Phenogrouping heart failure with preserved or mildly reduced ejection fraction using electronic health record data

期刊论文
出版模式：

开放获取
发表日期：

2024年7月5日

查看全文

Fardad Soltani,
David A. Jenkins,
Amit Kaura,
Joshua Bradley,
Nicholas Black,
John P. Farrant,
Simon G. Williams,
Abdulrahim Mulla,
Benjamin Glampson,
Jim Davies,
Dimitri Papadimitriou,
Kerrie Woods,
Anoop D. Shah,
Mark R. Thursz,
Bryan Williams,
Folkert W. Asselbergs,
Erik K. Mayer,
Christopher Herbert,
Stuart Grant,
Nick Curzen,
Iain Squire,
Thomas Johnson,
Kevin O’Gallagher,
Ajay M. Shah,
Divaka Perera,
Rajesh Kharbanda,
Riyaz S. Patel,
Keith M. Channon,
Richard Lee,
Niels Peek,
Jamil Mayet,
Christopher A. Miller

摘要

Background

Heart failure (HF) with preserved or mildly reduced ejection fraction includes a heterogenous group of patients. Reclassification into distinct phenogroups to enable targeted interventions is a priority. This study aimed to identify distinct phenogroups, and compare phenogroup characteristics and outcomes, from electronic health record data.

Methods

2,187 patients admitted to five UK hospitals with a diagnosis of HF and a left ventricular ejection fraction ≥ 40% were identified from the NIHR Health Informatics Collaborative database. Partition-based, model-based, and density-based machine learning clustering techniques were applied. Cox Proportional Hazards and Fine-Gray competing risks models were used to compare outcomes (all-cause mortality and hospitalisation for HF) across phenogroups.

Results

Three phenogroups were identified: (1) Younger, predominantly female patients with high prevalence of cardiometabolic and coronary disease; (2) More frail patients, with higher rates of lung disease and atrial fibrillation; (3) Patients characterised by systemic inflammation and high rates of diabetes and renal dysfunction. Survival profiles were distinct, with an increasing risk of all-cause mortality from phenogroups 1 to 3 (p < 0.001). Phenogroup membership significantly improved survival prediction compared to conventional factors. Phenogroups were not predictive of hospitalisation for HF.

Conclusions

Applying unsupervised machine learning to routinely collected electronic health record data identified phenogroups with distinct clinical characteristics and unique survival profiles.