","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9233651","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9233651","identity":"rs-9233651","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}