COPD-Aware Modelling of Heart Failure Hospital Admissions Using Routinely Collected Primary Care Prescription Data

Abstract

Heart failure (HF) is a leading cause of unplanned hospital admissions in the United Kingdom (UK), consuming 1–2% of the National Health Service (NHS) annual budget, with most costs from inpatient care. Many predictive models oversimplify medication histories, relying on static indicators instead of time-aware prescribing patterns. This study improves HF admission prediction using UK primary care data, focusing on monthly dosage trends of three therapeutic classes angiotensin converting en- zyme inhibitors (ACEIs), beta-blockers, and angiotensin receptor blockers (ARBs) and the influence of Chronic Obstructive Pulmonary Disease (COPD). Three linked datasets patient demographics and comorbidities (patientinfo), prescription records (prescriptions), and chronic condition diagnoses (indexdates) were merged after cleaning and validation. Static attributes and temporal medication features were used to train Long Short-Term Memory (LSTM) networks, Random Forest, and Logistic Regression. Due to poor performance of the LSTM and Random Forest in a multi-class setting (ad- mission count categories), the task was reframed as binary classification (admission vs. no admission), with class imbalance addressed using the Synthetic Minority Oversampling Technique (SMOTE). The final dataset included 963 patients and over 109521 monthly prescription records. The best perfor- mance was from standard Random Forest (without SMOTE), which retained clinical interpretability, identifying COPD status, total monthly medication dosage, and age at HF diagnosis as top predic- tors. COPD patients had a 12% higher admission rate (59.1% vs. 41.8%). These findings show that granular, dosage-aware prescribing data can enhance HF admission prediction. Future work will ex- plore hybrid classification regression models, incorporate laboratory and lifestyle data, and validate externally to improve generalisability and support NHS decision-making.