Introduction: Reducing undiagnosed type 2 diabetes (T2D) cases worldwide is an urgent public health challenge. Most current screening methods are invasive, lab-based, and costly. Meanwhile, there is a growing focus on noninvasive T2D detection through advanced artificial intelligence (AI) and digital technology. This study explores the feasibility of using a voice-based AI algorithm to predict T2D status in adults, a preliminary step toward innovative screening tools. Objective: To develop and assess the performance of a voice-based AI algorithm for T2D status detection in the adult population in the US. Methods: We analyzed text reading voice recordings from 607 US participants from the Colive Voice study, adhering to the CONSORT AI standards. We trained and cross-validated algorithms with BYOL-S/CvT embeddings for each gender, evaluating them on accuracy, precision, recall, and AUC. Performance of the best models was stratified by age, BMI, and hypertension, and compared to the American Diabetes Association (ADA) score for T2D risk assessment using a Bland-Altman analysis. Results: We analyzed 323 females and 284 males; Females with T2D (age: 49.5 years, BMI: 35.8 kg/m²) vs without (40.0 years, 28.0 kg/m²). Males with T2D (47.6 years, 32.8 kg/m²) vs without (41.6 years, 26.6 kg/m²). The voice-based algorithm achieved good overall predictive capacity (AUC=75% for males, 71% for females) and correctly predicted 71% of male and 66% of female T2D cases. It is enhanced in females aged 60 years (AUC=74%) or older but also with the presence of hypertension for both genders (AUC=75%). We observed an overall agreement above 93% with the ADA risk score. Conclusion: This study demonstrates the feasibility of detecting T2D using exclusively voice features. It is the first step toward using voice analysis as a first-line T2D screening strategy. While the findings are promising, further research and validation are necessary to specifically target early-stage T2D cases. Disclosure A. Elbeji: None. M. Pizzimenti: None. G.A. Aguayo: None. A. Fischer: None. H. Ayadi: None. F. Mauvais-Jarvis: None. J. Riveline: Board Member; Abbott, Novo Nordisk A/S, Sanofi, Eli Lilly and Company, Medtronic, Dexcom, Inc., Insulet Corporation, Air Liquide, AstraZeneca. V. Despotovic: None. G. Fagherazzi: Speaker's Bureau; Sanofi. Advisory Panel; Timkl, SAB Biotherapeutics, Inc., Vitalaire, Roche Diabetes Care.

中文翻译：

---

1308-P：基于语音的 AI 算法可以预测 2 型糖尿病状态 - 针对美国成人参与者的 Colive 语音研究结果


简介：减少全球未确诊的 2 型糖尿病 (T2D) 病例是一项紧迫的公共卫生挑战。目前大多数筛查方法都是侵入性的、基于实验室的且成本高昂。与此同时，人们越来越关注通过先进人工智能 (AI) 和数字技术进行的无创 T2D 检测。这项研究探讨了使用基于语音的人工智能算法来预测成人 T2D 状态的可行性，这是迈向创新筛查工具的第一步。目标：开发和评估基于语音的 AI 算法在美国成年人中检测 T2D 状态的性能。方法：我们遵循 CONSORT AI 标准，分析了 Colive Voice 研究中 607 名美国参与者的文本阅读语音记录。我们使用每个性别的 BYOL-S/CvT 嵌入来训练和交叉验证算法，评估它们的准确性、精确度、召回率和 AUC。最佳模型的表现按年龄、BMI 和高血压进行分层，并使用 Bland-Altman 分析与美国糖尿病协会 (ADA) 的 T2D 风险评估评分进行比较。结果：我们分析了 323 名女性和 284 名男性；患有 T2D 的女性（年龄：49.5 岁，BMI：35.8 kg/m²）与未患 T2D 的女性（40.0 岁，28.0 kg/m²）。患有 T2D 的男性（47.6 岁，32.8 公斤/平方米）与未患 T2D 的男性（41.6 岁，26.6 公斤/平方米）。基于语音的算法实现了良好的整体预测能力（AUC = 男性 75%，女性 71%），正确预测了 71% 的男性和 66% 的女性 T2D 病例。它在 60 岁（AUC=74%）或以上的女性中增强，但在男女都患有高血压的情况下（AUC=75%）。我们观察到与 ADA 风险评分的总体一致性超过 93%。结论：本研究证明了仅使用语音特征检测 T2D 的可行性。 这是使用语音分析作为一线 T2D 筛查策略的第一步。虽然研究结果很有希望，但还需要进一步研究和验证，以专门针对早期 T2D 病例。披露 A. Elbeji：无。 M. 皮齐门蒂：没有。 GA阿瓜约：没有。 A. 费舍尔：没有。 H.阿亚迪：没有。 F. Mauvais-Jarvis：没有。 J. Riveline：董事会成员；雅培、诺和诺德公司、赛诺菲、礼来公司、美敦力、Dexcom, Inc.、Insulet Corporation、液化空气集团、阿斯利康。 V. 德斯波托维奇：没有。 G. Fagherazzi：议长局；赛诺菲。顾问小组； Timkl、SAB Biotherapeutics, Inc.、Vitalaire、罗氏糖尿病护理。