Detecting Patient Position Using Bed-Reaction Forces for Pressure Injury Prevention and Management.

A key best practice to prevent and treat pressure injuries (PIs) is to ensure at-risk individuals are repositioned regularly. Our team designed a non-contact position detection system that predicts an individual's position in bed using data from load cells under the bed legs. The system was originally designed to predict the individual's position as left-side lying, right-side lying, or supine. Our previous work suggested that a higher precision for detecting position (classifying more than three positions) may be needed to determine whether key bony prominences on the pelvis at high risk of PIs have been off-loaded. The objective of this study was to determine the impact of categorizing participant position with higher precision using the system prediction F1 score. Data from 18 participants was collected from four load cells placed under the bed legs and a pelvis-mounted inertial measurement unit while the participants assumed 21 positions. The data was used to train classifiers to predict the participants' transverse pelvic angle using three different position bin sizes (45°, ~30°, and 15°). A leave-one-participant-out cross validation approach was used to evaluate classifier performance for each bin size. Results indicated that our prediction F1 score dropped as the position category precision was increased.

Measuring Repositioning in Home Care for Pressure Injury Prevention and Management.

Despite the widespread agreement on the need for the regular repositioning of at-risk individuals for pressure injury prevention and management, adherence to repositioning schedules remains poor in the clinical environment. The situation in the home environment is likely even worse. Our team has developed a non-contact system that can determine an individual's position in bed (left-side lying, supine, or right-side lying) using data from a set of inexpensive load cells placed under the bed. This system was able to detect whether healthy participants were left-side lying, supine, or right-side lying with 94.2% accuracy in the lab environment. The objective of the present work was to deploy and test our system in the home environment for use with individuals who were sleeping in their own beds. Our system was able to detect the position of our nine participants with an F1 score of 0.982. Future work will include improving generalizability by training our classifier on more participants as well as using this system to evaluate adherence to two-hour repositioning schedules for pressure injury prevention or management. We plan to deploy this technology as part of a prompting system to alert a caregiver when a patient requires repositioning.

An evidence-based approach to artificial intelligence education for medical students: A systematic review.

The exponential growth of artificial intelligence (AI) in the last two decades has been recognized by many as an opportunity to improve the quality of patient care. However, medical education systems have been slow to adapt to the age of AI, resulting in a paucity of AI-specific education in medical schools. The purpose of this systematic review is to evaluate the current evidence-based recommendations for the inclusion of an AI education curriculum in undergraduate medicine. Six databases were searched from inception to April 23, 2022 for cross sectional and cohort studies of fair quality or higher on the Newcastle-Ottawa scale, systematic, scoping, and integrative reviews, randomized controlled trials, and Delphi studies about AI education in undergraduate medical programs. The search yielded 991 results, of which 27 met all the criteria and seven more were included using reference mining. Despite the limitations of a high degree of heterogeneity among the study types and a lack of follow-up studies evaluating the impacts of current AI strategies, a thematic analysis of the key AI principles identified six themes needed for a successful implementation of AI in medical school curricula. These themes include ethics, theory and application, communication, collaboration, quality improvement, and perception and attitude. The themes of ethics, theory and application, and communication were further divided into subthemes, including patient-centric and data-centric ethics; knowledge for practice and knowledge for communication; and communication for clinical decision-making, communication for implementation, and communication for knowledge dissemination. Based on the survey studies, medical professionals and students, who generally have a low baseline knowledge of AI, have been strong supporters of adding formal AI education into medical curricula, suggesting more research needs to be done to push this agenda forward.

Early functional mobilization for non-operative treatment of simple elbow dislocations: a systematic review.

Purpose: This systematic review aims to elucidate a non-operative rehabilitation program that optimizes recovery based on published approaches and outcomes. Methods: Searches of four databases from inception to 1 January 2020 were performed to identify clinical studies addressing the non-operative management of simple elbow dislocations. Results: Of 2435 studies that were eligible for title screen, 15 studies satisfied inclusion criteria. Three randomized control studies demonstrated that early mobilization expedited the return of range of motion, function and return to work or activities, however, resulted in increased pain within the six-week rehabilitation period compared to Plaster of Paris casting for 21 days. Patients returned to work sooner after early mobilization (10 vs. 18 days; p = 0.02) compared to Plaster of Paris casting. In all studies, early mobilization resulted in similar re-dislocation rates of 1.3% (3/237) versus 2.2% (12/549) in those with Plaster of Paris casting as well as lower incidence of heterotopic ossification (36% vs. 54%). No significant differences between rehabilitation protocols were determined; however, the large majority of recent papers utilized rehabilitation protocols. Conclusion: Early mobilization of simple elbow dislocations results in early return of Range-of-Motion, function and return to work with no increase in complication rates; however, increased pain during the rehabilitation period.