Prediction Model of in-Hospital Venous Thromboembolism in Chinese Adult Patients after Hernia Surgery: The CHAT Score

Machine Learning to Dynamically Predict In-Hospital Venous Thromboembolism After Inguinal Hernia Surgery: Results From the CHAT-1 Study

BACKGROUND

The accuracy of current prediction tools for venous thromboembolism (VTE) events following hernia surgery remains insufficient for individualized patient management strategies. To address this issue, we have developed a machine learning (ML)-based model to dynamically predict in-hospital VTE in Chinese patients after hernia surgery.

METHODS

ML models for the prediction of postoperative VTE were trained on a cohort of 11 305 adult patients with hernia from the CHAT-1 trial, which included patients across 58 institutions in China. In data processing, data imputation was conducted using random forest (RF) algorithm, and balanced sampling was done by adaptive synthetic sampling algorithm. Data were split into a training cohort (80%) and internal validation cohort (20%) prior to oversampling. Clinical features available pre-operatively and postoperatively were separately selected using the Sequence Forward Selection algorithm. Nine-candidate ML models were applied to the pre-operative and combined datasets, and their performance was evaluated using various metrics, including area under the receiver operating characteristic curve (AUROC). Model interpretations were generated using importance scores, which were calculated by transforming model features into scaled variables and representing them in radar plots.

RESULTS

The modeling cohort included 2856 patients, divided into 2536 cases for derivation and 320 cases for validation. Eleven pre-operative variables and 15 combined variables were explored as predictors related to in-hospital VTE. Acceptable-performing models for pre-operative data had an AUROC ≥ 0.60, including logistic regression, support vector machine with linear kernel (SVM_Linear), attentive interpretable Tabular learning (TabNet), and RF. For combined data, logistic regression, SVM_Linear, and TabNet had better performance, with an AUROC ≥ 0.65 for each model. Based on these models, 7 pre-operative predictors and 10 combined predictors were depicted in radar plots.

CONCLUSIONS

A ML-based approach for the identification of in-hospital VTE events after hernia surgery is feasible. TabNet showed acceptable performance, and might be useful to guide clinical decision making and VTE prevention. Further validated study will strengthen this finding.

Prevalence, risk factors, and prediction of inappropriate use of non-vitamin K antagonist oral anticoagulants in elderly Chinese patients with atrial fibrillation: A study protocol

Background

Atrial fibrillation (AF) is an arrhythmia that is prevalent globally, and its incidence grows exponentially with aging. Non-vitamin K antagonist oral anticoagulants (NOACs) have been developed in recent years, and it challenges the supremacy of warfarin for thromboembolism prophylaxis in AF. Nevertheless, there are limited data specifically evaluating the real-life use of NOACs in elderly patients with AF in China.

Methods

This is a national, multicenter, non-interventional, cross-sectional study that enrolls patients with AF aged 75 years and above from 31 institutions across China. Data were collected using the Hospital Information System. The primary outcomes include (1) profiles of NOAC use in the elderly; (2) frequency of inappropriate NOAC use based on guidelines and approved labeling recommendations; (3) exploring potential risk factors related to NOACs inappropriate use; and (4) creating a prediction tool for inappropriate NOACs use.

Conclusion

The results of this study reveal the prevalence, risk factors, and corresponding prediction tool of inappropriate NOACs use in older patients with AF in China, as well as provide valuable insights into the clinical application of NOACs in high-risk populations in the real-world setting.

Clinical trial registration

www.ClinicalTrials.gov, identifier: NCT 05361889.