|
|||||
|
|
Machine learning for non-invasive sensing of hypoglycaemia while driving in people with diabetes |
|
| Authors: | Vera Lehmann MD Thomas Zueger MD Martin Maritsch PhD Mathias Kraus PhD Caroline Albrecht BSc Caterina Bérubé MSc Stefan Feuerriegel PhD Felix Wortmann PhD Tobias Kowatsch PhD Naïma Styger BSc Sophie Lagger MSc Markus Laimer MD Elgar Fleisch PhD Christoph Stettler MD |
| Affiliation: | 1. Department of Diabetes, Endocrinology, Nutritional Medicine and Metabolism, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland;2. Department of Diabetes, Endocrinology, Nutritional Medicine and Metabolism, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland Department of Management, Technology, and Economics, ETH Zurich, Zurich, Switzerland;3. Department of Management, Technology, and Economics, ETH Zurich, Zurich, Switzerland;4. Department of Management, Technology, and Economics, ETH Zurich, Zurich, Switzerland School of Business, Economics and Society, Friedrich-Alexander University Erlangen-Nürnberg, Nürnberg, Germany;5. Institute of AI in Management, LMU Munich, Munich, Germany;6. Institute of Technology Management, University of St. Gallen, St. Gallen, Switzerland;7. Department of Management, Technology, and Economics, ETH Zurich, Zurich, Switzerland Institute for Implementation Science in Health Care, University of Zurich, Zurich, Switzerland School of Medicine, University of St. Gallen, St. Gallen, Switzerland;8. Department of Management, Technology, and Economics, ETH Zurich, Zurich, Switzerland Institute of Technology Management, University of St. Gallen, St. Gallen, Switzerland |
| Abstract: | AimTo develop and evaluate the concept of a non-invasive machine learning (ML) approach for detecting hypoglycaemia based exclusively on combined driving (CAN) and eye tracking (ET) data.Materials and MethodsWe first developed and tested our ML approach in pronounced hypoglycaemia, and then we applied it to mild hypoglycaemia to evaluate its early warning potential. For this, we conducted two consecutive, interventional studies in individuals with type 1 diabetes. In study 1 (n = 18), we collected CAN and ET data in a driving simulator during euglycaemia and pronounced hypoglycaemia (blood glucose [BG] 2.0-2.5 mmol L−1). In study 2 (n = 9), we collected CAN and ET data in the same simulator but in euglycaemia and mild hypoglycaemia (BG 3.0-3.5 mmol L−1).ResultsHere, we show that our ML approach detects pronounced and mild hypoglycaemia with high accuracy (area under the receiver operating characteristics curve 0.88 ± 0.10 and 0.83 ± 0.11, respectively).ConclusionsOur findings suggest that an ML approach based on CAN and ET data, exclusively, enables detection of hypoglycaemia while driving. This provides a promising concept for alternative and non-invasive detection of hypoglycaemia. |
| Keywords: | diabetes complications hypoglycaemia type 1 diabetes glycaemic control |