Derivation of an electronic frailty index for predicting short‐term mortality in heart failure: a machine learning approach

ESC Heart Failure

Sharen Lee¹  Esther W.Y. Chan²  Martin Sebastian Tan³  Kamalan Jeevaratnam⁴  Li Wei⁵  Ian Chi Kei Wong⁵  Chengsheng Ju⁵  Jiandong Zhou⁶  Qingpeng Zhang⁶  George Bazoukis⁷  Gary Tse⁸  Tong Liu⁸ 

[1]Cardiovascular Analytics Group, Laboratory of Cardiovascular Physiology, LKS Institute of Health Sciences Chinese University of Hong Kong Hong Kong SAR China

[2]Centre for Safe Medication Practice and Research, Department of Pharmacology and Pharmacy The University of Hong Kong Hong Kong SAR China

[3]Faculty of Arts and Science University of Toronto Toronto Ontario Canada

[4]Faculty of Health and Medical Sciences University of Surrey Guildford UK

[5]Research Department of Practice and Policy, School of Pharmacy University College London London UK

[6]School of Data Science City University of Hong Kong Hong Kong SAR China

[7]Second Department of Cardiology Evangelismos General Hospital Athens Greece

[8]Tianjin Key Laboratory of Ionic‐Molecular Function of Cardiovascular Disease, Department of Cardiology, Tianjin Institute of Cardiology Second Hospital of Tianjin Medical University Tianjin China

关键词: Frailty index;    Heart failure;    Mortality;    Inflammation;    Nutrition;    Machine learning;   

DOI  :  10.1002/ehf2.13358

来源: DOAJ

【 摘 要 】

Abstract Aims Frailty may be found in heart failure patients especially in the elderly and is associated with a poor prognosis. However, assessment of frailty status is time‐consuming, and the electronic frailty indices developed using health records have served as useful surrogates. We hypothesized that an electronic frailty index developed using machine learning can improve short‐term mortality prediction in patients with heart failure. Methods and results This was a retrospective observational study that included patients admitted to nine public hospitals for heart failure from Hong Kong between 2013 and 2017. Age, sex, variables in the modified frailty index, Deyo's Charlson co‐morbidity index (≥2), neutrophil‐to‐lymphocyte ratio (NLR), and prognostic nutritional index at baseline were analysed. Gradient boosting, which is a supervised sequential ensemble learning algorithm with weak prediction submodels (typically decision trees), was applied to predict mortality. Variables were ranked in the order of importance with a total score of 100 and used to build the frailty models. Comparisons were made with decision tree and multivariable logistic regression. A total of 8893 patients (median: age 81, Q1–Q3: 71–87 years old) were included, in whom 9% had 30 day mortality and 17% had 90 day mortality. Prognostic nutritional index, age, and NLR were the most important variables predicting 30 day mortality (importance score: 37.4, 32.1, and 20.5, respectively) and 90 day mortality (importance score: 35.3, 36.3, and 14.6, respectively). Gradient boosting significantly outperformed decision tree and multivariable logistic regression. The area under the curve from a five‐fold cross validation was 0.90 for gradient boosting and 0.87 and 0.86 for decision tree and logistic regression in predicting 30 day mortality. For the prediction of 90 day mortality, the area under the curve was 0.92, 0.89, and 0.86 for gradient boosting, decision tree, and logistic regression, respectively. Conclusions The electronic frailty index based on co‐morbidities, inflammation, and nutrition information can readily predict mortality outcomes. Their predictive performances were significantly improved by gradient boosting techniques.

【 授权许可】

Unknown