Machine learning (ML) is currently being widely studied and applied in data analysis and prediction in various fields, including laboratory medicine. To comprehensively evaluate the application of ML in laboratory medicine, we reviewed the literature on ML applications in laboratory medicine published between February 2014 and March 2024. A PubMed search using a search string yielded 779 articles on the topic, among which 144 articles were selected for this review. These articles were analyzed to extract and categorize related fields within laboratory medicine, research objectives, specimen types, data types, ML models, evaluation metrics, and sample sizes. Sankey diagrams and pie charts were used to illustrate the relationships between categories and the proportions within each category. We found that most studies involving the application of ML in laboratory medicine were designed to improve efficiency through automation or expand the roles of clinical laboratories. The most common ML models used are convolutional neural networks, multilayer perceptrons, and tree-based models, which are primarily selected based on the type of input data. Our findings suggest that, as the technology evolves, ML will rise in prominence in laboratory medicine as a tool for expanding research activities. Nonetheless, expertise in ML applications should be improved to effectively utilize this technology.

Although complex fractionated electrogram (CFE) is known to be a target for catheter ablation of fibrillation, its physiological meaning in fibrillation wave-dynamics remains to be clarified. We evaluated the spatiotemporal relationships among the parameters of fibrillation wave-dynamics by simulation modeling. We generated maps of CFE-cycle length (CFE-CL), local dominant frequency (LDF), wave break (WB), and phase singularity (PS) of fibrillation in 2-dimensional homogeneous bidomain cardiac modeling (1,000 x 1,000 cells ten Tusscher model). We compared spatiotemporal correlations by dichotomizing each maps into 10 x 10 lattice zones. In spatial distribution, WB and PS showed excellent correlation (R = 0.963, P < 0.001). CFE-CL had weak correlations with WB (R = 0.288, P < 0.001), PS (R = 0.313, P < 0.001), and LDF (R = -0.411, P < 0.001). However, LDF did not show correlation with PS or WB. PSs were mostly distributed at the periphery of low CFE-CL area. Virtual ablation (5% of critical mass) of CFE-CL < 100 ms terminated fibrillation at 14.3 sec, and high LDF ablation (5% of critical mass) changed fibrillation to organized tachycardia, respectively. In homogeneous 2D fibrillation modeling, CFE-CL was weakly correlated with WB, PS, and LDF, spatiotemporally. PSs are mostly positioned at the periphery of low CFE-CL areas, and virtual ablation targeting low CFE-CL regions terminated fibrillation successfully.
Algorithms ; Atrial Fibrillation/*physiopathology ; Body Surface Potential Mapping ; Catheter Ablation ; *Electrocardiography ; Electrodes ; Heart Atria/physiopathology ; Humans ; *Models, Biological