AI saves pediatricians time, provides ‘more actionable guidance’ for asthma care

An AI tool for managing pediatric asthma shaved 7.8 minutes from the time pediatricians spent dealing with electronic health records in a randomized clinical trial conducted at the Mayo Clinic and published Aug. 2 in Plos One.

To evaluate the accuracy and efficiency of an existing clinical decision support tool outfitted with AI, senior author Young Juhn, MD, and colleagues enrolled 42 pediatric primary-care practitioners and 184 children with asthma (median age, 8.5 years).

The tool they tested, called A-GPS for Asthma-Guidance and Prediction System, is designed to warn physicians of worsening asthma symptoms well before the symptoms become severe.

It works by quickly extracting, and accurately predicting from, relevant clinical information stored in the EHR.

The time-savings aspect is intended as a secondary aim to the clinical decision support.

Splitting the participant pool about evenly between experimental (90 patients) and control (94 patients) subgroups, Juhn and colleagues found little to no difference in the frequency of asthma exacerbation between the two groups.

However, the physicians who used A-GPS spent significantly less time manually reviewing clinical charts and notes in the EHR.

The difference in minutes, 3.5 with the AI vs. 11.3 without, represented 67% less time with eyes on a screen—or 33% more time available (7.8 minutes) for direct patient care.

Mean costs weren’t much different between the two groups, but the patients in the AI group had timelier follow-up visits.

Further, the tool “provided more actionable guidance for asthma management to primary care providers in a way better addressing the needs of patients compared to control group (usual care). We believe this is a key benefit of A-GPS in asthma care.”

More:

To our knowledge, this exploratory pragmatic trial is the first randomized clinical trial that assessed the comparative effectiveness of an AI-assisted CDS leveraging EHRs for asthma management in reducing asthma exacerbation.”

The study is available in full for free.

Around the web

The Palo Alto giant used exams from nearly 250,000 patients to upgrade its already robust algorithm.

Exams performed using the deep learning-based reconstruction tool also maintained high image quality, experts reported Wednesday.

Stratifying exams according to risk can reduce unnecessary imaging and downstream costs of care, Hawaiian researchers reported in Radiology.

Trimed Popup
Trimed Popup