Self-Supervised Learning-Based General Laboratory Progress Pretrained Model for Cardiovascular Event Detection

• Published in: IEEE journal of translational engineering in health and medicine Vol. 12; pp. 43 - 55
• Main Authors: Chen, Li-Chin, Hung, Kuo-Hsuan, Tseng, Yi-Ju, Wang, Hsin-Yao, Lu, Tse-Min, Huang, Wei-Chieh, Tsao, Yu
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Absenteeism; Availability; Benchmarking; cardiometabolic disease; Cardiovascular diseases; Cardiovascular Diseases - diagnosis; Constraints; Disease; Disease Progression; Electrocardiography; Glucose; Humans; Interpolation; Laboratories; laboratory examinations; Machine learning; Mathematical models; Parameters; pre-train model; Representation learning; Self-supervised learning; Supervised Machine Learning; Target detection; time-series data; Training; Transfer learning; laboratory examinations; transfer learning; time-series data; cardiometabolic disease; representation learning; self-supervised learning; disease progression; Cardiovascular diseases; pre-train model
• ISSN: 2168-2372; 2168-2372
• DOI: 10.1109/JTEHM.2023.3307794

Objective: Leveraging patient data through machine learning techniques in disease care offers a multitude of substantial benefits. Nonetheless, the inherent nature of patient data poses several challenges. Prevalent cases amass substantial longitudinal data owing to their patient volume and consistent follow-ups, however, longitudinal laboratory data are renowned for their irregularity, temporality, absenteeism, and sparsity; In contrast, recruitment for rare or specific cases is often constrained due to their limited patient size and episodic observations. This study employed self-supervised learning (SSL) to pretrain a generalized laboratory progress (GLP) model that captures the overall progression of six common laboratory markers in prevalent cardiovascular cases, with the intention of transferring this knowledge to aid in the detection of specific cardiovascular event. Methods and procedures: GLP implemented a two-stage training approach, leveraging the information embedded within interpolated data and amplify the performance of SSL. After GLP pretraining, it is transferred for target vessel revascularization (TVR) detection. Results: The proposed two-stage training improved the performance of pure SSL, and the transferability of GLP exhibited distinctiveness. After GLP processing, the classification exhibited a notable enhancement, with averaged accuracy rising from 0.63 to 0.90. All evaluated metrics demonstrated substantial superiority (<inline-formula> <tex-math notation="LaTeX">{p} < 0.01 </tex-math></inline-formula>) compared to prior GLP processing. Conclusion: Our study effectively engages in translational engineering by transferring patient progression of cardiovascular laboratory parameters from one patient group to another, transcending the limitations of data availability. The transferability of disease progression optimized the strategies of examinations and treatments, and improves patient prognosis while using commonly available laboratory parameters. The potential for expanding this approach to encompass other diseases holds great promise. Clinical impact: Our study effectively transposes patient progression from one cohort to another, surpassing the constraints of episodic observation. The transferability of disease progression contributed to cardiovascular event assessment.