http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Machine Learning for Benchmarking Critical Care Outcomes
Louis Atallah,Mohsen Nabian,Ludmila Brochini,Pamela J. Amelung 대한의료정보학회 2023 Healthcare Informatics Research Vol.29 No.4
Objectives: Enhancing critical care efficacy involves evaluating and improving system functioning. Benchmarking, a retrospectivecomparison of results against standards, aids risk-adjusted assessment and helps healthcare providers identify areasfor improvement based on observed and predicted outcomes. The last two decades have seen the development of severalmodels using machine learning (ML) for clinical outcome prediction. ML is a field of artificial intelligence focused on creatingalgorithms that enable computers to learn from and make predictions or decisions based on data. This narrative reviewcenters on key discoveries and outcomes to aid clinicians and researchers in selecting the optimal methodology for criticalcare benchmarking using ML. Methods: We used PubMed to search the literature from 2003 to 2023 regarding predictivemodels utilizing ML for mortality (592 articles), length of stay (143 articles), or mechanical ventilation (195 articles). Wesupplemented the PubMed search with Google Scholar, making sure relevant articles were included. Given the narrative style,papers in the cohort were manually curated for a comprehensive reader perspective. Results: Our report presents comparativeresults for benchmarked outcomes and emphasizes advancements in feature types, preprocessing, model selection, andvalidation. It showcases instances where ML effectively tackled critical care outcome-prediction challenges, including nonlinearrelationships, class imbalances, missing data, and documentation variability, leading to enhanced results. Conclusions:Although ML has provided novel tools to improve the benchmarking of critical care outcomes, areas that require further researchinclude class imbalance, fairness, improved calibration, generalizability, and long-term validation of published models.