Detecting cardiovascular diseases using unsupervised machine learning clustering based on electronic medical records

• Published in: BMC medical research methodology 2024-12, Vol.24 (1), p.309-11, Article 309
• Main Authors: Hu, Ying, Yan, Hai, Liu, Ming, Gao, Jing, Xie, Lianhong, Zhang, Chunyu, Wei, Lili, Ding, Yinging, Jiang, Hong
• Format: Article
• Language: English
• Subjects: Adult; Aged; Bayes Theorem; Bayesian theorem; Cardiovascular diseases; Cardiovascular Diseases - diagnosis; China - epidemiology; Cluster Analysis; Data mining; Diagnosis; Electronic Health Records - statistics & numerical data; Electronic records; EMR; Female; Humans; K-means clustering; Machine Learning; Male; Medical records; Methods; Middle Aged; Risk factors; Unsupervised Machine Learning
• ISSN: 1471-2288; 1471-2288
• DOI: 10.1186/s12874-024-02422-z

Electronic medical records (EMR)-trained machine learning models have the potential in CVD risk prediction by integrating a range of medical data from patients, facilitate timely diagnosis and classification of CVDs. We tested the hypothesis that unsupervised ML approach utilizing EMR could be used to develop a new model for detecting prevalent CVD in clinical settings. We included 155,894 patients (aged ≥ 18 years) discharged between January 2014 and July 2022, from Xuhui Hospital, Shanghai, China, including 64,916 CVD cases and 90,979 non-CVD cases. K-means clustering was used to generate the clustering models with k = 2, 4, and 8 as predetermined number of clusters k = 2, 4, and 8. Bayesian theorem was used to estimate the models' predictive accuracy. The overall predictive accuracy of the 2-, 4-, and 8-classification clustering models in the training set was 0.856, 0.8634, and 0.8506, respectively. Similarly, the predictive accuracy of the 2-, 4-, and 8-classification clustering models in the testing set was 0.8598, 0.8659, and 0.8525, respectively. After reducing from 19 dimensions to 2 dimensions by principal component analysis, significant separation was observed for CVD cases and non-CVD cases in both training and testing sets. Our findings indicate that the utilization of EMR data can support the development of a robust model for CVD detection through an unsupervised ML approach. Further investigation using longitudinal design is needed to refine the model for its applications in clinical settings.