How Machine Learning Could Be Used to Improve Patient Care

Back to QNT News


August 23, 2017

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 utilized many different types of medical data, including electronic health records to predict outcomes in hospitals. One team used an ML 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.

Copyright 2017 Nine Dot Nine Mediaworx Pvt. Ltd. All Rights Reserved.

Copyright © LexisNexis, a division of Reed Elsevier Inc. All rights reserved.  
Terms and Conditions    Privacy Policy

Quality News Today is an ASQ member benefit offering quality related news
from around the world every business day.

ASQ is a global community of people passionate about quality, who use the tools, their ideas and expertise to make our world work better. ASQ: The Global Voice of Quality.