XGBoost-based machine learning test improves the accuracy of hemorrhage prediction among geriatric patients with long-term administration of rivaroxaban

Artificial Intelligence in Atrial Fibrillation: From Early Detection to Precision Therapy

Atrial fibrillation (AF) is the most prevalent cardiac arrhythmia, associated with significant morbidity, mortality, and healthcare burden. Despite advances in AF management, challenges persist in early detection, risk stratification, and treatment optimization, necessitating innovative solutions. Artificial intelligence (AI) has emerged as a transformative tool in AF care, leveraging machine learning and deep learning algorithms to enhance diagnostic accuracy, improve risk prediction, and guide therapeutic interventions. AI-powered electrocardiographic screening has demonstrated the ability to detect asymptomatic AF, while wearable photoplethysmography-based technologies have expanded real-time rhythm monitoring beyond clinical settings. AI-driven predictive models integrate electronic health records and multimodal physiological data to refine AF risk stratification, stroke prediction, and anticoagulation decision making. In the realm of treatment, AI is revolutionizing individualized therapy and optimizing anticoagulation management and catheter ablation strategies. Notably, AI-enhanced electroanatomic mapping and real-time procedural guidance hold promise for improving ablation success rates and reducing AF recurrence. Despite these advancements, the clinical integration of AI in AF management remains an evolving field. Future research should focus on large-scale validation, model interpretability, and regulatory frameworks to ensure widespread adoption. This review explores the current and emerging applications of AI in AF, highlighting its potential to enhance precision medicine and patient outcomes.

Novel machine-learning model for predicting lymph node metastasis in resectable pancreatic ductal adenocarcinoma

Aim

Lymph node metastasis is an adverse prognostic factor in pancreatic ductal adenocarcinoma. However, it remains a challenge to predict lymph node metastasis using preoperative imaging alone. We used machine learning (combining preoperative imaging findings, tumor markers, and clinical information) to create a novel prediction model for lymph node metastasis in resectable pancreatic ductal adenocarcinoma.

Methods

The data of patients with resectable pancreatic ductal adenocarcinoma who underwent surgery between September 1991 and October 2022 were retrospectively examined. Machine-learning software (Statistical Package for the Social Sciences Modeler) was used to create a prediction model, and parameter tuning was performed to improve the model's accuracy. We also analyzed the contribution of each feature to prediction using individual conditional expectation and partial dependence plots.

Results

Of the 331 cases included in the study, 241 comprised the training cohort and 90 comprised the test cohort. After parameter tuning, the areas under the receiver operating characteristic curves for the training and test cohorts were 0.780 and 0.795, respectively. Individual conditional expectation and partial dependence plots showed that larger tumor size and carbohydrate antigen 19-9 and Duke pancreatic monoclonal antigen type 2 levels were associated with positive lymph node metastasis prediction in this model; neoadjuvant treatment was associated with negative lymph node metastasis prediction.

Conclusion

Machine learning may contribute to the creation of an effective predictive model of lymph node metastasis in pancreatic ductal adenocarcinoma. Prediction models using machine learning may contribute to the development of new treatment strategies in resectable pancreatic ductal adenocarcinoma.

Bioinformatics Identification of angiogenesis-related biomarkers and therapeutic targets in cerebral ischemia-reperfusion

Promoting vascular endothelial cell regeneration can enhance recovery from cerebral ischemia reperfusion injury (CIRI), but there is a lack of bioinformatic studies on angiogenesis-related biomarkers in CIRI. In this study, we utilized the GSE97537 and GSE61616 datasets from GEO to identify 181 angiogenesis-related genes (ARGs) and analyzed differentially expressed genes (DEGs) between CIRI and control groups. We converted ARGs to 169 rat homologues and intersected them with DEGs to find DE-ARGs. RF and XGBoost models were employed to identify five biomarkers (Stat3, Hmox1, Egfr, Col18a1, Ptgs2) and conducted GSEA on these biomarkers, revealing their enrichment in pathways such as ECM-receptor interaction and hematopoietic cell lineage. We also analyzed the immune microenvironment, finding significant differences in 21 immune cells between CIRI and control groups. Furthermore, we constructed lncRNA-miRNA-mRNA networks and drug-gene networks. Finally, biomarker expression was compared between the CIRI and control groups by qRT-PCR in tissue and blood samples. Overall, our bioinformatic exploration of angiogenesis-related biomarkers in CIRI provides new insights for the diagnosis and treatment of CIRI.

Predicting adverse drug event using machine learning based on electronic health records: a systematic review and meta-analysis

Introduction

Adverse drug events (ADEs) pose a significant challenge in current clinical practice. Machine learning (ML) has been increasingly used to predict specific ADEs using electronic health record (EHR) data. This systematic review provides a comprehensive overview of the application of ML in predicting specific ADEs based on EHR data.

Methods

A systematic search of PubMed, Web of Science, Embase, and IEEE Xplore was conducted to identify relevant articles published from the inception to 20 May 2024. Studies that developed ML models for predicting specific ADEs or ADEs associated with particular drugs were included using EHR data.

Results

A total of 59 studies met the inclusion criteria, covering 15 drugs and 15 ADEs. In total, 38 machine learning algorithms were reported, with random forest (RF) being the most frequently used, followed by support vector machine (SVM), eXtreme gradient boosting (XGBoost), decision tree (DT), and light gradient boosting machine (LightGBM). The performance of the ML models was generally strong, with an average area under the curve (AUC) of 76.68% ± 10.73, accuracy of 76.00% ± 11.26, precision of 60.13% ± 24.81, sensitivity of 62.35% ± 20.19, specificity of 75.13% ± 16.60, and an F1 score of 52.60% ± 21.10. The combined sensitivity, specificity, diagnostic odds ratio (DOR), and AUC from the summary receiver operating characteristic (SROC) curve using a random effects model were 0.65 (95% CI: 0.65-0.66), 0.89 (95% CI: 0.89-0.90), 12.11 (95% CI: 8.17-17.95), and 0.8069, respectively. The risk factors associated with different drugs and ADEs varied.

Discussion

Future research should focus on improving standardization, conducting multicenter studies that incorporate diverse data types, and evaluating the impact of artificial intelligence predictive models in real-world clinical settings.

Systematic Review Registration

https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42024565842, identifier CRD42024565842.

Machine learning models for prediction of lymph node metastasis in patients with T1b gastric cancer

The prognosis of early gastric cancer (EGC) patients is associated with lymph node metastasis (LNM). Considering the relatively high rate of LNM in T1b EGC patients, it is crucial to determine the factors associated with LNM. In this study, we constructed and validated predictive models based on machine learning (ML) algorithms for LNM in patients with T1b EGC. Data from patients with T1b gastric cancer were extracted from the Korean Gastric Cancer Association database. ML algorithms such as logistic regression (LR), random forest (RF), extreme gradient boosting (XGBoost), and support vector machine (SVM) were applied for model construction utilizing five-fold cross-validation. The performances of these models were assessed in terms of discrimination, calibration, and clinical applicability. Moreover, external validation of XGBoost models was performed using the T1b gastric cancer database of The Catholic University Medical Center. In total, 3,468 T1b EGC patients were included in the analysis, whom 550 (15.9%) had LNM. Eleven variables were selected to construct the models. The LR, RF, XGBoost, and SVM models were established, revealing area under the receiver operating characteristic curve values of 0.8284, 0.7921, 0.8776, and 0.8323, respectively. Among the models, the XGBoost model exhibited the best predictive performance in terms of discrimination, calibration, and clinical applicability. ML models are reliable for predicting LNM in T1b EGC patients. The XGBoost model exhibited the best predictive performance and can be used by surgeons for the identification of EGC patients with a high-risk of LNM, thereby facilitating treatment selection.

Artificial intelligence and atrial fibrillation: A bibliometric analysis from 2013 to 2023

Background

In the study of atrial fibrillation (AF), a prevalent cardiac arrhythmia, the utilization of artificial intelligence (AI) in diagnostic and therapeutic strategies holds the potential to address existing limitations. This research employs bibliometrics to objectively investigate research hotspots, development trends, and existing issues in the application of AI within the AF field, aiming to provide targeted recommendations for relevant researchers.

Methods

Relevant publications on the application of AI in AF field were retrieved from the Web of Science Core Collection (WoSCC) database from 2013 to 2023. The bibliometric analysis was conducted by the R (4.2.2) "bibliometrix" package and VOSviewer(1.6.19).

Results

Analysis of 912 publications reveals that the field of AI in AF is currently experiencing rapid development. The United States, China, and the United Kingdom have made outstanding contributions to this field. Acharya UR is a notable contributor and pioneer in the area. The following topics have been elucidated: AI's application in managing the risk of AF complications is a hot mature topic; AI-electrocardiograph for AF diagnosis and AI-assisted catheter ablation surgery are the emerging and booming topics; smart wearables for real-time AF monitoring and AI for individualized AF medication are niche and well-developed topics.

Conclusion

This study offers comprehensive analysis of the origin, current status, and future trends of AI applications in AF, aiming to advance the development of the field.

Development of a machine learning algorithm to predict the residual cognitive reserve index

Elucidating the mechanisms by which late-life neurodegeneration causes cognitive decline requires understanding why some individuals are more resilient than others to the effects of brain change on cognition (cognitive reserve). Currently, there is no way of measuring cognitive reserve that is valid (e.g. capable of moderating brain-cognition associations), widely accessible (e.g. does not require neuroimaging and large sample sizes), and able to provide insight into resilience-promoting mechanisms. To address these limitations, this study sought to determine whether a machine learning approach to combining standard clinical variables could (i) predict a residual-based cognitive reserve criterion standard and (ii) prospectively moderate brain-cognition associations. In a training sample combining data from the University of California (UC) Davis and the Alzheimer's Disease Neuroimaging Initiative-2 (ADNI-2) cohort (N = 1665), we operationalized cognitive reserve using an MRI-based residual approach. An eXtreme Gradient Boosting machine learning algorithm was trained to predict this residual reserve index (RRI) using three models: Minimal (basic clinical data, such as age, education, anthropometrics, and blood pressure), Extended (Minimal model plus cognitive screening, word reading, and depression measures), and Full [Extended model plus Clinical Dementia Rating (CDR) and Everyday Cognition (ECog) scale]. External validation was performed in an independent sample of ADNI 1/3/GO participants (N = 1640), which examined whether the effects of brain change on cognitive change were moderated by the machine learning models' cognitive reserve estimates. The three machine learning models differed in their accuracy and validity. The Minimal model did not correlate strongly with the criterion standard (r = 0.23) and did not moderate the effects of brain change on cognitive change. In contrast, the Extended and Full models were modestly correlated with the criterion standard (r = 0.49 and 0.54, respectively) and prospectively moderated longitudinal brain-cognition associations, outperforming other cognitive reserve proxies (education, word reading). The primary difference between the Minimal model-which did not perform well as a measure of cognitive reserve-and the Extended and Full models-which demonstrated good accuracy and validity-is the lack of cognitive performance and informant-report data in the Minimal model. This suggests that basic clinical variables like anthropometrics, vital signs, and demographics are not sufficient for estimating cognitive reserve. Rather, the most accurate and valid estimates of cognitive reserve were obtained when cognitive performance data-ideally augmented by informant-reported functioning-was used. These results indicate that a dynamic and accessible proxy for cognitive reserve can be generated for individuals without neuroimaging data and gives some insight into factors that may promote resilience.