Two teams of researchers have published their research papers on applying Machine Learning to improve healthcare
Machine Learning (ML)and Artificial Intelligence (AI) are being employed in all facets of our lives. MIT’s Computer Science and AI Labs (CASIL) have come up with two ways to help doctors make better decisions. Two teams of MIT researchers have described their latest techniques employing ML in healthcare in two disparate research papers.
In the current scenario, doctors need to manage many different forms of information such as test results, charts and much more. Doctors make inferences based on this information and it can be difficult as there is a colossal amount of data to be analyzed coming from a number of patients. All this along with inconsistent documentations makes it harder for doctors to make sound decision under real-time treatment situations.
The new CASIL research utilised many different types of medical data, including electronic health records to predict outcomes in hospitals. One team used a Machine Learning approach called “ICU intervene”. According to the research, this method makes use of a large amount of ICU data, ranging from vitals and lab notes to demographics and determines what kind of treatment is required for different symptoms. Lead author on the paper about ICU Intervene, Ph.D. student Harini Suresh said, “The system could potentially be an aid for doctors in the ICU, which is a high-stress, high-demand environment,”. She further added, “The goal is to leverage data from medical records to improve health care and predict actionable interventions.”
Another team developed an approach called “EHR Model Transfer”. This method can enable and help in the application of predictive models on an electronic health record (EHR) system, despite being trained on data from a different EHR system. The team specifically showed that using this approach, predictive models for mortality and prolonged length of stay can be trained on one EHR system and used to make predictions in another.
The research claims that both the models were trained using data from the critical care database MIMIC, which includes de-identified data from roughly 40,000 critical care patients and was developed by the MIT Lab for Computational Physiology.
Follow Us
Shubham Sharma
Interested in tech, gaming, cyber-security, anime, and more View Full Profile
