U-PASS: An uncertainty-guided deep learning pipeline for automated sleep staging.

With the increasing prevalence of machine learning in critical fields like healthcare, ensuring the safety and reliability of these systems is crucial. Estimating uncertainty plays a vital role in enhancing reliability by identifying areas of high and low confidence and reducing the risk of errors. This study introduces U-PASS, a specialized human-centered machine learning pipeline tailored for clinical applications, which effectively communicates uncertainty to clinical experts and collaborates with them to improve predictions. U-PASS incorporates uncertainty estimation at every stage of the process, including data acquisition, training, and model deployment. Training is divided into a supervised pre-training step and a semi-supervised recording-wise finetuning step. We apply U-PASS to the challenging task of sleep staging and demonstrate that it systematically improves performance at every stage. By optimizing the training dataset, actively seeking feedback from domain experts for informative samples, and deferring the most uncertain samples to experts, U-PASS achieves an impressive expert-level accuracy of 85% on a challenging clinical dataset of elderly sleep apnea patients. This represents a significant improvement over the starting point at 75% accuracy. The largest improvement gain is due to the deferral of uncertain epochs to a sleep expert. U-PASS presents a promising AI approach to incorporating uncertainty estimation in machine learning pipelines, improving their reliability and unlocking their potential in clinical settings.

From unsupervised to semi-supervised adversarial domain adaptation in electroencephalography-based sleep staging.

Objective.The recent breakthrough of wearable sleep monitoring devices has resulted in large amounts of sleep data. However, as limited labels are available, interpreting these data requires automated sleep stage classification methods with a small need for labeled training data. Transfer learning and domain adaptation offer possible solutions by enabling models to learn on a source dataset and adapt to a target dataset.Approach.In this paper, we investigate adversarial domain adaptation applied to real use cases with wearable sleep datasets acquired from diseased patient populations. Different practical aspects of the adversarial domain adaptation framework are examined, including the added value of (pseudo-)labels from the target dataset and the influence of domain mismatch between the source and target data. The method is also implemented for personalization to specific patients.Main results.The results show that adversarial domain adaptation is effective in the application of sleep staging on wearable data. When compared to a model applied on a target dataset without any adaptation, the domain adaptation method in its simplest form achieves relative gains of 7%-27% in accuracy. The performance in the target domain is further boosted by adding pseudo-labels and real target domain labels when available, and by choosing an appropriate source dataset. Furthermore, unsupervised adversarial domain adaptation can also personalize a model, improving the performance by 1%-2% compared to a non-personalized model.Significance.In conclusion, adversarial domain adaptation provides a flexible framework for semi-supervised and unsupervised transfer learning. This is particularly useful in sleep staging and other wearable electroencephalography applications. (Clinical trial registration number: S64190.).

Artificial Neural Network-Based Automatic Detection of Food Intake for Neuromodulation in Treating Obesity and Diabetes.

PURPOSE: Neuromodulation, such as vagal nerve stimulation and intestinal electrical stimulation, has been introduced for the treatment of obesity and diabetes. Ideally, neuromodulation should be applied automatically after food intake. The purpose of this study was to develop a method of automatic food intake detection through dynamic analysis of heart rate variability (HRV). MATERIALS AND METHODS: Two experiments were conducted: (1) a small sample series with a standard test meal and (2) a large sample series with varying meal size. Electrocardiograms (ECGs) were collected in the fasting and postprandial states. Each ECG was processed to compute the HRV. For each HRV segment, time- and frequency-domain features were derived and used as inputs to train and test an artificial neural network (ANN). The ANN was trained and tested with different cross-validation methods. RESULTS: The highest classification accuracy reached with leave-one-subject-out-leave-one-sample-out cross-validation was 0.93 in experiment 1 and 0.88 in experiment 2. Retraining the ANN on recordings of a subject drastically increased the achieved accuracy for that subject to values of 0.995 and 0.95 in experiments 1 and 2, respectively. CONCLUSIONS: Automatic food intake detection by ANNs, using features from the HRV, is feasible and may have a great potential for neuromodulation-based treatments of meal-related disorders.