Symptom Prediction and Mortality Risk Calculation for COVID-19 Using Machine Learning.

Autor:	Jamshidi E; Functional Neurosurgery Research Center, Shohada Tajrish Comprehensive Neurosurgical Center of Excellence, Shahid Beheshti University of Medical Sciences, Tehran, Iran., Asgary A; Department of Biotechnology, College of Sciences, University of Tehran, Tehran, Iran., Tavakoli N; Trauma and Injury Research Center, Iran University of Medical Sciences, Tehran, Iran., Zali A; Functional Neurosurgery Research Center, Shohada Tajrish Comprehensive Neurosurgical Center of Excellence, Shahid Beheshti University of Medical Sciences, Tehran, Iran., Dastan F; Department of Clinical Pharmacy, School of Pharmacy, Shahid Beheshti University of Medical Sciences, Tehran, Iran., Daaee A; School of Mechanical Engineering, Sharif University of Technology, Tehran, Iran., Badakhshan M; School of Electrical and Computer Engineering, Engineering Faculty, University of Tehran, Tehran, Iran., Esmaily H; Department of Clinical Pharmacy, School of Pharmacy, Shahid Beheshti University of Medical Sciences, Tehran, Iran., Jamaldini SH; Department of Genetic, Faculty of Advanced Science and Technology, Tehran Medical Sciences, Islamic Azad University, Tehran, Iran., Safari S; Functional Neurosurgery Research Center, Shohada Tajrish Comprehensive Neurosurgical Center of Excellence, Shahid Beheshti University of Medical Sciences, Tehran, Iran., Bastanhagh E; Department of Anesthesiology, Tehran University of Medical Sciences, Tehran, Iran., Maher A; School of Management and Medical Education, Shahid Beheshti University of Medical Sciences, Tehran, Iran., Babajani A; Department of Pharmacology, School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran., Mehrazi M; Trauma and Injury Research Center, Iran University of Medical Sciences, Tehran, Iran., Sendani Kashi MA; Department of Business Management, Faculty of Management, University of Tehran, Tehran, Iran., Jamshidi M; Department of Exercise Physiology, Tehran University, Tehran, Iran., Sendani MH; Department of Computer Engineering, Sharif University of Technology, Tehran, Iran., Rahi SJ; Laboratory of the Physics of Biological Systems, Institute of Physics, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland., Mansouri N; Division of Pulmonary Medicine, Department of Medicine, Lausanne University Hospital (CHUV), University of Lausanne (UNIL), Lausanne, Switzerland.; Swiss Institute for Experimental Cancer Research (ISREC), School of Life Sciences, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland.; Research Group on Artificial Intelligence in Pulmonary Medicine, Division of Pulmonary Medicine, Lausanne University Hospital (CHUV), Lausanne, Switzerland.
Jazyk:	angličtina
Zdroj:	Frontiers in artificial intelligence [Front Artif Intell] 2021 Jun 22; Vol. 4, pp. 673527. Date of Electronic Publication: 2021 Jun 22 (Print Publication: 2021).
DOI:	10.3389/frai.2021.673527
Abstrakt:	Background: Early prediction of symptoms and mortality risks for COVID-19 patients would improve healthcare outcomes, allow for the appropriate distribution of healthcare resources, reduce healthcare costs, aid in vaccine prioritization and self-isolation strategies, and thus reduce the prevalence of the disease. Such publicly accessible prediction models are lacking, however. Methods: Based on a comprehensive evaluation of existing machine learning (ML) methods, we created two models based solely on the age, gender, and medical histories of 23,749 hospital-confirmed COVID-19 patients from February to September 2020: a symptom prediction model (SPM) and a mortality prediction model (MPM). The SPM predicts 12 symptom groups for each patient: respiratory distress, consciousness disorders, chest pain, paresis or paralysis, cough, fever or chill, gastrointestinal symptoms, sore throat, headache, vertigo, loss of smell or taste, and muscular pain or fatigue. The MPM predicts the death of COVID-19-positive individuals. Results: The SPM yielded ROC-AUCs of 0.53-0.78 for symptoms. The most accurate prediction was for consciousness disorders at a sensitivity of 74% and a specificity of 70%. 2,440 deaths were observed in the study population. MPM had a ROC-AUC of 0.79 and could predict mortality with a sensitivity of 75% and a specificity of 70%. About 90% of deaths occurred in the top 21 percentile of risk groups. To allow patients and clinicians to use these models easily, we created a freely accessible online interface at www.aicovid.net. Conclusion: The ML models predict COVID-19-related symptoms and mortality using information that is readily available to patients as well as clinicians. Thus, both can rapidly estimate the severity of the disease, allowing shared and better healthcare decisions with regard to hospitalization, self-isolation strategy, and COVID-19 vaccine prioritization in the coming months. Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. (Copyright © 2021 Jamshidi, Asgary, Tavakoli, Zali, Dastan, Daaee, Badakhshan, Esmaily, Jamaldini, Safari, Bastanhagh, Maher, Babajani, Mehrazi, Sendani Kashi, Jamshidi, Sendani, Rahi and Mansouri.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu