Dataset Information

Machine-learning-based prediction models for high-need high-cost patients using nationwide clinical and claims data.

ABSTRACT: High-need, high-cost (HNHC) patients-usually defined as those who account for the top 5% of annual healthcare costs-use as much as half of the total healthcare costs. Accurately predicting future HNHC patients and designing targeted interventions for them has the potential to effectively control rapidly growing healthcare expenditures. To achieve this goal, we used a nationally representative random sample of the working-age population who underwent a screening program in Japan in 2013-2016, and developed five machine-learning-based prediction models for HNHC patients in the subsequent year. Predictors include demographics, blood pressure, laboratory tests (e.g., HbA1c, LDL-C, and AST), survey responses (e.g., smoking status, medications, and past medical history), and annual healthcare cost in the prior year. Our prediction models for HNHC patients combining clinical data from the national screening program with claims data showed a c-statistics of 0.84 (95%CI, 0.83-0.86), and overperformed traditional prediction models relying only on claims data.

SUBMITTER: Osawa I

PROVIDER: S-EPMC7658979 | biostudies-literature | 2020 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine-learning-based prediction models for high-need high-cost patients using nationwide clinical and claims data.

Osawa Itsuki I Goto Tadahiro T Yamamoto Yuji Y Tsugawa Yusuke Y

NPJ digital medicine 20201111 1

High-need, high-cost (HNHC) patients-usually defined as those who account for the top 5% of annual healthcare costs-use as much as half of the total healthcare costs. Accurately predicting future HNHC patients and designing targeted interventions for them has the potential to effectively control rapidly growing healthcare expenditures. To achieve this goal, we used a nationally representative random sample of the working-age population who underwent a screening program in Japan in 2013-2016, and ...[more]

PMID: 33299137

Similar Datasets

Project description:BackgroundIn an effort to improve both quality of care and cost-effectiveness, various care-management programmes have been developed for high-need high-cost (HNHC) patients. Early identification of patients at risk of becoming HNHC (i.e. case finding) is crucial to a programme's success. We aim to systematically identify prediction models predicting future HNHC healthcare use in adults, to describe their predictive performance and to assess their applicability.MethodsOvid MEDLINE® All, EMBASE, CINAHL, Web of Science and Google Scholar were systematically searched from inception through January 31, 2021. Risk of bias and methodological quality assessment was performed through the Prediction model Risk Of Bias Assessment Tool (PROBAST).ResultsOf 5890 studies, 60 studies met inclusion criteria. Within these studies, 313 unique models were presented using a median development cohort size of 20,248 patients (IQR 5601-174,242). Predictors were derived from a combination of data sources, most often claims data (n = 37; 62%) and patient survey data (n = 29; 48%). Most studies (n = 36; 60%) estimated patients' risk to become part of some top percentage of the cost distribution (top-1-20%) within a mean time horizon of 16 months (range 12-60). Five studies (8%) predicted HNHC persistence over multiple years. Model validation was performed in 45 studies (76%). Model performance in terms of both calibration and discrimination was reported in 14 studies (23%). Overall risk of bias was rated as 'high' in 40 studies (67%), mostly due to a 'high' risk of bias in the subdomain 'Analysis' (n = 37; 62%).DiscussionThis is the first systematic review (PROSPERO CRD42020164734) of non-proprietary prognostic models predicting HNHC healthcare use. Meta-analysis was not possible due to heterogeneity. Most identified models estimated a patient's risk to incur high healthcare expenditure during the subsequent year. However, case-finding strategies for HNHC care-management programmes are best informed by a model predicting HNHC persistence. Therefore, future studies should not only focus on validating and extending existing models, but also concentrate on clinical usefulness.

Dataset Information

Machine-learning-based prediction models for high-need high-cost patients using nationwide clinical and claims data.

Publications

Machine-learning-based prediction models for high-need high-cost patients using nationwide clinical and claims data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets