Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Ensemble Machine Learning Models for Predicting Death in Post-Acute Skilled Nursing Facilities.

Anupam Chandra1, Paul Y Takahashi1, Parvez A Rahman2

  • 1Division of Community Internal Medicine, Geriatrics, and Palliative Care, Mayo Clinic, Rochester, MN, USA.

Journal of the American Medical Directors Association
|April 18, 2026
PubMed
Summary

Related Concept Videos

Mechanistic Models: Compartment Models in Individual and Population Analysis01:23

Mechanistic Models: Compartment Models in Individual and Population Analysis

342
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
342
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

415
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
415

You might also read

Related Articles

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

Sort by
Same author

Financial Comparison of Single- vs 2-Stage Management of Bile Duct Stones.

JAMA surgery·2026
Same author

Understanding what motivates job choices among registered nurses: A discrete choice experiment study.

Nursing outlook·2026
Same author

Real-World Health Care Resource Utilization and Economic Burden Among Patients with Idiopathic Pulmonary Fibrosis in Commercially Insured and Medicare Advantage Populations in the United States.

Journal of health economics and outcomes research·2026
Same author

Digitally enriching a screening population for pancreatic cancer using routine blood-based measures and clinical histories.

ArXiv·2026
Same author

Predicting Treatment Response After Total Neoadjuvant Therapy for Locally Advanced Rectal Cancer.

Annals of surgery·2026
Same author

Real-World Economic Burden Associated with Progressive Pulmonary Fibrosis in the US: An Administrative Claims Database Analysis.

PharmacoEconomics·2026

Machine learning models accurately predict death within 180 days for patients discharged to skilled nursing facilities (SNFs). These tools can aid in risk stratification and patient-centered care discussions.

Area of Science:

  • Medical Informatics
  • Machine Learning in Healthcare
  • Predictive Analytics

Background:

  • Patients discharged to skilled nursing facilities (SNFs) face a high risk of adverse outcomes, including mortality.
  • Accurate prediction of mortality is crucial for effective post-acute care planning.

Purpose of the Study:

  • To develop and validate machine learning (ML) models for predicting death within 30 or 180 days post-discharge to SNFs.
  • To identify high-risk patients needing targeted interventions and support.

Main Methods:

  • Retrospective cohort study involving 7103 SNF admissions from Mayo Clinic.
  • Ensemble ML models (random forest, gradient boosting variants) were trained using supervised learning.
  • Model performance was evaluated using Area Under the Curve (AUC) with 10-fold cross-validation.
Keywords:
Machine learningmortalityskilled nursing facility

Related Experiment Videos

Main Results:

  • The developed ML models demonstrated strong predictive performance.
  • AUCs were 0.84 for 30-day mortality and 0.82 for 180-day mortality.
  • 4.7% of patients died within 30 days, and 18.7% died within 180 days.

Conclusions:

  • Robust ML models were successfully developed to predict mortality after SNF discharge.
  • These models can support risk-stratified, patient-centered care and facilitate advance care planning.
  • Further external validation is recommended for broader clinical implementation.