Long‐Term Mortality Predictors Using a Machine‐Learning Approach in Patients With Chronic Limb‐Threatening Ischemia After Peripheral Vascular Intervention

Topic: Risk, prevention and care in population studies

Patients with CLTI undergoing peripheral vascular intervention from 2017 to 2018 were derived from the Medicare-linked VQI (Vascular Quality Initiative) registry. We constructed a random survival forest to rank 66 preprocedural variables according to their relative importance and mean minimal depth for 3-year all-cause mortality. A random survival forest of 2000 trees was built using a training sample (80% of the cohort). Accuracy was assessed in a testing sample (20%) using continuous ranked probability score, Harrell C-index, and out-of-bag error rate. A total of 10 114 patients were included (mean±SD age, 72.0±11.0 years; 59% men). The 3-year mortality rate was 39.1%, with a median survival of 1.4 years (interquartile range, 0.7-2.0 years). The most predictive variables were chronic kidney disease, age, congestive heart failure, dementia, arrhythmias, requiring assisted care, living at home, and body mass index. A total of 41 variables spanning all domains of the biopsychosocial model were ranked as mortality predictors. The accuracy of the model was excellent (continuous ranked probability score, 0.172; Harrell C-index, 0.70; out-of-bag error rate, 29.7%). Our random survival forest accurately predicts long-term CLTI mortality, which is driven by demographic, functional, behavioral, and medical comorbidities. Broadening frameworks of risk and refining health care plans to include multidimensional risk factors could improve individualized care for CLTI.

Key findings

• Patients with CLTI undergoing peripheral vascular intervention from 2017 to 2018 were derived from the Medicare-linked VQI (Vascular Quality Initiative) registry.
• We constructed a random survival forest to rank 66 preprocedural variables according to their relative importance and mean minimal depth for 3-year all-cause mortality.
• A random survival forest of 2000 trees was built using a training sample (80% of the cohort).
• Accuracy was assessed in a testing sample (20%) using continuous ranked probability score, Harrell C-index, and out-of-bag error rate.
• A total of 10 114 patients were included (mean±SD age, 72.0±11.0 years; 59% men).

Why it matters

In patients with chronic limb-threatening ischemia after peripheral vascular intervention, dementia was among the variables ranked as predictive of 3-year mortality by a machine-learning model. This is about predicting death risk in a vascular disease population, not about treating, curing or preventing Alzheimer's disease.

Study details

• Participants114
• Effect size39.1%; 29.7%
• Evidence strengthModerate

Read the original

• DOI: 10.1161/jaha.124.034477
• PubMed: 38761075
• Original source →
• Free full text: Journal of the American Heart Association →

Full text: free to read — OpenAlex lists this copy as free to read: the link above (checked 6 Feb 1020).

@article{callegari2024-38761075,
  author  = {Callegari, Santiago and Romain, Gaëlle and Cleman, Jacob and Scierka, Lindsey E. and Jacque, Francky and Smolderen, Kim G. E. and Mena‐Hurtado, Carlos},
  title   = {{Long‐Term Mortality Predictors Using a Machine‐Learning Approach in Patients With Chronic Limb‐Threatening Ischemia After Peripheral Vascular Intervention}},
  journal = {Journal of the American Heart Association},
  year    = {2024},
  doi     = {10.1161/jaha.124.034477},
  pmid    = {38761075},
  url     = {https://doi.org/10.1161/jaha.124.034477}
}

Related studies in Health systems and care delivery

• A multimodal machine learning model for predicting dementia conversion in Alzheimer’s disease Scientific Reports · 2024-05-29 · usefulness score 53/100
• Screening for the Spectrum of Cognitive Impairment in Primary Care: Development of a Machine Learning Informed, Workflow‐Friendly Care Model Alzheimer s & Dementia · 2024-12-01 · usefulness score 39/100
• Long-Term Care Service Trajectories and Their Predictors for Persons Living With Dementia: Results From a Canadian Study Journal of aging and health · 2017-08-17 · usefulness score 50/100
• Intervention Fidelity of a Volunteer-Led Montessori-Based Intervention in a Canadian Long-Term Care Home Canadian journal on aging = La revue canadienne du vieillissement · 2020-09-30 · usefulness score 41/100
• Mortality in long-term care residents: retrospective national cohort study BMJ supportive & palliative care · 2025-12-23 · usefulness score 71/100
• Long-term effect of discontinuing anticholinesterase treatment on cognitive decline and mortality in Alzheimer's disease in France: a quasi-experiment and target trial emulation study The Lancet regional health. Europe · 2026-02-24 · usefulness score 40/100

Also tagged “delirium”

858 studies in the library carry the topic tag “delirium”; these are this study's neighbours in a fixed, alphabetical-by-hash tour of them, not the closest in content. All 858 tagged studies.

• AI-delirium guard: Predictive modeling of postoperative delirium in elderly surgical patients PLoS ONE · 2025-06-05 · usefulness score 50/100 · Clinical safety
• Projections of multi-morbidity in the older population in England to 2035: estimates from the Population Ageing and Care Simulation (PACSim) model Age and ageing · 2018-05-01 · usefulness score 72/100 · Prevention and risk
• Demographic, Health, and Social Predictors of Place of Death in England, 2004-2013: Identifying barriers to dying in the community Journal of Aging & Social Policy · 2025-04-01 · usefulness score 47/100 · End-of-life care

Similar studies

• Machine learning-based prediction of short- and long-term mortality for shared decision-making in older hip fracture patients: the Dutch Hip Fracture Audit algorithms in 74,396 cases 2025 · Digital health tools
• Predicting six-month mortality for patients who are on maintenance hemodialysis 2010 · End-of-life care
• Predictors of Documented Goals-of-Care Discussion for Hospitalized Patients With Chronic Illness 2023 · End-of-life care
• Development and Validation of a Deep Learning Algorithm for Mortality Prediction in Selecting Patients With Dementia for Earlier Palliative Care Interventions 2019 · Clinical safety
• Machine-learning-based COVID-19 mortality prediction model and identification of patients at low and high risk of dying 2021 · Digital health tools
• Machine Learning Algorithm Using Electronic Chart-Derived Data to Predict Delirium After Elderly Hip Fracture Surgeries: A Retrospective Case-Control Study 2021 · Digital health tools

More on Health systems and care delivery

• A review that covers this ground Monitoring and Evaluation of Dementia-Friendly Neighborhoods Using a Walkshed Approach: Protocol for a Scoping Review JMIR Research Protocols · 2023-11-01 · usefulness score 45/100
• Newest in this subject Family physicians' attitudes toward people with dementia and their association with empathy Research Square · 2026-10-14 · Preprint — not yet peer-reviewed · usefulness score 16/100
• Newest in this subject Performance of Claims-based Alzheimer’s Disease and Related Dementias Algorithms in Medicare Advantage and Fee-for-Service Populations The Journals of Gerontology Series A · 2026-09-17 · Peer-reviewed · usefulness score 52/100

See all studies in Health systems and care delivery →