%Aigaion2 BibTeX export from Idiap Publications
%Thursday 04 December 2025 04:32:11 PM

@ARTICLE{Lehmann_DIABETESCARE_2025,
                      author = {Lehmann, Vera and Hilpert, Martin and Mostaani, Zohreh and Hovsepyan, Sevada and Wallace, Esm{\'{e}} and Verzat, Colombine and Feuerriegel, Stefan and Kraus, Mathias and Rosenthal, James and Yilmaz, G{\"{u}}rkan and Magimai-Doss, Mathew and Stettler, Christoph},
                    keywords = {detection, hypoglycemia, machine learning, noninvasive, voice},
                    projects = {Idiap, EMIL, TIPS},
         mainresearchprogram = {AI for Life},
  additionalresearchprograms = {AI for Everyone},
                       title = {Listening to Hypoglycemia: Voice as a Biomarker for Detection of a Medical Emergency Using Machine Learning},
                     journal = {Diabetes Care},
                        year = {2025},
                         doi = {https://doi.org/10.2337/dc25-1680},
                    abstract = {OBJECTIVE
Hypoglycemia is a hazardous diabetes-related emergency. We aimed to develop a machine learning (ML) approach for noninvasive hypoglycemia detection using voice data.

RESEARCH DESIGN AND METHODS
We collected voice data (540 recordings) with a smartphone in standardized euglycemia and hypoglycemia in two sequential clinical studies in people with type 1 diabetes. Using these data, we trained and evaluated an ML approach to detect hypoglycemia solely based on voice features.

RESULTS
Twenty-two individuals were included (11 female, age 37.3 ± 12.4 years, HbA1c 7.1 ± 0.5\%). The ML approach detected hypoglycemia noninvasively with high accuracy (area under the receiver operating characteristic curve 0.90 ± 0.12 for reading a text aloud and 0.87 ± 0.15 for rapid repetition of syllables [diadochokinetic task]).

CONCLUSIONS
An ML approach exclusively based on voice data allows for noninvasive hypoglycemia detection, corroborating the potential of ML-based approaches to infer acute health states through voice}
}