Search

Objective: To develop a machine learning framework to forecast emergency department (ED) crowding and to evaluate model performance under spatial and temporal data drift.Materials and Methods: We obtained four datasets, identified by the location: 1-large academic hospital and 2-rural hospital, and time period: pre-COVID (Jan 1, 2019-Feb 1, 2020) and COVID-era (May 15, 2020-Feb 1, 2021). Our primary target was a binary outcome that is equal to 1 if the number of patients with acute respiratory illness that were ED boarding for more than four hours was above a prescribed historical percentile. We trained a random forest and used the area under the curve (AUC) to evaluate out-of-sample performance for two experiments: 1) we evaluated the impact of sudden temporal drift by training models using pre-COVID data and testing them during the COVID-era, 2) we evaluated the impact of spatial drift by testing models trained at Location 1 on data from Location 2, and vice versa.Results: The baseline AUC values for ED boarding ranged from 0.54 (pre-COVID at Location 2) to 0.81 (COVID-era at Location 1). Models trained with pre-COVID data performed similarly to COVID-era models (0.82 vs. 0.78 at Location 1). Models that were transferred from Location 2 to Location 1 performed worse than models trained at Location 1 (0.51 vs. 0.78).Discussion and Conclusion: Our results demonstrate that ED boarding is a predictable metric for ED crowding, models were not significantly impacted by temporal data drift, and any attempts at implementation must consider spatial data drift. [ABSTRACT FROM AUTHOR]

Background: Ambient artificial intelligence offers promise for improving documentation efficiency and reducing provider burden through clinical note generation. However, challenges persist in workflow integration, compliance, and widespread adoption. This study leveraged a Learning Health System (LHS) framework to align research and operations using a hybrid effectiveness-implementation protocol, embedded as pragmatic trial operations within the electronic health record (EHR)., Methods: An alpha phase was conducted to pilot technical integration, refine workflows, and determine sample size in planning for a beta phase designed as a pragmatic randomized controlled trial with the Stanford Professional Fulfillment Index (PFI) as primary outcome. During alpha, bi-directional governance was established between IS operations and LHS team with multidisciplinary workgroups for analytics, technical, documentation, and user experience. Ambient AI was embedded into the EHR using Fast Healthcare Interoperability Resources (FHIR), with real-time data dashboards tracking utilization and documentation accuracy for operations and research. Performance metrics were monitored serially using a difference-in-differences (DiD) analysis to detect drift caused by software workflow changes., Results: The alpha phase, designed as Type 1 Hybrid, informed a 24-week beta phase stepped-wedge trial with 90% power to detect changes in PFI. Across the alpha phase, the weighted median of average provider Ambient AI utilization was 65.4% following Plan-Do-Study-Act cycles addressing organizational feasibility and task-dependent adoption. During initial implementation, a workflow issue caused discrepancies between ICD-10 diagnosis entries and note content, reducing accuracy from 79% to 35% (p < 0.01). After implementing a new note template and provider training, accuracy returned to pre-intervention levels. DiD did not detect significant drifts in work outside of work or time in notes two weeks before and after the new note template. Beta phase enrollment achieved its targeted 66 providers across eight specialties, initiating on schedule., Conclusions and Relevance: We provide a novel playbook for integrating Generative AI platforms in healthcare, combining pragmatic trial operations, human-centered design, and real-time monitoring to advance evidence-based implementation., Clinicaltrialsgov Id: NCT06517082.

Hospitalized adults with opioid use disorder (OUD) are at high risk for adverse events and rehospitalizations. This pre-post quasi-experimental study evaluated whether an AI-driven OUD screener embedded in the electronic health record (EHR) was non-inferior to usual care in identifying patients for Addiction Medicine consults, aiming to provide a similarly effective but more scalable alternative to human-led ad hoc consultations. The AI screener analyzed EHR notes in real-time with a convolutional neural network to identify patients at risk and recommend consultation. The primary outcome was the proportion of patients receiving consults, comparing a 16-month pre-intervention period to an 8-month post-intervention period with the AI screener. Consults did not change between periods (1.35% vs 1.51%, p < 0.001 for non-inferiority). The AI screener was associated with a reduction in 30-day readmissions (OR: 0.53, 95% CI: 0.30-0.91, p = 0.02) with an incremental cost of $6,801 per readmission avoided, demonstrating its potential as a scalable, cost-effective solution for OUD care., Clinicaltrialsgov Id: NCT05745480., Competing Interests: Declarations DECLARATION OF INTEREST All authors have no conflicts of interest.

Background:  Existing monitoring of machine-learning-based clinical decision support (ML-CDS) is focused predominantly on the ML outputs and accuracy thereof. Improving patient care requires not only accurate algorithms but also systems of care that enable the output of these algorithms to drive specific actions by care teams, necessitating expanding their monitoring., Objectives:  In this case report, we describe the creation of a dashboard that allows the intervention development team and operational stakeholders to govern and identify potential issues that may require corrective action by bridging the monitoring gap between model outputs and patient outcomes., Methods:  We used an iterative development process to build a dashboard to monitor the performance of our intervention in the broader context of the care system., Results:  Our investigation of best practices elsewhere, iterative design, and expert consultation led us to anchor our dashboard on alluvial charts and control charts. Both the development process and the dashboard itself illuminated areas to improve the broader intervention., Conclusion:  We propose that monitoring ML-CDS algorithms with regular dashboards that allow both a context-level view of the system and a drilled down view of specific components is a critical part of implementing these algorithms to ensure that these tools function appropriately within the broader care system., Competing Interests: None declared., (Thieme. All rights reserved.)

Background: Emergency department (ED) providers are important collaborators in preventing falls for older adults because they are often the first health care providers to see a patient after a fall and because at-home falls are often preceded by previous ED visits. Previous work has shown that ED referrals to falls interventions can reduce the risk of an at-home fall by 38%. Screening patients at risk for a fall can be time-consuming and difficult to implement in the ED setting. Machine learning (ML) and clinical decision support (CDS) offer the potential of automating the screening process. However, it remains unclear whether automation of screening and referrals can reduce the risk of future falls among older patients., Objective: The goal of this paper is to describe a research protocol for evaluating the effectiveness of an automated screening and referral intervention. These findings will inform ongoing discussions about the use of ML and artificial intelligence to augment medical decision-making., Methods: To assess the effectiveness of our program for patients receiving the falls risk intervention, our primary analysis will be to obtain referral completion rates at 3 different EDs. We will use a quasi-experimental design known as a sharp regression discontinuity with regard to intent-to-treat, since the intervention is administered to patients whose risk score falls above a threshold. A conditional logistic regression model will be built to describe 6-month fall risk at each site as a function of the intervention, patient demographics, and risk score. The odds ratio of a return visit for a fall and the 95% CI will be estimated by comparing those identified as high risk by the ML-based CDS (ML-CDS) and those who were not but had a similar risk profile., Results: The ML-CDS tool under study has been implemented at 2 of the 3 EDs in our study. As of April 2023, a total of 1326 patient encounters have been flagged for providers, and 339 unique patients have been referred to the mobility and falls clinic. To date, 15% (45/339) of patients have scheduled an appointment with the clinic., Conclusions: This study seeks to quantify the impact of an ML-CDS intervention on patient behavior and outcomes. Our end-to-end data set allows for a more meaningful analysis of patient outcomes than other studies focused on interim outcomes, and our multisite implementation plan will demonstrate applicability to a broad population and the possibility to adapt the intervention to other EDs and achieve similar results. Our statistical methodology, regression discontinuity design, allows for causal inference from observational data and a staggered implementation strategy allows for the identification of secular trends that could affect causal associations and allow mitigation as necessary., Trial Registration: ClinicalTrials.gov NCT05810064; https://www.clinicaltrials.gov/study/NCT05810064., International Registered Report Identifier (irrid): DERR1-10.2196/48128., (©Daniel J Hekman, Amy L Cochran, Apoorva P Maru, Hanna J Barton, Manish N Shah, Douglas Wiegmann, Maureen A Smith, Frank Liao, Brian W Patterson. Originally published in JMIR Research Protocols (https://www.researchprotocols.org), 03.08.2023.)