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

• Published in: BMJ open 2020-01, Vol.10 (1), p.e031622-e031622
• Main Authors: Ng, Sheryl Hui Xian, Rahman, Nabilah, Ang, Ian Yi Han, Sridharan, Srinath, Ramachandran, Sravan, Wang, Debby Dan, Khoo, Astrid, Tan, Chuen Seng, Feng, Mengling, Toh, Sue-Anne Ee Shiow, Tan, Xin Quan
• Format: Article
• Language: English
• Subjects: Adult; Aged; Algorithms; Cohort analysis; Expenditures; Female; Government subsidies; Health Care Costs - statistics & numerical data; Health Services - economics; Health Services Research; healthcare costs; high utiliser; Hospitals; Humans; Intervention; Machine Learning; Male; Middle Aged; Patient Acceptance of Health Care - statistics & numerical data; Patients; Performance evaluation; persistence; Population; Retrospective Studies; Singapore
• ISSN: 2044-6055; 2044-6055
• DOI: 10.1136/bmjopen-2019-031622

ObjectiveWe 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 settingThis is a retrospective cohort study using administrative data from an Academic Medical Centre (AMC) in Singapore.ParticipantsPatients 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 measuresPHU 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.ResultsPHUs 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%).ConclusionsThe 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.