On Merging Feature Engineering and Deep Learning for Diagnosis, Risk Prediction and Age Estimation Based on the 12-Lead ECG.

OBJECTIVE: Over the past few years, deep learning (DL) has been used extensively in research for 12-lead electrocardiogram (ECG) analysis. However, it is unclear whether the explicit or implicit claims made on DL superiority to the more classical feature engineering (FE) approaches, based on domain knowledge, hold. In addition, it remains unclear whether combining DL with FE may improve performance over a single modality. METHODS: To address these research gaps and in-line with recent major experiments, we revisited three tasks: cardiac arrhythmia diagnosis (multiclass-multilabel classification), atrial fibrillation risk prediction (binary classification), and age estimation (regression). We used an overall dataset of 2.3M 12-lead ECG recordings to train the following models for each task: i) a random forest taking FE as input; ii) an end-to-end DL model; and iii) a merged model of FE+DL. RESULTS: FE yielded comparable results to DL while necessitating significantly less data for the two classification tasks. DL outperformed FE for the regression task. For all tasks, merging FE with DL did not improve performance over DL alone. These findings were confirmed on the additional PTB-XL dataset. CONCLUSION: We found that for traditional 12-lead ECG based diagnosis tasks, DL did not yield a meaningful improvement over FE, while it improved significantly the nontraditional regression task. We also found that combining FE with DL did not improve over DL alone, which suggests that the FE was redundant with the features learned by DL. SIGNIFICANCE: Our findings provides important recommendations on 12-lead ECG based machine learning strategy and data regime to choose for a given task. When looking at maximizing performance as the end goal, if the task is nontraditional and a large dataset is available then DL is preferable. If the task is a classical one and/or a small dataset is available then a FE approach may be the better choice.

An analysis of ambulatory blood pressure monitoring using multi-label classification.

Ambulatory blood pressure monitoring (ABPM) involves measuring blood pressure by means of a tensiometer carried by the patient for a duration of 24 h, it currently occupies a central place in the diagnosis and follow-up of hypertensive patients, it provides crucial information which allows to make a specific diagnosis and adapt therapeutic attitude accordingly. The traditional analysis process suffers from different problems: it requires a lot of time and expertise, and several calculations should be performed manually by the expert, who is generally very busy. In this work, we attempt to improve the analysis of ABPM data using multi-label classification methods, where a record is associated with more than one label (class) at the same time. Seven algorithms are experimentally compared on a new multi-label ABPM-dataset. Experiments are conducted on 270 hypertensive patient records characterized by 40 attributes and associated with six labels. Results show that the multi-label modeling of ABPM data helps to investigate label dependencies and provide interesting insights, which can be integrated into the ABPM devices to dispense automatically detailed reports with possible future complications.