Development of a nomogram for predicting the outcome in patients with prolonged disorders of consciousness based on the multimodal evaluative information

Development of a nomogram for predicting the outcome in patients with prolonged disorders of consciousness based on the multimodal evaluative information | 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 Development of a nomogram for predicting the outcome in patients with prolonged disorders of consciousness based on the multimodal evaluative information Juanjuan Fu, Yongli Wu, Hui Feng, Fangyu Chen, Huiyue Feng, Huaping Pan, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5693803/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 23 Apr, 2025 Read the published version in BMC Neurology → Version 1 posted 7 You are reading this latest preprint version Abstract Objective To establish a nomogram prediction model for the patients with prolonged disorders of consciousness (PDOC) caused by brain injury at six months based on behavioral scale scores, neuroelectro-physiological techniques and hypothalamic-pituitary hormone levels. Methods The clinical data of patients with PDOC who were first diagnosed and hospitalized in the Department of Rehabilitation Medicine of The Affiliated Jiangning Hospital of Nanjing Medical University from March 2023 to July 2024 were collected retrospectively. We performed stratified sampling based on etiology and divided into a training set (121 cases) and a validation set (49 cases) in a ratio of 7:3. After a 6-month follow-up, patients were divided into groups with improved consciousness and those without improved consciousness based on changes in CRS-R scores.Clinical behavioral scores, somatosensory evoked potentials, brainstem auditory evoked potentials, and levels of hypothalamic-pituitary hormones were utilized to identify prognostic factors for prolonged disorders of consciousness. Concurrently, a nomogram prediction model was crafted and validated to forecast the prognosis of patients with prolonged disorders of consciousness. Decision curve analysis (DCA) was subsequently employed to appraise the clinical applicability of this predictive model. Results The comparison of clinical data between the training and validation cohorts revealed no significant statistical disparities (P > 0.05). Within the training cohort of 121 PDOC patients, 63 (52.1%)PDOC patients exhibited enhanced consciousness levels. Similarly, in the validation cohort of 49 PDOC patients, 25 (51%) PDOC patients showed improvements in consciousness. Utilizing a combination of random forest analysis, LASSO regression, and multivariate Logistic regression, we identified four key predictive variables: CRS-R score (OR = 1.05, 95%CI 1.02–1.08, P = 0.002), BAEP grading(OR = 0.88, 95%CI 0.79–0.98, P = 0.02), N60 classification (OR = 1.22, 95%CI 1.01–1.48, P = 0.02), and Estradiol (OR = 1.01, 95%CI 1.00–1.02, P = 0.01). The area under the curve (AUC) for the predictive model in the training set was 0.919(95%CI 0.87–0.968),while in the validation set, it was 0.888(95%CI 0.796–0.98). The calibration curves demonstrated a high degree of concordance between predicted probabilities and actual results, suggesting that the model possesses strong discriminative power and calibration accuracy. Furthermore, in the context of clinical decision-making, Decision Curve Analysis indicated a superior net benefit for our predictive model. Conclusion The nomogram model, which integrates CRS-R score,BAEP grading,N60 classification and Estradiol, provides a comprehensive assessment of short-term prognosis in patients with prolonged disorders of consciousness, demonstrating high accuracy. disorder of consciousness brain injury minimally conscious state vegetative state cohort Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Introduction As emergency and critical care medicine has made rapid strides, the survival rate of patients with brain injuries has markedly improved, resulting in a significant rise in the prevalence of disorders of consciousness (DOC). In China, it is estimated that there are between 300,000 and 500,000 individuals with DOC, with over 70,000 new cases reported annually. This translates to an annual medical expenditure of 30 to 50 billion yuan[ 1 ],imposing a considerable burden on both the caregivers and families of DOC patients, and sparking numerous ethical and legal concerns[ 2 ]. Within the first year following the emergence of consciousness disorders, the mortality rate stands at a staggering 35%, with only 40% of patients experiencing any improvement in their level of consciousness[ 3 ]. There is an urgent need for early, objective, and precise prognostic assessments, as these will significantly impact future medical decisions. The Coma Recovery Scale-Revised (CRS-R) is recognized as the preeminent clinical tool for the structured assessment of patients with disorders of consciousness, showcasing robust reliability and validity. Nonetheless, complications such as severe movement disorders, aphasia, endotracheal intubation, and fluctuations in arousal levels can impede behavioral evaluations, resulting in a misdiagnosis rate that reaches up to 43%[ 4 ]. Neuroelectrophysiological assessments are straightforward to conduct and enable continuous, real-time monitoring at the bedside. They offer critical insights into the extent and severity of brain damage, potentially aiding in the prognostic determination for individuals with disorders of consciousness. The bilateral absence of N20 waves in Somatosensory Evoked Potentials (SEPs) post-median nerve stimulation serves as an early marker for poor prognosis in patients with anoxic coma, albeit with limited sensitivity[ 5 , 6 ]. The short-latency SEP are primarily concerned with evaluating the integrity of sensory pathways and their corresponding cortical regions, excluding the secondary processing within higher-order cortical networks, which renders their prognostic significance a matter of debate [ 7 – 10 ]. Middle-Latency Somatosensory Evoked Potentials (MLSEP), such as N35, N60, and N70, are capable of reflecting the integrity of secondary cortical networks and could be potential indicators of consciousness recovery in patients with disorders of consciousness[ 11 , 12 ]. Nevertheless, the sensitivity and specificity of MLSEP in prognostic assessment are less than ideal, potentially attributable to variations in sample size and timing of prediction[ 11 , 13 – 16 ]. Furthermore, research on the prognostic implications of evoked potentials in PDOC patients is scarce, leaving the clarity of their prognostic value undetermined. Furthermore, neuroendocrine disorders are commonly observed in patients with brain injuries[ 16 – 21 ]. A study found that neuroendocrine disorders affect cognitive functions such as attention, memory, and executive ability in post-brain injury patients [ 22 ]. Additionally, a study has demonstrated substantial correlations between sex hormone levels and the Glasgow Outcome Scale extended (GOSE), with sex hormones showing a positive correlation and IGF-1 a negative correlation with GOSE scores[ 23 ]. These findings highlight the potential influence of neuroendocrine functions on the prognosis of patients with prolonged disorders of consciousness. Consequently, this study endeavors to uncover prognostic factors associated with prolonged disorders of consciousness by leveraging clinical baseline information, behavioral evaluations, neuroelectrophysiological assessments, and hypothalamic-pituitary hormonal levels. Furthermore, it seeks to develop a predictive model that facilitates a visual and probabilistic prognosis assessment for patients grappling with prolonged disorders of consciousness. Materials and methods Patients We conducted a retrospective analysis of 170 patients with prolonged disorders of consciousness treated in the Department of Rehabilitation Medicine of The Affiliated Jiangning Hospital of Nanjing Medical University from March 2023 to July 2024. The inclusion criteria were as follows: (i) aged 18–75 years; (ii) severe trauma, hypoxia, or vascular brain injury; (iii) a clinical diagnosis of VS (Vegetative State) or MCS (Minimally Conscious State) made by the Chinese version of the Coma Recovery Scale-Revised (CRS-R)[ 24 , 25 ]; (IV) 1–3 months post-injury; and (V) stabilized medical clinical conditions. Patients with mixed etiology (e.g., traumatic and anoxic brain injury) or a premorbid history of psychiatric or neurodegenerative diseases were excluded. Exclusion criteria included: (I) Unstable vital signs such as severe heart failure or respiratory failure; (II) previous history of brain injury or neurodegenerative disease; (III) use of sedatives drugs, antiepileptic drugs, and nerve excitation drugs; (IV) known hearing impairment; and (V) incomplete clinical data. Note Clinical evaluations were performed bedside, facilitated by caregivers who provide significant stimulation to the patients. The registration of information was the responsibility of three physicians participating in the study, who also managed the clinical care of the patients. Sample size estimation We relied on the Events Per Variable criterion (EPV), particularly EPV ≥ 10, to determine the minimum sample size required[ 26 ]. With four independent variables selected and 40% of patients showing clinical improvement[ 3 ], the minimum sample size calculated was 100. Considering a dropout rate of 20% during the study period, a minimum of 120 participants were required. Clinical evaluation We collected clinical data on the age, gender, etiology, duration of ICU stay, decompressive craniectomy status, history of hypertension, history of diabetes, history of coronary heart disease, and CRS-R scores of patients with prolonged disorders of consciousness. Brainstem Auditory Evoked Potentials (BAEP) and upper limb somatosensory evoked potentials were recorded following standard laboratory protocols[ 27 , 28 ], utilizing the Neuron-Spectrum-4 electromyography and evoked potential instrument manufactured by the Russian neurosoft company. Cortical SEPs were deemed present if they were observed either bilaterally or unilaterally. Conversely, SEPs were classified as absent in cases where no bilateral SEPs were detected. BAEP grading followed the Hall classification[ 29 ]: Grade 1, normal; Grade 2, slightly abnormal, exhibiting moderate waveform differentiation, with possible issues such as prolonged peak latency of the I, III, or (and) V waves, prolonged interpeak latency of the I–III, III–V, or (and) I–V waves, peak-to-peak latency ratio of III–V/I –III > 1, and amplitude ratio of V/I < 0.15; Grade 3, moderate abnormality, featuring poor waveform differentiation and repeatability, with possible issues such as prolonged peak latency of the III or V waves, or disappearance of the V wave; and Grade 4, severe abnormality, characterized by only the I wave's presence or the disappearance of all waveforms. We collected the following hormone levels from patients with prolonged disorders of consciousness (PDOC)within 48 hours of admission: cortisol, adrenocorticotropic hormone (ACTH), thyroid stimulating hormone (TSH), free thyroxine (FT4), free triiodothyronine (FT3), prolactin (PRL), luteinizing hormone (LH), follicle stimulating hormone (FSH), testosterone, and estradiol (E2). Outcome definition All PDOC patients were categorized into Vegetative State (VS)/Unresponsive Wakefulness Syndrome (UWS), Minimally Conscious State (MCS) based on repeated CRS-R scores. Clinical diagnosis of UWS/VS was assigned when patients exhibited a sleep-wake cycle, autonomic nerve and motor reflexes, but lacked self or environmental signs of conscious behavior [ 30 ]. Patients may transition to MCS[ 31 ], characterized by clear signs of consciousness and behavior, such as following simple commands and responding to harmful stimuli. Consideration for emergence from MCS was given if patients could functionally communicate or use objects. After a 6-month follow-up, patients were classified as "improved" if they transitioned from MCS to eMCS, or from VS/UWS to MCS, or if they ultimately regained consciousness. Patients were classified as "NO improved" if MCS patients at baseline regressed to VS/UWS, showed no improvement, or died [ 32 ]. Statistical analysis The data were analyzed and processed using R software(version 4.2.1, R Foundation for Statistical Computing, Vienna, Austria);The specific R packages "caret", "rfPermute", "glmnet", "rms", "pROC"and "rmda" were used for model construction and validation.Normally distributed continuous variables were presented as mean ± standard deviation and compared using independent sample t-tests. Non-normally distributed data were presented as median (interquartile range) and analyzed using the Kruskal-Wallis rank-sum test. Categorical variables were expressed as frequency (percentage) and compared using the chi-square test or Fisher's exact probability. This study retrospectively analyzed clinical data from 170 patients with PDOC. Collected parameters included 17 electrophysiological and biochemical measures. The raw data underwent dual-independent verification before being entered into an Excel database. Data cleaning was performed using R software, with exclusion of variables showing > 10% missing values. Through the "caret "package (v6.0-94), stratified sampling was implemented with stratification by etiology, dividing the cohort into training (n = 121) and validation (n = 49) sets at a 7:3 ratio.The training set was utilized for feature selection and model construction, while the validation set was employed to evaluate the model's effectiveness. Inter-group comparability was confirmed by chi-square tests (p > 0.05). Random forest for Variable Selection:Importance assessment was performed using the "rfPermute"package (v2.5.1) to construct a permutation-based random forest model. The number of decision trees (number of trees[ntree] = 134) was determined by monitoring the stability of the Out-of-Bag (OOB) error. When the number of trees exceeded 100, the fluctuation range of the OOB error remained below 0.5%, indicating model convergence. Parallel computing was implemented with num.cores = 3 to accelerate the analysis. Permutation tests were employed to generate p-values by simulating a random distribution, with the precision of these estimates directly dependent on the number of permutations (nrep = 134). Variable importance was assessed based on the mean decrease in accuracy (Mean Decrease Accuracy), and statistical significance was defined as p < 0.05.After correcting for multiple testing bias using permutation-derived p-values, nine candidate variables were selected for subsequent analysis based on their ranked importance. Lasso Regression for variable selection was performed using L1-regularized regression (alpha = 1) implemented in the"glmnet"package (v4.1-7). The optimal penalty parameter (λ) was determined via 10-fold stratified cross-validation, with λ.min selected to minimize the cross-validated deviance, ensuring an optimal trade-off between model fit and overfitting risk. Following variable compression, four core predictors were retained based on non-zero coefficients: CRS-R score,BAEP grading,Estradiol,N60 classification.The variable selection process was visualized using elastic net coefficient paths, and multicollinearity was assessed via variance inflation factors (VIFs), all of which were < 5, confirming the absence of significant collinearity among selected predictors.A forced-entry multivariable logistic regression model was built using the selected predictors. odds ratios (ORs) and 95% confidence intervals (95%CI)were computed via the"rms"package(v6.7-0), with results visualized in a nomogram. Akaike Information Criterion (AIC) for the optimally parsimonious model (AIC = 82.3) was presented as a clinically interpretable nomogram for individualized outcome prediction. We conducted comprehensive validation of model performance across three key domains - discrimination, calibration, and clinical utility - through both training set and independent validation set validation approaches.ROC curve analysis was performed using the "pROC" package (v1.18.2). We calculated:Area under the curve (AUC) with 95% CI(DeLong's method),Optimal cutoff determined by Youden's index (sensitivity + specificity-1);Internal validation: AUC computation on training set(n = 119) with 10-fold cross-validation; External validation: Independent testing on validation cohort (n = 51) without model refitting.Calibration curves were assessed via 1,000 bootstrap resamples, with LOESS smoothing to evaluate agreement between predicted and observed probabilities.Overall prediction accuracy was quantified using the Brier score (range: 0–1).Internal validation: Calibration curves were plotted for the training set.External validation: Curves were generated for the validation set to test calibration on new data.Decision Curve Analysis(DCA) was performed using the "rmda"package(v1.6), calculating net benefit across threshold probabilities (5%-95%);The clinically actionable range was highlighted via shaded regions. Internal validation: Initial net benefit estimation;External validation: Confirmation of clinical applicability.Finally, We developed an interactive interface for the final model was established based on the validation set to facilitate clinical evaluation applications. Results Baseline data A total of 170 patients with PDOC were included in the final analysis (Fig. 1 ). The demographic and clinical characteristics of the training and validation sets are summarized in Table 1 . After a 6-month follow-up, 88 patients (51.8%) showed an improvement in their level of consciousness; in the raining set, there were 121 patients with an average age of 60.11 ± 12.01 years and a CRS-R score of 10.17 ± 4.14 points; 63 patients (52.1%) showed an improvement in their level of consciousness. In the validation set, there were 49 patients with an average age of 57.61 ± 11.78 years and a CRS-R score of 9.41 ± 3.85 points; among them, 25 patients (51%) showed an improvement in their level of consciousness. Table 1 Demographic and clinical characteristics of the patients in two group Factors Classify Training set(121) Validation set(49) P Age(years) 60.11 ± 12.01 57.61 ± 11.78 0.22 Sex Female 41(33.9%) 18(36.7%) 0.73 Male 80(66.1%) 31(63.3%) Smoke history NO 61(51.4%) 22(44.9%) 0.32 YES 60(49.6%) 27(55.1%) Drink history NO 64(52.9%) 24(49.0%) 0.39 YES 57(47.1%) 25(51.0%) Hypertension history NO 26(21.5%) 7(14.3%) 0.19 YES 95(78.5%) 42(85.7%) Diabetes history NO 98(81.0%) 42(85.7%) 0.31 YES 23(19.0%) 7(14.3%) Coronary heart disease NO 106(87.6%) 43(87.8%) 0.60 YES 15(12.4%) 6(12.2%) Decompressive Craniotomy NO 54(44.6%) 22(44.9%) 0.47 YES 67(55.4%) 27(55.1%) Etiology Trauma 31(25.6%) 12(24.5%) 0.99 Stroke 76(62.8%) 32(65.3%) Anoxia 14(11.6%) 5(10.2%) Diagnosis Vegetative State 80(66.1%) 26(53.1%) 0.08 Minimally Conscious State 41(33.9%) 23(46.9%) Improved outcome NO 58(47.9%) 24(49.0%) 0.52 YES 63(52.1%) 25(51.0%) N20 classification NO 31(25.6%) 13(26.5%) 0.52 YES 90(74.4%) 36(73.5%) YES 87(73.1%) 34(66.7%) N60 classification NO 47(38.8%) 19(38.8%) 0.59 YES 74(61.2%) 30(61.2%) Brainstem Auditory Evoked Potentials grading Level 1 17(14.0%) 5(10.2%) 0.62 Level 2 57(47.1%) 29(59.2%) Level 3 42(34.7%) 13(26.5%) Level 4 5(4.1%) 2(4.1%) The duration of ICU(days) 24.67 ± 14.24 25.31 ± 10.57 0.78 Course (days) 91.55 ± 46.64 96.86 ± 42.39 0.49 CRS-R score 10.17 ± 4.14 9.41 ± 3.85 0.27 Progesterone(ng/ml) 0.72 ± 0.28 0.67 ± 0.33 0.33 Testosterone(nmol/L) 6.51 ± 5.69 6.69 ± 6.19 0.85 Prolactin(ng/ml) 25.39 ± 14.79 23.88 ± 13.99 0.54 Estradiol (pg/ml) 26.98 ± 12.17 28.01 ± 11.79 0.62 Luteotropichormone(IU/ L) 10.26 ± 8.52 12.01 ± 10.78 0.26 Follicle-stimulating hormone(IU/L) 18.78 ± 17.21 19.21 ± 18.44 0.89 Cortisol (nmol/L) 467.94 ± 141.66 434.22 ± 135.34 0.16 Adreno-cortico-tropic-hormone(pg/ml) 49.16 ± 26.09 44.47 ± 21.61 0.27 Free triiodothyronine (pmol/L) 3.56 ± 0.88 3.42 ± 0.75 0.34 Free triiodothyronine (pmol/L) 16.79 ± 3.37 15.97 ± 3.08 0.14 Thyroid-stimulating hormone (mIU /L) 3.18 ± 2.03 4.09 ± 3.65 0.11 Data are expressed as n (%), mean ± SD, median (IQR), as appropriate Identify predictors Using the random forest method, 27 independent variables were screened, and ultimately 9 variables were identified as statistically significant (**P < 0.01, *P < 0.05). After testing and adjustment, when ntree = 134, nreo = 134, and num.cores = 3, the top most important feature variables were determined to be CRS-R score,Diagnosis,BAEP grading, Estradiol, Etiology,N60 classification, Cortisol,TSH,and N20 classification(Fig. 2 ). Using the Lasso regression model, 9 characteristics were tested for their ability to predict the clinical outcomes and to avoid overfitting. The Lasso coefficient profiles of features and the optimal penalization coefficient lambda + 1se are shown in Fig. 3 . The feature selection results revealed that nine variables, including CRS-R score,Diagnosis,BAEP grading, Estradiol, Etiology,N60 classification, Cortisol and N20 classification, could be used to predict clinical prognosis for PDOC patients. Finally, the findings from the random forest analysis and lasso regression analysis were synergistically combined to identify the six most influential predictors of recovery in consciousness levels: CRS-R score,Diagnosis,BAEP grading,Estradiol,N60 classification and TSH.These predictors were further examined through multivariate logistic regression in Table 2 . Table 2 Multivariate logistic regression analysis Variable OR(95%CI) P-Values CRS-R score 1.05(1.02,1.08) 0.002 Diagnosis 1.13(0.91,1.41) 0.26 BAEP grading 0.88(0.79,0.98) 0.02 Estradiol 1.01(1.00,1.02) 0.01 N60 classification 1.22(1.01,1.48) 0.04 TSH 1.03(0.99,1.05) 0.07 OR, odd ratio; CI, confidence interval; coma recovery scale-revised ,CRS-R Construction of clinical prediction model Based on the results of multivariate logistic regression analysis, a nomogram model was constructed for predicting the 6-month prognosis of patients with PDOC using CRS-R score, BAEP grading,N60 classification and estradiol (Fig. 4 ). The nomogram consists of variable names and tick marks. Points in the first row can calculate the single score of each prognostic factor. Lines 2–5 represent the specific classification of each prognostic factor, with scores calculated separately according to the first row. The total points in the sixth row represent the sum of scores from all prognostic factors. The individual prognostic score of each factor for a patient is determined by adding up the total score. Line 7 indicates the clinical prognosis prediction of DOC patients. To obtain the corresponding clinical improvement probability of the patient, a vertical line is drawn based on the total score of the patient (Fig. 4 ). The independent risk factors included in the nomogram were validated using the R packages (caret,rfPermute,rms,glmnet,pROC,rmda) to draw the receiver operating characteristic curve. The AUC values of the training set and the validation set were 0.919(95%CI 0.87–0.968)and 0.888(95%CI 0.796–0.98), respectively(Fig. 4 A, 4 B).Thus,the nomogram achieved a C-index of 0.888 in the validation set. Nomogram model calibration and decision curve In order to assess the consistency between the actual risk and predicted risk of the model, calibration curves were plotted,demonstrating a high degree of consistency between the observed and predicted probabilities of consciousness recovery in PDOC patients(Figs. 6 A, 6 B). The blue calibration curve represents the predicted proportion of the clinical outcome to the probability of the actual outcome. The dashed black line indicates that the actual risk is equal to the predicted risk. As shown in Fig. 6 (A and B), the DCA plots showed that the logistic model was clinically useful and had good predictive ability in the training set. Additionally, the fluctuation observed at the end of the prediction model curve may be attributed to the relatively small sample size. We have successfully developed a user-friendly clinical interactive interface designed for the short-term prognosis prediction of patients with prolonged disorders of consciousness. This tool enables medical professionals to conveniently determine the 6-month prognosis for PDOC patients with ease and efficiency;We also provide a website for the convenience of clinical doctors to use, and the interface is shown in Fig. 8 . Discussion In this study, we developed a nomogram using CRS-R score, BAEP grading,N60 classification and estradiol in Fig. 4 , which achieved a C-index of 0.888 in the validation set, indicating a good fit and suitability for clinical outcomes of patients with Prolonged Disorders of Consciousness after a 6-month follow-up. The ROC curves for this nomogram’s prognosis prediction are presented in Fig. 5 .Calibration and decision curve analysis demonstrated that clinicians can benefit from the decision-making supported by this model. The main etiologies of PDOC include traumatic brain injury, ischemic stroke, hemorrhagic stroke, or hypoxic-ischemic disease. The recovery of consciousness in DOC patients varies according to the etiology[ 33 ]. Compared with patients with non-traumatic injuries, patients with traumatic injuries are more likely to recover consciousness[ 34 , 35 ]. Our analysis revealed that etiology was not an independent predictor in this study, potentially reflecting the uneven distribution of etiologies within our patient cohort. Specifically, stroke cases were disproportionately represented compared to traumatic brain injuries, which may have influenced the statistical significance of etiology as a standalone predictor.Additionally,age, course of disease, and ICU stay were not significantly correlated with prognosis. This may be due to selection bias and limited sample size, and further studies with larger sample sizes are needed to verify these findings.After taking into account the etiology, age, course of disease and Coma Recovery Scale-Revised (CRS-R) scores remain significant prognostic factors for DOC patients[ 36 – 38 ]. Our study also supports that higher CRS-R scores are associated with better clinical outcomes, which aligns with findings from previous research[ 39 , 40 ]. Damage to the brainstem ascending reticular activating system is one cause of disorders of consciousness. The severity of brainstem injury is closely correlated with the level of consciousness. Brainstem auditory evoked potentials, as a method for assessing brainstem conduction pathways, is one of the earliest clinical tools used to predict the prognosis of patients with disorders of consciousness. While bilateral absence of N20 and BAEP wave V showed the highest specificity (100%, 95% CI: 85.9%-100%) and positive predictive value (100%, 95% CI: 80.8%-100%) for poor outcome in patients with severe ischemic brain injury[ 41 ].Our study and previous study[ 42 ]support that BAEP grading is associated with the prognosis of DOC patients and can serve as an independent predictor for PDOC patients. The halamic-cortical dysfunction is crucial in the pathophysiology of DOC patients. Median nerve SEPs, as one of the representatives reflecting the thalamocortical pathway, still have controversial predictive value in the prognosis of PDOC patients; in our study, the classification of N20 cannot be serve as an independent predictive factor for the prognosis of chronic disorders of consciousness, which is inconsistent with previous studies[ 43 , 44 ]. Secondly, while short-latency potential measurements are effective in evaluating the integrity of sensory pathways and their corresponding cortical regions, they do not account for the secondary processing that occurs within higher-order cortical networks. The engagement of more distant cortical regions necessitates the intactness of these second-order networks, which in turn are responsible for the generation of medium and long-latency potentials[ 45 ].MLSEP are not only regulated by the ascending reticular activation system but are also correlated with cortical and subcortical functional connectivity integrity [ 12 , 46 ]. They can reflect higher-order brain processes, which are essential for the recovery of consciousness and favorable outcomes after acquired brain injury. Previous studies have indicated that bilateral absence of the N60 component is associated with Previous studies suggest that the presence of N60/N70 responses may be a potential indicator of good prognosis[ 47 – 50 ],while the absence of N60 bilaterally indicates poor prognosispoor prognosis[ 12 ], with a false positive rate of 8% (95% CI 0.04–0.16) [ 51 ].However, these studies mainly focus on patients with early coma, and there is limited research on MLSEP in patients with PDOC. In this study, we found that the presence of N60 was an independent predictor of the 6-month prognosis of PDOC, indicating better subcortical functional connectivity and a higher likelihood of consciousness recovery. Pituitary dysfunction is a common complication after brain injuries[ 16 – 20 ]. Therefore, changes in the endocrine function of the hypothalamic-pituitary axis can be considered one of the initially measurable alterations after brain injury[ 51 ].Brain injury orcerebral edema can damage the anatomical structure of the hypothalamus, leading to a decrease in gonadal hormone level[ 52 , 53 ]. Some studies have identified a deficiency in hypothalamic-pituitary-related hormones in patients with severe DOC[ 54 , 55 ]. Our study revealed that estradiol levels were independent predictors of the prognosis of PDOC. Evidence suggests that estradiol has neuroprotective effects [ 56 , 57 ]and can directly regulate cortical excitability and interhemispheric connectivity. In a comparative study investigating the efficacy of high-frequency repetitive transcranial magnetic stimulation (HF-rTMS) and sham stimulation of the left dorsolateral prefrontal cortex in patients with PDOC, researchers observed that responders to HF-rTMS treatment exhibited relatively high estradiol levels compared to non-responders. Based on these findings, HF-rTMS may potentially therapeutically impact PDOC by enhancing estradiol levels[ 58 ]. The aforementioned studies provide a theoretical basis for considering estradiol as a predictor of prognosis in patients with PDOC. In our study, the combination of CRS-R score, BAEP grading,N60 classification and Estradiol was found to be a reliable predictor of the prognosis for patients with prolonged disorders of consciousness, with an AUC of 0.888 in the validation set.Liu and colleagues found that the combination of N60 and MMN within 7 days after coma had good predictive performance for arousal, with an AUC value of 0.852[ 50 ].It's important to note that while the former model is primarily designed to predict patients in the acute phase, our study focuses on patients with PDOC. Additionally, our study incorporated behavioral assessment and estradiol levels alongside electrophysiological indicators, enhancing the prognostic value from various perspectives. Kang et al. conducted a study utilizing age, diagnosis, GCS score, and BAEP grading, yielding an AUC of 0.815 in their retrospective prognostic model study[ 42 ]. This AUC was lower than that of our model (AUC = 0.888), possibly owing to the fact that compared to the GCS score, the CRS-R score is more suitable for the behavioral assessment of patients with PDOC. Secondly, N60 may provide information on higher-order cortical information processing capabilities. Moreover, estradiol can serve as an objective indicator to reflect the serological changes in patients with PDOC and provide partial prognostic information. In our study, several limitations should be acknowledged. First and foremost, it is important to acknowledge that our study, being a single-center investigation with a relatively small sample size, may not be fully representative of broader patient populations, thereby potentially limiting the generalizability of our findings. Moreover, the etiological distribution of our study cohort was not uniform, with stroke cases significantly outnumbering other etiologies. This uneven distribution could introduce a degree of bias in our analysis. Additionally, considering the complexity of our predictive model, which incorporates multiple variables, we recognize the necessity for validation in a larger and more diverse cohort to further substantiate our results and enhance the robustness of our conclusions.Future research endeavors should prioritize the implementation of dynamic monitoring of hormone levels, a strategy that holds the potential to significantly enhance the precision of patient classification and stratification in clinical management. It is imperative to recognize that neurophysiological data, often gathered within the complex signal-to-noise milieu of intensive care rehabilitation units, predominantly depend on visual analysis that is notably less reliable for interpreting evoked potential outcomes. Given these limitations, there is a pressing need to develop and deploy robust quantitative analytical methods or to harness the power of machine learning techniques. Such advancements could markedly improve the stability and reliability of research findings, thereby bolstering the overall validity and applicability of the results. Conclusion In conclusion, the nomogram model, which incorporates CRS-R score, BAEP grading,N60 classification and Estradiol, proves to be advantageous for assessing the short-term prognosis of patients with prolonged disorders of consciousness, with a high degree of accuracy. This model not only aids in prognostication for PDOC but also assists in refining treatment strategies and ensuring the judicious use of healthcare resources. Declarations Acknowledgments Not applicable Conflict of interest The authors declare that they have no conflict of interest. Funding This work was supported by the National Key Research and Development Program of China (Grant No.:2022YFC2009700) and Nanjing Science and technology development Foundation (Grant No:YKK22219). Ethics approval The study adhered to the Declaration of Helsinki II and good clinical practice guidelines, and was approved by the ethics committee of Jiangning Hospital Affiliated to Nanjing Medical University (Approval Code:2022-03-047-k01,Date:2023-02-22). Consent to Participate Legal caregivers of all participants provided written informed consent. Consent to Publish Not applicable Author contributions JuanjuanFu and Hui Feng carried out the studies, participated in collecting data, and drafted the manuscript.Huaping Pan and Yongli Wu performed the statistical analysis and participated in its design.Fangyu Chen and Huiyue Feng participated in acquisition, analysis, or interpretation of data and draft the manuscript.Hongxing Wang was responsible for research supervision, guidance and fund acquisition.All authors read and approved the final manuscript. Availability of data and materials All data generated or analysed during this study are included in this published article References Wei-Guan C, Ran L, Ye Z, Jian-Hui H, Ju-Bao D, Ai-Song G, Wei-Qun S. Recovery from prolonged disorders of consciousness: A dual-center prospective cohort study in China. World J Clin Cases 2020, 8. Rohaut B, Eliseyev A, Claassen J. Uncovering Consciousness in Unresponsive ICU Patients: Technical, Medical and Ethical Considerations. Crit Care. 2019;23(1):78. Julia N, Mikhail K, Ilya B, Pranil P, Denis S, Alexey V, Maria S, Vera P, Marina VP, Elena L et al. One-Year Demographical and Clinical Indices of Patients with Chronic Disorders of Consciousness. Brain Sci 2021, 11(5). Kaitlen H, Eva G, Anke-Maria K, Andreas S, Andreas B. Rehabilitation outcome of anoxic-ischaemic encephalopathy survivors with prolonged disorders of consciousness. Resuscitation 2013, 84(10). Maenia S, Riccardo C, Francesco L, Giovanni L, Maddalena S, Franco V, Maria L, Daniela A, Sara C, Maria Grazia C et al. Neurophysiology for predicting good and poor neurological outcome at 12 and 72 h after cardiac arrest: The ProNeCA multicentre prospective study. Resuscitation 2019, 147(0). Claudio S, Sonia DA, Jerry PN. Prognostication after cardiac arrest. Crit Care 2018, 22(1). Thijs M, vS A-F, vR, Marjolein MA, Wouter VP, Johannes HMTK, Janneke H. SSEP amplitudes add information for prognostication in postanoxic coma. Resuscitation 2021, 163(0). Riccardo C, Maenia S, Francesco L, Maddalena S, Giovanni L, Adriano P, Chiara L, Aldo A, Antonello G. Early-SEPs' amplitude reduction is reliable for poor-outcome prediction after cardiac arrest? Acta Neurol Scand 2018, 139(2). Christian E, Christian S, Christoph JP, Christoph L. Amplitudes of SSEP and outcome in cardiac arrest survivors: A prospective cohort study. Neurology 2015, 85(20). Stefano dB G, Luigi G, Simone L, Claudio B, Patrizia S, Gianluca R, Federica B, Matteo F, Antonio C, Davide T et al. The importance of polysomnography in the evaluation of prolonged disorders of consciousness: sleep recordings more adequately correlate than stimulus-related evoked potentials with patients' clinical status. Sleep Med 2014, 15(4). E G J Z, J H T M K RJ, dH AH. SSEPs and prognosis in postanoxic coma: only short or also long latency responses? Neurology 2006, 67(4). Yan Z, Miao W, Ying Ying S. The role of middle latency evoked potentials in early prediction of favorable outcomes among patients with severe ischemic brain injuries. J Neurol Sci 2014, 345(0). Zhang Y, Wang M, Su YY. The role of middle latency evoked potentials in early prediction of favorable outcomes among patients with severe ischemic brain injuries. J Neurol Sci. 2014;345(1–2):112–7. L AG, G C F KMH, C Z, C FSMHEB. M: Time-dependency of sensory evoked potentials in comatose cardiac arrest survivors. Intensive Care Med 2001, 27(8). Damian C, Loretta N, Teneille G, Bryan G, Adrian Y. M O: Positive prognostication from median-nerve somatosensory evoked cortical potentials. Neurocrit Care 2014, 21(2). M R A MB, M C Z, N B. E C DU: Prevalence of hypopituitarism in patients with cerebrovascular diseases. J Endocrinol Invest 2008, 31(0). Aleksandra G-J, Łukasz K, Alicja H-D. Traumatic brain injuries induced pituitary dysfunction: a call for algorithms. Endocr Connect 2020, 9(5). John AE, Hannah F, Jamie JL, Kieran M, Peter JDA. Prevalence of Anterior Pituitary Dysfunction Twelve Months or More following Traumatic Brain Injury in Adults: A Systematic Review and Meta-Analysis. J Neurotrauma 2019, 37(2). Wei-Hsun Y, Pau-Chung C, Ting-Chung W, Ting-Yu K, Chun-Yu C, Yao-Hsu Y. Endocrine dysfunction following traumatic brain injury: a 5-year follow-up nationwide-based study. Sci Rep 2016, 6(0). A MK, N G M JJS, U F-R. M K, : Acute and long-term pituitary insufficiency in traumatic brain injury: a prospective single-centre study. Clin Endocrinol (Oxf) 2007, 67(4). Tamás N, Helga M, Veronika G, Bertalan A, Csongor SA, József K. Abnormalities of pituitary function after traumatic brain injury in children. J Neurotrauma 2007, 24(1). Josef Z, Osborne FXA. Neuropsychology of Neuroendocrine Dysregulation after Traumatic Brain Injury. J Clin Med 2015, 4(5). Anna T, Charlotte H, Bo-Michael B, Jörgen B. Impact of pituitary dysfunction on cognitive and global outcome after traumatic brain injury and aneurysmal subarachnoid haemorrhage. J Rehabil Med 2019, 51(4). Joseph TG, Kathleen K, John W. The JFK Coma Recovery Scale-Revised: measurement characteristics and diagnostic utility. Arch Phys Med Rehabil 2004, 85(12). Sarah W, Lizette H, Marie T, Olivia G, Steven L. The repetition of behavioral assessments in diagnosis of disorders of consciousness. Ann Neurol 2017, 81(6). Maarten vS, Karel Gm M, Joris Ah dG, Gary SC, Douglas GA, Marinus Jc E, Johannes BR. Sample size for binary logistic prediction models: Beyond events per variable criteria. Stat Methods Med Res 2018, 28(8). M J A GC, J M G GC, R RKFMPM, R-D T. L G-L: Recommendations for the clinical use of somatosensory-evoked potentials. Clin Neurophysiol 2008, 119(8). T W P, S A H, H I K RG. Human auditory evoked potentials. I. Evaluation of components. Electroencephalogr Clin Neurophysiol 1974, 36(2). J W 3rd H, M H-f, T A G: Auditory function in acute severe head injury. Laryngoscope 1982, 92(0). Steven L, Gastone GC, Francois C, Jan L, José L-C, Walter GS, Leon S, Erich S, Klaus R, vW, Adam Z et al. Unresponsive wakefulness syndrome: a new name for the vegetative state or apallic syndrome. BMC Med 2010, 8(0). Joseph TG, D I K SANCRCBJ, J P K JHR. J W, R D Z : The minimally conscious state: definition and diagnostic criteria. Neurology 2002, 58(3). Qi X, Kai L, Yong W, Yunliang T, Xiaoyang D, Yuan Z, Yao Z, Zhen F. A prediction model of clinical outcomes in prolonged disorders of consciousness: A prospective cohort study. Front Neurosci 2023, 16(0). Medical aspects of. the persistent vegetative state (1). N Engl J Med 1994, 330(21). Robert GK, Flora MH, Alan HW, Risa N-R, Ross DZ, John W, Joseph TG. Recovery of Consciousness and Functional Outcome in Moderate and Severe Traumatic Brain Injury. JAMA Neurol 2021, 78(5). Michael AM, Joseph TG, Jason B, Nancy RT, Lindsay DN, Harvey SL, Sureyya D, Murray S, Yelena GB, Kim B et al. Functional Outcomes Over the First Year After Moderate to Severe Traumatic Brain Injury in the Prospective, Longitudinal TRACK-TBI Study. JAMA Neurol 2021, 78(8). Anna E, Salvatore F, Alfonso M, Rita F, Donatella M, Antonello G, Anna Maria R, Efthymios A, Helena C, Aurore T et al. Multicenter prospective study on predictors of short-term outcome in disorders of consciousness. Neurology 2020, 95(11). Anna E, Pasquale M, Telese T, Luigi T. Predictors of recovery of responsiveness in prolonged anoxic vegetative state. Author reply. Neurology 2013, 81(14). Estraneo A, Fiorenza S, Magliacano A, Formisano R, Mattia D, Grippo A, Romoli AM, Angelakis E, Cassol H, Thibaut A, et al. Multicenter prospective study on predictors of short-term outcome in disorders of consciousness. Neurology. 2020;95(11):e1488–99. Emilio P, Azzurra M, Anna Maria R, Bahia H, Maria Pia T, Elena L, Martina DR, Antonello G, Claudio M. Score on Coma Recovery Scale-Revised at admission predicts outcome at discharge in intensive rehabilitation after severe brain injury. Brain Inj 2018, 32(6). Ching CF, James JML, Paul MB. The Relationship of the FOUR Score to Patient Outcome: A Systematic Review. J Neurotrauma 2019, 36(17). Zhang Y, Su YY, Haupt WF, Zhao JW, Xiao SY, Li HL, Pang Y, Yang QL. Application of electrophysiologic techniques in poor outcome prediction among patients with severe focal and diffuse ischemic brain injury. J Clin Neurophysiol. 2011;28(5):497–503. Kang J, Huang L, Tang Y, Chen G, Ye W, Wang J, Feng Z. A dynamic model to predict long-term outcomes in patients with prolonged disorders of consciousness. Aging. 2022;14(2):789–99. Sergio B, Cristina B, Antonino Sa, Alexander AF, Andrew AF, Giuseppe G. Emerging from an unresponsive wakefulness syndrome: brain plasticity has to cross a threshold level. Neurosci Biobehav Rev 2013, 37(0). Lawrence RR, Paula JM, David LT, Henry LL. Predictive value of somatosensory evoked potentials for awakening from coma. Crit Care Med 2003, 31(3). J-M G AA, K V A PA, dW SBA, C EF. F, P H, V J : Consensus on the use of neurophysiological tests in the intensive care unit (ICU): electroencephalogram (EEG), evoked potentials (EP), and electroneuromyography (ENMG). Neurophysiol Clin 2009, 39(2). Aldo R, Massimo C, Fabio G, Damian C, Bryan G, Carlo Y, Simone M. R: Clinical neurophysiology of prolonged disorders of consciousness: From diagnostic stimulation to therapeutic neuromodulation. Clin Neurophysiol 2017, 128(9). Andrea Victoria A-V, Eva María F-D, Emilio G-G, Javier S-P, David M-L, Tomás S. Functional and Prognostic Assessment in Comatose Patients: A Study Using Somatosensory Evoked Potentials. Front Hum Neurosci 2022, 16(0). Christian E, Erik W, Martin K, Kaspar JS, Hans K, Werner S, Christian S, Christoph JP, Tobias C, Hans F et al. Hypoxic-Ischemic Encephalopathy Evaluated by Brain Autopsy and Neuroprognostication After Cardiac Arrest. JAMA Neurol 2020, 77(11). Alessandra DF, Stefano B, Federico L, Bruno S, Emanuela F, Paolo B, Stefano M, Paolo Z. The potential role of pain-related SSEPs in the early prognostication of long-term functional outcome in post-anoxic coma. Eur J Phys Rehabil Med 2017, 53(6). Yifei L, Huijin H, Yingying S, Miao W, Yan Z, Weibi C, Gang L, Mengdi J. The Combination of N60 with Mismatch Negativity Improves the Prediction of Awakening from Coma. Neurocrit Care 2021, 36(3). Claudio S, Fabio C, Clifton WC, Sonia DA, Tommaso S, Michael AK, Matteo B, Giacomo DM, Alessio F, Jerry PN. Predictors of poor neurological outcome in adult comatose survivors of cardiac arrest: a systematic review and meta-analysis. Part 2: Patients treated with therapeutic hypothermia. Resuscitation 2013, 84(10). Andrea L, Ruth T, Faten EA, Ali M, Christopher LK, Christos L, Fernando DG. Neuroendocrine Dysfunction in the Acute Setting of Penetrating Brain Injury: A Systematic Review. World Neurosurg 2020, 147(0). M HJKSMJK. J, F H: The corticosterone synthesis inhibitor metyrapone prevents hypoxia/ischemia-induced loss of synaptic function in the rat hippocampus. Stroke 2000, 31(5). Yu HZ, Hong YW, Ren HH, Bi EZ, Jian ZF. Sex Differences in Sex Hormone Profiles and Prediction of Consciousness Recovery After Severe Traumatic Brain Injury. Front Endocrinol (Lausanne) 2019, 10(0). Amy KW, Emily HM, Christian N, Haishin O, Tammy LL, Julie AD, Christopher AB, Martina S, Edward C, Sarah D. L B : Acute serum hormone levels: characterization and prognosis after severe traumatic brain injury. J Neurotrauma 2011, 28(6). Paco SH, Ines PK, Patricia DH. Sex, sex steroids, and brain injury. Semin Reprod Med 2009, 27(3). Lee S, Chung S, Rogasch N, Thomson C, Worsley R, Kulkarni J, Thomson R, Fitzgerald P, Segrave R. The influence of endogenous estrogen on transcranial direct current stimulation: A preliminary study. Eur J Neurosci. 2018;48(4):2001–12. He R, Wang H, Zhou Z, Fan J, Zhang S, Zhong Y. The influence of high-frequency repetitive transcranial magnetic stimulation on endogenous estrogen in patients with disorders of consciousness. Brain Stimul. 2021;14(3):461–6. Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 23 Apr, 2025 Read the published version in BMC Neurology → Version 1 posted Editorial decision: Revision requested 04 Apr, 2025 Editor assigned by journal 04 Apr, 2025 Reviews received at journal 04 Apr, 2025 Reviewers agreed at journal 01 Apr, 2025 Reviewers invited by journal 01 Apr, 2025 Submission checks completed at journal 01 Apr, 2025 First submitted to journal 30 Mar, 2025 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-5693803","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":436906246,"identity":"72444d31-1b8e-4326-bc56-8d1cfae785fc","order_by":0,"name":"Juanjuan Fu","email":"","orcid":"","institution":"Zhongda Hospital Southeast University","correspondingAuthor":false,"prefix":"","firstName":"Juanjuan","middleName":"","lastName":"Fu","suffix":""},{"id":436906248,"identity":"d252dd1e-7ea1-431c-88df-29952a277ca1","order_by":1,"name":"Yongli Wu","email":"","orcid":"","institution":"The Affiliated Jiangning Hospital of Nanjing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yongli","middleName":"","lastName":"Wu","suffix":""},{"id":436906249,"identity":"808c1ab9-d309-439b-9754-ca6803966716","order_by":2,"name":"Hui Feng","email":"","orcid":"","institution":"The Affiliated Jiangning Hospital of Nanjing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Hui","middleName":"","lastName":"Feng","suffix":""},{"id":436906250,"identity":"d8c83c11-dfa3-4548-a71d-e49937f6e17e","order_by":3,"name":"Fangyu Chen","email":"","orcid":"","institution":"The Affiliated Jiangning Hospital of Nanjing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Fangyu","middleName":"","lastName":"Chen","suffix":""},{"id":436906251,"identity":"d4e23a00-f482-4284-8d11-b1ff1d462b04","order_by":4,"name":"Huiyue Feng","email":"","orcid":"","institution":"The Affiliated Jiangning Hospital of Nanjing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Huiyue","middleName":"","lastName":"Feng","suffix":""},{"id":436906253,"identity":"9e2a1d2a-f3da-4704-89ba-08ba61fcfbf9","order_by":5,"name":"Huaping Pan","email":"","orcid":"","institution":"The Affiliated Jiangning Hospital of Nanjing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Huaping","middleName":"","lastName":"Pan","suffix":""},{"id":436906254,"identity":"e09b5c88-0a5c-4ca7-9264-6cd9054de8b6","order_by":6,"name":"Hongxing Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4ElEQVRIie3RMQrCMBSA4UggWR52bSjqFSIBXYpniQidegA3WwJO4i56iB4h2qGLB6jgkCLUxcFVBBUdRWzdHPKPj/ct7yFks/1hBDciLcc+dmj0GjSiKtKkKjZmG1A20zVJGzLVLaYbh+eyJiHucOpKoj22OBYHQH4r0bg01QT2wvFCIQAFItGkz6uJW47YMiQeoHSYaCBuNeHpJNllxyugew0Ca8WlTDHPUQ8D0jUIjWMjdYDZLBRsxUdikZLeV9JR1Kwvt+crs+J8Gg9a80yVX8lbz1PhH/ZtNpvN9rkH1rxKp1GTFTAAAAAASUVORK5CYII=","orcid":"","institution":"Zhongda Hospital Southeast University","correspondingAuthor":true,"prefix":"","firstName":"Hongxing","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2024-12-22 12:53:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5693803/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5693803/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s12883-025-04189-2","type":"published","date":"2025-04-23T15:58:02+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":79805130,"identity":"7d3b54ae-bcf9-4619-966f-3dc06c039be8","added_by":"auto","created_at":"2025-04-03 05:11:13","extension":"jpeg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":174568,"visible":true,"origin":"","legend":"\u003cp\u003eFlow chart of patient enrollment\u003c/p\u003e","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-5693803/v1/d2976b6808fb3daf0ad52417.jpeg"},{"id":79805124,"identity":"20ac751e-e713-40ea-a0aa-a4493206fbec","added_by":"auto","created_at":"2025-04-03 05:11:13","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":346479,"visible":true,"origin":"","legend":"\u003cp\u003eVariable importance diagram of the random forest model\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-5693803/v1/fb2411291e872bd77a5c78ef.png"},{"id":79805122,"identity":"78b1c61c-308d-447a-ae95-beed3d4156a4","added_by":"auto","created_at":"2025-04-03 05:11:12","extension":"jpeg","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":109945,"visible":true,"origin":"","legend":"\u003cp\u003e3A Lasso coefficient profiles of 9 alternative factors. \u0026nbsp;3B The tuning parameter λ (lambda) selection in the Lasso models used 10-fold cross validation by minimum criteria.\u003c/p\u003e","description":"","filename":"floatimage36.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-5693803/v1/0836120064f2a75877394f5e.jpeg"},{"id":79805179,"identity":"c30544cc-57da-453c-baac-5dc4e70b6662","added_by":"auto","created_at":"2025-04-03 05:11:15","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":200479,"visible":true,"origin":"","legend":"\u003cp\u003eA visual nomogram for predicting the improvement of consciousness in PDOC patients; for instance, the case indicated by the pink arrow,a CRS-R score of 10, BAEP gradingof 4,N60 presence and an estradiol level of 28 pg/ml. Considering these four variables, the corresponding probability of regaining consciousness is 0.49.\u003c/p\u003e","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-5693803/v1/5bfc9a66d60bba474e70c586.png"},{"id":79805127,"identity":"e2742926-1305-4e79-bb9d-c9276fb54e28","added_by":"auto","created_at":"2025-04-03 05:11:13","extension":"jpeg","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":155362,"visible":true,"origin":"","legend":"\u003cp\u003e5A The ROC curves in the training set \u0026nbsp;5B The ROC curves in the validation set\u003c/p\u003e","description":"","filename":"floatimage57.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-5693803/v1/93439ecbaf979617c9bb1d0d.jpeg"},{"id":79806643,"identity":"5a3e7e0d-a634-471f-9639-bb3e12b5c24b","added_by":"auto","created_at":"2025-04-03 05:29:21","extension":"jpeg","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":127450,"visible":true,"origin":"","legend":"\u003cp\u003e6A The calibration curve in the training set 6B The calibration curve in the validation set\u003c/p\u003e","description":"","filename":"floatimage67.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-5693803/v1/759be19604d051d59032b962.jpeg"},{"id":79805135,"identity":"9ba555fc-e9d3-4b9c-8792-266ea05e668c","added_by":"auto","created_at":"2025-04-03 05:11:13","extension":"jpeg","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":118998,"visible":true,"origin":"","legend":"\u003cp\u003e7A The decision curve in the training set 7B The decision curve in the validation set\u003c/p\u003e","description":"","filename":"floatimage73.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-5693803/v1/dba25aa70de6f7894e060227.jpeg"},{"id":79805128,"identity":"8bb9ca82-1877-49cb-aa7c-c2ea511d6d48","added_by":"auto","created_at":"2025-04-03 05:11:13","extension":"png","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":66385,"visible":true,"origin":"","legend":"\u003cp\u003eConstruction of a web-based calculator for predicting outcomes of prolonged disorders of consciousness based on the mode（https://outcome-prediction.shinyapps.io/outcome-prediction-1/）\u003c/p\u003e","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-5693803/v1/d34f6905fe53aa688d4f48af.png"},{"id":81569693,"identity":"12739c95-bc63-4c63-8644-aa8c6e8442ce","added_by":"auto","created_at":"2025-04-28 16:10:12","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1898578,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5693803/v1/cd5edc61-baa3-4b29-88fe-4018df6ddc9a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Development of a nomogram for predicting the outcome in patients with prolonged disorders of consciousness based on the multimodal evaluative information","fulltext":[{"header":"Introduction","content":"\u003cp\u003eAs emergency and critical care medicine has made rapid strides, the survival rate of patients with brain injuries has markedly improved, resulting in a significant rise in the prevalence of disorders of consciousness (DOC). In China, it is estimated that there are between 300,000 and 500,000 individuals with DOC, with over 70,000 new cases reported annually. This translates to an annual medical expenditure of 30 to 50\u0026nbsp;billion yuan[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e],imposing a considerable burden on both the caregivers and families of DOC patients, and sparking numerous ethical and legal concerns[\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. Within the first year following the emergence of consciousness disorders, the mortality rate stands at a staggering 35%, with only 40% of patients experiencing any improvement in their level of consciousness[\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. There is an urgent need for early, objective, and precise prognostic assessments, as these will significantly impact future medical decisions.\u003c/p\u003e \u003cp\u003eThe Coma Recovery Scale-Revised (CRS-R) is recognized as the preeminent clinical tool for the structured assessment of patients with disorders of consciousness, showcasing robust reliability and validity. Nonetheless, complications such as severe movement disorders, aphasia, endotracheal intubation, and fluctuations in arousal levels can impede behavioral evaluations, resulting in a misdiagnosis rate that reaches up to 43%[\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. Neuroelectrophysiological assessments are straightforward to conduct and enable continuous, real-time monitoring at the bedside. They offer critical insights into the extent and severity of brain damage, potentially aiding in the prognostic determination for individuals with disorders of consciousness.\u003c/p\u003e \u003cp\u003eThe bilateral absence of N20 waves in Somatosensory Evoked Potentials (SEPs) post-median nerve stimulation serves as an early marker for poor prognosis in patients with anoxic coma, albeit with limited sensitivity[\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e, \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. The short-latency SEP are primarily concerned with evaluating the integrity of sensory pathways and their corresponding cortical regions, excluding the secondary processing within higher-order cortical networks, which renders their prognostic significance a matter of debate [\u003cspan additionalcitationids=\"CR8 CR9\" citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. Middle-Latency Somatosensory Evoked Potentials (MLSEP), such as N35, N60, and N70, are capable of reflecting the integrity of secondary cortical networks and could be potential indicators of consciousness recovery in patients with disorders of consciousness[\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e, \u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. Nevertheless, the sensitivity and specificity of MLSEP in prognostic assessment are less than ideal, potentially attributable to variations in sample size and timing of prediction[\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e, \u003cspan additionalcitationids=\"CR14 CR15\" citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. Furthermore, research on the prognostic implications of evoked potentials in PDOC patients is scarce, leaving the clarity of their prognostic value undetermined.\u003c/p\u003e \u003cp\u003eFurthermore, neuroendocrine disorders are commonly observed in patients with brain injuries[\u003cspan additionalcitationids=\"CR17 CR18 CR19 CR20\" citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. A study found that neuroendocrine disorders affect cognitive functions such as attention, memory, and executive ability in post-brain injury patients [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]. Additionally, a study has demonstrated substantial correlations between sex hormone levels and the Glasgow Outcome Scale extended (GOSE), with sex hormones showing a positive correlation and IGF-1 a negative correlation with GOSE scores[\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]. These findings highlight the potential influence of neuroendocrine functions on the prognosis of patients with prolonged disorders of consciousness.\u003c/p\u003e \u003cp\u003eConsequently, this study endeavors to uncover prognostic factors associated with prolonged disorders of consciousness by leveraging clinical baseline information, behavioral evaluations, neuroelectrophysiological assessments, and hypothalamic-pituitary hormonal levels. Furthermore, it seeks to develop a predictive model that facilitates a visual and probabilistic prognosis assessment for patients grappling with prolonged disorders of consciousness.\u003c/p\u003e"},{"header":"Materials and methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003ePatients\u003c/h2\u003e \u003cp\u003eWe conducted a retrospective analysis of 170 patients with prolonged disorders of consciousness treated in the Department of Rehabilitation Medicine of The Affiliated Jiangning Hospital of Nanjing Medical University from March 2023 to July 2024. The inclusion criteria were as follows: (i) aged 18\u0026ndash;75 years; (ii) severe trauma, hypoxia, or vascular brain injury; (iii) a clinical diagnosis of VS (Vegetative State) or MCS (Minimally Conscious State) made by the Chinese version of the Coma Recovery Scale-Revised (CRS-R)[\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e, \u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]; (IV) 1\u0026ndash;3 months post-injury; and (V) stabilized medical clinical conditions. Patients with mixed etiology (e.g., traumatic and anoxic brain injury) or a premorbid history of psychiatric or neurodegenerative diseases were excluded. Exclusion criteria included: (I) Unstable vital signs such as severe heart failure or respiratory failure; (II) previous history of brain injury or neurodegenerative disease; (III) use of sedatives drugs, antiepileptic drugs, and nerve excitation drugs; (IV) known hearing impairment; and (V) incomplete clinical data.\u003c/p\u003e \u003cp\u003e \u003cstrong\u003eNote\u003c/strong\u003e Clinical evaluations were performed bedside, facilitated by caregivers who provide significant stimulation to the patients. The registration of information was the responsibility of three physicians participating in the study, who also managed the clinical care of the patients.\u003c/p\u003e \u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eSample size estimation\u003c/h3\u003e\n\u003cp\u003eWe relied on the Events Per Variable criterion (EPV), particularly EPV\u0026thinsp;\u0026ge;\u0026thinsp;10, to determine the minimum sample size required[\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]. With four independent variables selected and 40% of patients showing clinical improvement[\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e], the minimum sample size calculated was 100. Considering a dropout rate of 20% during the study period, a minimum of 120 participants were required.\u003c/p\u003e\n\u003ch3\u003eClinical evaluation\u003c/h3\u003e\n\u003cp\u003eWe collected clinical data on the age, gender, etiology, duration of ICU stay, decompressive craniectomy status, history of hypertension, history of diabetes, history of coronary heart disease, and CRS-R scores of patients with prolonged disorders of consciousness.\u003c/p\u003e \u003cp\u003eBrainstem Auditory Evoked Potentials (BAEP) and upper limb somatosensory evoked potentials were recorded following standard laboratory protocols[\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e, \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e], utilizing the Neuron-Spectrum-4 electromyography and evoked potential instrument manufactured by the Russian neurosoft company. Cortical SEPs were deemed present if they were observed either bilaterally or unilaterally. Conversely, SEPs were classified as absent in cases where no bilateral SEPs were detected. BAEP grading followed the Hall classification[\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]: Grade 1, normal; Grade 2, slightly abnormal, exhibiting moderate waveform differentiation, with possible issues such as prolonged peak latency of the I, III, or (and) V waves, prolonged interpeak latency of the I\u0026ndash;III, III\u0026ndash;V, or (and) I\u0026ndash;V waves, peak-to-peak latency ratio of III\u0026ndash;V/I \u0026ndash;III\u0026thinsp;\u0026gt;\u0026thinsp;1, and amplitude ratio of V/I\u0026thinsp;\u0026lt;\u0026thinsp;0.15; Grade 3, moderate abnormality, featuring poor waveform differentiation and repeatability, with possible issues such as prolonged peak latency of the III or V waves, or disappearance of the V wave; and Grade 4, severe abnormality, characterized by only the I wave's presence or the disappearance of all waveforms.\u003c/p\u003e \u003cp\u003eWe collected the following hormone levels from patients with prolonged disorders of consciousness (PDOC)within 48 hours of admission: cortisol, adrenocorticotropic hormone (ACTH), thyroid stimulating hormone (TSH), free thyroxine (FT4), free triiodothyronine (FT3), prolactin (PRL), luteinizing hormone (LH), follicle stimulating hormone (FSH), testosterone, and estradiol (E2).\u003c/p\u003e\n\u003ch3\u003eOutcome definition\u003c/h3\u003e\n\u003cp\u003eAll PDOC patients were categorized into Vegetative State (VS)/Unresponsive Wakefulness Syndrome (UWS), Minimally Conscious State (MCS) based on repeated CRS-R scores. Clinical diagnosis of UWS/VS was assigned when patients exhibited a sleep-wake cycle, autonomic nerve and motor reflexes, but lacked self or environmental signs of conscious behavior [\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e]. Patients may transition to MCS[\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e], characterized by clear signs of consciousness and behavior, such as following simple commands and responding to harmful stimuli. Consideration for emergence from MCS was given if patients could functionally communicate or use objects. After a 6-month follow-up, patients were classified as \"improved\" if they transitioned from MCS to eMCS, or from VS/UWS to MCS, or if they ultimately regained consciousness. Patients were classified as \"NO improved\" if MCS patients at baseline regressed to VS/UWS, showed no improvement, or died [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e].\u003c/p\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003eStatistical analysis\u003c/h2\u003e \u003cp\u003e The data were analyzed and processed using R software(version 4.2.1, R Foundation for Statistical Computing, Vienna, Austria);The specific R packages \"caret\", \"rfPermute\", \"glmnet\", \"rms\", \"pROC\"and \"rmda\" were used for model construction and validation.Normally distributed continuous variables were presented as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation and compared using independent sample t-tests. Non-normally distributed data were presented as median (interquartile range) and analyzed using the Kruskal-Wallis rank-sum test. Categorical variables were expressed as frequency (percentage) and compared using the chi-square test or Fisher's exact probability.\u003c/p\u003e \u003cp\u003eThis study retrospectively analyzed clinical data from 170 patients with PDOC. Collected parameters included 17 electrophysiological and biochemical measures. The raw data underwent dual-independent verification before being entered into an Excel database. Data cleaning was performed using R software, with exclusion of variables showing\u0026thinsp;\u0026gt;\u0026thinsp;10% missing values. Through the \"caret \"package (v6.0-94), stratified sampling was implemented with stratification by etiology, dividing the cohort into training (n\u0026thinsp;=\u0026thinsp;121) and validation (n\u0026thinsp;=\u0026thinsp;49) sets at a 7:3 ratio.The training set was utilized for feature selection and model construction, while the validation set was employed to evaluate the model's effectiveness. Inter-group comparability was confirmed by chi-square tests (p\u0026thinsp;\u0026gt;\u0026thinsp;0.05).\u003c/p\u003e \u003cp\u003eRandom forest for Variable Selection:Importance assessment was performed using the \"rfPermute\"package (v2.5.1) to construct a permutation-based random forest model. The number of decision trees (number of trees[ntree]\u0026thinsp;=\u0026thinsp;134) was determined by monitoring the stability of the Out-of-Bag (OOB) error. When the number of trees exceeded 100, the fluctuation range of the OOB error remained below 0.5%, indicating model convergence. Parallel computing was implemented with num.cores\u0026thinsp;=\u0026thinsp;3 to accelerate the analysis.\u003c/p\u003e \u003cp\u003ePermutation tests were employed to generate p-values by simulating a random distribution, with the precision of these estimates directly dependent on the number of permutations (nrep\u0026thinsp;=\u0026thinsp;134). Variable importance was assessed based on the mean decrease in accuracy (Mean Decrease Accuracy), and statistical significance was defined as p\u0026thinsp;\u0026lt;\u0026thinsp;0.05.After correcting for multiple testing bias using permutation-derived p-values, nine candidate variables were selected for subsequent analysis based on their ranked importance.\u003c/p\u003e \u003cp\u003eLasso Regression for variable selection was performed using L1-regularized regression (alpha\u0026thinsp;=\u0026thinsp;1) implemented in the\"glmnet\"package (v4.1-7). The optimal penalty parameter (λ) was determined via 10-fold stratified cross-validation, with λ.min selected to minimize the cross-validated deviance, ensuring an optimal trade-off between model fit and overfitting risk. Following variable compression, four core predictors were retained based on non-zero coefficients: CRS-R score,BAEP grading,Estradiol,N60 classification.The variable selection process was visualized using elastic net coefficient paths, and multicollinearity was assessed via variance inflation factors (VIFs), all of which were \u0026lt;\u0026thinsp;5, confirming the absence of significant collinearity among selected predictors.A forced-entry multivariable logistic regression model was built using the selected predictors. odds ratios (ORs) and 95% confidence intervals (95%CI)were computed via the\"rms\"package(v6.7-0), with results visualized in a nomogram. Akaike Information Criterion (AIC) for the optimally parsimonious model (AIC\u0026thinsp;=\u0026thinsp;82.3) was presented as a clinically interpretable nomogram for individualized outcome prediction.\u003c/p\u003e \u003cp\u003eWe conducted comprehensive validation of model performance across three key domains - discrimination, calibration, and clinical utility - through both training set and independent validation set validation approaches.ROC curve analysis was performed using the \"pROC\" package (v1.18.2). We calculated:Area under the curve (AUC) with 95% CI(DeLong's method),Optimal cutoff determined by Youden's index (sensitivity\u0026thinsp;+\u0026thinsp;specificity-1);Internal validation: AUC computation on training set(n\u0026thinsp;=\u0026thinsp;119) with 10-fold cross-validation; External validation: Independent testing on validation cohort (n\u0026thinsp;=\u0026thinsp;51) without model refitting.Calibration curves were assessed via 1,000 bootstrap resamples, with LOESS smoothing to evaluate agreement between predicted and observed probabilities.Overall prediction accuracy was quantified using the Brier score (range: 0\u0026ndash;1).Internal validation: Calibration curves were plotted for the training set.External validation: Curves were generated for the validation set to test calibration on new data.Decision Curve Analysis(DCA) was performed using the \"rmda\"package(v1.6), calculating net benefit across threshold probabilities (5%-95%);The clinically actionable range was highlighted via shaded regions. Internal validation: Initial net benefit estimation;External validation: Confirmation of clinical applicability.Finally, We developed an interactive interface for the final model was established based on the validation set to facilitate clinical evaluation applications.\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec9\" class=\"Section2\"\u003e\n \u003ch2\u003eBaseline data\u003c/h2\u003e\n \u003cp\u003eA total of 170 patients with PDOC were included in the final analysis (Fig. \u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e). The demographic and clinical characteristics of the training and validation sets are summarized in Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e. After a 6-month follow-up, 88 patients (51.8%) showed an improvement in their level of consciousness; in the raining set, there were 121 patients with an average age of 60.11\u0026thinsp;\u0026plusmn;\u0026thinsp;12.01 years and a CRS-R score of 10.17\u0026thinsp;\u0026plusmn;\u0026thinsp;4.14 points; 63 patients (52.1%) showed an improvement in their level of consciousness. In the validation set, there were 49 patients with an average age of 57.61\u0026thinsp;\u0026plusmn;\u0026thinsp;11.78 years and a CRS-R score of 9.41\u0026thinsp;\u0026plusmn;\u0026thinsp;3.85 points; among them, 25 patients (51%) showed an improvement in their level of consciousness.\u003c/p\u003e\n \u003cdiv class=\"gridtable\"\u003e\u0026nbsp;\u003ctable id=\"Tab1\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eDemographic and clinical characteristics of the patients in two group\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003ccolgroup cols=\"5\"\u003e\u003c/colgroup\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eFactors\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eClassify\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eTraining set(121)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eValidation set(49)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eAge(years)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e60.11\u0026thinsp;\u0026plusmn;\u0026thinsp;12.01\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e57.61\u0026thinsp;\u0026plusmn;\u0026thinsp;11.78\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.22\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003eSex\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFemale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e41(33.9%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e18(36.7%)\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003e0.73\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e80(66.1%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e31(63.3%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003eSmoke history\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNO\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e61(51.4%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e22(44.9%)\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003e0.32\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eYES\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e60(49.6%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e27(55.1%)\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003eDrink history\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNO\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e64(52.9%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e24(49.0%)\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003e0.39\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eYES\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e57(47.1%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e25(51.0%)\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003eHypertension history\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNO\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e26(21.5%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e7(14.3%)\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003e0.19\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eYES\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e95(78.5%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e42(85.7%)\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003eDiabetes history\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNO\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e98(81.0%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e42(85.7%)\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003e0.31\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eYES\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e23(19.0%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e7(14.3%)\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003eCoronary heart disease\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNO\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e106(87.6%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e43(87.8%)\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003e0.60\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eYES\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e15(12.4%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e6(12.2%)\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003eDecompressive Craniotomy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNO\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e54(44.6%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e22(44.9%)\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003e0.47\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eYES\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e67(55.4%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e27(55.1%)\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"5\"\u003e\n \u003cp\u003eEtiology\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eTrauma\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e31(25.6%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e12(24.5%)\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003e0.99\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eStroke\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e76(62.8%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e32(65.3%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eAnoxia\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e14(11.6%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5(10.2%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"5\"\u003e\n \u003cp\u003eDiagnosis\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eVegetative State\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e80(66.1%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e26(53.1%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003e0.08\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eMinimally Conscious State\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e41(33.9%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e23(46.9%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003eImproved outcome\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNO\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e58(47.9%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e24(49.0%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003e0.52\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eYES\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e63(52.1%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e25(51.0%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003eN20 classification\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNO\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e31(25.6%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e13(26.5%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003e0.52\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eYES\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e90(74.4%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e36(73.5%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eYES\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e87(73.1%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e34(66.7%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003eN60 classification\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNO\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e47(38.8%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e19(38.8%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003e0.59\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eYES\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e74(61.2%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e30(61.2%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"5\"\u003e\n \u003cp\u003eBrainstem Auditory Evoked Potentials grading\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eLevel 1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e17(14.0%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5(10.2%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"4\"\u003e\n \u003cp\u003e0.62\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eLevel 2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e57(47.1%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e29(59.2%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eLevel 3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e42(34.7%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e13(26.5%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eLevel 4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5(4.1%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2(4.1%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eThe duration of\u0026ensp;ICU(days)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e24.67\u0026thinsp;\u0026plusmn;\u0026thinsp;14.24\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e25.31\u0026thinsp;\u0026plusmn;\u0026thinsp;10.57\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.78\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eCourse (days)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e91.55\u0026thinsp;\u0026plusmn;\u0026thinsp;46.64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e96.86\u0026thinsp;\u0026plusmn;\u0026thinsp;42.39\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.49\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eCRS-R score\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e10.17\u0026thinsp;\u0026plusmn;\u0026thinsp;4.14\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e9.41\u0026thinsp;\u0026plusmn;\u0026thinsp;3.85\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.27\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eProgesterone(ng/ml)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.72\u0026thinsp;\u0026plusmn;\u0026thinsp;0.28\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.67\u0026thinsp;\u0026plusmn;\u0026thinsp;0.33\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.33\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eTestosterone(nmol/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6.51\u0026thinsp;\u0026plusmn;\u0026thinsp;5.69\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6.69\u0026thinsp;\u0026plusmn;\u0026thinsp;6.19\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.85\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eProlactin(ng/ml)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e25.39\u0026thinsp;\u0026plusmn;\u0026thinsp;14.79\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e23.88\u0026thinsp;\u0026plusmn;\u0026thinsp;13.99\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.54\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eEstradiol (pg/ml)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e26.98\u0026thinsp;\u0026plusmn;\u0026thinsp;12.17\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e28.01\u0026thinsp;\u0026plusmn;\u0026thinsp;11.79\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.62\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eLuteotropichormone(IU/ L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e10.26\u0026thinsp;\u0026plusmn;\u0026thinsp;8.52\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.01\u0026thinsp;\u0026plusmn;\u0026thinsp;10.78\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.26\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eFollicle-stimulating hormone(IU/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e18.78\u0026thinsp;\u0026plusmn;\u0026thinsp;17.21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e19.21\u0026thinsp;\u0026plusmn;\u0026thinsp;18.44\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.89\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eCortisol (nmol/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e467.94\u0026thinsp;\u0026plusmn;\u0026thinsp;141.66\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e434.22\u0026thinsp;\u0026plusmn;\u0026thinsp;135.34\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.16\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eAdreno-cortico-tropic-hormone(pg/ml)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e49.16\u0026thinsp;\u0026plusmn;\u0026thinsp;26.09\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e44.47\u0026thinsp;\u0026plusmn;\u0026thinsp;21.61\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.27\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eFree triiodothyronine (pmol/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.56\u0026thinsp;\u0026plusmn;\u0026thinsp;0.88\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.42\u0026thinsp;\u0026plusmn;\u0026thinsp;0.75\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.34\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eFree triiodothyronine\u0026nbsp;(pmol/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e16.79\u0026thinsp;\u0026plusmn;\u0026thinsp;3.37\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e15.97\u0026thinsp;\u0026plusmn;\u0026thinsp;3.08\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.14\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eThyroid-stimulating hormone (mIU /L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.18\u0026thinsp;\u0026plusmn;\u0026thinsp;2.03\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e4.09\u0026thinsp;\u0026plusmn;\u0026thinsp;3.65\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.11\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n \u003c/div\u003e\n \u003cp\u003eData are expressed as n (%), mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD, median (IQR), as appropriate\u003c/p\u003e\n\u003c/div\u003e\n\u003ch3\u003eIdentify predictors\u003c/h3\u003e\n\u003cp\u003eUsing the random forest method, 27 independent variables were screened, and ultimately 9 variables were identified as statistically significant (**P\u0026thinsp;\u0026lt;\u0026thinsp;0.01, *P\u0026thinsp;\u0026lt;\u0026thinsp;0.05). After testing and adjustment, when ntree\u0026thinsp;=\u0026thinsp;134, nreo\u0026thinsp;=\u0026thinsp;134, and num.cores\u0026thinsp;=\u0026thinsp;3, the top most important feature variables were determined to be CRS-R score,Diagnosis,BAEP grading, Estradiol, Etiology,N60 classification, Cortisol,TSH,and N20 classification(Fig. \u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e).\u003c/p\u003e\n\u003cp\u003eUsing the Lasso regression model, 9 characteristics were tested for their ability to predict the clinical outcomes and to avoid overfitting. The Lasso coefficient profiles of features and the optimal penalization coefficient lambda\u0026thinsp;+\u0026thinsp;1se are shown in Fig. \u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e. The feature selection results revealed that nine variables, including CRS-R score,Diagnosis,BAEP grading, Estradiol, Etiology,N60 classification, Cortisol and N20 classification, could be used to predict clinical prognosis for PDOC patients.\u003c/p\u003e\n\u003cp\u003eFinally, the findings from the random forest analysis and lasso regression analysis were synergistically combined to identify the six most influential predictors of recovery in consciousness levels: CRS-R score,Diagnosis,BAEP grading,Estradiol,N60 classification and TSH.These predictors were further examined through multivariate logistic regression in Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\u0026nbsp;\u003ctable id=\"Tab2\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eMultivariate logistic regression analysis\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003ccolgroup cols=\"3\"\u003e\u003c/colgroup\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eVariable\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eOR(95%CI)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eP-Values\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCRS-R score\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.05(1.02,1.08)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.002\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDiagnosis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.13(0.91,1.41)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.26\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eBAEP grading\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.88(0.79,0.98)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.02\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eEstradiol\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.01(1.00,1.02)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.01\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eN60 classification\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.22(1.01,1.48)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.04\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eTSH\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.03(0.99,1.05)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.07\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003eOR, odd ratio; CI, confidence interval; coma recovery scale-revised ,CRS-R\u003c/p\u003e\n\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e\n \u003ch2\u003eConstruction of clinical prediction model\u003c/h2\u003e\n \u003cp\u003eBased on the results of multivariate logistic regression analysis, a nomogram model was constructed for predicting the 6-month prognosis of patients with PDOC using CRS-R score, BAEP grading,N60 classification and estradiol (Fig. \u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003e). The nomogram consists of variable names and tick marks. Points in the first row can calculate the single score of each prognostic factor. Lines 2\u0026ndash;5 represent the specific classification of each prognostic factor, with scores calculated separately according to the first row. The total points in the sixth row represent the sum of scores from all prognostic factors. The individual prognostic score of each factor for a patient is determined by adding up the total score. Line 7 indicates the clinical prognosis prediction of DOC patients. To obtain the corresponding clinical improvement probability of the patient, a vertical line is drawn based on the total score of the patient (Fig. \u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003e).\u003c/p\u003e\n \u003cp\u003eThe independent risk factors included in the nomogram were validated using the R packages (caret,rfPermute,rms,glmnet,pROC,rmda) to draw the receiver operating characteristic curve. The AUC values of the training set and the validation set were 0.919(95%CI 0.87\u0026ndash;0.968)and 0.888(95%CI 0.796\u0026ndash;0.98), respectively(Fig. \u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003eA, \u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003eB).Thus,the nomogram achieved a C-index of 0.888 in the validation set.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\n \u003ch2\u003eNomogram model calibration and decision curve\u003c/h2\u003e\n \u003cp\u003eIn order to assess the consistency between the actual risk and predicted risk of the model, calibration curves were plotted,demonstrating a high degree of consistency between the observed and predicted probabilities of consciousness recovery in PDOC patients(Figs. \u003cspan class=\"InternalRef\"\u003e6\u003c/span\u003eA, \u003cspan class=\"InternalRef\"\u003e6\u003c/span\u003eB).\u003c/p\u003e\n \u003cp\u003eThe blue calibration curve represents the predicted proportion of the clinical outcome to the probability of the actual outcome. The dashed black line indicates that the actual risk is equal to the predicted risk.\u003c/p\u003e\n \u003cp\u003eAs shown in Fig. \u003cspan class=\"InternalRef\"\u003e6\u003c/span\u003e (A and B), the DCA plots showed that the logistic model was clinically useful and had good predictive ability in the training set. Additionally, the fluctuation observed at the end of the prediction model curve may be attributed to the relatively small sample size.\u003c/p\u003e\n \u003cp\u003eWe have successfully developed a user-friendly clinical interactive interface designed for the short-term prognosis prediction of patients with prolonged disorders of consciousness. This tool enables medical professionals to conveniently determine the 6-month prognosis for PDOC patients with ease and efficiency;We also provide a website for the convenience of clinical doctors to use, and the interface is shown in Fig. \u003cspan class=\"InternalRef\"\u003e8\u003c/span\u003e.\u003c/p\u003e\n\u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eIn this study, we developed a nomogram using CRS-R score, BAEP grading,N60 classification and estradiol in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e, which achieved a C-index of 0.888 in the validation set, indicating a good fit and suitability for clinical outcomes of patients with Prolonged Disorders of Consciousness after a 6-month follow-up. The ROC curves for this nomogram\u0026rsquo;s prognosis prediction are presented in Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e.Calibration and decision curve analysis demonstrated that clinicians can benefit from the decision-making supported by this model.\u003c/p\u003e \u003cp\u003eThe main etiologies of PDOC include traumatic brain injury, ischemic stroke, hemorrhagic stroke, or hypoxic-ischemic disease. The recovery of consciousness in DOC patients varies according to the etiology[\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e]. Compared with patients with non-traumatic injuries, patients with traumatic injuries are more likely to recover consciousness[\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e, \u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e]. Our analysis revealed that etiology was not an independent predictor in this study, potentially reflecting the uneven distribution of etiologies within our patient cohort. Specifically, stroke cases were disproportionately represented compared to traumatic brain injuries, which may have influenced the statistical significance of etiology as a standalone predictor.Additionally,age, course of disease, and ICU stay were not significantly correlated with prognosis. This may be due to selection bias and limited sample size, and further studies with larger sample sizes are needed to verify these findings.After taking into account the etiology, age, course of disease and Coma Recovery Scale-Revised (CRS-R) scores remain significant prognostic factors for DOC patients[\u003cspan additionalcitationids=\"CR37\" citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e]. Our study also supports that higher CRS-R scores are associated with better clinical outcomes, which aligns with findings from previous research[\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e, \u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eDamage to the brainstem ascending reticular activating system is one cause of disorders of consciousness. The severity of brainstem injury is closely correlated with the level of consciousness. Brainstem auditory evoked potentials, as a method for assessing brainstem conduction pathways, is one of the earliest clinical tools used to predict the prognosis of patients with disorders of consciousness.\u003c/p\u003e \u003cp\u003eWhile bilateral absence of N20 and BAEP wave V showed the highest specificity (100%, 95% CI: 85.9%-100%) and positive predictive value (100%, 95% CI: 80.8%-100%) for poor outcome in patients with severe ischemic brain injury[\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e].Our study and previous study[\u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e]support that BAEP grading is associated with the prognosis of DOC patients and can serve as an independent predictor for PDOC patients.\u003c/p\u003e \u003cp\u003eThe halamic-cortical dysfunction is crucial in the pathophysiology of DOC patients. Median nerve SEPs, as one of the representatives reflecting the thalamocortical pathway, still have controversial predictive value in the prognosis of PDOC patients; in our study, the classification of N20 cannot be serve as an independent predictive factor for the prognosis of chronic disorders of consciousness, which is inconsistent with previous studies[\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e, \u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e]. Secondly, while short-latency potential measurements are effective in evaluating the integrity of sensory pathways and their corresponding cortical regions, they do not account for the secondary processing that occurs within higher-order cortical networks. The engagement of more distant cortical regions necessitates the intactness of these second-order networks, which in turn are responsible for the generation of medium and long-latency potentials[\u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e45\u003c/span\u003e].MLSEP are not only regulated by the ascending reticular activation system but are also correlated with cortical and subcortical functional connectivity integrity [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e, \u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e46\u003c/span\u003e]. They can reflect higher-order brain processes, which are essential for the recovery of consciousness and favorable outcomes after acquired brain injury. Previous studies have indicated that bilateral absence of the N60 component is associated with Previous studies suggest that the presence of N60/N70 responses may be a potential indicator of good prognosis[\u003cspan additionalcitationids=\"CR48 CR49\" citationid=\"CR47\" class=\"CitationRef\"\u003e47\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e50\u003c/span\u003e],while the absence of N60 bilaterally indicates poor prognosispoor prognosis[\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e], with a false positive rate of 8% (95% CI 0.04\u0026ndash;0.16) [\u003cspan citationid=\"CR51\" class=\"CitationRef\"\u003e51\u003c/span\u003e].However, these studies mainly focus on patients with early coma, and there is limited research on MLSEP in patients with PDOC. In this study, we found that the presence of N60 was an independent predictor of the 6-month prognosis of PDOC, indicating better subcortical functional connectivity and a higher likelihood of consciousness recovery.\u003c/p\u003e \u003cp\u003ePituitary dysfunction is a common complication after brain injuries[\u003cspan additionalcitationids=\"CR17 CR18 CR19\" citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. Therefore, changes in the endocrine function of the hypothalamic-pituitary axis can be considered one of the initially measurable alterations after brain injury[\u003cspan citationid=\"CR51\" class=\"CitationRef\"\u003e51\u003c/span\u003e].Brain injury orcerebral edema can damage the anatomical structure of the hypothalamus, leading to a decrease in gonadal hormone level[\u003cspan citationid=\"CR52\" class=\"CitationRef\"\u003e52\u003c/span\u003e, \u003cspan citationid=\"CR53\" class=\"CitationRef\"\u003e53\u003c/span\u003e]. Some studies have identified a deficiency in hypothalamic-pituitary-related hormones in patients with severe DOC[\u003cspan citationid=\"CR54\" class=\"CitationRef\"\u003e54\u003c/span\u003e, \u003cspan citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e]. Our study revealed that estradiol levels were independent predictors of the prognosis of PDOC. Evidence suggests that estradiol has neuroprotective effects [\u003cspan citationid=\"CR56\" class=\"CitationRef\"\u003e56\u003c/span\u003e, \u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e]and can directly regulate cortical excitability and interhemispheric connectivity. In a comparative study investigating the efficacy of high-frequency repetitive transcranial magnetic stimulation (HF-rTMS) and sham stimulation of the left dorsolateral prefrontal cortex in patients with PDOC, researchers observed that responders to HF-rTMS treatment exhibited relatively high estradiol levels compared to non-responders. Based on these findings, HF-rTMS may potentially therapeutically impact PDOC by enhancing estradiol levels[\u003cspan citationid=\"CR58\" class=\"CitationRef\"\u003e58\u003c/span\u003e]. The aforementioned studies provide a theoretical basis for considering estradiol as a predictor of prognosis in patients with PDOC.\u003c/p\u003e \u003cp\u003eIn our study, the combination of CRS-R score, BAEP grading,N60 classification and Estradiol was found to be a reliable predictor of the prognosis for patients with prolonged disorders of consciousness, with an AUC of 0.888 in the validation set.Liu and colleagues found that the combination of N60 and MMN within 7 days after coma had good predictive performance for arousal, with an AUC value of 0.852[\u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e50\u003c/span\u003e].It's important to note that while the former model is primarily designed to predict patients in the acute phase, our study focuses on patients with PDOC. Additionally, our study incorporated behavioral assessment and estradiol levels alongside electrophysiological indicators, enhancing the prognostic value from various perspectives. Kang et al. conducted a study utilizing age, diagnosis, GCS score, and BAEP grading, yielding an AUC of 0.815 in their retrospective prognostic model study[\u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e]. This AUC was lower than that of our model (AUC\u0026thinsp;=\u0026thinsp;0.888), possibly owing to the fact that compared to the GCS score, the CRS-R score is more suitable for the behavioral assessment of patients with PDOC. Secondly, N60 may provide information on higher-order cortical information processing capabilities.\u003c/p\u003e \u003cp\u003eMoreover, estradiol can serve as an objective indicator to reflect the serological changes in patients with PDOC and provide partial prognostic information.\u003c/p\u003e \u003cp\u003eIn our study, several limitations should be acknowledged. First and foremost, it is important to acknowledge that our study, being a single-center investigation with a relatively small sample size, may not be fully representative of broader patient populations, thereby potentially limiting the generalizability of our findings. Moreover, the etiological distribution of our study cohort was not uniform, with stroke cases significantly outnumbering other etiologies. This uneven distribution could introduce a degree of bias in our analysis. Additionally, considering the complexity of our predictive model, which incorporates multiple variables, we recognize the necessity for validation in a larger and more diverse cohort to further substantiate our results and enhance the robustness of our conclusions.Future research endeavors should prioritize the implementation of dynamic monitoring of hormone levels, a strategy that holds the potential to significantly enhance the precision of patient classification and stratification in clinical management. It is imperative to recognize that neurophysiological data, often gathered within the complex signal-to-noise milieu of intensive care rehabilitation units, predominantly depend on visual analysis that is notably less reliable for interpreting evoked potential outcomes. Given these limitations, there is a pressing need to develop and deploy robust quantitative analytical methods or to harness the power of machine learning techniques. Such advancements could markedly improve the stability and reliability of research findings, thereby bolstering the overall validity and applicability of the results.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eIn conclusion, the nomogram model, which incorporates CRS-R score, BAEP grading,N60 classification and Estradiol, proves to be advantageous for assessing the short-term prognosis of patients with prolonged disorders of consciousness, with a high degree of accuracy. This model not only aids in prognostication for PDOC but also assists in refining treatment strategies and ensuring the judicious use of healthcare resources.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAcknowledgments\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConflict of interest\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare that they have no conflict of interest.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis work was supported by the National Key Research and Development Program of China (Grant No.:2022YFC2009700) and Nanjing Science and technology development Foundation (Grant No:YKK22219).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics approval\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study adhered to the Declaration of Helsinki II and good clinical practice guidelines, and was approved by the ethics committee of Jiangning Hospital Affiliated to Nanjing Medical University (Approval Code:2022-03-047-k01,Date:2023-02-22). \u003c/pre\u003e\n\u003ch4\u003eConsent to Participate\u003c/h4\u003e\n\u003cp\u003eLegal caregivers of all participants provided written informed consent.\u003c/p\u003e\n\u003ch4\u003eConsent to Publish\u003c/h4\u003e\n\u003cp\u003eNot applicable\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eJuanjuanFu and Hui Feng carried out the studies, participated in collecting data, and drafted the manuscript.Huaping Pan and Yongli Wu performed the statistical analysis and participated in its design.Fangyu Chen and Huiyue Feng participated in acquisition, analysis, or interpretation of data and draft the manuscript.Hongxing Wang was\u0026nbsp;responsible for research supervision, guidance and fund acquisition.All authors read and approved the final manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAvailability of data and materials\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll data generated or analysed during this study are included in this published article\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eWei-Guan C, Ran L, Ye Z, Jian-Hui H, Ju-Bao D, Ai-Song G, Wei-Qun S. Recovery from prolonged disorders of consciousness: A dual-center prospective cohort study in China. World J Clin Cases 2020, 8.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRohaut B, Eliseyev A, Claassen J. Uncovering Consciousness in Unresponsive ICU Patients: Technical, Medical and Ethical Considerations. Crit Care. 2019;23(1):78.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJulia N, Mikhail K, Ilya B, Pranil P, Denis S, Alexey V, Maria S, Vera P, Marina VP, Elena L et al. One-Year Demographical and Clinical Indices of Patients with Chronic Disorders of Consciousness. Brain Sci 2021, 11(5).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKaitlen H, Eva G, Anke-Maria K, Andreas S, Andreas B. Rehabilitation outcome of anoxic-ischaemic encephalopathy survivors with prolonged disorders of consciousness. Resuscitation 2013, 84(10).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMaenia S, Riccardo C, Francesco L, Giovanni L, Maddalena S, Franco V, Maria L, Daniela A, Sara C, Maria Grazia C et al. Neurophysiology for predicting good and poor neurological outcome at 12 and 72 h after cardiac arrest: The ProNeCA multicentre prospective study. \u003cem\u003eResuscitation\u003c/em\u003e 2019, 147(0).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eClaudio S, Sonia DA, Jerry PN. Prognostication after cardiac arrest. Crit Care 2018, 22(1).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eThijs M, vS A-F, vR, Marjolein MA, Wouter VP, Johannes HMTK, Janneke H. SSEP amplitudes add information for prognostication in postanoxic coma. Resuscitation 2021, 163(0).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRiccardo C, Maenia S, Francesco L, Maddalena S, Giovanni L, Adriano P, Chiara L, Aldo A, Antonello G. Early-SEPs' amplitude reduction is reliable for poor-outcome prediction after cardiac arrest? Acta Neurol Scand 2018, 139(2).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChristian E, Christian S, Christoph JP, Christoph L. Amplitudes of SSEP and outcome in cardiac arrest survivors: A prospective cohort study. Neurology 2015, 85(20).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eStefano dB G, Luigi G, Simone L, Claudio B, Patrizia S, Gianluca R, Federica B, Matteo F, Antonio C, Davide T et al. The importance of polysomnography in the evaluation of prolonged disorders of consciousness: sleep recordings more adequately correlate than stimulus-related evoked potentials with patients' clinical status. Sleep Med 2014, 15(4).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eE G J Z, J H T M K RJ, dH AH. SSEPs and prognosis in postanoxic coma: only short or also long latency responses? \u003cem\u003eNeurology\u003c/em\u003e 2006, 67(4).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYan Z, Miao W, Ying Ying S. The role of middle latency evoked potentials in early prediction of favorable outcomes among patients with severe ischemic brain injuries. J Neurol Sci 2014, 345(0).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang Y, Wang M, Su YY. The role of middle latency evoked potentials in early prediction of favorable outcomes among patients with severe ischemic brain injuries. J Neurol Sci. 2014;345(1\u0026ndash;2):112\u0026ndash;7.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eL AG, G C F KMH, C Z, C FSMHEB. M: Time-dependency of sensory evoked potentials in comatose cardiac arrest survivors. Intensive Care Med 2001, 27(8).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDamian C, Loretta N, Teneille G, Bryan G, Adrian Y. M O: Positive prognostication from median-nerve somatosensory evoked cortical potentials. Neurocrit Care 2014, 21(2).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eM R A MB, M C Z, N B. E C DU: Prevalence of hypopituitarism in patients with cerebrovascular diseases. J Endocrinol Invest 2008, 31(0).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAleksandra G-J, Łukasz K, Alicja H-D. Traumatic brain injuries induced pituitary dysfunction: a call for algorithms. Endocr Connect 2020, 9(5).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJohn AE, Hannah F, Jamie JL, Kieran M, Peter JDA. Prevalence of Anterior Pituitary Dysfunction Twelve Months or More following Traumatic Brain Injury in Adults: A Systematic Review and Meta-Analysis. J Neurotrauma 2019, 37(2).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWei-Hsun Y, Pau-Chung C, Ting-Chung W, Ting-Yu K, Chun-Yu C, Yao-Hsu Y. Endocrine dysfunction following traumatic brain injury: a 5-year follow-up nationwide-based study. Sci Rep 2016, 6(0).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eA MK, N G M JJS, U F-R. M K, : Acute and long-term pituitary insufficiency in traumatic brain injury: a prospective single-centre study. Clin Endocrinol (Oxf) 2007, 67(4).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTam\u0026aacute;s N, Helga M, Veronika G, Bertalan A, Csongor SA, J\u0026oacute;zsef K. Abnormalities of pituitary function after traumatic brain injury in children. J Neurotrauma 2007, 24(1).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJosef Z, Osborne FXA. Neuropsychology of Neuroendocrine Dysregulation after Traumatic Brain Injury. J Clin Med 2015, 4(5).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAnna T, Charlotte H, Bo-Michael B, J\u0026ouml;rgen B. Impact of pituitary dysfunction on cognitive and global outcome after traumatic brain injury and aneurysmal subarachnoid haemorrhage. J Rehabil Med 2019, 51(4).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJoseph TG, Kathleen K, John W. The JFK Coma Recovery Scale-Revised: measurement characteristics and diagnostic utility. Arch Phys Med Rehabil 2004, 85(12).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSarah W, Lizette H, Marie T, Olivia G, Steven L. The repetition of behavioral assessments in diagnosis of disorders of consciousness. Ann Neurol 2017, 81(6).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMaarten vS, Karel Gm M, Joris Ah dG, Gary SC, Douglas GA, Marinus Jc E, Johannes BR. Sample size for binary logistic prediction models: Beyond events per variable criteria. Stat Methods Med Res 2018, 28(8).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eM J A GC, J M G GC, R RKFMPM, R-D T. L G-L: Recommendations for the clinical use of somatosensory-evoked potentials. Clin Neurophysiol 2008, 119(8).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eT W P, S A H, H I K RG. Human auditory evoked potentials. I. Evaluation of components. Electroencephalogr Clin Neurophysiol 1974, 36(2).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJ W 3rd H, M H-f, T A G: Auditory function in acute severe head injury. Laryngoscope 1982, 92(0).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSteven L, Gastone GC, Francois C, Jan L, Jos\u0026eacute; L-C, Walter GS, Leon S, Erich S, Klaus R, vW, Adam Z et al. Unresponsive wakefulness syndrome: a new name for the vegetative state or apallic syndrome. BMC Med 2010, 8(0).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJoseph TG, D I K SANCRCBJ, J P K JHR. J W, R D Z : The minimally conscious state: definition and diagnostic criteria. Neurology 2002, 58(3).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eQi X, Kai L, Yong W, Yunliang T, Xiaoyang D, Yuan Z, Yao Z, Zhen F. A prediction model of clinical outcomes in prolonged disorders of consciousness: A prospective cohort study. Front Neurosci 2023, 16(0).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMedical aspects of. the persistent vegetative state (1). N Engl J Med 1994, 330(21).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRobert GK, Flora MH, Alan HW, Risa N-R, Ross DZ, John W, Joseph TG. Recovery of Consciousness and Functional Outcome in Moderate and Severe Traumatic Brain Injury. JAMA Neurol 2021, 78(5).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMichael AM, Joseph TG, Jason B, Nancy RT, Lindsay DN, Harvey SL, Sureyya D, Murray S, Yelena GB, Kim B et al. Functional Outcomes Over the First Year After Moderate to Severe Traumatic Brain Injury in the Prospective, Longitudinal TRACK-TBI Study. JAMA Neurol 2021, 78(8).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAnna E, Salvatore F, Alfonso M, Rita F, Donatella M, Antonello G, Anna Maria R, Efthymios A, Helena C, Aurore T et al. Multicenter prospective study on predictors of short-term outcome in disorders of consciousness. Neurology 2020, 95(11).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAnna E, Pasquale M, Telese T, Luigi T. Predictors of recovery of responsiveness in prolonged anoxic vegetative state. Author reply. Neurology 2013, 81(14).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEstraneo A, Fiorenza S, Magliacano A, Formisano R, Mattia D, Grippo A, Romoli AM, Angelakis E, Cassol H, Thibaut A, et al. Multicenter prospective study on predictors of short-term outcome in disorders of consciousness. Neurology. 2020;95(11):e1488\u0026ndash;99.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEmilio P, Azzurra M, Anna Maria R, Bahia H, Maria Pia T, Elena L, Martina DR, Antonello G, Claudio M. Score on Coma Recovery Scale-Revised at admission predicts outcome at discharge in intensive rehabilitation after severe brain injury. Brain Inj 2018, 32(6).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChing CF, James JML, Paul MB. The Relationship of the FOUR Score to Patient Outcome: A Systematic Review. J Neurotrauma 2019, 36(17).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang Y, Su YY, Haupt WF, Zhao JW, Xiao SY, Li HL, Pang Y, Yang QL. Application of electrophysiologic techniques in poor outcome prediction among patients with severe focal and diffuse ischemic brain injury. J Clin Neurophysiol. 2011;28(5):497\u0026ndash;503.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKang J, Huang L, Tang Y, Chen G, Ye W, Wang J, Feng Z. A dynamic model to predict long-term outcomes in patients with prolonged disorders of consciousness. Aging. 2022;14(2):789\u0026ndash;99.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSergio B, Cristina B, Antonino Sa, Alexander AF, Andrew AF, Giuseppe G. Emerging from an unresponsive wakefulness syndrome: brain plasticity has to cross a threshold level. Neurosci Biobehav Rev 2013, 37(0).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLawrence RR, Paula JM, David LT, Henry LL. Predictive value of somatosensory evoked potentials for awakening from coma. Crit Care Med 2003, 31(3).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJ-M G AA, K V A PA, dW SBA, C EF. F, P H, V J : Consensus on the use of neurophysiological tests in the intensive care unit (ICU): electroencephalogram (EEG), evoked potentials (EP), and electroneuromyography (ENMG). Neurophysiol Clin 2009, 39(2).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAldo R, Massimo C, Fabio G, Damian C, Bryan G, Carlo Y, Simone M. R: Clinical neurophysiology of prolonged disorders of consciousness: From diagnostic stimulation to therapeutic neuromodulation. Clin Neurophysiol 2017, 128(9).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAndrea Victoria A-V, Eva Mar\u0026iacute;a F-D, Emilio G-G, Javier S-P, David M-L, Tom\u0026aacute;s S. Functional and Prognostic Assessment in Comatose Patients: A Study Using Somatosensory Evoked Potentials. Front Hum Neurosci 2022, 16(0).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChristian E, Erik W, Martin K, Kaspar JS, Hans K, Werner S, Christian S, Christoph JP, Tobias C, Hans F et al. Hypoxic-Ischemic Encephalopathy Evaluated by Brain Autopsy and Neuroprognostication After Cardiac Arrest. JAMA Neurol 2020, 77(11).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAlessandra DF, Stefano B, Federico L, Bruno S, Emanuela F, Paolo B, Stefano M, Paolo Z. The potential role of pain-related SSEPs in the early prognostication of long-term functional outcome in post-anoxic coma. Eur J Phys Rehabil Med 2017, 53(6).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYifei L, Huijin H, Yingying S, Miao W, Yan Z, Weibi C, Gang L, Mengdi J. The Combination of N60 with Mismatch Negativity Improves the Prediction of Awakening from Coma. Neurocrit Care 2021, 36(3).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eClaudio S, Fabio C, Clifton WC, Sonia DA, Tommaso S, Michael AK, Matteo B, Giacomo DM, Alessio F, Jerry PN. Predictors of poor neurological outcome in adult comatose survivors of cardiac arrest: a systematic review and meta-analysis. Part 2: Patients treated with therapeutic hypothermia. Resuscitation 2013, 84(10).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAndrea L, Ruth T, Faten EA, Ali M, Christopher LK, Christos L, Fernando DG. Neuroendocrine Dysfunction in the Acute Setting of Penetrating Brain Injury: A Systematic Review. World Neurosurg 2020, 147(0).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eM HJKSMJK. J, F H: The corticosterone synthesis inhibitor metyrapone prevents hypoxia/ischemia-induced loss of synaptic function in the rat hippocampus. Stroke 2000, 31(5).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYu HZ, Hong YW, Ren HH, Bi EZ, Jian ZF. Sex Differences in Sex Hormone Profiles and Prediction of Consciousness Recovery After Severe Traumatic Brain Injury. Front Endocrinol (Lausanne) 2019, 10(0).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAmy KW, Emily HM, Christian N, Haishin O, Tammy LL, Julie AD, Christopher AB, Martina S, Edward C, Sarah D. L B : Acute serum hormone levels: characterization and prognosis after severe traumatic brain injury. J Neurotrauma 2011, 28(6).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePaco SH, Ines PK, Patricia DH. Sex, sex steroids, and brain injury. Semin Reprod Med 2009, 27(3).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLee S, Chung S, Rogasch N, Thomson C, Worsley R, Kulkarni J, Thomson R, Fitzgerald P, Segrave R. The influence of endogenous estrogen on transcranial direct current stimulation: A preliminary study. Eur J Neurosci. 2018;48(4):2001\u0026ndash;12.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHe R, Wang H, Zhou Z, Fan J, Zhang S, Zhong Y. The influence of high-frequency repetitive transcranial magnetic stimulation on endogenous estrogen in patients with disorders of consciousness. Brain Stimul. 2021;14(3):461\u0026ndash;6.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-neurology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nurl","sideBox":"Learn more about [BMC Neurology](http://bmcneurol.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/nurl","title":"BMC Neurology","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"disorder of consciousness, brain injury, minimally conscious state, vegetative state, cohort","lastPublishedDoi":"10.21203/rs.3.rs-5693803/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5693803/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eObjective\u003c/h2\u003e \u003cp\u003eTo establish a nomogram prediction model for the patients with prolonged disorders of consciousness (PDOC) caused by brain injury at six months based on behavioral scale scores, neuroelectro-physiological techniques and hypothalamic-pituitary hormone levels.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eThe clinical data of patients with PDOC who were first diagnosed and hospitalized in the Department of Rehabilitation Medicine of The Affiliated Jiangning Hospital of Nanjing Medical University from March 2023 to July 2024 were collected retrospectively. We performed stratified sampling based on etiology and divided into a training set (121 cases) and a validation set (49 cases) in a ratio of 7:3. After a 6-month follow-up, patients were divided into groups with improved consciousness and those without improved consciousness based on changes in CRS-R scores.Clinical behavioral scores, somatosensory evoked potentials, brainstem auditory evoked potentials, and levels of hypothalamic-pituitary hormones were utilized to identify prognostic factors for prolonged disorders of consciousness. Concurrently, a nomogram prediction model was crafted and validated to forecast the prognosis of patients with prolonged disorders of consciousness. Decision curve analysis (DCA) was subsequently employed to appraise the clinical applicability of this predictive model.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eThe comparison of clinical data between the training and validation cohorts revealed no significant statistical disparities (P\u0026thinsp;\u0026gt;\u0026thinsp;0.05). Within the training cohort of 121 PDOC patients, 63 (52.1%)PDOC patients exhibited enhanced consciousness levels. Similarly, in the validation cohort of 49 PDOC patients, 25 (51%) PDOC patients showed improvements in consciousness. Utilizing a combination of random forest analysis, LASSO regression, and multivariate Logistic regression, we identified four key predictive variables: CRS-R score (OR\u0026thinsp;=\u0026thinsp;1.05, 95%CI 1.02\u0026ndash;1.08, P\u0026thinsp;=\u0026thinsp;0.002), BAEP grading(OR\u0026thinsp;=\u0026thinsp;0.88, 95%CI 0.79\u0026ndash;0.98, P\u0026thinsp;=\u0026thinsp;0.02), N60 classification (OR\u0026thinsp;=\u0026thinsp;1.22, 95%CI 1.01\u0026ndash;1.48, P\u0026thinsp;=\u0026thinsp;0.02), and Estradiol (OR\u0026thinsp;=\u0026thinsp;1.01, 95%CI 1.00\u0026ndash;1.02, P\u0026thinsp;=\u0026thinsp;0.01). The area under the curve (AUC) for the predictive model in the training set was 0.919(95%CI 0.87\u0026ndash;0.968),while in the validation set, it was 0.888(95%CI 0.796\u0026ndash;0.98). The calibration curves demonstrated a high degree of concordance between predicted probabilities and actual results, suggesting that the model possesses strong discriminative power and calibration accuracy. Furthermore, in the context of clinical decision-making, Decision Curve Analysis indicated a superior net benefit for our predictive model.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eThe nomogram model, which integrates CRS-R score,BAEP grading,N60 classification and Estradiol, provides a comprehensive assessment of short-term prognosis in patients with prolonged disorders of consciousness, demonstrating high accuracy.\u003c/p\u003e","manuscriptTitle":"Development of a nomogram for predicting the outcome in patients with prolonged disorders of consciousness based on the multimodal evaluative information","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-03 05:11:07","doi":"10.21203/rs.3.rs-5693803/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-04-04T17:42:49+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-04-04T17:40:22+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-04T15:50:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"102578283045234707559468661872099761680","date":"2025-04-01T13:04:53+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-04-01T12:50:18+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-01T11:54:11+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Neurology","date":"2025-03-30T05:58:39+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-neurology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nurl","sideBox":"Learn more about [BMC Neurology](http://bmcneurol.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/nurl","title":"BMC Neurology","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"f48c8690-b64c-425b-81b1-f68340e31af8","owner":[],"postedDate":"April 3rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-04-28T16:02:58+00:00","versionOfRecord":{"articleIdentity":"rs-5693803","link":"https://doi.org/10.1186/s12883-025-04189-2","journal":{"identity":"bmc-neurology","isVorOnly":false,"title":"BMC Neurology"},"publishedOn":"2025-04-23 15:58:02","publishedOnDateReadable":"April 23rd, 2025"},"versionCreatedAt":"2025-04-03 05:11:07","video":"","vorDoi":"10.1186/s12883-025-04189-2","vorDoiUrl":"https://doi.org/10.1186/s12883-025-04189-2","workflowStages":[]},"version":"v1","identity":"rs-5693803","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5693803","identity":"rs-5693803","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}