Toni Witt was on location last week at the HIMSS23 Global Health Conference and Exhibition in Chicago. In this special report, Toni relates how a researcher showed a model that aims to reduce asthma hospitalizations in children through artificial intelligence (AI) and machine learning (ML).
Highlights
00:43 — The researcher leading the session developed a model that aims to predict whether a pre-diagnosed patient with asthma would be hospitalized in the next 90 days based on a set of input factors. These factors include age, behaviors such as smoking, gender, ethnicity, and even the patient’s zip code — which are then ranked in terms of risk.
01:09 — Based on the model’s outputs, the researchers would reach out to the high-risk children to notify them and encourage preventative measures. They also work with relevant local health organizations to take “real-world actions.”
01:26 — In terms of “real-world ROI,” Toni explains that “the project resulted in an estimated 166 asthma-related hospitalizations per year” that were “prevented because those in high risk were warned and then they were helped with preventative measures.”
01:44 — Not only does this translate to fewer lives lost but it also means there is less strain on the hospital system.
01:59 — Toni considers this project to be a great example of “preventative care done through the lens of SDOH.” He explains how, this week, he learned about the term “Social Determinants of Health” which are non-medical factors that can impact someone’s health, such as socio-economic status.
02:14 — AI and ML are unlocking the use of SDOH data in the healthcare industry, which is a “hot topic” at HIMSS.
