Artificial intelligence approach to optimise safety for hospitalised patients with dementia.

Background: The aim of the study is to develop a machine learning (ML) model to identify contributing factors to dementia-related safety events using patient safety event report data.

Method: This study uses dementia-related safety event reports from a patient safety reporting system of a 10-hospital health system in the USA. Contributing factors to safety events were coded using the Yorkshire contributory factors framework based on free-text descriptions in the reports.

Bridging diagnostic safety and mental health: a systematic review highlighting inequities in autism spectrum disorder diagnosis.

Introduction: There is increased recognition that diagnostic errors disproportionately affect marginalised and underserved patient populations in the USA. However, evidence on diagnostic inequities in mental disorders is sparse and not well integrated into the overall diagnostic safety literature.

Objective: We systematically reviewed and narratively synthesised evidence on inequities in diagnosis of mental disorders, guided by the Diagnostic Process Framework developed by The National Academies of Sciences, Engineering, and Medicine.

Assessing Medication CDS Usability: Pilot Results from 10 Outpatient Clinics.

This study aimed to develop a human factors assessment for medication-related clinical decision support (CDS) based on a previously validated tool that assessed the integration of human factors principles in CDS, the instrument for evaluating human factors principles in medication-related decision support alerts (I-MeDeSA), and pilot it with 10 outpatient clinics across the United States.The human factors assessment was developed based on past validations of I-MeDeSA. Examples included changing the wording of questions and reformatting answer choices to check-box options, allowing for multiple answer choices.

Patient Perspectives on Artificial Intelligence in Health Care: Focus Group Study for Diagnostic Communication and Tool Implementation.

Background: Artificial intelligence (AI) is rapidly transforming health care, offering potential benefits in diagnosis, treatment, and workflow efficiency. However, limited research explores patient perspectives on AI, especially in its role in diagnosis and communication. This study examines patient perceptions of various AI applications, focusing on the diagnostic process and communication.

Rethinking Anesthesia Medication "Errors": The OR-SMART Patient Safety Learning Laboratory.

Purpose: We combine the results of multiple studies to describe a systems engineering approach to a well-recognized patient safety problem. The goal of the Operating Room Systems-based Medication Administration error Reduction Team (OR-SMART) patient safety learning laboratory was to study the anesthesia medication work system to identify the characteristics of technologies and interventions that might feasibly reduce anesthesia medication errors.

Scope: The work was conducted at 2 large urban academic medical centers: Johns Hopkins (JHU) and the Medical University of South Carolina (MUSC).

An evaluation framework for ambient digital scribing tools in clinical applications.

Ambient digital scribing (ADS) tools alleviate clinician documentation burden, reducing burnout and enhancing efficiency. As AI-driven ADS tools integrate into clinical workflows, robust governance is essential for ethical and secure deployment. This study proposes a comprehensive ADS evaluation framework incorporating human evaluation, automated metrics, simulation testing, and large language models (LLMs) as evaluators.

Meaningfully meeting the interoperability mandate: a review of the Assistant Secretary for Technology Policy Real World Testing practices.

Objectives: We analyzed interoperability-related Real World Testing results to identify whether developers are providing meaningful results with the appropriate context to enable stakeholders to understand the Certified Health IT conformance and interoperability when deployed in production environments.

Materials And Methods: This qualitative study analyzed components of the Assistant Secretary for Technology Policy's transitions of care criterion Real World Testing results of 5 inpatient and 5 ambulatory health IT developers with the largest market share.

Results: Developers provided interoperability measures; however, none of the developers' presented results in a meaningful way with the appropriate context to understand product interoperability.

Use of ChatGPT for Urinary Symptom Management Among People With Spinal Cord Injury or Disease: Qualitative Study.

Background: Individuals with spinal cord injury or disease (SCI/D) experience disproportionately high rates of recurrent urinary tract infections, which are often complicated by atypical symptoms and delayed diagnoses. Patient-centered tools, like the Urinary Symptom Questionnaires for Neurogenic Bladder (USQNB), have been developed to support symptom assessment yet remain underused. Generative artificial intelligence tools such as ChatGPT may offer a more usable approach to improving symptom management by providing real-time, tailored health information directly to patients.

Building healthcare-community partnerships: process evaluation of a coalition approach to addressing cancer survivors' health-related social needs.

Background: Coalitions involving both healthcare organizations and community organizations, are a way of providing community support to patients. However, the impact of these collaborations and partner satisfaction can be hard to measure without the use of a theoretical framework to guide progress.

Methods: In January 2023 we established the BEAT-C coalition, guided by the Community Coalition Action Theory (CCAT), to improve clinical-community linkages for addressing non-medical needs among individuals affected by cancer in the Washington, D.

The impact of inpatient medication administration technologies on nursing autonomy and practice: a meta-ethnographic synthesis of the qualitative literature.

Objective: To conduct a meta-ethnographic synthesis summarizing the overarching themes of the qualitative literature on nurse interaction with medication administration technologies (MAT) comprising electronic medication administration record (eMAR) and bar-coded medication administration (BCMA).

Materials And Methods: We searched scientific databases from their inception until September 23, 2024, resulting in 2270 unique articles, and extracted data from 27 articles. Scientific rigor was assessed by the Standards for Reporting Qualitative Research (SRQR) checklist.

EMR usability and patient safety: a national survey of physicians.

Despite widespread adoption of electronic medical records (EMRs), concerns persist regarding their usability and implications for patient safety. This national cross-sectional survey assessed physicians' perceptions of EMR usability across safety-relevant domains. Among 1933 respondents from diverse care settings, 56% reported that their EMR did not enhance patient safety, and 50% perceived their system as inefficient.

Extending care beyond the clinic: integrating patient-reported outcomes in chronic pain management through human factors engineering.

Objectives: Tapering prescription opioid pain medication through evidence-based guidelines can help in combating the opioid epidemic. Integrating clinical decision support (CDS) into the clinical workflow of tapering can help in translating guidelines to formulate and implement a tapering plan that manages pain symptoms while minimizing withdrawal, and optimally engages with the patient. The purpose of our project was to develop patient- and clinician-facing CDS in the area of chronic pain management in one integrated application (app) called Tapering And Patient Reporting outcomes for Chronic Pain Management (TAPR-CPM) App.

Opportunities and risks of artificial intelligence in patient portal messaging in primary care.

The rapid increase in patient portal messaging has heightened the workload for primary care physicians (PCPs), contributing to burnout. The use of generative artificial intelligence (AI) to draft responses to patient messages has shown promise in reducing cognitive burden, yet there is still much unknown about the safety and perceptions of using AI drafts. This cross-sectional simulation study assessed whether PCPs could identify and correct errors in AI-generated draft responses to patient portal messages.

Providing Reminders and Education Prior to lung cancer screening: Feasibility and acceptability of a multilevel approach to address disparities in lung cancer screening.

Background: African American individuals experience disparities in the burden of lung cancer compared to other racial or ethnic groups. Yet, African Americans are less likely than White patients to have provider-initiated discussions about lung cancer screening (LCS). In addition to provider-level barriers, predictors of racial disparities include patient-level knowledge barriers and medical mistrust.

The value of simulation testing for the evaluation of ambient digital scribes: a case report.

Objectives: The objective of this work is to demonstrate the value of simulation testing for rapidly evaluating artificial intelligence (AI) products.

Materials And Methods: Researcher-physician teams simulated the use of 2 Ambient Digital Scribe (ADS) products by reading scripts of outpatient encounters while using both products, yielding a total of 44 draft notes. Time to edit, perceived amount of effort and editing, and errors in the AI-generated draft notes were analyzed.

Patient and Provider Perspectives of a Web-Based Intervention to Support Symptom Management After Radioactive Iodine Treatment for Differentiated Thyroid Cancer: Qualitative Study.

Background: Patients diagnosed with differentiated thyroid cancer (DTC) who receive radioactive iodine (RAI) treatment experience acute, medium, and late treatment effects. The timing and severity of these effects vary by individual; common posttreatment effects include dry mouth, salivary gland swelling, dry eyes, and nose bleeds. The nature of symptoms that patients experience after RAI treatment can significantly and negatively impact health-related quality of life.

Leading the way in pediatric sexual health screenings: evaluating pediatric emergency department workflows for the integration of STI screening tools.

Introduction: Emergency department (ED) encounters offer strategic opportunities for sexually transmitted infection (STI) screening, prevention, and treatment for adolescents at risk for STIs who may not otherwise have access to routine screening. This study determined optimal ED implementation of the Teen Health Screen (THS), a validated, tablet-based, patient-reported, sexual risk assessment, and evaluated its implementation feasibility under variable workflows and high-stress tasks.

Methods: Workflow analysis included semi-structured interviews with patients, caregivers, and clinical staff members and clinical observations to understand patient and clinical workflow.

A review of human factors and infusion pumps: lessons for procurement.

Integrating advanced technologies like medical devices in healthcare is crucial for addressing critical challenges, but patient safety must remain the top priority. In modern clinical settings, medical devices, such as infusion devices used to administer fluids and drugs, carry risks from use errors, requiring a focus on usability and human factors engineering (HFE). Despite the significance of integrating HFE into technology selection processes, it is often overlooked.

Social risk factors screening preferences among breast and prostate cancer survivors: A qualitative study.

Objectives: This project aimed to understand the experiences and preferences for social risk factor screening among racially, ethnically, and linguistically diverse cancer survivors in the Washington, DC, region.

Methods: Semi-structured interviews were conducted with English, Spanish, and Amharic-speaking breast and prostate cancer survivors. Data were inductively coded to identify themes, and differences by race and preferred language were evaluated.

Accuracy and Safety of AI-Enabled Scribe Technology: Instrument Validation Study.

Artificial intelligence-enabled ambient digital scribes may have many potential benefits, yet results from our study indicate that there are errors that must be evaluated to mitigate safety risks.

Development of a Preliminary Patient Safety Classification System for Generative AI.

Generative artificial intelligence (AI) technologies have the potential to revolutionise healthcare delivery but require classification and monitoring of patient safety risks. To address this need, we developed and evaluated a preliminary classification system for categorising generative AI patient safety errors. Our classification system is organised around two AI system stages (input and output) with specific error types by stage.

Artificial intelligence related safety issues associated with FDA medical device reports.

The Biden 2023 Artificial Intelligence (AI) Executive Order calls for the creation of a patient safety program. Patient safety reports are a natural starting point for identifying issues. We examined the feasibility of this approach by analyzing reports associated with AI/Machine Learning (ML)-enabled medical devices.

Using Z Codes to Document Social Risk Factors in the Electronic Health Record: A Scoping Review.

Introduction: Individual-level social risk factors have a significant impact on health. Social risks can be documented in the electronic health record using ICD-10 diagnosis codes (the "Z codes"). This study aims to summarize the literature on using Z codes to document social risks.

Inbox message prioritization and management approaches in primary care.

Objectives: Patient messaging to clinicians has dramatically increased since the pandemic, leading to informatics efforts to categorize incoming messages. We examined how message prioritization (as distinct from categorization) occurs in primary care, and how primary care clinicians managed their inbox workflows.

Materials And Methods: Semi-structured interviews and inbox work observations with 11 primary care clinicians at MedStar Health.