[3H5-OS-10c] OS-10

[3H5-OS-10c-03] Exploring Predictive Indicators for Patients with Low Thrombotic Drug Concentrations Using Exhaustive Time-Series Feature Extraction

〇Yuto Shimazaki^1,2, Masako Yamazaki¹, Teruto Hashiguchi³, Osamu Kumano⁴, Masahiro Ieko⁵, Yuta Fujimori⁶, Masatoshi Wakui⁷, Tetsuo Ishikawa^1,2,7, Eiryo Kawakami^1,2 (1. Chiba University , 2. RIKEN, 3. Kagoshima University , 4. National Institute of Advanced Industrial Science and Technology, 5. Sapporo University of Health Sciences, 6. Keio University Hospital, 7. Keio University)

Keywords:Machine Learning, Clinical Medicine, Time-Series Data, Explainability, Social Implementation

The use of direct oral anticoagulants (DOACs) in thrombosis treatment involves risks of recurrence when efficacy is insufficient and bleeding when excessive. An optimal index for treatment modulation remains undefined. This study aims to explore predictive indicators for identifying patients with low DOACs plasma levels (<50 ng/mL) using time-series changes in blood light transmission. A prediction model is constructed using exhaustive features extracted from time-series changes in transmitted light using a method developed based on tsfresh. Results are compared with those using conventional indicators from the perspective of eXplainable Artificial Intlligence. The tsfresh-based model outperforms conventional models, demonstrating higher AUCs for both ROC and PR curves. Notably, some highly predictive features exhibited low correlations with traditional indicators, suggesting that this approach introduces a novel evaluation perspective distinct from existing methods. The finding has the potential to develop new clinical indicators for accurately estimating low DOACs levels.