دورية أكاديمية
أعرض في EDS

Characterising and predicting persistent high-cost utilisers in healthcare: a retrospective cohort study in Singapore.

التفاصيل البيبلوغرافية
العنوان: Characterising and predicting persistent high-cost utilisers in healthcare: a retrospective cohort study in Singapore.
المؤلفون: Ng SHX; Saw Swee Hock School of Public Health, National University of Singapore, Singapore, Singapore.; Regional Health System Office, National University Health System, Singapore, Singapore., Rahman N; Saw Swee Hock School of Public Health, National University of Singapore, Singapore, Singapore.; Regional Health System Office, National University Health System, Singapore, Singapore., Ang IYH; Saw Swee Hock School of Public Health, National University of Singapore, Singapore, Singapore.; Regional Health System Office, National University Health System, Singapore, Singapore., Sridharan S; Saw Swee Hock School of Public Health, National University of Singapore, Singapore, Singapore., Ramachandran S; Saw Swee Hock School of Public Health, National University of Singapore, Singapore, Singapore., Wang DD; Saw Swee Hock School of Public Health, National University of Singapore, Singapore, Singapore., Khoo A; Regional Health System Office, National University Health System, Singapore, Singapore., Tan CS; Saw Swee Hock School of Public Health, National University of Singapore, Singapore, Singapore., Feng M; Saw Swee Hock School of Public Health, National University of Singapore, Singapore, Singapore., Toh SES; Regional Health System Office, National University Health System, Singapore, Singapore.; Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.; Singapore Population Health Improvement Centre (SPHERiC), National University Health System, Singapore, Singapore., Tan XQ; Saw Swee Hock School of Public Health, National University of Singapore, Singapore, Singapore kyletanxq@gmail.com.; Regional Health System Office, National University Health System, Singapore, Singapore.
المصدر: BMJ open [BMJ Open] 2020 Jan 06; Vol. 10 (1), pp. e031622. Date of Electronic Publication: 2020 Jan 06.
نوع المنشور: Journal Article; Research Support, Non-U.S. Gov't
اللغة: English
بيانات الدورية: Publisher: BMJ Publishing Group Ltd Country of Publication: England NLM ID: 101552874 Publication Model: Electronic Cited Medium: Internet ISSN: 2044-6055 (Electronic) Linking ISSN: 20446055 NLM ISO Abbreviation: BMJ Open Subsets: MEDLINE
أسماء مطبوعة: Original Publication: [London] : BMJ Publishing Group Ltd, 2011-
مواضيع طبية MeSH: Machine Learning*, Health Care Costs/*statistics & numerical data , Health Services/*economics , Patient Acceptance of Health Care/*statistics & numerical data, Adult ; Aged ; Female ; Humans ; Male ; Middle Aged ; Retrospective Studies ; Singapore
مستخلص: Objective: We aim to characterise persistent high utilisers (PHUs) of healthcare services, and correspondingly, transient high utilisers (THUs) and non-high utilisers (non-HUs) for comparison, to facilitate stratifying HUs for targeted intervention. Subsequently we apply machine learning algorithms to predict which HUs will persist as PHUs, to inform future trials testing the effectiveness of interventions in reducing healthcare utilisation in PHUs.
Design and Setting: This is a retrospective cohort study using administrative data from an Academic Medical Centre (AMC) in Singapore.
Participants: Patients who had at least one inpatient admission to the AMC between 2005 and 2013 were included in this study. HUs incurred Singapore Dollar 8150 or more within a year. PHUs were defined as HUs for three consecutive years, while THUs were HUs for 1 or 2 years. Non-HUs did not incur high healthcare costs at any point during the study period.
Outcome Measures: PHU status at the end of the third year was the outcome of interest. Socio-demographic profiles, clinical complexity and utilisation metrics of each group were reported. Area under curve (AUC) was used to identify the best model to predict persistence.
Results: PHUs were older and had higher comorbidity and mortality. Over the three observed years, PHUs' expenditure generally increased, while THUs and non-HUs' spending and inpatient utilisation decreased. The predictive model exhibited good performance during both internal (AUC: 83.2%, 95% CI: 82.2% to 84.2%) and external validation (AUC: 79.8%, 95% CI: 78.8% to 80.8%).
Conclusions: The HU population could be stratified into PHUs and THUs, with distinctly different utilisation trajectories. We developed a model that could predict at the end of 1 year, whether a patient in our population will continue to be a HU in the next 2 years. This knowledge would allow healthcare providers to target PHUs in our health system with interventions in a cost-effective manner.
Competing Interests: Competing interests: None declared.
(© Author(s) (or their employer(s)) 2020. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)
References: Health Aff (Millwood). 2015 Aug;34(8):1312-9. (PMID: 26240244)
Nat Methods. 2018 Apr;15(4):233-234. (PMID: 30100822)
Health Aff (Millwood). 2007 May-Jun;26(3):808-16. (PMID: 17485760)
Health Serv Res. 2018 Oct;53(5):3898-3916. (PMID: 29862504)
Int J Environ Res Public Health. 2017 Nov 24;14(12):. (PMID: 29186782)
BMJ Open. 2018 Sep 8;8(9):e023113. (PMID: 30196269)
CMAJ Open. 2015 Jan 13;3(1):E111-8. (PMID: 25844363)
Health Serv Res. 2016 Feb;51(1):205-19. (PMID: 25989510)
Biomed Eng Online. 2018 Nov 20;17(Suppl 1):131. (PMID: 30458798)
Med Care. 2013 Mar;51(3):251-8. (PMID: 23269109)
Biometrics. 1988 Sep;44(3):837-45. (PMID: 3203132)
Healthc Policy. 2013 Aug;9(1):44-51. (PMID: 23968673)
JMIR Med Inform. 2018 Dec 21;6(4):e10933. (PMID: 30578188)
CMAJ. 2016 Feb 16;188(3):182-188. (PMID: 26755672)
Am J Med. 2017 May;130(5):601.e17-601.e22. (PMID: 28065773)
Med Care Res Rev. 2015 Jun;72(3):277-97. (PMID: 25701579)
Health Aff (Millwood). 2019 Jan;38(1):107-114. (PMID: 30615516)
BMJ Open. 2017 Jan 11;7(1):e011580. (PMID: 28077408)
Popul Health Manag. 2015 Dec;18(6):467-76. (PMID: 26102363)
Dtsch Arztebl Int. 2010 May;107(19):343-8. (PMID: 20532129)
BMC Health Serv Res. 2018 Jan 30;18(1):65. (PMID: 29382327)
Health Aff (Millwood). 2016 May 1;35(5):769-75. (PMID: 27140981)
Med Care. 2016 Sep;54(9):860-7. (PMID: 27219632)
Evolution. 1989 Jan;43(1):223-225. (PMID: 28568501)
J Palliat Med. 2016 Sep;19(9):995-1008. (PMID: 27533892)
Prev Chronic Dis. 2015 Nov 12;12:E197. (PMID: 26564013)
Int J Health Plann Manage. 2017 Jan;32(1):36-49. (PMID: 26119067)
BMJ Open. 2019 May 22;9(5):e027220. (PMID: 31122989)
Comput Biol Med. 2014 Oct;53:9-18. (PMID: 25105749)
Soc Sci Med. 2018 Aug;211:147-156. (PMID: 29936332)
Eur J Public Health. 2016 Aug;26(4):549-55. (PMID: 26850904)
JAMA. 2009 Feb 11;301(6):603-18. (PMID: 19211468)
Am J Manag Care. 2015 Apr;21(4):309-16. (PMID: 26014469)
Inquiry. 2009-2010 Winter;46(4):405-17. (PMID: 20184167)
Med Care Res Rev. 2019 Apr 26;:1077558719845722. (PMID: 31027455)
J Am Geriatr Soc. 2018 May;66(5):1002-1008. (PMID: 29427509)
Med Care. 2016 Sep;54(9):852-9. (PMID: 27326548)
فهرسة مساهمة: Keywords: healthcare costs; high utiliser; machine learning; persistence
تواريخ الأحداث: Date Created: 20200109 Date Completed: 20210210 Latest Revision: 20210210
رمز التحديث: 20240829
مُعرف محوري في PubMed: PMC6955475
DOI: 10.1136/bmjopen-2019-031622
PMID: 31911514
قاعدة البيانات: MEDLINE
الوصف
تدمد:2044-6055
DOI:10.1136/bmjopen-2019-031622