Analyzing Physician In Basket Burden and Efficiency Using K-Means Clustering

Abstract

Background

Electronic health record (EHR) systems are essential for modern healthcare but contribute to a significant documentation burden, affecting physician workflow and well-being. While previous studies have identified differences in EHR usage across demographics, systematic methods for identifying high-burden physician groups remain limited. This study applies cluster analysis to uncover distinct EHR usage profiles and provide a framework to inform the development of targeted interventions.

Objectives

This study investigated two research questions: (1) Can cluster analysis effectively identify distinct physician EHR usage profiles? (2) How do these profiles vary across physician demographics and practice characteristics? We hypothesized that (1) EHR usage clusters would emerge based on workload intensity, after-hours documentation, and In Basket management patterns, and (2) would be significantly associated with physician experience, sex, and specialty.

Methods

We analyzed outpatient EHR usage data from 323 physicians at an academic health system using Epic Signal, an analytical tool for Epic EHR. Using k-means clustering, we examined six metrics representing EHR workload (after-hours and extended-day activities) and In Basket efficiency (message handling and management patterns). We assessed cluster differences and conducted subgroup analyses by physician sex and specialty.

Results

Two distinct physician clusters emerged: one high-burden cluster, predominantly comprising experienced primary care physicians, and another lower-burden cluster, consisting mostly of younger specialists. Physicians in the high-burden cluster spent nearly three times as much time on after-hours documentation and In Basket management. While message response times remained similar, subgroup analyses revealed significant sex and specialty-based differences, particularly in the lower-burden cluster.

Conclusion

Cluster analysis effectively identified distinct EHR usage patterns, highlighting disparities in workload by experience, sex, and specialty. This approach provides a scalable, data-driven method for health systems to identify at-risk groups and design targeted interventions to mitigate documentation burden and enhance EHR efficiency.

Keywords

electronic health records and systems - documentation burden - cluster analysis - machine learning - COVID-19

Protection of Human and Animal Subjects

This study was performed in compliance with the World Medical Association Declaration of Helsinki on Ethical Principles for Medical Research Involving Human Subjects and was reviewed by the Albert Einstein College of Medicine Institutional Review Board (IRB#2020-11339).

Publication History

Received: 13 November 2024

Accepted: 18 March 2025

Accepted Manuscript online:
19 March 2025

Article published online:
16 July 2025

• References

• 1 Mullins A, O'Donnell R, Mousa M. et al. Health outcomes and healthcare efficiencies associated with the use of electronic health records in hospital emergency departments: a systematic review. J Med Syst 2020; 44 (12) 200
• 2 Dyrbye LN, Gordon J, O'Horo J. et al. Relationships between EHR-based audit log data and physician burnout and clinical practice process measures. Mayo Clin Proc 2023; 98 (03) 398-409
• 3 Majumder MA, Guerrini CJ, Bollinger JM, Cook-Deegan R, McGuire AL. Sharing data under the 21st Century Cures Act. Genet Med 2017; 19 (12) 1289-1294
• 4 Tai-Seale M, Baxter S, Millen M. et al. Association of physician burnout with perceived EHR work stress and potentially actionable factors. J Am Med Inform Assoc 2023; 30 (10) 1665-1672
• 5 Baxter SL, Saseendrakumar BR, Cheung M. et al. Association of electronic health record inbasket message characteristics with physician burnout. JAMA Netw Open 2022; 5 (11) e2244363
• 6 Tai-Seale M, Dillon EC, Yang Y. et al. Physicians' well-being linked to in-basket messages generated by algorithms in electronic health records. Health Aff (Millwood) 2019; 38 (07) 1073-1078
• 7 Ripp JA, Pietrzak RH, de Guillebon E, Peccoralo LA. Association of clerical burden and EHR frustration with burnout and career intentions among physician faculty in an urban academic health system. Int J Med Inform 2025; 195: 105740
• 8 Patel SY, Mehrotra A, Huskamp HA, Uscher-Pines L, Ganguli I, Barnett ML. Trends in outpatient care delivery and telemedicine during the COVID-19 pandemic in the US. JAMA Intern Med 2021; 181 (03) 388-391
• 9 Holmgren AJ, Thombley R, Sinsky CA, Adler-Milstein J. Changes in physician electronic health record use with the expansion of telemedicine. JAMA Intern Med 2023; 183 (12) 1357-1365
• 10 Doleman G, De Leo A, Bloxsome D. The impact of pandemics on healthcare providers' workloads: a scoping review. J Adv Nurs 2023; 79 (12) 4434-4454
• 11 Seys D, Peeters B, Doggen K, Vanhaecht K. The evolving personal, professional and physical impact on healthcare professionals during three COVID-19 waves: a cross-sectional study. Int J Qual Health Care 2022; 34 (03) mzac069
• 12 Arndt BG, Micek MA, Rule A, Shafer CM, Baltus JJ, Sinsky CA. More tethered to the EHR: EHR workload trends among academic primary care physicians, 2019-2023. Ann Fam Med 2024; 22 (01) 12-18
• 13 Holmgren AJ, Downing NL, Tang M, Sharp C, Longhurst C, Huckman RS. Assessing the impact of the COVID-19 pandemic on clinician ambulatory electronic health record use. J Am Med Inform Assoc 2022; 29 (03) 453-460
• 14 Ruan E, Beiser M, Lu V. et al. Physician electronic health record usage as affected by the COVID-19 pandemic. Appl Clin Inform 2022; 13 (04) 785-793
• 15 Hansen MA, Chen R, Hirth J, Langabeer J, Zoorob R. Impact of COVID-19 lockdown on patient-provider electronic communications. J Telemed Telecare 2024; 30 (08) 1285-1292
• 16 Rotenstein LS, Apathy N, Holmgren AJ, Bates DW. Physician note composition patterns and time on the EHR across specialty types: a national, cross-sectional study. J Gen Intern Med 2023; 38 (05) 1119-1126
• 17 Orenstein EW, Kandaswamy S, Muthu N. et al. Alert burden in pediatric hospitals: a cross-sectional analysis of six academic pediatric health systems using novel metrics. J Am Med Inform Assoc 2021; 28 (12) 2654-2660
• 18 Bali AS, Hashash JG, Picco MF, Kinnucan JA, Farraye FA. Electronic health record burden among gastroenterology providers associated with subspecialty and training. Am J Gastroenterol 2023; 118 (07) 1282-1284
• 19 Melnick ER, Ong SY, Fong A. et al. Characterizing physician EHR use with vendor derived data: a feasibility study and cross-sectional analysis. J Am Med Inform Assoc 2021; 28 (07) 1383-1392
• 20 Sim J, Mani K, Fazzari M. et al. Using K-means clustering to identify physician clusters by electronic health record burden and efficiency. Telemed J E Health 2024; 30 (02) 585-594
• 21 Rittenberg E, Liebman JB, Rexrode KM. Primary care physician gender and electronic health record workload. J Gen Intern Med 2022; 37 (13) 3295-3301
• 22 Kokkonen EWJ, Davis SA, Lin H-C, Dabade TS, Feldman SR, Fleischer Jr AB. Use of electronic medical records differs by specialty and office settings. J Am Med Inform Assoc 2013; 20 (e1): e33-e38
• 23 Calvitti A, Hochheiser H, Ashfaq S. et al. Physician activity during outpatient visits and subjective workload. J Biomed Inform 2017; 69: 135-149
• 24 Mani K, Canarick J, Ruan E, Liu J, Kitsis E, Jariwala SP. Effect of telemedicine and the COVID-19 pandemic on medical trainees' usage of the electronic health record in the outpatient setting. Appl Clin Inform 2023; 14 (02) 309-320
• 25 Apathy NC, Rotenstein L, Bates DW, Holmgren AJ. Documentation dynamics: Note composition, burden, and physician efficiency. Health Serv Res 2023; 58 (03) 674-685
• 26 Liu H, Chen J, Dy J, Fu Y. Transforming complex problems into K-means solutions. IEEE Trans Pattern Anal Mach Intell 2023; 45 (07) 9149-9168
• 27 Estiri H, Klann JG, Murphy SN. A clustering approach for detecting implausible observation values in electronic health records data. BMC Med Inform Decis Mak 2019; 19 (01) 142
• 28 Wagstaff K, Cardie C, Rogers S, Schroedl S. Constrained K-means Clustering with Background Knowledge. June 2001. Accessed January 10, 2024 at: https://dl.acm.org/doi/10.5555/645530.655669
• 29 Chatterji P, Li Y. Effects of the COVID-19 pandemic on outpatient providers in the United States. Med Care 2021; 59 (01) 58-61
• 30 Bovonratwet P, Chen AZ, Song J. et al. Telemedicine in spine patients: utilization and satisfaction remain high even after easing of COVID-19 lockdown restrictions. Spine 2024; 49 (03) 208-213
• 31 Gellad ZF, Diamond S, Crockett SD, Cross RK. AGA clinical practice update on telemedicine in gastroenterology: commentary. Gastroenterology 2023; 164 (04) 690-695
• 32 Price DW, Eden AR, Baxley EG, Williamson A, Newton WP. Practice adjustments made by family physicians during the COVID-19 pandemic. J Am Board Fam Med 2022; 35 (02) 274-283
• 33 Khairat S, Burke G, Archambault H, Schwartz T, Larson J, Ratwani RM. Perceived burden of EHRs on physicians at different stages of their career. Appl Clin Inform 2018; 9 (02) 336-347
• 34 Yan Q, Jiang Z, Harbin Z, Tolbert PH, Davies MG. Exploring the relationship between electronic health records and provider burnout: a systematic review. J Am Med Inform Assoc 2021; 28 (05) 1009-1021
• 35 Campione J, Liu H. Perceptions of hospital electronic health record (EHR) training, support, and patient safety by staff position and tenure. BMC Health Serv Res 2024; 24 (01) 955
• 36 Adler-Milstein J, Zhao W, Willard-Grace R, Knox M, Grumbach K. Electronic health records and burnout: time spent on the electronic health record after hours and message volume associated with exhaustion but not with cynicism among primary care clinicians. J Am Med Inform Assoc 2020; 27 (04) 531-538
• 37 Peccoralo LA, Kaplan CA, Pietrzak RH, Charney DS, Ripp JA. The impact of time spent on the electronic health record after work and of clerical work on burnout among clinical faculty. J Am Med Inform Assoc 2021; 28 (05) 938-947
• 38 Akbar F, Mark G, Warton EM. et al. Physicians' electronic inbox work patterns and factors associated with high inbox work duration. J Am Med Inform Assoc 2021; 28 (05) 923-930
• 39 Rotenstein LS, Holmgren AJ, Horn DM. et al. System-level factors and time spent on electronic health records by primary care physicians. JAMA Netw Open 2023; 6 (11) e2344713
• 40 Vos JFJ, Boonstra A, Kooistra A, Seelen M, van Offenbeek M. The influence of electronic health record use on collaboration among medical specialties. BMC Health Serv Res 2020; 20 (01) 676
• 41 Barnett ML, Bitton A, Souza J, Landon BE. Trends in outpatient care for medicare beneficiaries and implications for primary care, 2000 to 2019. Ann Intern Med 2021; 174 (12) 1658-1665
• 42 Doty MM, Tikkanen R, Shah A, Schneider EC. Primary care physicians' role in coordinating medical and health-related social needs in eleven countries. Health Aff (Millwood) 2020; 39 (01) 115-123
• 43 Malacon K, Touponse G, Yoseph E. et al. Gender differences in electronic health record usage among surgeons. JAMA Netw Open 2024; 7 (07) e2421717
• 44 Rotenstein L, Jay Holmgren A. COVID exacerbated the gender disparity in physician electronic health record inbox burden. J Am Med Inform Assoc 2023; 30 (10) 1720-1724
• 45 Apathy NC, Hartman-Hall H, Tran A, Kim DH, Ratwani RM, Marchalik D. Accounting for taste: preferences mediate the relationship between documentation time and ambulatory physician burnout. J Am Med Inform Assoc 2024; 31 (10) 2246-2254
• 46 Li H, Rotenstein L, Jeffery MM. et al. Quantifying EHR and policy factors associated with the gender productivity gap in ambulatory, general internal medicine. J Gen Intern Med 2024; 39 (04) 557-565
• 47 Hitti E, Hadid D, Khoury SJ, Tamim H, Makki M, Karam CM. Domestic tethers: gender differences in career paths and domestic responsibilities of top-research medical school graduates. PLoS One 2022; 17 (04) e0267288
• 48 Starmer AJ, Frintner MP, Matos K, Somberg C, Freed G, Byrne BJ. Gender discrepancies related to pediatrician work-life balance and household responsibilities. Pediatrics 2019; 144 (04) e20182926
• 49 Ly DP, Jena AB. Sex differences in time spent on household activities and care of children among US physicians, 2003-2016. Mayo Clin Proc 2018; 93 (10) 1484-1487
• 50 Holmgren AJ, Hendrix N, Maisel N. et al. Electronic health record usability, satisfaction, and burnout for family physicians. JAMA Netw Open 2024; 7 (08) e2426956
• 51 Moy AJ, Hobensack M, Marshall K. et al. Understanding the perceived role of electronic health records and workflow fragmentation on clinician documentation burden in emergency departments. J Am Med Inform Assoc 2023; 30 (05) 797-808
• 52 Vainiomäki S, Heponiemi T, Vänskä J, Hyppönen H. Tailoring EHRs for specific working environments improves work well-being of physicians. Int J Environ Res Public Health 2020; 17 (13) 4715
• 53 Nguyen OT, Turner K, Apathy NC. et al. Primary care physicians' electronic health record proficiency and efficiency behaviors and time interacting with electronic health records: a quantile regression analysis. J Am Med Inform Assoc 2022; 29 (03) 461-471
• 54 Verma G, Ivanov A, Benn F. et al. Analyses of electronic health records utilization in a large community hospital. PLoS One 2020; 15 (07) e0233004
• 55 Melnick ER, Dyrbye LN, Sinsky CA. et al. The association between perceived electronic health record usability and professional burnout among US physicians. Mayo Clin Proc 2020; 95 (03) 476-487
• 56 Melnick ER, Harry E, Sinsky CA. et al. Perceived electronic health record usability as a predictor of task load and burnout among US physicians: mediation analysis. J Med Internet Res 2020; 22 (12) e23382
• 57 Eschenroeder HC, Manzione LC, Adler-Milstein J. et al. Associations of physician burnout with organizational electronic health record support and after-hours charting. J Am Med Inform Assoc 2021; 28 (05) 960-966
• 58 Patel R, Yang Y, Lin F-C. et al. Descriptive analysis of documentation time for the national developmental-behavioral pediatric physician workforce using a commercial electronic health record system. J Dev Behav Pediatr 2023; 44 (05) e365-e369
• 59 Boyd AD, Gonzalez-Guarda R, Lawrence K. et al. Potential bias and lack of generalizability in electronic health record data: reflections on health equity from the National Institutes of Health Pragmatic Trials Collaboratory. J Am Med Inform Assoc 2023; 30 (09) 1561-1566
• 60 Wong ZS-Y, Rigby M. Identifying and addressing digital health risks associated with emergency pandemic response: problem identification, scoping review, and directions toward evidence-based evaluation. Int J Med Inform 2022; 157: 104639
• 61 Acacio-Claro PJ, Justina Estuar MR, Villamor DA, Bautista MC, Sugon Jr. Q, Pulmano C. A micro-analysis approach in understanding electronic medical record usage in rural communities: comparison of frequency of use on performance before and during the COVID-19 pandemic. Procedia Comput Sci 2022; 196: 572-580
• 62 Madhavan S, Bastarache L, Brown JS. et al. Use of electronic health records to support a public health response to the COVID-19 pandemic in the United States: a perspective from 15 academic medical centers. J Am Med Inform Assoc 2021; 28 (02) 393-401
• 63 Smith L, Kirk W, Bennett MM, Youens K, Ramm J. From headache to handled: advanced in-basket management system in primary care clinics reduces provider workload burden and self-reported burnout. Appl Clin Inform 2024; 15 (05) 869-876
• 64 Sieja A, Markley K, Pell J. et al. Optimization sprints: improving clinician satisfaction and teamwork by rapidly reducing electronic health record burden. Mayo Clin Proc 2019; 94 (05) 793-802
• 65 Lourie EM, Utidjian LH, Ricci MF, Webster L, Young C, Grenfell SM. Reducing electronic health record-related burnout in providers through a personalized efficiency improvement program. J Am Med Inform Assoc 2021; 28 (05) 931-937