Effectiveness of Machine Learning for COVID-19 Patient Mortality Prediction Using WEKA
Timely detection of patients with a high mortality risk in coronavirus disease 2019 (COVID-19) can substantially improve triage, bed allocation, time reduction, and potential outcomes. A potential solution is using machine learning (ML) algorithms to predict mortality in COVID-19 hospitalized patien...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitas Islam Bandung
2023-12-01
|
| Series: | Global Medical & Health Communication |
| Subjects: | |
| Online Access: | https://ejournal.unisba.ac.id/index.php/gmhc/article/view/12119 |
| _version_ | 1827379440442671104 |
|---|---|
| author | Husnul Khuluq Prasandhya Astagiri Yusuf Dyah Aryani Perwitasari |
| author_facet | Husnul Khuluq Prasandhya Astagiri Yusuf Dyah Aryani Perwitasari |
| author_sort | Husnul Khuluq |
| collection | DOAJ |
| description | Timely detection of patients with a high mortality risk in coronavirus disease 2019 (COVID-19) can substantially improve triage, bed allocation, time reduction, and potential outcomes. A potential solution is using machine learning (ML) algorithms to predict mortality in COVID-19 hospitalized patients. The study's objective was to create and verify individual risk assessments for mortality using anonymous demographic, clinical, and laboratory findings at admission, as well as to assess the possibility of death using machine learning. We used a standardized format and electronic medical records. Data from 2,313 patients were collected from two Muhammadiyah hospitals from January 2020 to July 2022. Utilizing each patient's clinical manifestation state at admission and laboratory parameters, 24 demographic, clinical, and laboratory results were studied. The algorithms analyzed were AdaBoost, logistic regression, random forest, support vector machine, naïve Bayes, and decision tree, which were applied through WEKA version 3.8.6. Random forest performed better than the other machine learning techniques, with precision, sensitivity, receiver operating characteristic (ROC), and accuracy of 78.6%, 78.7%, 85%, and 78.65%, respectively. The three top predictors were septic shock (OR=21.518, 95% CI=4.933–93.853), respiratory failure (OR=15.503, 95% CI=8.507–28.254), and D-dimer (OR=3.288, 95% CI=2.510–4.306). Machine learning–based predictive models, especially the random forest algorithm, may make it easier to identify patients at high risk of death and guide physicians' appropriate interventions. |
| first_indexed | 2024-03-08T13:16:39Z |
| format | Article |
| id | doaj.art-bb0187153e744f15b511ec767715a994 |
| institution | Directory Open Access Journal |
| issn | 2301-9123 2460-5441 |
| language | English |
| last_indexed | 2024-03-08T13:16:39Z |
| publishDate | 2023-12-01 |
| publisher | Universitas Islam Bandung |
| record_format | Article |
| series | Global Medical & Health Communication |
| spelling | doaj.art-bb0187153e744f15b511ec767715a9942024-01-18T06:47:38ZengUniversitas Islam BandungGlobal Medical & Health Communication2301-91232460-54412023-12-0111310.29313/gmhc.v11i3.121194958Effectiveness of Machine Learning for COVID-19 Patient Mortality Prediction Using WEKAHusnul Khuluq0Prasandhya Astagiri Yusuf1Dyah Aryani Perwitasari2Department of Pharmacy, Faculty of Health Sciences, Universitas Muhammadiyah Gombong, KebumenDepartment of Medical Physiology and Biophysics/Medical Technology Cluster IMERI, Faculty of Medicine, Universitas Indonesia, Central JakartaFaculty of Pharmacy, Universitas Ahmad Dahlan, YogyakartaTimely detection of patients with a high mortality risk in coronavirus disease 2019 (COVID-19) can substantially improve triage, bed allocation, time reduction, and potential outcomes. A potential solution is using machine learning (ML) algorithms to predict mortality in COVID-19 hospitalized patients. The study's objective was to create and verify individual risk assessments for mortality using anonymous demographic, clinical, and laboratory findings at admission, as well as to assess the possibility of death using machine learning. We used a standardized format and electronic medical records. Data from 2,313 patients were collected from two Muhammadiyah hospitals from January 2020 to July 2022. Utilizing each patient's clinical manifestation state at admission and laboratory parameters, 24 demographic, clinical, and laboratory results were studied. The algorithms analyzed were AdaBoost, logistic regression, random forest, support vector machine, naïve Bayes, and decision tree, which were applied through WEKA version 3.8.6. Random forest performed better than the other machine learning techniques, with precision, sensitivity, receiver operating characteristic (ROC), and accuracy of 78.6%, 78.7%, 85%, and 78.65%, respectively. The three top predictors were septic shock (OR=21.518, 95% CI=4.933–93.853), respiratory failure (OR=15.503, 95% CI=8.507–28.254), and D-dimer (OR=3.288, 95% CI=2.510–4.306). Machine learning–based predictive models, especially the random forest algorithm, may make it easier to identify patients at high risk of death and guide physicians' appropriate interventions.https://ejournal.unisba.ac.id/index.php/gmhc/article/view/12119data mininginpatient mortalitymachine learning algorithmprediction model |
| spellingShingle | Husnul Khuluq Prasandhya Astagiri Yusuf Dyah Aryani Perwitasari Effectiveness of Machine Learning for COVID-19 Patient Mortality Prediction Using WEKA Global Medical & Health Communication data mining inpatient mortality machine learning algorithm prediction model |
| title | Effectiveness of Machine Learning for COVID-19 Patient Mortality Prediction Using WEKA |
| title_full | Effectiveness of Machine Learning for COVID-19 Patient Mortality Prediction Using WEKA |
| title_fullStr | Effectiveness of Machine Learning for COVID-19 Patient Mortality Prediction Using WEKA |
| title_full_unstemmed | Effectiveness of Machine Learning for COVID-19 Patient Mortality Prediction Using WEKA |
| title_short | Effectiveness of Machine Learning for COVID-19 Patient Mortality Prediction Using WEKA |
| title_sort | effectiveness of machine learning for covid 19 patient mortality prediction using weka |
| topic | data mining inpatient mortality machine learning algorithm prediction model |
| url | https://ejournal.unisba.ac.id/index.php/gmhc/article/view/12119 |
| work_keys_str_mv | AT husnulkhuluq effectivenessofmachinelearningforcovid19patientmortalitypredictionusingweka AT prasandhyaastagiriyusuf effectivenessofmachinelearningforcovid19patientmortalitypredictionusingweka AT dyaharyaniperwitasari effectivenessofmachinelearningforcovid19patientmortalitypredictionusingweka |