Advancing Motivational Interviewing Training with Artificial Intelligence: ReadMI

Motivational interviewing skills practice enhanced with artificial intelligence: ReadMI

BACKGROUND

Finding time in the medical curriculum to focus on motivational interviewing (MI) training is a challenge in many medical schools. We developed a software-based training tool, "Real-time Assessment of Dialogue in Motivational Interviewing" (ReadMI), that aims to advance the skill acquisition of medical students as they learn the MI approach. This human-artificial intelligence teaming may help reduce the cognitive load on a training facilitator.

METHODS

During their Family Medicine clerkship, 125 third-year medical students were scheduled in pairs to participate in a 90-minute MI training session, with each student doing two role-plays as the physician. Intervention group students received both facilitator feedback and ReadMI metrics after their first role-play, while control group students received only facilitator feedback.

RESULTS

While students in both conditions improved their MI approach from the first to the second role-play, those in the intervention condition used significantly more open-ended questions, fewer closed-ended questions, and had a higher ratio of open to closed questions.

CONCLUSION

MI skills practice can be gained with a relatively small investment of student time, and artificial intelligence can be utilized both for the measurement of MI skill acquisition and as an instructional aid.

Rapid identification of the resistance of urinary tract pathogenic bacteria using deep learning-based spectroscopic analysis

The resistance of urinary tract pathogenic bacteria to various antibiotics is increasing, which requires the rapid detection of infectious pathogens for accurate and timely antibiotic treatment. Here, we propose a rapid diagnosis strategy for the antibiotic resistance of bacteria in urinary tract infections (UTIs) based on surface-enhanced Raman scattering (SERS) using a positively charged gold nanoparticle planar solid SERS substrate. Then, an intelligent identification model for SERS spectra based on the deep learning technique is constructed to realize the rapid, ultrasensitive, and non-labeled detection of pathogenic bacteria. A total of 54,000 SERS spectra were collected from 18 isolates belonging to 6 species of common UTI bacteria in this work to realize identification of bacterial species, antibiotic sensitivity, and multidrug resistance (MDR) via convolutional neural networks (CNN). This method significantly simplify the Raman data processing processes without background removing and smoothing, however, achieving 96% above classification accuracy, which was significantly greater than the 85% accuracy of the traditional multivariate statistical analysis algorithm principal component analysis combined with the K-nearest neighbor (PCA-KNN). This work clearly elucidated the potential of combining SERS and deep learning technique to realize culture-free identification of pathogenic bacteria and their associated antibiotic sensitivity.