2023 AI Community of Practice Projects


David Kessler - Vice Chair of Innovation & Associate Professor of Emergency Medicine at VP&S

In febrile infants younger than 30 days, lumbar puncture (LP) is a procedure routinely performed to evaluate for meningitis. LPs are mainly performed in the emergency setting by clinicians and trainees. Novice practitioners are often challenged with a high failure rate during LPs, which can cause prolonged pain for infants and create uncertainty in the diagnosis. Point-of-care ultrasound has the potential to improve the success of LPs by providing better visualization of the anatomy. However, its effectiveness is limited by the operator's ability to accurately interpret the ultrasound findings. This project aims to develop a model that can automatically identify spinal anatomical features on point-of-care ultrasound in infants. The goal is to assist clinicians in performing infant lumbar punctures with increased safety and accuracy.


Jennifer Mootz - Assistant Professor of Clinical Medical Psychology (in Psychiatry)

Adolescents and young adults, particularly those from racial/ethnic minorities, face significant challenges in accessing outpatient care for mental health and substance use disorders. The COVID-19 pandemic has worsened these disparities. Utilizing technology to provide remote mental health and substance use services could help address the unmet needs of these individuals. The project aims to integrate a conversational agent and ML model within the mobile app coach to enhance user engagement and safely reduce mental health and substance use symptoms. The objectives include understanding the application of AI conversational agents and ML models in digital mental health and substance use care, establishing safety parameters, and assessing acceptability and feasibility.