Machine learning algorithms for the prediction of adverse prognosis in patients undergoing peritoneal dialysis

• Published in: BMC medical informatics and decision making 2024-01, Vol.24 (1), p.8-8, Article 8
• Main Authors: Yang, Jie, Wan, Jingfang, Feng, Lei, Hou, Shihui, Yv, Kaizhen, Xu, Liang, Chen, Kehong
• Format: Article
• Language: English
• Subjects: Algorithms; Antibodies; Antigens; Blood pressure; Care and treatment; Cholesterol; Continuous ambulatory peritoneal dialysis; Data mining; Dialysis; Disease; Health aspects; Hemodialysis; Hepatitis; Humans; Indicators; Kidney transplants; Kinases; Learning algorithms; Machine Learning; Machine learning; Medical prognosis; Methods; Mortality; Patient outcomes; Patients; Performance prediction; Peritoneal Dialysis; Peritoneal dialysis; Peritoneum; Peritonitis; Prediction models; Prediction model; Prognosis; Renal replacement therapy; Retrospective Studies; Technology assessment; Uremia
• ISSN: 1472-6947; 1472-6947
• DOI: 10.1186/s12911-023-02412-z

An appropriate prediction model for adverse prognosis before peritoneal dialysis (PD) is lacking. Thus, we retrospectively analysed patients who underwent PD to construct a predictive model for adverse prognoses using machine learning (ML). A retrospective analysis was conducted on 873 patients who underwent PD from August 2007 to December 2020. A total of 824 patients who met the inclusion criteria were included in the analysis. Five commonly used ML algorithms were used for the initial model training. By using the area under the curve (AUC) and accuracy (ACC), we ranked the indicators with the highest impact and displayed them using the values of Shapley additive explanation (SHAP) version 0.41.0. The top 20 indicators were selected to build a compact model that is conducive to clinical application. All model-building steps were implemented in Python 3.8.3. At the end of follow-up, 353 patients withdrew from PD (converted to haemodialysis or died), and 471 patients continued receiving PD. In the complete model, the categorical boosting classifier (CatBoost) model exhibited the strongest performance (AUC = 0.80, 95% confidence interval [CI] = 0.76-0.83; ACC: 0.78, 95% CI = 0.72-0.83) and was selected for subsequent analysis. We reconstructed a compression model by extracting 20 key features ranked by the SHAP values, and the CatBoost model still showed the strongest performance (AUC = 0.79, ACC = 0.74). The CatBoost model, which was built using the intelligent analysis technology of ML, demonstrated the best predictive performance. Therefore, our developed prediction model has potential value in patient screening before PD and hierarchical management after PD.