Enter Note Done

Media

5-LB - A Machine Learning–Based Approach to Noninvasively Detect Hypoglycemia from Gaze Behavior While Driving

View session detail


Author Block: VERA LEHMANN, MARTIN MARITSCH, THOMAS ZUEGER, ANDREAS MARXER, CATERINA BÉRUBÉ, MATHIAS KRAUS, CAROLINE ALBRECHT, STEFAN FEUERRIEGEL, TOBIAS KOWATSCH, ELGAR FLEISCH, FELIX WORTMANN, CHRISTOPH STETTLER, Bern, Switzerland, Zürich, Switzerland, Nuremberg, Germany, St. Gallen, Switzerland
Disclosure Block: V.Lehmann: None. E.Fleisch: Research Support; Self; CSS Health Insurance, Switzerland, Stock/Shareholder; Self; Pathmate-Technologies AG, Switzerland. F.Wortmann: None. C.Stettler: None. M.Maritsch: None. T.Zueger: None. A.Marxer: None. C.Bérubé: None. M.Kraus: None. C.Albrecht: None. S.Feuerriegel: None. T.Kowatsch: Advisory Panel; Self; Pathmate Technologies AG, Switzerland and Germany, Stock/Shareholder; Self; Pathmate Technologies AG, Switzerland and Germany.
Aim: To non-invasively detect hypoglycemia in individuals with type 1 diabetes (T1D) based on gaze behavior while driving.
Methods: Controlled hypoglycemia was induced in 19 individuals (12 males, age 32 ± 7.1 yrs) with T1D (HbA1c 7.1 ± 0.6% [54 ± 6 mmol/mol]) using an adapted hypoglycemic clamp protocol. Gaze and blood glucose (BG) data were gathered while driving in a simulator during three 18 min sessions: session 1 (BG 90-144 mg/dL), session 2 (BG declining from 72 to 45 mg/dL), and session 3 (BG 36-45 mg/dL). A gradient-boosting machine learning (ML) model was built for hypoglycemia (BG < 70 mg/dL) detection based on gaze behavior.
Results: Mean venous BG was 105.4 ± 11.4 mg/dL during session 1, declined from 61.4 ± 6.1 mg/dL to 47.2 ± 8.5 mg/dL during session 2, and was 42.7 ± 4.1 mg/dL during session 3, respectively. Gaze analysis provided 29,968 data samples (1,577.5 ± 52 per subject, 10,041 euglycemia, 19,927 hypoglycemia). Overall, ML achieved an area under the receiver-operating-characteristics curve of 0.83 ± 0.09 for hypoglycemia detection with leave-one-subject-out cross-validation.
Conclusion: ML-based gaze analysis shows high accuracy in non-invasive hypoglycemia detection while driving. Our approach offers promising potential in various settings where cameras are available.