Artificial Neural Network-Based Automatic Detection of Food Intake for Neuromodulation in Treating Obesity and Diabetes
- PDF / 841,590 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 15 Downloads / 204 Views
ORIGINAL CONTRIBUTIONS
Artificial Neural Network-Based Automatic Detection of Food Intake for Neuromodulation in Treating Obesity and Diabetes Elisabeth R. M. Heremans 1,2 & Amy S. Chen 3 & Ximeng Wang 1 & Jiafei Cheng 1 & Feng Xu 4 & Agustin E. Martinez 2 & Georgios Lazaridis 2 & Sabine Van Huffel 2 & Jiande D. Z. Chen 1
# Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract 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. Keywords Food intake detection . Obesity . Diabetes . Neuromodulation . Machine learning
Abbreviations ANN Artificial neural networks FGIDs Functional gastrointestinal disorders HRV Heart rate variability
* Jiande D. Z. Chen [email protected] 1
Departments of Medicine and Biomedical Engineering, Johns Hopkins University, School of Medicine, Baltimore, MD, USA
2
Department of Electrical Engineering-ESAT, STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, KU Leuven, B-3001 Leuven, Belgium
3
College of Letters and Science, University of California, Berkeley, CA, USA
4
Yinzhou Hospital Affiliated with Ningbo University School of Medicine, Ningbo, China
Introduction Many of the most prevalent health problems in the world are associated with food intake, digestion, and nutrient absorption. These problems include obesity, diabetes, and functional gastrointestinal disorders (FGIDs). Around 31% of adults in the United States (US) are obese; they are at a high risk of numerous chronic and sometimes fatal diseases, such as coronary heart diseases, type 2 diabetes, hypertension, stroke, and cancers [1, 2]. In addition, obesity represents a substantial economic impact in healthcare, with an estimated total annual cos
Data Loading...
