1. Using Machine Learning Algorithms to Develop a Clinical Decision-Making Tool for COVID-19 Inpatients
- Author
-
Prithwiraj Chakrabarti, Alireza Daneshkhah, Diana Dharmaraj, Kambiz Rakhshan, Nader Salari, Abhinav Vepa, Poonam Kapila, Shamarina Shohaimi, Shital Parekh, Amer Saleem, Omid Chatrabgoun, Amr S Omar, Mohammed Raza, Tabassom Sedighi, Junaid Sami, and Mohamed Izham Mohamed Ibrahim
- Subjects
Adult ,medicine.medical_specialty ,Health, Toxicology and Mutagenesis ,Clinical Decision-Making ,risk stratification ,Article ,Machine Learning ,synthetic minority oversampling technique (SMOTE) ,03 medical and health sciences ,Bayes' theorem ,0302 clinical medicine ,medicine ,Humans ,030212 general & internal medicine ,Intensive care medicine ,Retrospective Studies ,030304 developmental biology ,Inpatients ,0303 health sciences ,SARS-CoV-2 ,business.industry ,Multivariable calculus ,Public Health, Environmental and Occupational Health ,Probabilistic logic ,Bayesian network ,COVID-19 ,Bayes Theorem ,Retrospective cohort study ,Outcome (probability) ,Random forest ,Feature (computer vision) ,SARS CoV ,Medicine ,business ,Algorithms ,random forest - Abstract
Background: Within the UK, COVID-19 has contributed towards over 103,000 deaths. Although multiple risk factors for COVID-19 have been identified, using this data to improve clinical care has proven challenging. The main aim of this study is to develop a reliable, multivariable predictive model for COVID-19 in-patient outcomes, thus enabling risk-stratification and earlier clinical decision-making. Methods: Anonymised data consisting of 44 independent predictor variables from 355 adults diagnosed with COVID-19, at a UK hospital, was manually extracted from electronic patient records for retrospective, case–control analysis. Primary outcomes included inpatient mortality, required ventilatory support, and duration of inpatient treatment. Pulmonary embolism sequala was the only secondary outcome. After balancing data, key variables were feature selected for each outcome using random forests. Predictive models were then learned and constructed using Bayesian networks. Results: The proposed probabilistic models were able to predict, using feature selected risk factors, the probability of the mentioned outcomes. Overall, our findings demonstrate reliable, multivariable, quantitative predictive models for four outcomes, which utilise readily available clinical information for COVID-19 adult inpatients. Further research is required to externally validate our models and demonstrate their utility as risk stratification and clinical decision-making tools.
- Published
- 2021