Journal article
Toward alert triage: scalable qualitative coding framework for analyzing alert notes from the Telehealth Intervention Program for Seniors (TIPS)
JAMIA open, v 6(3), ooad061
01 Oct 2023
PMID: 37560155
Abstract
Lay Summary Community-based telehealth care and telehealth in general can end up creating vast amounts of data from the technology used to monitor patients and the information that has to be transmitted (measurements, alerts). This can overwhelm nurses and doctors with information and take a lot of time to review as they try to provide high-quality care. Telehealth is helpful for older adults who benefit from being able to monitor their health closer to home. However, it is important that the information created from telehealth technology is as correct and accurate as possible and efficiently delivered to the telehealth providers. To achieve this goal, the first step is generating data called training data which helps researcher develop a future and improved system. To that end, we developed a coding method based on the information of 24 931 alert notes from a community-based telehealth program, which provides remote monitoring to low-income older adults in the northeast region of the United States. Our method helped to code the information from each participants' check-in, any alert they might have made, their vitals, and what happened as a result of the alert. We found it is feasible to code and understand large amounts of data and help identify false information and reduce the burden on the telehealth providers. This in turn would help the providers to give better quality of care to older adults. Our findings inform the field practice and future research on developing an automated alert triaging system for remote patient monitoring and telehealth services.
Objective Combined with mobile monitoring devices, telehealth generates overwhelming data, which could cause clinician burnout and overlooking critical patient status. Developing novel and efficient ways to correctly triage such data will be critical to a successful telehealth adoption. We aim to develop an automated classification framework of existing nurses' notes for each alert that will serve as a training dataset for a future alert triage system for telehealth programs. Materials and Methods We analyzed and developed a coding framework and a regular expression-based keyword match approach based on the information of 24 931 alert notes from a community-based telehealth program. We evaluated our automated alert triaging model for its scalability on a stratified sampling of 800 alert notes for precision and recall analysis. Results We found 22 717 out of 24 579 alert notes (92%) belonging to at least one of the 17 codes. The evaluation of the automated alert note analysis using the regular expression-based information extraction approach resulted in an average precision of 0.86 (SD = 0.13) and recall 0.90 (SD = 0.13). Discussion The high-performance results show the feasibility and the scalability potential of this approach in community-based, low-income older adult telehealth settings. The resulting coded alert notes can be combined with participants' health monitoring results to generate predictive models and to triage false alerts. The findings build steps toward developing an automated alert triaging model to improve the identification of alert types in remote health monitoring and telehealth systems.
Metrics
Details
- Title
- Toward alert triage: scalable qualitative coding framework for analyzing alert notes from the Telehealth Intervention Program for Seniors (TIPS)
- Creators
- Phuong Nguyen - University of IowaMelody K. Schiaffino - San Diego State UniversityZhan Zhang - Pace UniversityHyung Wook Choi - Drexel Univ, Dept Informat Sci, Philadelphia, PA USAJina Huh-Yoo (Corresponding Author) - Drexel University, Information Science (Informatics)
- Publication Details
- JAMIA open, v 6(3), ooad061
- Publisher
- Oxford University Press
- Number of pages
- 7
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Information Science (Informatics)
- Web of Science ID
- WOS:001043029600001
- Scopus ID
- 2-s2.0-85168558166
- Other Identifier
- 991020843803904721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- Web of Science research areas
- Health Care Sciences & Services
- Medical Informatics