Truace
Subscribe

An application of random forest regression for predicting healthcare costs using administrative databases

Background Accurate healthcare cost predictions are essential for health economic decision-making. We propose a bottom-up approach that aggregates individual-level predictions to estimate expenditures for specific population segments without relying on a priori segmentation. Methods This retrospective population-based study used administrative healthcare data (2011-2023) from the Health Protection Agency of Bergamo (Italy). We traced 5-year healthcare resource utilization to predict individual's healthcare costs…

By the Truvace desk1 min read1 sourcePeer-reviewedTRV-2026-1163· cite & verify
An application of random forest regression for predicting healthcare costs using administrative databases
PREDICTING U.S. ARMY FIRST-TERM ATTRITION AFTER INITIAL ENTRY TRAINING by Speten, Karey J.. Public domain

In brief

Background Accurate healthcare cost predictions are essential for health economic decision-making. We propose a bottom-up approach that aggregates individual-level predictions to estimate expenditures for specific population segments without relying on a priori segmentation.

We traced 5-year healthcare resource utilization to predict individual's healthcare costs in the following year using random forest regression algorithms. Results At the individual-level, algorithms had a poor performance, systematically underestimating high-cost users.

Main points

  1. Background Accurate healthcare cost predictions are essential for health economic decision-making.
  2. We propose a bottom-up approach that aggregates individual-level predictions to estimate expenditures for specific population segments without relying on a priori segmentation.
  3. Methods This retrospective population-based study used administrative healthcare data (2011-2023) from the Health Protection Agency of Bergamo (Italy).

The problem

An application of random forest regression for predicting healthcare costs using administrative databases: Performance was assessed at the individual-level using error metrics, and at the population-level using prediction error (PE).

The rundown

Methods This retrospective population-based study used administrative healthcare data (2011-2023) from the Health Protection Agency of Bergamo (Italy). We traced 5-year healthcare resource utilization to predict individual's healthcare costs in the following year using random forest regression algorithms.

Sources

  1. Peer-reviewedExpert Review of Pharmacoeconomics & Outcomes Research2026-09-21

The debate