Search research articles

Search research articles

Related Experiment Videos

Integrating the Hospital Frailty Risk Score into Explainable Machine Learning to Predict Mortality in Older Adults

Yeny Concha-Cisternas^1,2, Eduardo Guzmán-Muñoz³, Manuel Vásquez-Muñoz^4,5

¹Escuela de Kinesiología, Facultad de Salud, Universidad Santo Tomás, Talca 3460000, Chile.

Diagnostics (Basel, Switzerland)

|May 27, 2026

Related Concept Videos

Pneumonia III: Complications and Assessment

Pneumonia III: Complications and Assessment

Pneumonia poses the potential for numerous complications that warrant consideration. These complications include the following:

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Agreement and Reliability of the G-Force System: Force Plate and Load Cell for the Isometric Mid-Thigh Pull in Physically Active Adults: A Repeated-Measures Method-Comparison Study.

Sensors (Basel, Switzerland)·2026

Same author

Link between physical activity, nutrition, and antimicrobial pharmacokinetics and therapeutic efficacy: Implications for resistance management.

SAGE open medicine·2026

Same author

Body fat estimation in the Mexican women's national soccer team: a cross-sectional agreement study between a derived Mexican Football Federation anthropometric equation and dual-energy X-ray absorptiometry.

Journal of the International Society of Sports Nutrition·2026

Same author

Physical Activity as a Mediator of the Relationship Between Mediterranean Diet Adherence and Anxiety Symptoms in Chilean Adolescents: A Cross-Sectional Study.

Children (Basel, Switzerland)·2026

Same author

Associations of Physical Fitness and Postural Balance with Psychosocial Well-Being in Early Adolescents: A School-Based Cross-Sectional Study.

Healthcare (Basel, Switzerland)·2026

Same author

Relationship Between Standing Long Jump Performance and Health-Related Indicators and Lifestyle Factors in Chilean Adolescents: A Cross-Sectional Study.

Healthcare (Basel, Switzerland)·2026

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Summary

Machine learning models integrating the Hospital Frailty Risk Score (HFRS) accurately predict mortality in older adults with community-acquired pneumonia (CAP). Frailty is the primary risk factor, enabling early patient stratification using hospital data.

Area of Science:

Gerontology
Computational Medicine
Public Health

Background:

Community-acquired pneumonia (CAP) poses a significant mortality risk for older adults.
Traditional prognostic scores may not adequately assess risk in frail individuals.
Explainable machine learning offers potential for improved risk prediction.

Purpose of the Study:

To develop and validate explainable machine learning models for predicting in-hospital mortality in older adults with CAP.
To integrate the administrative Hospital Frailty Risk Score (HFRS) into predictive models.
To compare the performance of machine learning models against traditional methods.

Main Methods:

Retrospective cohort study of 58,306 hospitalizations in adults aged ≥60 years in Chile.

Keywords:

community-acquired pneumonia frailty hospital frailty risk score machine learning mortality prediction

Related Experiment Videos

Trained 14 supervised machine learning algorithms using age, sex, HFRS, Charlson Comorbidity Index, and length of stay.

Evaluated models using AUC-ROC and SHAP values for predictor importance.

Main Results:

The Extra Trees classifier achieved the highest performance (AUC-ROC 0.862), significantly outperforming logistic regression (0.642).
Hospital Frailty Risk Score (HFRS) was the most influential predictor of mortality.
Length of stay, age, and comorbidities also contributed to risk prediction.

Conclusions:

Ensemble tree-based models incorporating HFRS demonstrate superior mortality prediction in older adults with CAP.
Frailty, as measured by HFRS, is a critical determinant of mortality risk.
Routinely available hospital data can be leveraged for scalable early risk stratification.