AUTHOR=Zhou Jiandong , Chou Oscar Hou In , Wong Ka Hei Gabriel , Lee Sharen , Leung Keith Sai Kit , Liu Tong , Cheung Bernard Man Yung , Wong Ian Chi Kei , Tse Gary , Zhang Qingpeng 

TITLE=Development of an Electronic Frailty Index for Predicting Mortality and Complications Analysis in Pulmonary Hypertension Using Random Survival Forest Model

JOURNAL=Frontiers in Cardiovascular Medicine

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/cardiovascular-medicine/articles/10.3389/fcvm.2022.735906

DOI=10.3389/fcvm.2022.735906

ISSN=2297-055X

ABSTRACT=Background: The long-term prognosis of the cardio-metabolic and renal complications, in addition to mortality in newly diagnosed pulmonary hypertension patients, are unclear. This study aims to develop a scalable predictive model in the form of an electronic frailty index (eFI) to predict different adverse outcomes. 
Methods: This was a population-based cohort study of patients diagnosed with pulmonary hypertension between January 1st, 2000 and December 31st, 2017, in Hong Kong public hospitals. The primary outcomes were mortality, cardiovascular complications, renal diseases, and diabetes mellitus. Univariable and multivariable Cox regression analyses were applied to identify significant risk factors, which were fed into the nonparametric random survival forest (RSF) model to develop an eFI. 
Results: A total of 2560 patients with a mean age of 63.4 years old (interquartile range: 38.0-79.0) were included. Over follow-up, 1347 died, and 1878, 437, and 684 patients developed cardiovascular complications, diabetes mellitus and renal disease, respectively. The RSF model identified age, average readmission, anti-hypertensive drugs, cumulative length of stay and total bilirubin were amongst the most important risk factors for predicting mortality. Pair-wise interactions of factors including diagnosis age, average readmission interval and cumulative hospital stay were also crucial for mortality prediction. Patients who developed all-cause mortality had higher values of the eFI compared to those who survived (P<0.0001). An eFI ≥9.5 was associated with increased risks of mortality (hazard ratio [HR]: 1.90; 95% confidence interval [CI]: 1.70-2.12; P<0.0001). The cumulative hazards were higher among patients who were 65 years old or above with eFI ≥9.5. Using the same cut-off point, the eFI predicted long-term mortality over ten years (HR: 1.71; 95% CI: 1.53-1.90; P<0.0001). Compared to multivariable Cox regression, the precision, recall, area-under-the-curve (AUC), and C-index were significantly higher for RSF in the prediction of outcomes.
Conclusions: RSF models identified the novel risks factors and interactions for the development of complications and mortality. The eFI constructed by RSF accurately predicts the complications and mortality of pulmonary hypertension patients, especially among the elderly.