Tehran University of Medical Sciences

Science Communicator Platform

Stay connected! Follow us on X network (Twitter):
Share this content! On (X network) By
Symptom Prediction and Mortality Risk Calculation for Covid-19 Using Machine Learning Publisher



Jamshidi E1 ; Asgary A2 ; Tavakoli N3 ; Zali A1 ; Dastan F4 ; Daaee A5 ; Badakhshan M6 ; Esmaily H4 ; Jamaldini SH7 ; Safari S1 ; Bastanhagh E8 ; Maher A9 ; Babajani A10 ; Mehrazi M3 Show All Authors
Authors
  1. Jamshidi E1
  2. Asgary A2
  3. Tavakoli N3
  4. Zali A1
  5. Dastan F4
  6. Daaee A5
  7. Badakhshan M6
  8. Esmaily H4
  9. Jamaldini SH7
  10. Safari S1
  11. Bastanhagh E8
  12. Maher A9
  13. Babajani A10
  14. Mehrazi M3
  15. Sendani Kashi MA11
  16. Jamshidi M12
  17. Sendani MH13
  18. Rahi SJ14
  19. Mansouri N15, 16, 17
Show Affiliations
Authors Affiliations
  1. 1. Functional Neurosurgery Research Center, Shohada Tajrish Comprehensive Neurosurgical Center of Excellence, Shahid Beheshti University of Medical Sciences, Tehran, Iran
  2. 2. Department of Biotechnology, College of Sciences, University of Tehran, Tehran, Iran
  3. 3. Trauma and Injury Research Center, Iran University of Medical Sciences, Tehran, Iran
  4. 4. Department of Clinical Pharmacy, School of Pharmacy, Shahid Beheshti University of Medical Sciences, Tehran, Iran
  5. 5. School of Mechanical Engineering, Sharif University of Technology, Tehran, Iran
  6. 6. School of Electrical and Computer Engineering, Engineering Faculty, University of Tehran, Tehran, Iran
  7. 7. Department of Genetic, Faculty of Advanced Science and Technology, Tehran Medical Sciences, Islamic Azad University, Tehran, Iran
  8. 8. Department of Anesthesiology, Tehran University of Medical Sciences, Tehran, Iran
  9. 9. School of Management and Medical Education, Shahid Beheshti University of Medical Sciences, Tehran, Iran
  10. 10. Department of Pharmacology, School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran
  11. 11. Department of Business Management, Faculty of Management, University of Tehran, Tehran, Iran
  12. 12. Department of Exercise Physiology, Tehran University, Tehran, Iran
  13. 13. Department of Computer Engineering, Sharif University of Technology, Tehran, Iran
  14. 14. Laboratory of the Physics of Biological Systems, Institute of Physics, Ecole Polytechnique Federale de Lausanne (EPFL), Lausanne, Switzerland
  15. 15. Division of Pulmonary Medicine, Department of Medicine, Lausanne University Hospital (CHUV), University of Lausanne (UNIL), Lausanne, Switzerland
  16. 16. Swiss Institute for Experimental Cancer Research (ISREC), School of Life Sciences, Ecole Polytechnique Federale de Lausanne (EPFL), Lausanne, Switzerland
  17. 17. Research Group on Artificial Intelligence in Pulmonary Medicine, Division of Pulmonary Medicine, Lausanne University Hospital (CHUV), Lausanne, Switzerland

Source: Frontiers in Artificial Intelligence Published:2021


Abstract

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. © Copyright © 2021 Jamshidi, Asgary, Tavakoli, Zali, Dastan, Daaee, Badakhshan, Esmaily, Jamaldini, Safari, Bastanhagh, Maher, Babajani, Mehrazi, Sendani Kashi, Jamshidi, Sendani, Rahi and Mansouri.
Other Related Docs
12. Identifying Techniques and Models for Covid-19 Prediction, Journal of Iranian Medical Council (2023)
18. Therapeutic Strategies for Covid-19 Patients: An Update, Infectious Disorders - Drug Targets (2022)
22. Antiviral Optical Techniques As a Possible Novel Approach to Covid-19 Treatment, Journal of Innovative Optical Health Sciences (2021)