Skip to content
Home » News » Cornell tool predicts hospitalizations, long-term health costs

Cornell tool predicts hospitalizations, long-term health costs

Cornell tool predicts hospitalizations, long-term health costs

A Cornell-developed measure of chronic health conditions predicted hospitalizations and health care costs for as long as five years, potentially helping medical systems identify patients who need additional care.

The Charlson Comorbidity Health Analytics tool evaluates 38 chronic conditions and assigns a score based on their seriousness, according to a study published June 29 in PLOS ONE.


Researchers tested the tool using six years of anonymized claims data from more than 27,000 Weill Cornell Medicine employees and dependents.

Among adults with a score of zero in 2016, 1.2% were hospitalized that year. The hospitalization rate rose to 61% for people with scores of eight or higher.

Average annual spending also increased with the scores, from $3,835 for patients with no measured comorbidity to $53,189 for those scoring eight or higher. Patients with scores of five or more made up 4.3% of the group but accounted for 17.5% of spending.

Researchers said the measure outperformed prior hospitalization history in predicting admissions and performed better than previous costs alone in forecasting future spending.

The team is testing whether longer primary care visits and added support for high-needs patients can prevent unplanned hospitalizations.



Categories: NewsHealth