Lumbar disc bulging or herniation (LDBH) is one of the major causes of spinal stenosis and related nerve compression, and its severity is the major determinant for spine surgery. MRI of the spine is the most important diagnostic tool for evaluating the need for surgical intervention in patients with LDBH. However, MRI utilization is limited by its low accessibility. Spinal X-rays can rapidly provide information on the bony structure of the patient. Our study aimed to identify the factors associated with LDBH, including disc height, and establish a clinical diagnostic tool to support its diagnosis based on lumbar X-ray findings. In this study, a total of 458 patients were used for analysis and 13 clinical and imaging variables were collected. Five machine-learning (ML) methods, including LASSO regression, MARS, decision tree, random forest, and extreme gradient boosting, were applied and integrated to identify important variables for predicting LDBH from lumbar spine X-rays. The results showed L4-5 posterior disc height, age, and L1-2 anterior disc height to be the top predictors, and a decision tree algorithm was constructed to support clinical decision-making. Our study highlights the potential of ML-based decision tools for surgeons and emphasizes the importance of L1-2 disc height in relation to LDBH. Future research will expand on these findings to develop a more comprehensive decision-supporting model.

BACKGROUND Sodium-glucose cotransporter 2 inhibitors (SGLT2i) can benefit patients with type 2 diabetes mellitus by reducing hazardous renal outcomes. This study compared the renal benefits of combining SGLT2i with renin-angiotensin system blockers (RASB) versus combining RASB with dipeptidyl peptidase 4 inhibitors (DPP4i). MATERIAL AND METHODS This was a retrospective cohort study with a new-user and active-comparator design. The study utilized data from the Taiwan National Health Insurance Research Database, including patients with type 2 diabetes mellitus enrolled between January 1, 2016 and December 31, 2016. Participants were divided into 2 groups: the case group (n=3622) receiving RASB plus SGLT2i and the comparison group (n=3622) receiving RASB plus DPP4i. The groups were matched 1: 1 based on sex, age, and Charlson comorbidity index. Both groups were followed until December 31, 2020. Additionally, a global dataset of TriNetX was used for external validation. RESULTS After matching, unadjusted hazard ratios (HRs) showed significant differences favoring the SGLT2i group for chronic kidney disease (CKD) (HR: 0.66; 95% CI, 0.58-0.74), advanced kidney failure (HR: 0.64; 95% CI, 0.44-0.93), and initiation of long-term dialysis (HR: 0.61; 95% CI, 0.38-0.97). These differences remained significant after multivariable adjusting: CKD (HR: 0.74; 95% CI, 0.65-0.84), advanced kidney failure (HR: 0.62; 95% CI, 0.42-0.92), and commencement of long-term dialysis (HR: 0.53; 95% CI, 0.32-0.87). The renal benefits of the combination therapy were consistently observed in the TriNetX dataset. CONCLUSIONS This study shows the real-world benefits of combining SGLT2i with RASB, providing clinicians with valuable evidence to optimize renal outcomes in patients with type 2 diabetes.

Background Sodium-glucose cotransporter 2 inhibitors (SGLT2i) can benefit patients with type 2 diabetes mellitus by reducing hazardous renal outcomes. This study aimed to evaluate whether the combination of sodium-glucose cotransporter 2 inhibitors (SGLT2i) and conventional renin-angiotensin system blockers (RASB) provides a synergistic effect on renal outcomes in patients with type 2 diabetes mellitus, compared to the combination of RASB and dipeptidyl peptidase 4 inhibitors (DPP4i). Methods This is a retrospective cohort study. The study utilized data from the Taiwan National Health Insurance Research Database (NHIRD), including patients with type 2 diabetes mellitus enrolled between January 1, 2016, and December 31, 2016. Participants were divided into two groups: the case group (n = 3,622) receiving RASB plus SGLT2i and the comparison group (n = 3,622) receiving RASB plus DPP4i. The groups were matched 1:1 based on gender, age, and Charlson comorbidity index. Additionally, TriNetX was used for external validation. Results Prior to matching, unadjusted hazard ratios (HRs) showed significant differences favoring the SGLT2i group for chronic kidney disease (CKD) (HR: 0.66; 95% CI, 0.58–0.74), advanced kidney failure (HR: 0.64; 95% CI, 0.44–0.93), and initiation of long-term dialysis (HR: 0.61; 95% CI, 0.38–0.97). These differences remained significant post-matching: CKD (HR: 0.74; 95% CI, 0.65–0.84), advanced kidney failure (HR: 0.62; 95% CI, 0.42–0.92), and commencement of long-term dialysis (HR: 0.53; 95% CI, 0.32–0.87). The renal benefits of the combination therapy were consistently observed in the TriNetX dataset. Limitations NHIRD lacks key clinical factors (e.g., physical features, lab data), potential baseline disparities due to retrospective design, and limited generalizability beyond Taiwanese patients, despite TriNexT validation. Conclusions In patients with type 2 diabetes mellitus, combination therapy with SGLT2i and RASB yielded better renal outcomes.

BACKGROUND In-hospital cardiac arrest (IHCA) remains a catastrophic event with persistently low survival, even amid advances in resuscitation and critical care. Conventional early warning scores provide only limited predictive accuracy, often failing to identify patients at highest risk. To overcome these limitations, we evaluated a multimodal prediction framework that integrates traditional logistic regression with advanced machine learning (ML) approaches to optimize risk stratification. OBJECTIVE This study aimed to develop and compare the performance of multiple machine learning algorithms against traditional logistic regression for predicting IHCA using a comprehensive set of electronic health record (EHR) data. METHODS We conducted a retrospective case–control study including 800 IHCA cases and 3,464 matched controls from a large tertiary medical center. Candidate predictors comprised demographics, comorbidities, laboratory values, and vital signs. Five models—logistic regression, decision tree, random forest, XGBoost, and multivariate adaptive regression splines (MARS)—were trained and validated. Model performance was assessed using accuracy, sensitivity, specificity, F1 score, and area under the receiver operating characteristic curve. RESULTS Among all models, XGBoost demonstrated the best predictive performance (AUC 0.909; accuracy 0.883), followed by random forest (AUC 0.910; accuracy 0.876). Logistic regression achieved robust but comparatively lower performance (AUC 0.895; accuracy 0.876). Importantly, ML models highlighted clinically relevant predictors—such as blood urea nitrogen, heart rate, and presence of heart failure—providing novel insights beyond traditional regression. CONCLUSIONS Integrating ML-based approaches with conventional regression substantially improved IHCA risk prediction. While logistic regression offers transparency and interpretability, ML models capture complex, non-linear interactions that enhance accuracy. This multimodal framework holds potential to strengthen hospital early warning systems, enabling earlier detection, timely intervention, and ultimately improved patient outcomes. CLINICALTRIAL The study protocol was approved by the Institutional Review Board of National Taiwan University Hospital (IRB No. 201807063RINC). Due to the retrospective nature of this study, which involved the analysis of pre-existing data, trial registration was not required.