BACKGROUND: Acute graft versus host disease (aGvHD) is a major factor that limits the successful outcomes of allogeneic hematopoietic cell transplantation (alloHSCT). Currently, there are few validated biomarkers that can help predict the risk of aGvHD in clinical settings. METHODS: We performed an integrated metabolomics and transcriptomics study and identified biomarkers that distinguish alloHSCT recipients with aGvHD from alloHSCT recipients without aGvHD in 2 separate cohorts. RESULTS: Pathway analysis of 38 significantly altered metabolites and 1,148 differentially expressed genes uncovered a distinctly altered glycerophospholipid (GPL) metabolism network. Subsequently, we developed an aGvHD risk score (GRS) based on 5 metabolite markers from GPL metabolism to predict the risk of aGvHD. GRS showed a positive predictive value of 92.2% and 89.6% in the training and validation cohorts, respectively. In addition, high GRS was correlated with poor overall survival. Gene expressions of GPL-related lipases were significantly altered in aGvHD samples, leading to dysregulated GPLs. CONCLUSION: Using integrative “Omic” analysis, we unraveled a comprehensive view of the molecular perturbations underlying the pathogenesis of aGvHD. Our work represents an initial investigation of a unique metabolic and transcriptomic network that may help identify aGvHD at an early stage and facilitate preemptive therapy. FUNDING: National Natural Science Foundation of China (NSFC; 81530047, 81870143, 81470321, 81770160, 81270567, 81270638, 81573396, 81703674) provided funding for material, processing, metabolomics, and transcriptomics studies. This work was also supported by Shanghai Sailing Program from Science and Technology Commission Shanghai Municipality (17YF1424700), the Scholarship from Shanghai Municipal Health and Family Planning Commission (2017BR012), and the Special Clinical Research in Health Industry in Shanghai (20184Y0054). The projects supporting young scholars are 17YF1424700 (to YL), 2017BR012 (to XH), and 20184Y0054 (to QC).

Background: Prehospital trauma triage is essential to get the right patient to the right hospital. However, the national field triage guidelines proposed by the American College of Surgeons have proven to be relatively insensitive when identifying severe traumas. Objective: This study aimed to build a prehospital triage model to predict severe trauma and enhance the performance of the national field triage guidelines. Methods: This was a multisite prediction study, and the data were extracted from the National Trauma Data Bank between 2017 and 2019. All patients with injury, aged 16 years of age or older, and transported by ambulance from the injury scene to any trauma center were potentially eligible. The data were divided into training, internal, and external validation sets of 672,309; 288,134; and 508,703 patients, respectively. As the national field triage guidelines recommended, age, 7 vital signs, and 8 injury patterns at the prehospital stage were included as candidate variables for model development. Outcomes were severe trauma with an Injured Severity Score ≥16 (primary) and critical resource use within 24 hours of emergency department arrival (secondary). The triage model was developed using an extreme gradient boosting model and Shapley additive explanation analysis. The model’s accuracy regarding discrimination, calibration, and clinical benefit was assessed. Results: At a fixed specificity of 0.5, the model showed a sensitivity of 0.799 (95% CI 0.797-0.801), an undertriage rate of 0.080 (95% CI 0.079-0.081), and an overtriage rate of 0.743 (95% CI 0.742-0.743) for predicting severe trauma. The model showed a sensitivity of 0.774 (95% CI 0.772-0.776), an undertriage rate of 0.158 (95% CI 0.157-0.159), and an overtriage rate of 0.609 (95% CI 0.608-0.609) when predicting critical resource use, fixed at 0.5 specificity. The triage model’s areas under the curve were 0.755 (95% CI 0.753-0.757) for severe trauma prediction and 0.736 (95% CI 0.734-0.737) for critical resource use prediction. The triage model’s performance was better than those of the Glasgow Coma Score, Prehospital Index, revised trauma score, and the 2011 national field triage guidelines RED criteria. The model’s performance was consistent in the 2 validation sets. Conclusions: The prehospital triage model is promising for predicting severe trauma and achieving an undertriage rate of <10%. Moreover, machine learning enhances the performance of field triage guidelines.

Background: Frailty is associated with mortality among older adults. We aimed to determine the appropriate time and frailty index (FI) threshold for frailty intervention in Chinese community-dwelling older adults. Methods: In this prospective cohort study, we used data from the 2011 wave of the Chinese Longitudinal Healthy Longevity Study. Follow-up was performed for seven years from baseline. Using the FI to evaluate frailty and define frailty status, we explored the best time point and FI score for frailty intervention, by comparing the relationships of FI and frailty status with mortality. Results: From 2011 to 2018, 8642 participants were included and followed-up. A total of 4458 participants died during the study period. After adjusting for variables such as age, sex, marital status, education level, and living conditions, the hazard ratio (HR) of mortality risk based on the FI at baseline was 37.484 (95% confidence interval [CI]: 30.217–46.498; P < 0.001); female sex, living in the city, being married, and living with spouse were found to be protective factors, whereas ageing was a risk factor for frailty. The mortality risk was higher in pre-frail than in frail participants (HR: 3.588, 95% CI: 3.212–4.009, P < 0.001). Piecewise linear regression analysis revealed an FI score threshold of 0.5. When the FI score was > 0.5, the HR of mortality based on the FI was 15.758 (95% CI: 3.656–67.924; P < 0.001); when the FI score was ≤ 0.5, the HR of mortality based on the FI was 48.944 (95% CI: 36.162–66.244; P < 0.001). Conclusion: Using FI as a continuous variable to predict death is more accurate than frailty status. The advancement of early interventions for mortality risk reduction is more beneficial in pre-frail than in frail patients, and an FI score of 0.5 was found to be the threshold for mortality prediction using the FI.

Background: Critical trauma patients are particularly prone to increased mortality risk; hence, an accurate prediction of their conditions enables early identification of patients' mortality status. Thus, we aimed to develop and validate a real-time prediction model for physiological changes, organ dysfunctions and mortality risk in critical trauma patients. Methods: We used Dynamic Bayesian Networks (DBNs) to model complicated relationships of physiological variables across time slices, accessing data of trauma patients from the Medical Information Mart for Intensive Care database (MIMIC-III) (n = 2915) and validated with patients' data from ICU admissions at the Changhai Hospital (ICU-CH) (n = 1909). The DBN model's evaluation included the predictive ability of physiological changes, organ dysfunctions and mortality risk. Results: Our DBN model included two static variables (age and sex) and 18 dynamic physiological variables. The differences in ratios between the real values and the 24- and 48-h predicted values of most physiological variables were within 5% in the two datasets. The accuracy of our DBN model for predicting renal, hepatic, cardiovascular and hematologic dysfunctions was more than 0.8.The calculated area under the curve (AUC) from receiver operating characteristic curves and 95% confidence interval for predicting the 24- and 48-h mortality risk were 0.977 (0.967–0.988) and 0.958 (0.945–0.971) in the MIMIC-III and 0.967 (0.947–0.987) and 0.946 (0.925–0.967) in ICU-CH. Conclusions: A DBN is a promising method for predicting medical temporal data such as trauma patients' mortality risk, demonstrated by high AUC scores and validation by a real-life ICU scenario; thus, our DBN prediction model can be used as a real-time tool to predict physiological changes, organ dysfunctions and mortality risk during ICU admissions.

Objective: Trauma is a leading cause of death worldwide, with many incidents resulting in hemorrhage before the patient reaches the hospital. Despite advances in trauma care, the majority of deaths occur within the first three hours of hospital admission, offering a very limited window for effective intervention. Unfortunately, a significant increase in mortality from hemorrhagic trauma is primarily due to delays in hemorrhage control. Therefore, we propose a machine learning model to predict the need for urgent hemorrhage intervention. Methods: This study developed and validated an XGBoost-based machine learning model using data from the National Trauma Data Bank (NTDB) from 2017 to 2019. It focuses on demographic and clinical data from the initial hours following trauma for model training and validation, aiming to predict whether trauma patients require urgent hemorrhage intervention. Results: The XGBoost model demonstrated superior performance across multiple datasets, achieving an AUROC of 0.872 on the training set, 0.869 on the internal validation set, and 0.875 on the external validation set. The model also showed high sensitivity (77.8% on the external validation set) and specificity (82.1% on the external validation set), with an accuracy exceeding 81% across all datasets, highlighting its high reliability for clinical applications. Conclusions: Our study shows that the XGBoost model effectively predicts urgent hemorrhage interventions using data from the National Trauma Data Bank (NTDB). It outperforms other machine learning algorithms in accuracy and robustness across various datasets. These results highlight machine learning’s potential to improve emergency responses and decision-making in trauma care.

Background: To build and validate a radiomics nomogram based on preoperative CT scans and clinical data for detecting synchronous ovarian metastasis (SOM) in female gastric cancer (GC) cases. Methods: Pathologically confirmed GC cases in 2 cohorts were retrospectively enrolled. All cases had presurgical abdominal contrast-enhanced CT and pelvis contrast-enhanced MRI and pathological examinations for any suspicious ovarian lesions detected by MRI. Cohort 1 cases (n = 101) were included as the training set. Radiomics features were obtained to develop a radscore. A nomogram combining the radscore and clinical factors was built to detect SOM. The bootstrap method was carried out in cohort 1 as internal validation. External validation was carried out in cohort 2 (n = 46). Receiver operating characteristic (ROC) curve analysis, decision curve analysis (DCA) and the confusion matrix were utilized to assess the performances of the radscore, nomogram and subjective evaluation model. Results: The nomogram, which combined age and the radscore, displayed a higher AUC than the radscore and subjective evaluation (0.910 vs 0.827 vs 0.773) in the training cohort. In the external validation cohort, the nomogram also had a higher AUC than the radscore and subjective evaluation (0.850 vs 0.790 vs 0.675). DCA and the confusion matrix confirmed the nomogram was superior to the radscore in both cohorts. Conclusions: This pilot study showed that a nomogram model combining the radscore and clinical characteristics is useful in detecting SOM in female GC cases. It may be applied to improve clinical treatment and is superior to subjective evaluation or the radscore alone.