{"id":1858,"date":"2026-08-06T20:45:58","date_gmt":"2026-08-06T18:45:58","guid":{"rendered":"https:\/\/www.hsu-hh.de\/dataeng\/?page_id=1858"},"modified":"2026-08-06T20:45:59","modified_gmt":"2026-08-06T18:45:59","slug":"diamant","status":"publish","type":"page","link":"https:\/\/www.hsu-hh.de\/dataeng\/en\/research\/current-projects\/diamant\/","title":{"rendered":"DiaMant"},"content":{"rendered":"\n

Objective<\/strong><\/h3>\n\n\n\n

DiaMant aims to help prevent hypoglycemic events in people with type 1 diabetes by predicting risk up to 120 minutes before onset. Through an app-based interface, the system provides timely alerts and intervention recommendations tailored to the predicted time horizon. A key objective of the project is to evaluate the role of personalization in improving hypoglycemia prediction and evaluate whether population-based models can generalize across subjects and age groups.<\/p>\n\n\n\n

Description<\/strong><\/h3>\n\n\n\n

Type 1 diabetes is an autoimmune disease that requires insulin therapy to regulate blood glucose levels. However, insulin treatment can lower glucose levels below 70 mg\/dL, leading to hypoglycemia. If not addressed in time, hypoglycemia may cause dizziness, loss of consciousness, coma, and, in severe cases, death. Early detection can support preventive actions such as eating a snack or resting.<\/p>\n\n\n\n

DiaMant addresses this challenge by classifying short-term hypoglycemia onset. The project aims to improve predictive performance and to overcome a key limitation in current research: the lack of sufficiently large, well-curated datasets that support robust analysis across broader patient populations rather than isolated study cohorts.<\/p>\n\n\n\n

Current Research<\/strong><\/h3>\n\n\n\n

To support model development, we curated DiaData by integrating 15 publicly available datasets. DiaData includes data from 2510 people with type 1 diabetes and combines continuous glucose monitoring data, heart rate values, demographic information, laboratory values, and personal health features, including age, sex, BMI, height, weight, and race [1]. The dataset was further improved using advanced data imputation and quality enhancement modules, applied individually to specific time ranges of gaps [2]. The system classifies hypoglycemia risk across clinically relevant prediction horizons: at onset and 5-15, 20-45, and 50-120 minutes before onset. These time windows support actionable interventions, particularly during the 5-15 minutes before onset, when self-treatment may still be possible [3].<\/p>\n\n\n\n

To improve robustness, we developed multiple model variants, including versions with and without heart rate data. The classification models were incorporated into a real-time application framework that supports data collection, model execution, and intervention recommendations based on the predicted time to hypoglycemia. For example, if risk is detected within 0-25 minutes, the app recommends sitting down and consuming a snack [4].<\/p>\n\n\n\n

In addition, we assessed whether adding personal features or vital signs to glucose time-series data improves model performance. We also trained specialized expert models for different age groups: children aged 2-13 years, teenagers aged 14-20 years, adults aged 21-44 years, and older adults aged 45+ years. These models were compared with a population-based model to evaluate generalizability across age groups, showing that children benefit from specialized expert models [3].<\/p>\n\n\n\n

Future Work<\/strong><\/h3>\n\n\n\n

Using DiaData, we will develop and compare a wide range of machine learning and deep learning models. To further improve prediction performance and interpretability, we will also investigate ensemble learning and conduct SHAP-based feature analysis.<\/p>\n\n\n\n

References<\/p>\n\n\n\n

[1] Cinar B, Maleshkova M. Benchmarking hypoglycemia classification using quality-enhanced DiaData. IEEE J Biomed Health Inform<\/em>. 2025;29(12):8831-8838. doi:10.1109\/JBHI.2025.3620603<\/p>\n\n\n\n

[2] Gupta V, Grensing F, Cinar B, Van Den Boom L, Maleshkova M. Fill in the gaps – applying polynomial-based imputation techniques for heart rate data. In: 2026 IEEE Conference on Artificial Intelligence (CAI)<\/em>. IEEE; 2026:1174-1181. doi:10.1109\/cai68641.2026.11536361<\/p>\n\n\n\n

[3] Cinar B, Maleshkova M. Evaluating generalizability of population-based and age-segmented models for hypoglycemia classification. In: 2026 IEEE Conference on Artificial Intelligence (CAI)<\/em>. IEEE; 2026:1348-1355. doi:10.1109\/cai68641.2026.11536643<\/p>\n\n\n\n

[4] Grensing F, Cinar B, Maleshkova M. Early warning of hypoglycemia via sensor-agnostic machine learning: a clinical app design for type 1 diabetes. In:\u00a0International Conferences on Applied Computing 2025 and WWW\/Internet 2025: Proceedings<\/em>. IADIS Press; 2025. Presented at: 22nd International Conference on Applied Computing 2025 and 24th International Conference on WWW\/Internet 2025 (AC ICWI 2025); November 1-3, 2025; Porto, Portugal. support robust analysis across broader patient populations rather than isolated study cohorts.<\/p>\n","protected":false},"excerpt":{"rendered":"

Objective DiaMant aims to help prevent hypoglycemic events in people with type 1 diabetes by predicting risk up to 120 minutes before onset. Through an app-based interface, the system provides […]<\/p>\n","protected":false},"author":4068,"featured_media":0,"parent":1820,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"categories":[7],"tags":[],"class_list":["post-1858","page","type-page","status-publish","hentry","category-research"],"lang":"en","translations":{"en":1858,"de":1848},"pll_sync_post":{},"_links":{"self":[{"href":"https:\/\/www.hsu-hh.de\/dataeng\/wp-json\/wp\/v2\/pages\/1858","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.hsu-hh.de\/dataeng\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.hsu-hh.de\/dataeng\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.hsu-hh.de\/dataeng\/wp-json\/wp\/v2\/users\/4068"}],"replies":[{"embeddable":true,"href":"https:\/\/www.hsu-hh.de\/dataeng\/wp-json\/wp\/v2\/comments?post=1858"}],"version-history":[{"count":2,"href":"https:\/\/www.hsu-hh.de\/dataeng\/wp-json\/wp\/v2\/pages\/1858\/revisions"}],"predecessor-version":[{"id":1865,"href":"https:\/\/www.hsu-hh.de\/dataeng\/wp-json\/wp\/v2\/pages\/1858\/revisions\/1865"}],"up":[{"embeddable":true,"href":"https:\/\/www.hsu-hh.de\/dataeng\/wp-json\/wp\/v2\/pages\/1820"}],"wp:attachment":[{"href":"https:\/\/www.hsu-hh.de\/dataeng\/wp-json\/wp\/v2\/media?parent=1858"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.hsu-hh.de\/dataeng\/wp-json\/wp\/v2\/categories?post=1858"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.hsu-hh.de\/dataeng\/wp-json\/wp\/v2\/tags?post=1858"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}