Machine Learning Algorithm Predicts The Outcomes of COVID-19 Patients

Published on November 27, 2020
algorithm
Image Credit: [Unsplash/Irwan Iwe]

A study was done recently that used an ML (Machine Learning) tool to create an algorithm that has the ability to predict the outcome of patients diagnosed with COVID-19.

The algorithm will be helpful to physicians by enabling them to provide a more effective intervention plan that is built around a patient’s specific health history disease status.

The study was published in the journal, ‘Medical Image Analysis,’ and was carried out by a team of researchers at the Rensselaer Polytechnic Institute. The technique was developed by feeding chest CT (Computed Tomography) images from patients along with data including the patient’s vitals, blood test results, and demographics.

As a practitioner of AI, I do believe in its power. It really enables us to analyze a large quantity of data and also extract the features that may not be that obvious to the human eye. We know that a key factor in COVID mortality is whether a patient has underlying conditions and heart disease is a significant comorbidity. How much this contributes to their disease progress is, right now, fairly subjective. So, we have to have a quantification of their heart condition and then determine how we factor that into this prediction.

Pingkun Yan PhD

All-in-all, some 295 patients from three hospitals in Italy, the US, and Iran had their data collected. The researchers were then able to use the AI to predict the type of treatment that the patients would end up needing.

This critical work, led by Professor Yan, offers an actionable solution for clinicians who are in the middle of a worldwide pandemic. This project highlights the capabilities of Rensselaer expertise in bioimaging combined with important partnerships with medical institutions.

Deepak Vashishth – Director, CBIS (Certified Brain Injury Specialist)
Enjoyed this video?
"No Thanks. Please Close This Box!"