Search research articles

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

Related Concept Videos

Alzheimer's Disease: Overview

Alzheimer's Disease: Overview

Alzheimer's Disease (AD) is a continually advancing neurodegenerative disorder, distinguished by escalating memory loss, cognitive dysfunction, and dementia. The disease unfolds in three stages: preclinical, mild cognitive impairment (MCI), and dementia. Its onset is insidious, and the progression gradual, with the cause not well explained by other disorders.
The clinical diagnosis of AD hinges on the presence of memory and other cognitive impairments. Biomarkers, such as changes in Aβ...

You might also read

Related Articles

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

Sort by

Same author

Detecting multimorbidity patterns in Alzheimer's disease using unsupervised machine learning: A nationwide emergency department study (2007-2022).

Journal of Alzheimer's disease : JAD·2026

Same author

Flagging high-risk comorbidities in Alzheimer's disease emergency department visits: A machine learning analysis of mortality outcomes.

Journal of Alzheimer's disease : JAD·2026

Same author

Red-flagging multimorbidity clusters for Alzheimer's disease risk using explainable machine learning: Evidence from a national emergency department sample.

Journal of Alzheimer's disease reports·2025

Same author

Reinforcement learning at the interface of artificial intelligence and cognitive science.

Neuroscience·2025

Same author

Quo Vadis, AI-Empowered Doctor?

JMIR medical education·2025

Same author

Quo vadis, "AI-empowered Doctor"?

JMIR medical education·2025

Same journal

The Association Between Active Aging and Health-Related Quality of Life.

Geriatrics (Basel, Switzerland)·2026

Same journal

From Complexity to Competency: International Nursing Perspectives on Comprehensive Geriatric Assessment.

Geriatrics (Basel, Switzerland)·2026

Same journal

Breaking the Vicious Cycle? A Systematic Review of Interventions Targeting Both Falls and Fear of Falling in Older Adults.

Geriatrics (Basel, Switzerland)·2026

Same journal

Sensory Blurring in Nociplastic Pain: The Role of Descending Inhibitory Dysfunction and Gut-Brain Axis Alterations in Older Adults.

Geriatrics (Basel, Switzerland)·2026

Same journal

The Impact of General Anesthetics on Postoperative Delirium: A Narrative Review Based on Clinical Randomized Controlled Trials from the Last Five Years.

Geriatrics (Basel, Switzerland)·2026

Same journal

Safety of Cholecystectomy in Nonagenarians: A Systematic Review and Meta-Analysis.

Geriatrics (Basel, Switzerland)·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Mar 25, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Risk Stratification for In-Hospital Mortality in Alzheimer's Disease Using Interpretable Regression and Explainable

Tursun Alkam¹, Ebrahim Tarshizi¹, Andrew H Van Benschoten¹

¹Master's Program of Applied Artificial Intelligence, University of San Diego, San Diego, CA 92110, USA.

Geriatrics (Basel, Switzerland)

|March 24, 2026

Summary

This summary is machine-generated.

Predicting in-hospital mortality for older adults with Alzheimer's disease (AD) is crucial. Machine learning and regression models identified key risk factors, offering improved patient care strategies.

Keywords:

Alzheimer’s disease SHAP XGBoost comorbidities explainable AI in-hospital mortality logistic regression risk prediction

More Related Videos

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Related Experiment Videos

Last Updated: Mar 25, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Area of Science:

Gerontology
Computational Medicine
Health Services Research

Background:

Older adults with Alzheimer's disease (AD) have a higher risk of adverse hospital outcomes, including mortality.
Early identification of high-risk AD patients is challenging.
Traditional regression models may miss complex interactions discoverable by machine learning.

Purpose of the Study:

To identify key predictors of in-hospital mortality in hospitalized Alzheimer's disease (AD) patients.
To compare the predictive performance of survey-weighted logistic regression and explainable machine learning (XGBoost).

Main Methods:

Analysis of hospitalizations among AD patients aged ≥60 using the 2017 Nationwide Inpatient Sample (NIS).
Utilized survey-weighted logistic regression and XGBoost with hospital-grouped cross-validation.
Assessed model performance using AUROC, AUPRC, Brier score, and log loss; evaluated feature importance with adjusted odds ratios and SHAP values.

Main Results:

XGBoost demonstrated slightly superior performance (AUROC 0.887, AUPRC 0.324) compared to logistic regression (AUROC 0.879, AUPRC 0.310).
Key predictors in the full model included palliative care, acute respiratory failure, DNR status, and sepsis.
Explainable AI (SHAP) highlighted dysphagia, malnutrition, and pressure ulcers, and identified actionable physiological and frailty-related features in models excluding end-of-life indicators.

Conclusions:

Combining regression and explainable machine learning provides robust mortality risk stratification for hospitalized AD patients.
Models excluding end-of-life indicators offer actionable insights for risk prediction when such documentation is unavailable.
The findings support improved resource allocation and goals-of-care discussions in AD patient management.