Medical Journal of the Islamic Republic Of Iran

en Prediction of COVID-19 Patients’ Survival by Deep Learning Approaches COVID 19 Original Research Original Research Background: Despite many studies done to predict severe coronavirus 2019 (COVID-19) patients, there is no applicable clinical prediction model to predict and distinguish severe patients early. Based on laboratory and demographic data, we have developed and validated a deep learning model to predict survival and assist in the triage of COVID-19 patients in the early stages.    Methods: This retrospective study developed a survival prediction model based on the deep learning method using demographic and laboratory data. The database consisted of data from 487 patients with COVID-19 diagnosed by the reverse transcription-polymerase chain reaction test and admitted to Imam Khomeini hospital affiliated to Tehran University of Medical Sciences from February 21, 2020, to June 24, 2020.    Results: The developed model achieved an area under the curve (AUC) of 0.96 for survival prediction. The results demonstrated the developed model provided high precision (0.95, 0.93), recall (0.90,0.97), and F1-score (0.93,0.95) for low- and high-risk groups.    Conclusion: The developed model is a deep learning-based, data-driven prediction tool that can predict the survival of COVID-19 patients with an AUC of 0.96. This model helps classify admitted patients into low-risk and high-risk groups and helps triage patients in the early stages.     COVID-19, Prediction, Survival Analysis, Triage, Deep Learning 1099 1106 http://mjiri.iums.ac.ir/browse.php?a_code=A-10-6223-2&slc_lang=en&sid=1 Moloud Taheriyan moloud.taheriyan@gmail.com 200319475328460074657 200319475328460074657 No Department of Health Information Management, School of Allied Medical Sciences, Tehran University of Medical Sciences, Tehran, Iran Seyed Mehdi Ayyoubzadeh ayyoubzs@mcmaster.ca 200319475328460074658 200319475328460074658 No Department of Electrical and Computer Engineering, McMaster University, Hamilton, Canada Mehdi Ebrahimi m_ebrahimi49@yahoo.com 200319475328460074659 200319475328460074659 No Department of Internal Medicine, School of Medicine, Tehran University of Medical Sciences, Tehran, Iran Sharareh Rostam Niakan Kalhor Niakan2@gmail.com 200319475328460074660 200319475328460074660 No Department of Health Information Management, School of Allied Medical Sciences, Tehran University of Medical Sciences, Tehran, Iran & Peter L. Reichertz Institute for Medical Informatics (PLRI) of Technical University of Braunschweig and Hannover Medical School, Braunschweig, Germany Amir Hossien Abooei abooeiamirhosein@yahoo.com 200319475328460074661 200319475328460074661 No Department of Laboratory Sciences, School of Allied Medical Sciences, Tehran University of Medical Sciences, Tehran, Iran Marsa Gholamzadeh marsa.gholamzadeh@yahoo.com 200319475328460074662 200319475328460074662 No Department of Health Information Management, School of Allied Medical Sciences, & Thoracic Research Center, Imam Khomeini Hospital, Tehran University of Medical Sciences, Tehran, Iran Seyed Mohammad Ayyoubzadeh smayyoubzadeh@sina.tums.ac.ir 200319475328460074663 200319475328460074663 Yes Department of Health Information Management, School of Allied Medical Sciences, Tehran University of Medical Sciences, Tehran, Iran