Symptom Prediction and Mortality Risk Calculation for COVID-19 Using Machine Learning
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 o...
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-06-01
|
| Series: | Frontiers in Artificial Intelligence |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frai.2021.673527/full |
| _version_ | 1819102693331828736 |
|---|---|
| author | Elham Jamshidi Amirhossein Asgary Nader Tavakoli Alireza Zali Farzaneh Dastan Amir Daaee Mohammadtaghi Badakhshan Hadi Esmaily Seyed Hamid Jamaldini Saeid Safari Ehsan Bastanhagh Ali Maher Amirhesam Babajani Maryam Mehrazi Mohammad Ali Sendani Kashi Masoud Jamshidi Mohammad Hassan Sendani Sahand Jamal Rahi Nahal Mansouri Nahal Mansouri Nahal Mansouri |
| author_facet | Elham Jamshidi Amirhossein Asgary Nader Tavakoli Alireza Zali Farzaneh Dastan Amir Daaee Mohammadtaghi Badakhshan Hadi Esmaily Seyed Hamid Jamaldini Saeid Safari Ehsan Bastanhagh Ali Maher Amirhesam Babajani Maryam Mehrazi Mohammad Ali Sendani Kashi Masoud Jamshidi Mohammad Hassan Sendani Sahand Jamal Rahi Nahal Mansouri Nahal Mansouri Nahal Mansouri |
| author_sort | Elham Jamshidi |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-22T01:38:37Z |
| format | Article |
| id | doaj.art-cfa95a5a6ccb4af69e7e907dda4816ef |
| institution | Directory Open Access Journal |
| issn | 2624-8212 |
| language | English |
| last_indexed | 2024-12-22T01:38:37Z |
| publishDate | 2021-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Artificial Intelligence |
| spelling | doaj.art-cfa95a5a6ccb4af69e7e907dda4816ef2022-12-21T18:43:19ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122021-06-01410.3389/frai.2021.673527673527Symptom Prediction and Mortality Risk Calculation for COVID-19 Using Machine LearningElham Jamshidi0Amirhossein Asgary1Nader Tavakoli2Alireza Zali3Farzaneh Dastan4Amir Daaee5Mohammadtaghi Badakhshan6Hadi Esmaily7Seyed Hamid Jamaldini8Saeid Safari9Ehsan Bastanhagh10Ali Maher11Amirhesam Babajani12Maryam Mehrazi13Mohammad Ali Sendani Kashi14Masoud Jamshidi15Mohammad Hassan Sendani16Sahand Jamal Rahi17Nahal Mansouri18Nahal Mansouri19Nahal Mansouri20Functional Neurosurgery Research Center, Shohada Tajrish Comprehensive Neurosurgical Center of Excellence, Shahid Beheshti University of Medical Sciences, Tehran, IranDepartment of Biotechnology, College of Sciences, University of Tehran, Tehran, IranTrauma and Injury Research Center, Iran University of Medical Sciences, Tehran, IranFunctional Neurosurgery Research Center, Shohada Tajrish Comprehensive Neurosurgical Center of Excellence, Shahid Beheshti University of Medical Sciences, Tehran, IranDepartment of Clinical Pharmacy, School of Pharmacy, Shahid Beheshti University of Medical Sciences, Tehran, IranSchool of Mechanical Engineering, Sharif University of Technology, Tehran, IranSchool of Electrical and Computer Engineering, Engineering Faculty, University of Tehran, Tehran, IranDepartment of Clinical Pharmacy, School of Pharmacy, Shahid Beheshti University of Medical Sciences, Tehran, IranDepartment of Genetic, Faculty of Advanced Science and Technology, Tehran Medical Sciences, Islamic Azad University, Tehran, IranFunctional Neurosurgery Research Center, Shohada Tajrish Comprehensive Neurosurgical Center of Excellence, Shahid Beheshti University of Medical Sciences, Tehran, IranDepartment of Anesthesiology, Tehran University of Medical Sciences, Tehran, IranSchool of Management and Medical Education, Shahid Beheshti University of Medical Sciences, Tehran, Iran0Department of Pharmacology, School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, IranTrauma and Injury Research Center, Iran University of Medical Sciences, Tehran, Iran1Department of Business Management, Faculty of Management, University of Tehran, Tehran, Iran2Department of Exercise Physiology, Tehran University, Tehran, Iran3Department of Computer Engineering, Sharif University of Technology, Tehran, Iran4Laboratory of the Physics of Biological Systems, Institute of Physics, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland5Division of Pulmonary Medicine, Department of Medicine, Lausanne University Hospital (CHUV), University of Lausanne (UNIL), Lausanne, Switzerland6Swiss Institute for Experimental Cancer Research (ISREC), School of Life Sciences, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland7Research Group on Artificial Intelligence in Pulmonary Medicine, Division of Pulmonary Medicine, Lausanne University Hospital (CHUV), Lausanne, SwitzerlandBackground: 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.https://www.frontiersin.org/articles/10.3389/frai.2021.673527/fullCOVID-19artificial intelligencemachine learningsymptommortality |
| spellingShingle | Elham Jamshidi Amirhossein Asgary Nader Tavakoli Alireza Zali Farzaneh Dastan Amir Daaee Mohammadtaghi Badakhshan Hadi Esmaily Seyed Hamid Jamaldini Saeid Safari Ehsan Bastanhagh Ali Maher Amirhesam Babajani Maryam Mehrazi Mohammad Ali Sendani Kashi Masoud Jamshidi Mohammad Hassan Sendani Sahand Jamal Rahi Nahal Mansouri Nahal Mansouri Nahal Mansouri Symptom Prediction and Mortality Risk Calculation for COVID-19 Using Machine Learning Frontiers in Artificial Intelligence COVID-19 artificial intelligence machine learning symptom mortality |
| title | Symptom Prediction and Mortality Risk Calculation for COVID-19 Using Machine Learning |
| title_full | Symptom Prediction and Mortality Risk Calculation for COVID-19 Using Machine Learning |
| title_fullStr | Symptom Prediction and Mortality Risk Calculation for COVID-19 Using Machine Learning |
| title_full_unstemmed | Symptom Prediction and Mortality Risk Calculation for COVID-19 Using Machine Learning |
| title_short | Symptom Prediction and Mortality Risk Calculation for COVID-19 Using Machine Learning |
| title_sort | symptom prediction and mortality risk calculation for covid 19 using machine learning |
| topic | COVID-19 artificial intelligence machine learning symptom mortality |
| url | https://www.frontiersin.org/articles/10.3389/frai.2021.673527/full |
| work_keys_str_mv | AT elhamjamshidi symptompredictionandmortalityriskcalculationforcovid19usingmachinelearning AT amirhosseinasgary symptompredictionandmortalityriskcalculationforcovid19usingmachinelearning AT nadertavakoli symptompredictionandmortalityriskcalculationforcovid19usingmachinelearning AT alirezazali symptompredictionandmortalityriskcalculationforcovid19usingmachinelearning AT farzanehdastan symptompredictionandmortalityriskcalculationforcovid19usingmachinelearning AT amirdaaee symptompredictionandmortalityriskcalculationforcovid19usingmachinelearning AT mohammadtaghibadakhshan symptompredictionandmortalityriskcalculationforcovid19usingmachinelearning AT hadiesmaily symptompredictionandmortalityriskcalculationforcovid19usingmachinelearning AT seyedhamidjamaldini symptompredictionandmortalityriskcalculationforcovid19usingmachinelearning AT saeidsafari symptompredictionandmortalityriskcalculationforcovid19usingmachinelearning AT ehsanbastanhagh symptompredictionandmortalityriskcalculationforcovid19usingmachinelearning AT alimaher symptompredictionandmortalityriskcalculationforcovid19usingmachinelearning AT amirhesambabajani symptompredictionandmortalityriskcalculationforcovid19usingmachinelearning AT maryammehrazi symptompredictionandmortalityriskcalculationforcovid19usingmachinelearning AT mohammadalisendanikashi symptompredictionandmortalityriskcalculationforcovid19usingmachinelearning AT masoudjamshidi symptompredictionandmortalityriskcalculationforcovid19usingmachinelearning AT mohammadhassansendani symptompredictionandmortalityriskcalculationforcovid19usingmachinelearning AT sahandjamalrahi symptompredictionandmortalityriskcalculationforcovid19usingmachinelearning AT nahalmansouri symptompredictionandmortalityriskcalculationforcovid19usingmachinelearning AT nahalmansouri symptompredictionandmortalityriskcalculationforcovid19usingmachinelearning AT nahalmansouri symptompredictionandmortalityriskcalculationforcovid19usingmachinelearning |