Key result
Deep neural network outperforms Cox model in predicting incident HF among diabetic patients.
Why the study?
Patients with T2DM have more than twice the risk of developing HF compared to those without diabetes, prompting the development of an AI prognostic model incorporating heterogeneous clinical factors to investigate this risk.
Does a deep neural network survival method (PHNN) improve prognostic modeling for incident heart failure compared to a Cox proportional hazard model in patients with type 2 diabetes?
Cohort (n=10,614)
Does a deep neural network survival method (PHNN) improve prognostic modeling for incident heart failure compared to a Cox proportional hazard model in patients with type 2 diabetes?
A deep learning-based survival model using electronic health records outperformed standard Cox proportional hazard models in predicting incident heart failure among patients with type 2 diabetes.
May enhance HF risk stratification in diabetes via EHR data; leaves open prospective validation before clinical use.
Patients with type 2 diabetes mellitus (T2DM) have more than twice the risk of developing heart failure (HF) compared to patients without diabetes. The present study is aimed to build an artificial intelligence (AI) prognostic model that takes in account a large and heterogeneous set of clinical factors and investigates the risk of developing HF in diabetic patients. We carried out an electronic health records- (EHR-) based retrospective cohort study that included patients with cardiological clinical evaluation and no previous diagnosis of HF. Information consists of features extracted from clinical and administrative data obtained as part of routine medical care. The primary endpoint was diagnosis of HF (during out-of-hospital clinical examination or hospitalization). We developed two prognostic models using (1) elastic net regularization for Cox proportional hazard model (COX) and (2) a deep neural network survival method (PHNN), in which a neural network was used to represent a non-linear hazard function and explainability strategies are applied to estimate the influence of predictors on the risk function. Over a median follow-up of 65 months, 17.3% of the 10,614 patients developed HF. The PHNN model outperformed COX both in terms of discrimination (c-index 0.768 vs 0.734) and calibration (2-year integrated calibration index 0.008 vs 0.018). The AI approach led to the identification of 20 predictors of different domains (age, body mass index, echocardiographic and electrocardiographic features, laboratory measurements, comorbidities, therapies) whose relationship with the predicted risk correspond to known trends in the clinical practice. Our results suggest that prognostic models for HF in diabetic patients may improve using EHRs in combination with AI techniques for survival analysis, which provide high flexibility and better performance with respect to standard approaches.
No takes yet. Share an insight, caveat, or question.
Gandin et al. (2023) conducted a cohort in Type 2 diabetes mellitus (n=10,614). Deep neural network survival method (PHNN) vs. Elastic net regularization for Cox proportional hazard model (COX) was evaluated on Diagnosis of heart failure (during out-of-hospital clinical examination or hospitalization). A deep neural network survival model outperformed a Cox proportional hazard model in predicting incident heart failure among diabetic patients (c-index 0.768 vs 0.734).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: