ABSTRACT
AIMS: Electronic health records (EHR) linked to Digital Imaging and Communications in Medicine (DICOM), biological specimens, and deep learning (DL) algorithms could potentially improve patient care through automated case detection and surveillance. We hypothesized that by applying keyword searches to routinely stored EHR, in conjunction with AI-powered automated reading of DICOM echocardiography images and analysing biomarkers from routinely stored plasma samples, we were able to identify heart failure (HF) patients. METHODS AND RESULTS: We used EHR data between 1993 and 2021 from Tayside and Fife (~20% of the Scottish population). We implemented a keyword search strategy complemented by filtering based on International Classification of Diseases (ICD) codes and prescription data to EHR data set. We then applied DL for the automated interpretation of echocardiographic DICOM images. These methods were then integrated with the analysis of routinely stored plasma samples to identify and categorize patients into HF with reduced ejection fraction (HFrEF), HF with preserved ejection fraction (HFpEF), and controls without HF. The final diagnosis was verified through a manual review of medical records, measured natriuretic peptides in stored blood samples, and by comparing clinical outcomes among groups. In our study, we selected the patient cohort through an algorithmic workflow. This process started with 60 850 EHR data and resulted in a final cohort of 578 patients, divided into 186 controls, 236 with HFpEF, and 156 with HFrEF, after excluding individuals with mismatched data or significant valvular heart disease. The analysis of baseline characteristics revealed that compared with controls, patients with HFrEF and HFpEF were generally older, had higher BMI, and showed a greater prevalence of co-morbidities such as diabetes, COPD, and CKD. Echocardiographic analysis, enhanced by DL, provided high coverage, and detailed insights into cardiac function, showing significant differences in parameters such as left ventricular diameter, ejection fraction, and myocardial strain among the groups. Clinical outcomes highlighted a higher risk of hospitalization and mortality for HF patients compared with controls, with particularly elevated risk ratios for both HFrEF and HFpEF groups. The concordance between the algorithmic selection of patients and manual validation demonstrated high accuracy, supporting the effectiveness of our approach in identifying and classifying HF subtypes, which could significantly impact future HF diagnosis and management strategies. CONCLUSIONS: Our study highlights the feasibility of combining keyword searches in EHR, DL automated echocardiographic interpretation, and biobank resources to identify HF subtypes.
ABSTRACT
OBJECTIVE: To identify the prevalence of stage B heart failure (SBHF) in patients with type 2 diabetes mellitus (T2DM) with no history of cardiovascular disease (CVD). DESIGN: Observational study. SETTING: A single-centre study in which eligible patients were recruited from T2DM clinic. Following consent, patients completed a questionnaire and underwent physical examinations. Patients had blood drawn for laboratory investigations and had a transthoracic echocardiography. PARTICIPANTS: A total of 305 patients who were not known to have CVD were recruited. Patients with deranged liver function tests and end stage renal failure were excluded. MAIN OUTCOME MEASURES: Echocardiographic parameters such as left ventricular ejection fraction, left ventricular mass index (LVMI), left ventricular hypertrophy, left atrial enlargement and diastolic function were examined. RESULTS: A total of 305 patients predominantly females (65%), with mean body mass index of 27.5 kg/m2 participated in this study. None of them had either a history or signs and symptoms of CVD. Seventy-seven percent of patients had a history of hypertension and 83% of this study population had T2DM for more than 10 years. Mean HbA1c of 8.3% was recorded. Almost all patients were taking metformin. Approximately, 40% of patients were on newer anti-T2DM agents such as sodium-glucose cotransporter-2 and dipeptidyl peptidase 4 inhibitors. Fifty-seven percent (n=174) of the study population had SBHF at the time of study: diastolic dysfunction, increased LVMI and increased left atrial volume index (LAVI) were noted in 51 patients (17%), 128 patients (42%) and 98 patients (32%), respectively. Thirty-seven patients (12%) had both increase LVMI and LAVI. CONCLUSION: Our study has revealed a high prevalence of SBHF in T2DM patients without overt cardiac disease in Malaysia that has one of the highest prevalence of TDM in the world.
