An interpretable machine learning model for the prevention of contrast-induced nephropathy in patients undergoing lower extremity endovascular interventions for peripheral arterial disease

Cox, Meredith; Panagides, J. C.; Capua, John Di; Dua, Anahita; Kalva, Sanjeeva P.; Kalpathy–Cramer, Jayashree; Daye, Dania

doi:10.1016/j.clinimag.2023.05.011

Cited by 7 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following a similar approach as previously conducted studies, we randomly divided our cohort into training (80%) and testing samples (20%). 30 , 31 Baseline variables between the 2 samples were summarized as count with percentage and were compared using χ 2 or Fisher exact test for categorical variables; continuous variables were summarized as mean with SD and were compared using Student t ‐test. The standardized difference was calculated to assess the effect size between the 2 samples, with a value <0.10 considered negligible.…”

Section: Methodsmentioning

confidence: 99%

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

Callegari,

Romain,

Cleman

et al. 2024

JAHA

View full text Add to dashboard Cite

Background Patients with chronic limb‐threatening ischemia (CLTI) face a high long‐term mortality risk. Identifying novel mortality predictors and risk profiles would enable individual health care plan design and improved survival. We aimed to leverage a random survival forest machine‐learning algorithm to identify long‐term all‐cause mortality predictors in patients with CLTI undergoing peripheral vascular intervention. Methods and Results 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%). Conclusions 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.

show abstract

Section: Methodsmentioning

confidence: 99%

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

Callegari,

Romain,

Cleman

et al. 2024

JAHA

View full text Add to dashboard Cite

show abstract

Predictive performance of machine learning models for kidney complications following coronary interventions: a systematic review and meta-analysis

Najdaghi,

Davani,

Shafie

et al. 2024

Int Urol Nephrol

View full text Add to dashboard Cite

Machine Learning in Vascular Medicine: Optimizing Clinical Strategies for Peripheral Artery Disease

Perez,

Thandra,

Mellah

et al. 2024

Curr Cardiovasc Risk Rep

View full text Add to dashboard Cite

Purpose of Review Peripheral Artery Disease (PAD), a condition affecting millions of patients, is often underdiagnosed due to a lack of symptoms in the early stages and management can be complex given differences in genetic and phenotypic characteristics. This review aims to provide readers with an update on the utility of machine learning (ML) in the management of PAD. Recent Findings Recent research leveraging electronic health record (EHR) data and ML algorithms have demonstrated significant advances in the potential use of automated systems, namely artificial intelligence (AI), to accurately identify patients who might benefit from further PAD screening. Additionally, deep learning algorithms can be used on imaging data to assist in PAD diagnosis and automate clinical risk stratification. ML models can predict major adverse cardiovascular events (MACE) and major adverse limb events (MALE) with considerable accuracy, with many studies also demonstrating the ability to more accurately risk stratify patients for deleterious outcomes after surgical intervention. These predictions can assist physicians in developing more patient-centric treatment plans and allow for earlier, more aggressive management of modifiable risk-factors in high-risk patients. The use of proteomic biomarkers in ML models offers a valuable addition to traditional screening and stratification paradigms, though clinical utility may be limited by cost and accessibility. Summary The application of AI to the care of PAD patients may enable earlier diagnosis and more accurate risk stratification, leveraging readily available EHR and imaging data, and there is a burgeoning interest in incorporating biological data for further refinement. Thus, the promise of precision PAD care grows closer. Future research should focus on validating these models via real-world integration into clinical practice and prospective evaluation of the impact of this new care paradigm.

show abstract

An interpretable machine learning model for the prevention of contrast-induced nephropathy in patients undergoing lower extremity endovascular interventions for peripheral arterial disease

Cited by 7 publications

References 26 publications

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

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

Predictive performance of machine learning models for kidney complications following coronary interventions: a systematic review and meta-analysis

Machine Learning in Vascular Medicine: Optimizing Clinical Strategies for Peripheral Artery Disease

Contact Info

Product

Resources

About