Literature DB >> 33576432

Mining tasks and task characteristics from electronic health record audit logs with unsupervised machine learning.

Bob Chen1,2, Wael Alrifai3,4, Cheng Gao3, Barrett Jones3, Laurie Novak3, Nancy Lorenzi3, Daniel France5, Bradley Malin3,6,7, You Chen3,7.   

Abstract

OBJECTIVE: The characteristics of clinician activities while interacting with electronic health record (EHR) systems can influence the time spent in EHRs and workload. This study aims to characterize EHR activities as tasks and define novel, data-driven metrics.
MATERIALS AND METHODS: We leveraged unsupervised learning approaches to learn tasks from sequences of events in EHR audit logs. We developed metrics characterizing the prevalence of unique events and event repetition and applied them to categorize tasks into 4 complexity profiles. Between these profiles, Mann-Whitney U tests were applied to measure the differences in performance time, event type, and clinician prevalence, or the number of unique clinicians who were observed performing these tasks. In addition, we apply process mining frameworks paired with clinical annotations to support the validity of a sample of our identified tasks. We apply our approaches to learn tasks performed by nurses in the Vanderbilt University Medical Center neonatal intensive care unit.
RESULTS: We examined EHR audit logs generated by 33 neonatal intensive care unit nurses resulting in 57 234 sessions and 81 tasks. Our results indicated significant differences in performance time for each observed task complexity profile. There were no significant differences in clinician prevalence or in the frequency of viewing and modifying event types between tasks of different complexities. We presented a sample of expert-reviewed, annotated task workflows supporting the interpretation of their clinical meaningfulness.
CONCLUSIONS: The use of the audit log provides an opportunity to assist hospitals in further investigating clinician activities to optimize EHR workflows.
© The Author(s) 2021. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.

Entities:  

Keywords:  Unsupervised learning; audit logs; electronic health records; human-computer interaction, clinician activities; metrics; tasks

Mesh:

Year:  2021        PMID: 33576432      PMCID: PMC8200270          DOI: 10.1093/jamia/ocaa338

Source DB:  PubMed          Journal:  J Am Med Inform Assoc        ISSN: 1067-5027            Impact factor:   4.497


  25 in total

Review 1.  Use of Electronic Health Records by Nurses for Symptom Management in Inpatient Settings: A Systematic Review.

Authors:  Mustafa Ozkaynak; Blaine Reeder; Lilian Hoffecker; Mary Beth Makic; Karen Sousa
Journal:  Comput Inform Nurs       Date:  2017-09       Impact factor: 1.985

2.  The impact of electronic health record use on physician productivity.

Authors:  Julia Adler-Milstein; Robert S Huckman
Journal:  Am J Manag Care       Date:  2013-11       Impact factor: 2.229

3.  Racing Against the Clock: Internal Medicine Residents' Time Spent On Electronic Health Records.

Authors:  Lu Chen; Uta Guo; Lijo C Illipparambil; Matt D Netherton; Bhairavi Sheshadri; Eric Karu; Stephen J Peterson; Parag H Mehta
Journal:  J Grad Med Educ       Date:  2016-02

4.  Using electronic health record audit logs to study clinical activity: a systematic review of aims, measures, and methods.

Authors:  Adam Rule; Michael F Chiang; Michelle R Hribar
Journal:  J Am Med Inform Assoc       Date:  2020-03-01       Impact factor: 4.497

5.  Interaction patterns of trauma providers are associated with length of stay.

Authors:  You Chen; Mayur B Patel; Candace D McNaughton; Bradley A Malin
Journal:  J Am Med Inform Assoc       Date:  2018-07-01       Impact factor: 4.497

6.  EHR audit logs: A new goldmine for health services research?

Authors:  Julia Adler-Milstein; Jason S Adelman; Ming Tai-Seale; Vimla L Patel; Chris Dymek
Journal:  J Biomed Inform       Date:  2019-12-07       Impact factor: 6.317

7.  Electronic Health Record Effects on Work-Life Balance and Burnout Within the I3 Population Collaborative.

Authors:  Sandy L Robertson; Mark D Robinson; Alfred Reid
Journal:  J Grad Med Educ       Date:  2017-08

8.  SCANPY: large-scale single-cell gene expression data analysis.

Authors:  F Alexander Wolf; Philipp Angerer; Fabian J Theis
Journal:  Genome Biol       Date:  2018-02-06       Impact factor: 13.583

9.  Automated optimized parameters for T-distributed stochastic neighbor embedding improve visualization and analysis of large datasets.

Authors:  Anna C Belkina; Christopher O Ciccolella; Rina Anno; Richard Halpert; Josef Spidlen; Jennifer E Snyder-Cappione
Journal:  Nat Commun       Date:  2019-11-28       Impact factor: 14.919

10.  Network Analysis Subtleties in ICU Structures and Outcomes.

Authors:  You Chen; Chao Yan; Mayur B Patel
Journal:  Am J Respir Crit Care Med       Date:  2020-12-01       Impact factor: 21.405

View more
  5 in total

1.  Identifying patterns in administrative tasks through structural topic modeling: A study of task definitions, prevalence, and shifts in a mental health practice's operations during the COVID-19 pandemic.

Authors:  Dessislava Pachamanova; Wiljeana Glover; Zhi Li; Michael Docktor; Nitin Gujral
Journal:  J Am Med Inform Assoc       Date:  2021-11-25       Impact factor: 7.942

2.  Predicting next-day discharge via electronic health record access logs.

Authors:  Xinmeng Zhang; Chao Yan; Bradley A Malin; Mayur B Patel; You Chen
Journal:  J Am Med Inform Assoc       Date:  2021-11-25       Impact factor: 7.942

3.  Characterizing Multitasking and Workflow Fragmentation in Electronic Health Records among Emergency Department Clinicians: Using Time-Motion Data to Understand Documentation Burden.

Authors:  Amanda J Moy; Lucy Aaron; Kenrick D Cato; Jessica M Schwartz; Jonathan Elias; Richard Trepp; Sarah Collins Rossetti
Journal:  Appl Clin Inform       Date:  2021-10-27       Impact factor: 2.762

4.  Progress toward a science of learning systems for healthcare.

Authors:  Suzanne Bakken
Journal:  J Am Med Inform Assoc       Date:  2021-06-12       Impact factor: 7.942

5.  Measuring and Maximizing Undivided Attention in the Context of Electronic Health Records.

Authors:  You Chen; Julia Adler-Milstein; Christine A Sinsky
Journal:  Appl Clin Inform       Date:  2022-07-05       Impact factor: 2.762

  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.