Nonlinear Association of Length of Stay with In-Hospital Mortality in Alzheimer’s Disease Hospitalizations: Admission-Only vs. Inpatient-Course Prediction Using Explainable Machine Learning

Tursun Alkam, Ebrahim Tarshizi, Andrew H. Van Benschoten · 2026

Read Nonlinear Association of Length of Stay with In-Hospital Mortality in Alzheimer’s Disease Hospitalizations: Admission-Only vs. Inpatient-Course Prediction Using Explainable Machine Learning by Tursun Alkam, Ebrahim Tarshizi, Andrew H. Van Benschoten (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/pmc-13600026.txt.

Description

Tursun Alkam, Ebrahim Tarshizi, and Andrew Van Benschoten ask whether a longer hospital stay protects or endangers Alzheimer's patients, using 249,507 admissions from a 2017 national database. Their 2026 study finds 12,666 in-hospital deaths, about five percent overall. Raw death rates traced a U-shape across stay length: worst on day one, best at four to six days, rising again past three weeks.

After adjustment, the pattern flipped: predicted mortality eased steadily as modeled stay grew. Two prediction models were compared, one using admission data only and one adding stay length, procedure count, and charges. The richer model scored clearly better on both accuracy measures. Sepsis, kidney injury, age, stroke, and pneumonia predicted death in both. The authors warn that stay length mixes cause and effect, and read it with care.

Catalog record

CREATORTursun Alkam, Ebrahim Tarshizi, Andrew H. Van Benschoten
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE30 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13600026

Browse the full library · About the Tower of Babel