A machine learning algorithm to increase COVID-19 inpatient diagnostic capacity

• DOI: 10.1371/journal.pone.0239474
• Publication Date: 2020-09-22T22:46:52Z
• Authors: David Goodman-Meza; Akos Rudas; Jeffrey N. Chiang; Paul C. Adamson; Joseph Ebinger; Nancy Sun; Patrick Botting; Jennifer A. Fulcher; Faysal G. Saab; Rachel Brook; Eleazar Eskin; Ulzee An; Misagh Kordi; Brandon Jew; Brunilda Balliu; Zeyuan Chen; Brian L. Hill; Elior Rahmani; Eran Halperin; Vladimir Manuel
• Keywords: Ensemble Learning

Worldwide, testing capacity for SARS-CoV-2 is limited and bottlenecks in the scale up of polymerase chain reaction (PCR-based exist. Our aim was to develop evaluate a machine learning algorithm diagnose COVID-19 inpatient setting. The based on basic demographic laboratory features serve as screening tool at hospitals where scarce or unavailable. We used retrospectively collected data from UCLA Health System Los Angeles, California. included all emergency room cases receiving PCR who also had set ancillary (n = 1,455) between 1 March 2020 24 May 2020. tested seven models combination those final diagnostic classification. In test 392), our combined model an area under receiver operator curve 0.91 (95% confidence interval 0.87–0.96). achieved sensitivity 0.93 CI 0.85–0.98), specificity 0.64 0.58–0.69). found that excellent metrics compared PCR. This ensemble has potential be hospital settings