Improving quality through AI: Applying machine learning to predict unplanned hospitalizations after radiation

At the 2019 American Society of Clinical Oncology (ASCO) Quality Care Symposium in San Diego, CA - Dr. Kaitlin Christopherson, MD, from MD Anderson Cancer Center presented our co-authored abstract titled, "Improving quality through AI: Applying machine learning to predict unplanned hospitalizations after radiation."

Each year only about 12 abstracts are selected as oral presentations at the ASCO Quality Care Symposium, validating our research efforts with MD Anderson Cancer Center. In addition to being one of the twelve oral presentations, this research also received a Merit Award from Conquer Cancer ASCO Foundation. Read more about the Merit Award here!

The abstract focused on gastrointestinal (GI) cancers patients who underwent RT, specifically abdominal and pelvic courses of radiotherapy treated at MD Anderson from 2016 through 2019. After analyzing more 700 clinical variables, the machine learning model successfully identified GI cancer patients undergoing radiotherapy who are at low vs high risk of 30-day unplanned hospitalization.

A success of Oncora and MD Anderson, showing we can use a machine learning approach to help improve quality and value of care. Helping reduce toxicity and health care spending. Future research should aim to understand whether determining high-risk patients upfront leads to clinical interventions that help minimize risk of unplanned hospitalization.

showing we can use a big data AI approach to predict unplanned hospitalization in patients undergoing rt for gi malignancies. This can help us reduce toxicity and save health care $

ASCO2019.jpg

Dr. Kaitlin Christopherson presenting during ASCO Quality Symposium 2019

Resources in this post:

Artificial Intelligence Helps MD Anderson Predict Unplanned Hospitalizations After Radiation Therapy

ASCO Quality Symposium Meeting Program