Machine learning–optimized discharge timing in typhoid care: Implications for clinical outcomes, cost efficiency, and health system performance

Shekoofeh Sadat Momahhed, Atefehsadat Haghighathoseini · 2026

Read Machine learning–optimized discharge timing in typhoid care: Implications for clinical outcomes, cost efficiency, and health system performance by Shekoofeh Sadat Momahhed, Atefehsadat Haghighathoseini (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0354148.txt.

Description

Momahhed and Haghighathoseini, in a 2026 study of Iranian insurance claims, build a machine learning model to spot typhoid patients who stay in hospital longer than they need to. Long stays cost patients and systems, and in Iran's split insurance system patients pay much of the bill themselves. Claims for one year were grouped into about thirteen thousand hospital stays.

The model sorted patients well, beating a standard statistical method. It flagged more than a third of stays as potentially shorter, adding up to thousands of recoverable bed-days subject to clinical review. In a costed subset, earlier discharge cut spending by nearly a quarter, and most savings landed with patients as lower out-of-pocket payments. Freed beds could take well over a thousand extra admissions. The strongest predictor of a long stay was not illness severity but the patient's insurance class, a structural flaw the authors highlight.

Catalog record

CREATORShekoofeh Sadat Momahhed, Atefehsadat Haghighathoseini
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE175012
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0354148

Browse the full library · About the Tower of Babel