# Developing e-Triggers to Detect Telemedicine Related Diagnostic Safety Events

> **NIH AHRQ R01** · BAYLOR COLLEGE OF MEDICINE · 2024 · $400,000

## Abstract

Despite the benefits of a rapid, large-scale deployment of telemedicine in the US, making an accurate
diagnosis via telemedicine involves several potential challenges that warrant further study. Currently, it is not
well known how telemedicine implementation impacts ‘telediagnosis,’ defined as the co-production of an
accurate and timely explanation of a patient’s health problems through remote interactions and transmitted
data, including the clear communication of that explanation to the patient. But early evidence of telemedicine-
related misdiagnosis is already emerging even though the precise frequency of diagnostic errors related to
telemedicine visits and the factors that contribute to these diagnostic errors are unknown. Even before the
global pandemic, diagnostic errors were common and underreported in health care. The goal of this project is
to identify contributory factors for telediagnosis errors, develop methods to efficiently detect them, and enable
risk-assessment strategies to prevent them. We will first use qualitative methods to understand factors
increasing the risk of telediagnosis errors and identify what clues can be used to detect a telediagnosis error.
We will then use these findings to develop electronic triggers (e-triggers, i.e., tools to mine vast amounts of
clinical and administrative data to identify signals for likely adverse events) to identify telemedicine-related
diagnostic errors. We will thus build on our prior work on using e-trigger algorithms to detect patterns of care
suggestive of missed or delayed diagnoses. Review and analysis of e-trigger identified cases can uncover
safety concerns and provide information on breakdowns related to the diagnostic process and contributory
factors. This will generate learning and feedback for improvement efforts by individuals, teams, and healthcare
organizations. Finally, we will perform co-design workshops and use these findings to develop a self-
assessment tool for systems, providers, and patients to identify and mitigate the risk of telediagnosis errors.
The project will capitalize on our existing strong collaborative partnerships at Baylor College of Medicine and
the U.S. Department of Veterans Affairs (VA) and leverage databases containing electronic health records
(EHRs) from over 10 million individuals to accomplish the following specific aims.
Aim 1: Evaluate factors that increase the risk of telediagnosis errors using interviews with clinicians,
 staff, patient safety personnel, telemedicine experts and patients.
Aim 2: Develop e-triggers to identify telemedicine-related diagnostic errors and identify potential
 contributory factors.
Aim 3: Develop a self-assessment tool to evaluate the risk of telemedicine-related diagnostic errors.
A portfolio of e-triggers to identify errors can be used for quality improvement activities and implementation of
solutions to reduce error. The risk assessment tool will enable health systems, providers, and patients to self-
assess ...

## Key facts

- **NIH application ID:** 10873233
- **Project number:** 5R01HS028595-03
- **Recipient organization:** BAYLOR COLLEGE OF MEDICINE
- **Principal Investigator:** Daniel R Murphy
- **Activity code:** R01 (R01, R21, SBIR, etc.)
- **Funding institute:** AHRQ
- **Fiscal year:** 2024
- **Award amount:** $400,000
- **Award type:** 5
- **Project period:** 2022-09-01 → 2026-06-30

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/10873233

## Citation

> US National Institutes of Health, RePORTER application 10873233, Developing e-Triggers to Detect Telemedicine Related Diagnostic Safety Events (5R01HS028595-03). Retrieved via AI Analytics 2026-05-23 from https://api.ai-analytics.org/grant/nih/10873233. Licensed CC0.

---

*[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*