Machine learning could help clinicians better predict patients' emergency hospitalization risk, according to a study published in PLOS Medicine.
For the study, researchers created a machine learning model to analyze EHR records for 4.6 million adult patients across 389 practices in England between 1985 and 2015. The model also considered factors such as a patient's socioeconomic factors, comorbidities and time since first diagnosis.
Researchers used 80 percent of the data to train the machine learning model and saved the remaining 20 percent to test the system. They found the machine learning model offered more robust predictions for emergency hospital admissions than other prediction models.
"We wanted to provide a tool that would enable healthcare workers to accurately monitor the risks faced by their patients, and as a result make better decisions around patient screening and proactive care that could help reduce the burden of emergency admissions," study author Fatemeh Rahimian, PhD, a former data scientist at The George Institute U.K., said in a press release. "Our findings show that with large datasets, which contain rich information about individuals, machine learning models outperform one of the best conventional statistical models."