Background: Sepsis remains a significant challenge in patients with major trauma in the ICU. Early detection and treatment are crucial for improving outcomes and reducing mortality rates. Nonetheless, clinical tools for predicting sepsis among patients with major trauma are limited. This study aimed to develop and validate an artificial intelligence (AI) platform for predicting the risk of sepsis among patients with major trauma. Patients and methods: This study involved 961 patients, with a prospective analysis of data from 244 patients with major trauma at our hospital and a retrospective analysis of data from 717 patients extracted from a database in the United States. The patients from our hospital constituted the model development cohort, and the patients from the database constituted the external validation cohort. The patients in the model development cohort were randomly divided into a training cohort and an internal validation cohort at a ratio of 8:2. The machine-learning algorithms used to train models included logistic regression, decision tree, extreme gradient boosting machine (eXGBM), neural network (NN), random forest, and light gradient boosting machine (LightGBM). Results: The incidence of sepsis for the model development cohort was 43.44%. Twelve predictors, including gender, abdominal trauma, open trauma, red blood cell count, heart rate, respiratory rate, injury severity score, sequential organ failure assessment score, Glasgow coma scale, smoking, total protein concentrations, and hematocrit, were used as features in the final model. Internal validation showed that the NN model had the highest area under the curve (AUC) of 0.932 (95% CI: 0.917–0.948), followed by the LightGBM and eXGBM models with AUCs of 0.913 (95% CI: 0.883–0.930) and 0.912 (95% CI: 0.880–0.935), respectively. In the external validation cohort, the eXGBM model (AUC: 0.891, 95% CI: 0.866–0.914) had the highest AUC value, followed by the LightGBM model (AUC: 0.886, 95% CI: 0.860–0.906), and the AUC value of the NN model was only 0.787 (95% CI: 0.751–0.829). Considering the predictive performance for both the internal and external validation cohorts, the LightGBM model had the highest score of 82, followed by the eXGBM (81) and NN (76) models. Thus, the LightGBM has emerged as the optimal model, and it was deployed online as an AI application. Conclusions: This study develops and validates an AI application to effectively assess the susceptibility of patients with major trauma to sepsis. The AI application equips healthcare professionals with a valuable tool to promptly identify individuals at high risk of developing sepsis. This will facilitate clinical decision-making and enable early intervention.

The aim of this study was to develop a scoring system for prediction of survival prognosis after surgery in patients with symptomatic metastatic spinal cord compression (MSCC) from non-small cell lung cancer (NSCLC). We retrospectively analyzed nine preoperative characteristics for survival in a series of 64 patients with NSCLC who were operated with posterior decompression and spine stabilization for MSCC. Characteristics significantly associated with survival on multivariate analysis were included in the scoring system. The scoring point for each significant characteristic was derived from the hazard ratios on Cox proportional hazards model. The total score for each patient was obtained by adding the scoring points of all significant characteristics. Eastern Cooperative Oncology Group (ECOG) performance status, number of involved vertebrae, visceral metastases, and time developing motor deficits had significant impact on survival on multivariate analysis and were included in the scoring system. According to the prognostic scores, which ranged from 4 to 10 points, three prognostic groups were designed: 4–5 points (n = 22), 6–7 points (n = 23), and 8–10 points (n = 19). The corresponding 6-month survival rates were 95, 47 and 11 %, respectively (P < 0.0001). In addition, the functional outcome was worse in the group of patients with 8–10 points compared with other two prognostic groups. The new scoring system will enable physicians to identify patient with MSCC from NSCLC who may be a candidate for decompression and spine stabilization, more radical surgery, or supportive care alone. Patients with scores of 4–5, who have the most favorable survival prognosis and functional outcome, can be treated with more radical surgery in order to realize better local control of disease and prevent the occurrence of local disease. Patients with scores of 6–7 points should be surgical candidates, because survival prognosis and functional outcome are acceptable after surgery, while patients with scores of 8–10 points, who have the shortest survival time and poorest functional outcome after surgery, appear to be best treated with radiotherapy or best supportive care.

Stress hyperglycemia ratio (SHR) has emerged as a potential prognostic marker in critical illness, but its association with mortality in cardiovascular disease remains incompletely characterized. This study investigated the relationship between SHR and all-cause mortality in critically ill patients with cardiovascular disease, adjusting for a variety of confounding factors using propensity score matching (PSM). A cohort of 3,352 critically ill patients with cardiovascular disease was stratified by SHR quartiles (Q1–Q4). Baseline characteristics, comorbidities (e.g., heart failure, diabetes), and severity scores (OASIS, APSIII, SOFA) were extracted from a large database containing de-identified health data patients admitted to the intensive care units (ICUs) of Beth Israel Deaconess Medical Center. PSM (670 matched pairs) balanced covariates between high (SHR > 1.355) and low SHR groups. The associations between SHR and mortality risk (in-hospital, 28-day, 90-day, 365-day) were evaluated using Cox models, restricted cubic spline (RCS) analysis, and Kaplan-Meier survival curves. Cox proportional hazards models were implemented with three sequential adjustment levels: Model 1 (unadjusted); Model 2 (adjusted for demographic factors and comorbidities); and Model 3 (fully adjusted). Predictive performance of SHR combined with severity scores was assessed via area under the curve (AUC) improvement. Higher SHR quartiles exhibited greater comorbidity burden (e.g., acute kidney injury: 84.6% in Q4 vs. 79.7% in Q1, P < 0.001) and severity scores (P < 0.001). Unadjusted analysis showed a significant association between SHR and mortality, with Q4 having the highest in-hospital (Q4: 16.3% vs. Q1–Q3: 5.1–6.4%, P < 0.001) and 365-day mortality (Q4: 29.2% vs. Q1–Q3: 15.7–16.9%, P < 0.001). The RCS analysis revealed a U-shaped mortality risk, with average optimal SHR cutoffs of 1.355. After PSM, cox proportional hazard models confirmed that high SHR (Q4) remained associated with early mortality (in-hospital HR = 2.117, [95% CI: 1.223–3.665], P = 0.007; 28-day HR = 1.859, [95% CI: 1.100-3.141], P = 0.020) but not long-term outcomes (90-day mortality, P = 0.127; 365-day mortality, P = 0.123) in the Model 1. Similar trends were obtained after adjusting for demographic factors and comorbidities (Model 2) and in the fully adjusted model (Model 3). Adding SHR improved short-term mortality prediction performance (e.g., OASIS AUC: +0.034 for in-hospital, P < 0.001), though benefits diminished post-PSM (e.g., OASIS: +0.012 for in-hospital, P = 0.009). However, incorporating SHR did not enhance the predictive performance of OASIS and SAPSII for 90-day and 365-day mortality prediction after PSM. Elevated SHR contributes to early mortality in patients with cardiovascular disease, even after rigorous confounder adjustment. The incremental predictive value of SHR support its utility for risk stratification, particularly for short-term outcomes, but its prognostic value fades for long-term mortalities. These findings highlight SHR as a favorable biomarker for clinical decision-making in acute cardiovascular care.

Background: Identification of patients with high-risk of experiencing inability to walk after surgery is important for surgeons to make therapeutic strategies for patients with metastatic spinal disease. However, there is a lack of clinical tool to assess postoperative ambulatory status for those patients. The emergence of artificial intelligence (AI) brings a promising opportunity to develop accurate prediction models. Methods: This study collected 455 patients with metastatic spinal disease who underwent posterior decompressive surgery at three tertiary medical institutions. Of these, 220 patients were collected from one medical institution to form the model derivation cohort, while 89 and 146 patients were collected from two other medical institutions to form the external validation cohorts 1 and 2, respectively. Patients in the model derivation cohort were used to develop and internally validate models. To establish the interactive AI platform, machine learning techniques were used to develop prediction models, including logistic regression (LR), decision tree (DT), random forest (RF), extreme gradient boosting machine (eXGBM), support vector machine (SVM), and neural network (NN). Furthermore, to enhance the resilience of the study’s model, an ensemble machine learning approach was employed using a soft-voting method by combining the results of the above six algorithms. A scoring system incorporating 10 evaluation metrics was used to comprehensively assess the prediction performance of the developed models. The scoring system had a total score of 0 to 60, with higher scores denoting better prediction performance. An interactive AI platform was further deployed via Streamlit. The prediction performance was compared between medical experts and the AI platform in assessing the risk of experiencing postoperative inability to walk among patients with metastatic spinal disease. Results: Among all developed models, the ensemble model outperformed the six other models with the highest score of 57, followed by the eXGBM model (54), SVM model (50), and NN model (50). The ensemble model had the best performance in accuracy and calibration slope, and the second-best performance in precise, recall, specificity, area under the curve (AUC), Brier score, and log loss. The scores of the LR model, RF model, and DT model were 39, 46, and 26, respectively. External validation demonstrated that the ensemble model had an AUC value of 0.873 (95% CI: 0.809–0.936) in the external validation cohort 1 and 0.924 (95% CI: 0.890–0.959) in the external validation cohort 2. In the new ensemble machine learning model excluding the feature of the number of comorbidities, the AUC value was still as high as 0.916 (95% CI: 0.863–0.969). In addition, the AUC values of the new model were 0.880 (95% CI: 0.819–0.940) in the external validation cohort 1 and 0.922 (95% CI: 0.887–0.958) in the external validation cohort 2, indicating favorable generalization of the model. The interactive AI platform was further deployed online based on the final machine learning model, and it was available at https://postoperativeambulatory-izpdr6gsxxwhitr8fubutd.streamlit.app/. By using the AI platform, researchers were able to obtain the individual predicted risk of postoperative inability to walk, gain insights into the key factors influencing the outcome, and find the stratified therapeutic recommendations. The AUC value obtained from the AI platform was significantly higher than the average AUC value achieved by the medical experts (P<0.001), denoting that the AI platform obviously outperformed the individual medical experts. Conclusions: The study successfully develops and validates an interactive AI platform for evaluating the risk of postoperative loss of ambulatory ability in patients with metastatic spinal disease. This AI platform has the potential to serve as a valuable model for guiding healthcare professionals in implementing surgical plans and ultimately enhancing patient outcomes.

Background: Individualized therapeutic strategies can be carried out under the guidance of expected lifespan, hence survival prediction is important. Nonetheless, reliable survival estimation in individuals with bone metastases from cancer of unknown primary (CUP) is still scarce. The objective of the study is to construct a model as well as a web-based calculator to predict three-month mortality among bone metastasis patients with CUP using machine learning-based techniques.Methods: This study enrolled 1010 patients from a large oncological database, the Surveillance, Epidemiology, and End Results (SEER) database, in the United States between 2010 and 2018. The entire patient population was classified into two cohorts at random: a training cohort (n=600, 60%) and a validation cohort (410, 40%). Patients from the validation cohort were used to validate models after they had been developed using the four machine learning approaches of random forest, gradient boosting machine, decision tree, and eXGBoosting machine on patients from the training cohort. In addition, 101 patients from two large teaching hospital were served as an external validation cohort. To evaluate each model’s ability to predict the outcome, prediction measures such as area under the receiver operating characteristic (AUROC) curves, accuracy, and Youden index were generated. The study’s risk stratification was done using the best cut-off value. The Streamlit software was used to establish a web-based calculator.Results: The three-month mortality was 72.38% (731/1010) in the entire cohort. The multivariate analysis revealed that older age (P=0.031), lung metastasis (P=0.012), and liver metastasis (P=0.008) were risk contributors for three-month mortality, while radiation (P=0.002) and chemotherapy (P<0.001) were protective factors. The random forest model showed the highest area under curve (AUC) value (0.796, 95% CI: 0.746-0.847), the second-highest precision (0.876) and accuracy (0.778), and the highest Youden index (1.486), in comparison to the other three machine learning approaches. The AUC value was 0.748 (95% CI: 0.653-0.843) and the accuracy was 0.745, according to the external validation cohort. Based on the random forest model, a web calculator was established: https://starxueshu-codeok-main-8jv2ws.streamlitapp.com/. When compared to patients in the low-risk groups, patients in the high-risk groups had a 1.99 times higher chance of dying within three months in the internal validation cohort and a 2.37 times higher chance in the external validation cohort (Both P<0.001).Conclusions: The random forest model has promising performance with favorable discrimination and calibration. This study suggests a web-based calculator based on the random forest model to estimate the three-month mortality among bone metastases from CUP, and it may be a helpful tool to direct clinical decision-making, inform patients about their prognosis, and facilitate therapeutic communication between patients and physicians.