Explainable Prediction of Long-Term Glycated Hemoglobin Response Change in Finnish Patients with Type 2 Diabetes Following Drug Initiation Using Evidence-Based Machine Learning Approaches
Using EHR and ML models allows for the development of more realistic and individualized predictions of HbA1c changes, accounting for more diverse patient populations and their heterogeneous nature, offering more tailored and effective treatment strategies for managing T2D. The use of XAI provided insights into the influence of specific predictors, enhancing model interpretability and clinical relevance. Future research will explore treatment selection models.
Authors
- Tiina Laatikainen (ORCID: https://orcid.org/0000-0002-6614-4782)
- Gunjan Chandra (ORCID: https://orcid.org/0000-0002-0051-0268)
- Janne Martikainen (ORCID: https://orcid.org/0000-0003-0855-3921)
- Pekka Siirtola (ORCID: https://orcid.org/0000-0002-5995-5421)
- Juha Röning (ORCID: https://orcid.org/0000-0001-9993-8602)
- Piia Lavikainen (ORCID: https://orcid.org/0000-0003-3560-8860)
- Satu Tamminen (ORCID: https://orcid.org/0000-0002-5215-6889)
- Anusha Ihalapathirana (ORCID: https://orcid.org/0000-0002-3276-2056)
Institutions
- University of Eastern Finland (FI)
- Karelia University of Applied Sciences (FI)
- Finnish Institute for Health and Welfare (FI)
- North Karelia Central Hospital (FI)
- University of Oulu (FI)
Publication Details
- Journal
- Clinical Epidemiology
- Published
- 2025-03-01
- DOI
- https://doi.org/10.2147/clep.s505966
- Citations
- 6
- Primary Topic
- Diabetes Treatment and Management
- Type
- article
- Field-Weighted Citation Impact
- 7.77
Funders
- European Commission
- Academy of Finland
- Kuopion Yliopistollinen Sairaala
- Diabetesliitto
- Strategic Research Council