Artificial Intelligence and Big Data Technologies in the Construction of Surgical Risk Prediction Model for Patients with Coronary Artery Bypass Grafting

Comprehensive Summary

In this study, Tang et al. developed a mortality risk prediction model for coronary artery bypass grafting (CABG) using artificial intelligence and big data technologies. To construct the model, the researchers gathered clinical data from 2,364 patients at a hospital in China. The data included patients’ demographic details, preoperative and postoperative medical history, coronary angiography data, cardiac ultrasound data, surgical data, and data from follow-ups after discharge. Three features of the model were integral to its success: case feature analysis service, risk early-warning service, and case retrieval service. In terms of precision, F1 score, and AUC, the gradient-boosted tree (GBT) model outperformed the others. By comparing in-hospital mortality rate (1.05%) and the predicted CABG mortality rate (2.67 ± 1.82%), an overestimation of intermediate-risk patients’ mortality risk was observed. However, it was found that the CABG risk prediction model has a better ability to predict surgical risk in higher-risk groups. Through continued research, development, and clinical trials, the model may be further improved and used for different heart conditions.

Outcomes and Implications

Since CABG is an important and widespread surgical procedure used to treat coronary heart disease (CHD), this risk assessment model is of great value to cardiac surgeons who face difficulties in patient assessment and surgical risk prediction as the model provides a theoretical basis for future complications. Additionally, if surgical risk is predicted early on, an individualized treatment plan may be produced in advance, potentially leading to improved patient prognosis.