Exploring Primary and Interaction Effects of Minor Physical Anomalies: Development and Validation of Prediction Models Using Explainable Machine Learning Algorithms for Early-Onset Schizophrenia.

To construct and validate the best predictive model for 28-day death risk in patients with septic shock based on different supervised machine learning algorithms. The patients with septic shock meeting the Sepsis-3 criteria were selected from Medical Information Mart for Intensive Care-IV v2.0 (MIMIC-IV v2.0). According to the principle of random allocation, 70% of these patients were used as the training set, and 30% as the validation set. Relevant predictive variables were extracted from three aspects: demographic characteristics and basic vital signs, serum indicators within 24 hours of intensive care unit (ICU) admission and complications possibly affecting indicators, functional scoring and advanced life support. The predictive efficacy of models constructed using five mainstream machine learning algorithms including decision tree classification and regression tree (CART), random forest (RF), support vector machine (SVM), linear regression (LR), and super learner [SL; combined CART, RF and extreme gradient boosting (XGBoost)] for 28-day death in patients with septic shock was compared, and the best algorithm model was selected. The optimal predictive variables were determined by intersecting the results from LASSO regression, RF, and XGBoost algorithms, and a predictive model was constructed. The predictive efficacy of the model was validated by drawing receiver operator characteristic curve (ROC curve), the accuracy of the model was assessed using calibration curves, and the practicality of the model was verified through decision curve analysis (DCA). A total of 3 295 patients with septic shock were included, with 2 164 surviving and 1 131 dying within 28 days, resulting in a mortality of 34.32%. Of these, 2 307 were in the training set (with 792 deaths within 28 days, a mortality of 34.33%), and 988 in the validation set (with 339 deaths within 28 days, a mortality of 34.31%). Five machine learning models were established based on the training set data. After including variables at three aspects, the area under the ROC curve (AUC) of RF, SVM, and LR machine learning algorithm models for predicting 28-day death in septic shock patients in the validation set was 0.823 [95% confidence interval (95%CI) was 0.795-0.849], 0.823 (95%CI was 0.796-0.849), and 0.810 (95%CI was 0.782-0.838), respectively, which were higher than that of the CART algorithm model (AUC = 0.750, 95%CI was 0.717-0.782) and SL algorithm model (AUC = 0.756, 95%CI was 0.724-0.789). Thus above three algorithm models were determined to be the best algorithm models. After integrating variables from three aspects, 16 optimal predictive variables were identified through intersection by LASSO regression, RF, and XGBoost algorithms, including the highest pH value, the highest albumin (Alb), the highest body temperature, the lowest lactic acid (Lac), the highest Lac, the highest serum creatinine (SCr), the highest Ca2+, the lowest hemoglobin (Hb), the lowest white blood cell count (WBC), age, simplified acute physiology score III (SAPS III), the highest WBC, acute physiology score III (APS III), the lowest Na+, body mass index (BMI), and the shortest activated partial thromboplastin time (APTT) within 24 hours of ICU admission. ROC curve analysis showed that the Logistic regression model constructed with above 16 optimal predictive variables was the best predictive model, with an AUC of 0.806 (95%CI was 0.778-0.835) in the validation set. The calibration curve and DCA curve showed that this model had high accuracy and the highest net benefit could reach 0.3, which was significantly outperforming traditional models based on single functional score [APS III score, SAPS III score, and sequential organ failure assessment (SOFA) score] with AUC (95%CI) of 0.746 (0.715-0.778), 0.765 (0.734-0.796), and 0.625 (0.589-0.661), respectively. The Logistic regression model, constructed using 16 optimal predictive variables including pH value, Alb, body temperature, Lac, SCr, Ca2+, Hb, WBC, SAPS III score, APS III score, Na+, BMI, and APTT, is identified as the best predictive model for the 28-day death risk in patients with septic shock. Its performance is stable, with high discriminative ability and accuracy.

Abnormalities in static neural activity have been widely reported in early onset schizophrenia (EOS). However, dynamic brain activity alterations over time in EOS are unclear. Here, we investigated whether temporal dynamic changes in spontaneous neural activity are influenced by EOS. A total of 78 drug-naïve first-episode patients with EOS and 90 healthy controls (HCs) were enrolled in this study. Dynamic amplitude of low-frequency fluctuations (dALFF) was performed to examine the abnormal time-varying local neural activity in EOS. Furthermore, we investigated the relationships between abnormalities in dALFF variability and clinical characteristics in EOS patients. Compared to HCs, EOS patients showed significantly decreased dALFF variability in the bilateral precuneus, right superior marginal gyrus, right post-central gyrus and increased dALFF in the right middle temporal gyrus (MTG). Moreover, increased dALFF variability in MTG was negatively associated with negative symptoms in EOS. Our findings reveal increased dynamic local neural activity in higher order networks of the cortex, suggesting that enhanced spontaneous brain activity may be a predominant neural marker for brain maturation. In addition, decreased dALFF variability in the default mode network (DMN) and limbic system may reflect unusually dynamic neural activity. This dysfunctional brain activity could distinguish between patients and HCs and deepen our understanding of the pathophysiological mechanisms of EOS.

Depression and anxiety are significant global public health, their comorbidity share similar clinical symptoms with heterogeneous progression patterns for patients. The early and accurate prediction of anxiety, depression, and comorbidity of anxiety and depression is essential for timely discrimination of high-risk patients, individual treatment strategies, and hierarchical management. This study aimed to develop and validate an interpretable, multi-task prediction model using heart rate variability (HRV) for discriminating anxiety alone, depression alone, and comorbid patients with psychiatric disorders. Patients diagnosed with anxiety or depression by trained psychiatrists were retrospectively enrolled from the Department of Psychiatry, the Affiliated Hospital of Southwest Medical University, between March 2024 and April 2025. The Synthetic Minority Over-sampling Technique (SMOTE) was applied to address class imbalance, and the Recursive feature elimination (RFE) was used for feature selection. Six machine-learning algorithms, including logistic regression (LR), support vector machine (SVM), random forest (RF), extreme gradient boosting (XGBoost), k-nearest neighbor (KNN), and naïve Bayes (NB), were adopt to develop multi-task prediction models for discriminating psychiatric comorbidities. Model performances were evaluated by receiver operating characteristic (ROC) curves, accuracy, sensitivity, specificity, F1 score, and Matthews correlation coefficient (MCC). The SHapley Additive exPlanation (SHAP) method was used to visualize the feature contributions and interpret the best model. A total of 546 patients, 114 with anxiety group(20.88%), 100 with depression group (18.32%), and 332 with comorbidity of anxiety and depression (60.81%), were included in this study. The ML-based models were developed for each task using the eleven contributing features. Among the six ML models, the XGBoost achieved the best performance across all tasks. In the validation set, this model achieved the AUCs of 0.8341 (95% confidence interval [CI]:0.761–0.907) for the task of anxiety versus comorbidity of anxiety and depression, and 0.8458(95% CI:0.775–0.917) for the task of depression versus comorbidity of anxiety and depression, respectively. The clinical utility was evaluated using Decision curve analysis (DCA) and calibration curves. The proposed model has potential clinical application prospects and may assist clinicians to improve the accuracy and efficiency of diagnosis, and thereby facilitating timely appropriate intervention measures for patients with psychiatric disorders. Not applicable.

Prediction models: stepwise development and simultaneous validation is a step back

Abnormal Thalamocortical Circuit in Adolescents With Early-Onset Schizophrenia

A number of live birth predictive model during assisted reproductive technology treatment have been available in recent years, but few targeted evaluating the chances of live birth in poor ovarian response(POR) patients. The aim of this study was to develop a nomogram based on POSEIDON criteria to predict live birth in patients with expected POR. This retrospective cohort study using clinical data from 657 patients in POSEIDON Groups 3 and 4 (antral follicle count [AFC] ≤5 and AMH <1.2 ng/ml) in the CenterforReproductiveMedicine, First Affiliated Hospital of Xinjiang Medical University, and Construction a nomogram model t. Among 657 expected POR patients, 111 (16.89%) had live births, and 546 (83.11%) did not have live births. These were divided into a training set(n=438) and a validation set (n=219). Multivariate logistic regression analysis showed that the age (OR = 0.91, 95% CI: 0.86-0.97), BMI (OR = 1.98, 95% CI: 1.09-3.67), AMH (OR = 3.48, 95% CI: 1.45-8.51), normal fertilized oocytes (OR = 1.40, 95% CI: 1.21-1.63), and the basal FSH (OR = 0.89, 95% CI: 0.80-0.98) of the female were independent factors predicting live birth in patients with expected POR. Then, an individualized nomogram prediction model was built from these five factors. The area under the ROC curve of the live birth prediction model was 0.820 in the training set and 0.879 in the validation set. We have developed a nomogram combining clinical and laboratory factors to predict the probability of live birth in patients with an expected POR during IVF/ICSI, which can helpful for clinician in decision-making. However, the data comes from the same center, needs a prospective multicenter study for further in-depth evaluation and validation of this prediction model.

Altered cortical maturation in adolescent cannabis users with and without schizophrenia

Simple SummaryThe objective response rate of lenvatinib combined with transarterial chemoembolization for unresectable hepatocellular carcinoma is unsatisfactory. We aimed to develop predictive models using demographic characteristics, pre-treatment serum biomarkers and tumor characteristics of unresectable hepatocellular carcinoma patients by five machine learning algorithms to predict the response under combined treatments. We identified the 10 most important predictors, including K, low-density lipoprotein, D-dimer, red blood cell, alanine aminotransferase, albumin, monocyte, tumor size, triglyceride, and age. In addition, we applied the Shapley Additive exPlanation to explain the best-performing random forest predictive model to provide a reasonable explanation of the efficacy prediction at an individualized level. The combination of machine learning and Shapley Additive exPlanation can provide valuable suggestions for clinical decision making.Background: Lenvatinib and transarterial chemoembolization (TACE) are first-line treatments for unresectable hepatocellular carcinoma (HCC), but the objective response rate (ORR) is not satisfactory. We aimed to predict the response to lenvatinib combined with TACE before treatment for unresectable HCC using machine learning (ML) algorithms based on clinical data. Methods: Patients with unresectable HCC receiving the combination therapy of lenvatinib combined with TACE from two medical centers were retrospectively collected from January 2020 to December 2021. The response to the combination therapy was evaluated over the following 4–12 weeks. Five types of ML algorithms were applied to develop the predictive models, including classification and regression tree (CART), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), random forest (RF), and support vector machine (SVM). The performance of the models was assessed by the receiver operating characteristic (ROC) curve and area under the receiver operating characteristic curve (AUC). The Shapley Additive exPlanation (SHAP) method was applied to explain the model. Results: A total of 125 unresectable HCC patients were included in the analysis after the inclusion and exclusion criteria, among which 42 (33.6%) patients showed progression disease (PD), 49 (39.2%) showed stable disease (SD), and 34 (27.2%) achieved partial response (PR). The nonresponse group (PD + SD) included 91 patients, while the response group (PR) included 34 patients. The top 40 most important features from all 64 clinical features were selected using the recursive feature elimination (RFE) algorithm to develop the predictive models. The predictive power was satisfactory, with AUCs of 0.74 to 0.91. The SVM model and RF model showed the highest accuracy (86.5%), and the RF model showed the largest AUC (0.91, 95% confidence interval (CI): 0.61–0.95). The SHAP summary plot and decision plot illustrated the impact of the top 40 features on the efficacy of the combination therapy, and the SHAP force plot successfully predicted the efficacy at the individualized level. Conclusions: A new predictive model based on clinical data was developed using ML algorithms, which showed favorable performance in predicting the response to lenvatinib combined with TACE for unresectable HCC. Combining ML with SHAP could provide an explicit explanation of the efficacy prediction.

To develop 10-year cardiovascular disease (CVD) risk prediction models in Chinese patients with type 2 diabetes mellitus (T2DM) managed in primary care using machine learning (ML) methods. In this 10-year population-based retrospective cohort study, 141 516 Chinese T2DM patients aged 18 years or above, without history of CVD or end-stage renal disease and managed in public primary care clinics in 2008, were included and followed up until December 2017. Two-thirds of the patients were randomly selected to develop sex-specific CVD risk prediction models. The remaining one-third of patients were used as the validation sample to evaluate the discrimination and calibration of the models. ML-based methods were applied to missing data imputation, predictor selection, risk prediction modelling, model interpretation, and model evaluation. Cox regression was used to develop the statistical models in parallel for comparison. During a median follow-up of 9.75 years, 32 445 patients (22.9%) developed CVD. Age, T2DM duration, urine albumin-to-creatinine ratio (ACR), estimated glomerular filtration rate (eGFR), systolic blood pressure variability and glycated haemoglobin (HbA1c) variability were the most important predictors. ML models also identified nonlinear effects of several predictors, particularly the U-shaped effects of eGFR and body mass index. The ML models showed a Harrell's C statistic of >0.80 and good calibration. The ML models performed significantly better than the Cox regression models in CVD risk prediction and achieved better risk stratification for individual patients. Using routinely available predictors and ML-based algorithms, this study established 10-year CVD risk prediction models for Chinese T2DM patients in primary care. The findings highlight the importance of renal function indicators, and variability in both blood pressure and HbA1c as CVD predictors, which deserve more clinical attention. The derived risk prediction tools have the potential to support clinical decision making and encourage patients towards self-care, subject to further research confirming the models' feasibility, acceptability and applicability at the point of care.

Introduction: The aim of this study was to compare various machine learning algorithms for constructing a diabetic retinopathy (DR) prediction model among type 2 diabetes mellitus (DM) patients and to develop a nomogram based on the best model. Methods: This cross-sectional study included DM patients receiving routine DR screening. Patients were randomly divided into training (244) and validation (105) sets. Least absolute shrinkage and selection operator regression was used for the selection of clinical characteristics. Six machine learning algorithms were compared: decision tree (DT), k-nearest neighbours (KNN), logistic regression model (LM), random forest (RF), support vector machine (SVM), and XGBoost (XGB). Model performance was assessed via receiver-operating characteristic (ROC), calibration, and decision curve analyses (DCAs). A nomogram was then developed on the basis of the best model. Results: Compared with the five other machine learning algorithms (DT, KNN, RF, SVM, and XGB), the LM demonstrated the highest area under the ROC curve (AUC, 0.894) and recall (0.92) in the validation set. Additionally, the calibration curves and DCA results were relatively favourable. Disease duration, DPN, insulin dosage, urinary protein, and ALB were included in the LM. The nomogram exhibited robust discrimination (AUC: 0.856 in the training set and 0.868 in the validation set), calibration, and clinical applicability across the two datasets after 1,000 bootstraps. Conclusion: Among the six different machine learning algorithms, the LM algorithm demonstrated the best performance. A logistic regression-based nomogram for predicting DR in type 2 DM patients was established. This nomogram may serve as a valuable tool for DR detection, facilitating timely treatment.

IntroductionThis study aimed to develop a diabetic retinopathy (DR) Prediction model using various machine learning algorithms incorporating the novel predictor Triglyceride-glucose index (TyG). Furthermore, the model was interpreted using the SHapley Additive exPlanations (SHAP) method.MethodReal-world data were collected from a general hospital in a major city and a county clinic, then divided into the DR Group (1392) and non-DR group (2358). Baseline data were collected, and variables were selected using Recursive Feature Elimination with Cross-Validation (RFECV). The performance of five machine learning algorithms, including Logistic Regression model (LR), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), and XGBoost (XGB), was assessed based on accuracy, sensitivity, specificity, and Area Under the Curve (AUC) of the Receiver Operating characteristic Curve (ROC). The optimal model was interpreted using SHAP.ResultLVM and LR demonstrated superior performance in both the test set and training set (ROC, 0.85 and 0.82, respectively). The top five predictors identified by SHAP analysis included TyG, Insulin therapy, HbA1c, Diabetes Course, HDL. HDL was identified as a protective factor, while the remaining factors were associated with retinopathy.ConclusionLR and SVM demonstrated the best performance. To our knowledge, this is the first machine learning-based DR prediction model integrating the triglyceride-glucose index (TyG) as a core predictor, overcoming limitations of insulin resistance (IR) assessment in resource-limited settings. TyG provides a cost-effective alternative to conventional IR biomarkers (e.g., HOMA-IR), enabling practical DR risk stratification in primary care.

Age at onset is the most important feature of schizophrenia that could indicate its origin. Minor physical anomalies (MPAs) characterize potential marker indices of disturbances in early neurodevelopment. However, the association between MPAs and age at onset of schizophrenia is still unclear. We aimed to compare risk assessment and familial aggregation in patients with early-onset schizophrenia (EOS) and adult-onset schizophrenia (AOS) with MPAs and craniofacial measures.We estimated the risk assessment of MPAs among patients with EOS (n = 68), patients with AOS (n = 183), nonpsychotic relatives (n = 147), and healthy controls (n = 241) using 3 data-mining algorithms. In addition, we assessed the magnitude of familial aggregation of MPAs with respect to the age at onset of schizophrenia.The performance of EOS was superior to that of AOS, with discrimination accuracies of 89% and 76%, respectively. Combined MPA scores as the risk assessment were significantly higher in all schizophrenia subgroups and the nonpsychotic relatives of EOS patients than in the healthy controls. The recurrence risk ratio for familial aggregation of the MPA scores of EOS families (odds ratio 9.27) was substantially higher than that of AOS families (odds ratio 2.47).The results highlight that EOS improves risk assessment and has a severe magnitude of familial aggregation of MPAs. These findings indicate that EOS might result from a stronger genetic susceptibility to neurodevelopmental deficits.

ObjectiveAnalyze the psychological and clinical factors of clinically significant tinnitus (THI score ≥38) in patients with hearing loss, construct predictive models based on four machine learning (ML) algorithms, and compare the predictive performance of different models.MethodsPatients with hearing loss who visited the Department of Otolaryngology at Qinghai University between August 2024 and May 2025 were enrolled in this study. Clinical data were retrieved from the hospital’s electronic medical record system. The study outcome was the occurrence of clinically significant tinnitus. Predictive variables were screened using univariate analysis, the least absolute shrinkage and selection operator (LASSO) regression, and the Boruta algorithm. Four ML algorithms—logistic regression (LR), random forest (RF), extreme gradient boosting (XGBoost), and support vector machine (SVM)—were applied to construct and validate predictive models. The area under the receiver operating characteristic curve (AUC) of each model in the validation set was compared using the DeLong test. Additionally, model performance metrics in the validation set were compared to identify the optimal model. Finally, the Shapley additive explanations (SHAP) algorithm was employed to interpret the best-performing model.ResultsNine key variables—age, hypertension, sleep disorder, anxiety, hearing loss severity, depression, noise exposure history, hearing side, and ototoxic drug use—were retained after LASSO and Boruta feature selection. Among the four ML models, the RF algorithm achieved the best predictive performance, with an AUC of 0.973 in the training set and 0.977 in the validation set, followed by XGBoost (AUC = 0.962 and 0.961, respectively). DeLong tests confirmed that RF significantly outperformed LR and SVM models (p < 0.001), while its difference from XGBoost was not significant. In the validation set, the RF model yielded the highest accuracy (0.923), sensitivity (0.929), specificity (0.914), precision (0.945), and F1-score (0.937). SHAP analysis indicated that hearing loss severity, age, and sleep disorder were the most influential predictors, suggesting that both auditory and non-auditory factors contribute substantially to the risk of clinically significant tinnitus.ConclusionThe RF model showed the best performance in predicting clinically significant tinnitus, with hearing loss severity, age, and sleep disorder identified as major predictors. Integrating auditory and psychological factors can improve early risk identification in patients with hearing loss.

This study aimed to develop and validate a machine learning-based predictive model for individualized assessment and management of chemotherapy-induced myelosuppression (CIM) in patients with colorectal cancer (CRC). A total of 450 patients with CRC undergoing chemotherapy were retrospectively enrolled in the training cohort, and an additional 150 patients were included for external validation. Feature selection was performed using the Least Absolute Shrinkage and Selection Operator (LASSO) regression. Three machine learning algorithms [Logistic Regression (LR), Random Forest (RF), and Extreme Gradient Boosting (XGBoost)] were applied to construct predictive models. Model performance was assessed using multiple metrics, including accuracy, area under the receiver operating characteristic curve (AUC), F1 score, sensitivity, and specificity. The SHapley Additive exPlanations (SHAP) method was employed to rank and interpret the importance of predictive features. In the training cohort, 52.4% of patients developed CIM. The feature selection process identified 19 significant variables that were incorporated into the predictive models. Both LR and RF demonstrated optimal performance, with an AUC of 0.83 and an accuracy of 0.76 in the training set. In the test set, RF continued to outperform other models, achieving an AUC of 0.77 and an accuracy of 0.71. External validation confirmed the robustness of the RF model, which achieved an AUC of 0.93 (95% CI: 0.89-0.97), an accuracy of 0.89, a sensitivity of 0.86, and a specificity of 0.92. SHAP analysis revealed that the most important predictors included hematological parameters, nutritional risk score (NRS2002), and a history of radiotherapy. The RF-based machine learning model demonstrated high accuracy and strong external validation capability for predicting the risk of CIM in CRC patients.

BACKGROUND Accumulating evidence suggests that the inflammatory cytokine interleukin-6 (IL-6) contributes to the pathophysiology of psychiatric disorders. However, there was no study concerning the relationship between IL-6 concentrations and clinical features in the chronic phase of early-onset schizophrenia (EOS). AIM To investigate the relationship between serum IL-6 concentration and the clinical features of EOS. METHODS We measured serum IL-6 Levels from 74 patients with chronic schizophrenia, including 33 with age at onset &lt; 21 years (EOS group) and 41 with onset ≥ 21 years in [adult-onset schizophrenia (AOS) group], and from 41 healthy controls. Symptom severities were evaluated using the Positive and Negative Syndrome Scale (PANSS). RESULTS Serum IL-6 concentrations were higher in both EOS and AOS groups than healthy controls (F = 22.32, P &lt; 0.01), but did not differ significantly between EOS and AOS groups (P &gt; 0.05) after controlling for age, body mass index, and other covariates. Negative symptom scores were higher in the EOS group than the AOS group (F = 6.199, P = 0.015). Serum IL-6 concentrations in the EOS group were negatively correlated with both total PANSS-negative symptom score (r = -0.389, P = 0.032) and avolition/asociality subscore (r = -0.387, P = 0.026). CONCLUSION Patients with EOS may have more severe negative symptoms than those with adult-onset schizophrenia during the chronic phase of the illness. IL-6 signaling may regulate negative symptoms and its avolition/asociality subsymptoms among the early-onset chronic schizophrenic patients.