Machine learning for predicting institutionalization and mortality risks among older home care recipients with routinely collected need assessment data: explainable AI for long-term care
Hongsoo Kim, Jimin Yoon, Hyerim Noh, Sunghun Yun, Seungyeon Chun, Woojoo Lee · 2026
Read Machine learning for predicting institutionalization and mortality risks among older home care recipients with routinely collected need assessment data: explainable AI for long-term care by Hongsoo Kim, Jimin Yoon, Hyerim Noh, Sunghun Yun, Seungyeon Chun, Woojoo Lee (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/PMC13560349.txt.
Description
Hongsoo Kim and colleagues develop explainable machine learning to predict which older home care recipients will move into institutions or die, using routine needs-assessment data from Korea's long-term care insurance. Their 2026 study covers 36,526 newly enrolled beneficiaries. Four models vied in a setup treating the two ends as rivals.
Within six months, 10.4 percent of recipients had entered facilities, rising to 18.8 percent by twelve months in the reported figures. A penalized regression model did best overall. Its strongest move-in signals were striking: eating nonfood items, a marker of advanced dementia, suctioning needs, and a dementia label. Death was best flagged by oxygen therapy, cancer pain care, and diabetic foot care. The authors propose embedding the algorithm in assessment workflows so care workers can aim preventive services at those likeliest to lose home care.
Catalog record
| CREATOR | Hongsoo Kim, Jimin Yoon, Hyerim Noh, Sunghun Yun, Seungyeon Chun, Woojoo Lee |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47615 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |