AI Science Tracker
EN

Estimating heterogeneous impacts Of subsidised health insurance: A causal machine learning approach

Centre for Health Economics, University of York, York, England, United Kingdom; The CHOICE Institute, School of Pharmacy, University of Washington, Seattle, Washington, United States of America · 29 Sep 2025 · medicine

Discovery

Estimating heterogeneous impacts Of subsidised health insurance: A causal machine learning approach

Source check: Source checked. Not independent scientific confirmation.

Finding: Causal-forest analysis of a nationally representative Indonesian survey estimated heterogeneous associations between subsidized JKN insurance and healthcare use. Average utilization was higher among insured respondents, while estimated outpatient participation effects were negative for about one-fifth of the sample. The cross-sectional observational design relies on measured covariates and does not establish randomized causal effects.

Technology: Causal forests estimate heterogeneous treatment effects; super-learner nuisance models and a two-part outcome model separate seeking care from care consumed. Sample splitting, cross-fitting, and doubly robust scores are used.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
Causal forests estimate heterogeneous treatment effects; super-learner nuisance models and a two-part outcome model separate seeking care from care consumed. Sample splitting, cross-fitting, and doubly robust scores are used.
Test and result
Causal forests, cross-fitting and doubly robust scores were applied to 912,812 respondents in the 2017 SUSENAS survey.
Limitation / still unknown
Observational estimates depend on measured-confounder assumptions and do not establish effects under random assignment.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0315057

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary full text, including Methods and Results; publication date and first result-bearing version checked..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse medicine discoveries.