Autonomous artificial intelligence increases real-world specialist clinic productivity in a cluster-randomized trial.

Autonomous artificial intelligence (AI) promises to increase healthcare productivity, but real-world evidence is lacking. We developed a clinic productivity model to generate testable hypotheses and study design for a preregistered cluster-randomized clinical trial, in which we tested the hypothesis that a previously validated US FDA-authorized AI for diabetic eye exams increases clinic productivity (number of completed care encounters per hour per specialist physician) among patients with diabetes. Here we report that 105 clinic days are cluster randomized to either intervention (using AI diagnosis; 51 days; 494 patients) or control (not using AI diagnosis; 54 days; 499 patients). The prespecified primary endpoint is met: AI leads to 40% higher productivity (1.59 encounters/hour, 95% confidence interval [CI]: 1.37-1.80) than control (1.14 encounters/hour, 95% CI: 1.02-1.25), p < 0.00; the secondary endpoint (productivity in all patients) is also met. Autonomous AI increases healthcare system productivity, which could potentially increase access and reduce health disparities. ClinicalTrials.gov NCT05182580.

Determinants for scalable adoption of autonomous AI in the detection of diabetic eye disease in diverse practice types: key best practices learned through collection of real-world data.

Autonomous Artificial Intelligence (AI) has the potential to reduce disparities, improve quality of care, and reduce cost by improving access to specialty diagnoses at the point-of-care. Diabetes and related complications represent a significant source of health disparities. Vision loss is a complication of diabetes, and there is extensive evidence supporting annual eye exams for prevention. Prior to the use of autonomous AI, store-and-forward imaging approaches using remote reading centers (asynchronous telemedicine) attempted to increase diabetes related eye exams with limited success. In 2018, after rigorous clinical validation, the first fully autonomous AI system [LumineticsCore™ (formerly IDx-DR), Digital Diagnostics Inc., Coralville, IA, United States] received U.S. Food and Drug Administration (FDA) De Novo authorization. The system diagnoses diabetic retinopathy (including macular edema) without specialist physician overread at the point-of-care. In addition to regulatory clearance, reimbursement, and quality measure updates, successful adoption requires local optimization of the clinical workflow. The general challenges of frontline care clinical workflow have been well documented in the literature. Because healthcare AI is so new, there remains a gap in the literature about challenges and opportunities to embed diagnostic AI into the clinical workflow. The goal of this review is to identify common workflow themes leading to successful adoption, measured as attainment number of exams per month using the autonomous AI system against targets set for each health center. We characterized the workflow in four different US health centers over a 12-month period. Health centers were geographically dispersed across the Midwest, Southwest, Northeast, and West Coast and varied distinctly in terms of size, staffing, resources, financing and demographics of patient populations. After 1 year, the aggregated number of diabetes-related exams per month increased from 89 after the first month of initial deployment to 174 across all sites. Across the diverse practice types, three primary determinants underscored sustainable adoption: (1) Inclusion of Executive and Clinical Champions; (2) Underlining Health Center Resources; and (3) Clinical workflows that contemplate patient identification (pre-visit), LumineticsCore Exam Capture and Provider Consult (patient visit), and Timely Referral Triage (post-visit). In addition to regulatory clearance, reimbursement and quality measures, our review shows that addressing the core determinants for workflow optimization is an essential part of large-scale adoption of innovation. These best practices can be generalizable to other autonomous AI systems in front-line care settings, thereby increasing patient access, improving quality of care, and addressing health disparities.

Trends in the use of dual mobility bearings in hip arthroplasty.

AIMS: Dual mobility (DM) bearings are an attractive treatment option to obtain hip stability during challenging primary and revision total hip arthroplasty (THA) cases. The purpose of this study was to analyze data submitted to the American Joint Replacement Registry (AJRR) to characterize utilization trends of DM bearings in the USA. METHODS: All primary and revision THA procedures reported to AJRR from 2012 to 2018 were analyzed. Patients of all ages were included and subdivided into DM and traditional bearing surface cohorts. Patient demographics, geographical region, hospital size, and teaching affiliation were assessed. Associations were determined by chi-squared analysis and logistic regression was performed to assess outcome variables. RESULTS: A total of 406,900 primary and 34,745 revision THAs were identified, of which 35,455 (8.7%) and 8,031 (23.1%) received DM implants respectively. For primary THA, DM usage increased from 6.7% in 2012 to 12.0% in 2018. Among revision THA, DM use increased from 19.5% in 2012 to 30.6% in 2018. Patients < 50 years of age had the highest rates of DM implantation in every year examined. For each year of increase in age, there was a 0.4% decrease in the rate of DM utilization (odds ratio (OR) 0.996 (95% confidence interval (CI) 0.995 to 0.997); p < 0.001). Females were more likely to receive a DM implant compared to males (OR 1.077 (95% CI 1.054 to 1.100); p < 0.001). Major teaching institutions and smaller hospitals were associated with higher rates of utilization. DM articulations were used more commonly for dysplasia compared with osteoarthritis (OR 2.448 (95% CI 2.032 to 2.949); p < 0.001) during primary THA and for instability (OR 3.130 (95% CI 2.751 to 3.562) vs poly-wear; p < 0.001) in the revision setting. CONCLUSION: DM articulations showed a marked increase in utilization during the period examined. Younger patient age, female sex, and hospital characteristics such as teaching status, smaller size, and geographical location were associated with increased utilization. DM articulations were used more frequently for primary THA in patients with dysplasia and for revision THA in patients being treated for instability. Cite this article: Bone Joint J 2020;102-B(7 Supple B):27-32.

Manipulation Under Anesthesia After Total Knee: Who Still Requires a Revision Arthroplasty?

BACKGROUND: Stiffness after total knee arthroplasty (TKA) is a multifactorial complication involving patient, implant, surgical technique, and rehabilitation, occasionally necessitating manipulation under anesthesia (MUA) or revision. Few modern databases contain sufficient longitudinal information of all factors. We characterized MUA after primary TKA and identified independent risk factors for revision TKA after MUA from the American Joint Replacement Registry. METHODS: We retrospectively reviewed primary TKAs for American Joint Replacement Registry patients ≥65 years from January 1, 2012 to 31 March, 2019. We linked these to the Centers for Medicare and Medicaid Services database to identify MUA and revision TKA procedure codes. We compared groups with chi-squared testing, identifying independent risk factors for subsequent revision with binary logistic regression presented as odds ratios with 95% confidence intervals. RESULTS: Of 664,604 primary TKAs, 3918 (0.6%) underwent MUA after a median of 2.0 ± 1.0 months. Revision surgery occurred in 131 (3.4%) MUA patients after a median of 9.0 months. Timing of MUA was not different between revision and no revision patients (P = .09). Patients undergoing MUA compared to no MUA were older (age 71.5 vs 70.7, P < .01), predominantly female (63.9% vs 61.2%, P < .01), current/former tobacco users (24.2% vs 13.3%, P < .01), with osteoarthritis diagnoses (98.0% vs 84.3%, P < .01). Independent risk factors for revision after MUA were male gender (1.56, 1.09-2.22). CONCLUSION: The incidence of MUA after primary TKA is low (0.6%) in Medicare patients ≥65 years of age; 3.4% progress to revision after a median of 9 months. Being male was significantly associated with revision TKA after MUA.