A new publication in Telehealth and Medicine Today (THMT) explores a high stakes frontier in maternal health: early risk prediction of preeclampsia using machine learning—paired with explainable AI.
Early Prediction of Preeclampsia by Using Ensemble Machine Learning With MM-XAI Approach, Sari Puspita, S.Si, M.Si, Gusrino Yanto, S.Kom, M.Kom, Rifa Turaina, S.Kom, M.Kom, Nency Extise Putri, S.Kom, M.Kom
PDF
HTML XML EPUB
Why this matters
Preeclampsia remains one of the most serious pregnancy complications—where timing and early detection can significantly
impact outcomes for both mother and child. AI has long been proposed as part of the solution. But one critical question persists: can clinicians trust what they can’t fully interpret?
What this study explores
The research introduces a hybrid approach that combines:
- Multiple machine learning models to assess preeclampsia risk
- A range of clinical indicators routinely captured in care settings
- A multi-method explainable AI (XAI) framework designed to make model outputs more transparent and interpretable
It goes beyond prediction—examining how insights are generated, understood, and potentially applied in clinical contexts.
Why it’s citable
This article contributes to a growing evidence base at the intersection of AI, clinical decision support, and responsible
innovation:
- Integrates ensemble machine learning with explainability methods
- Applies multiple XAI techniques to interrogate model behavior
- Grounded in clinically relevant variables and real-world constraints
- Explicitly addresses limitations and appropriate use, supporting responsible citation and interpretation
For researchers, clinicians, and policymakers, it offers methodological depth and practical relevance in one of healthcare’s most critical domains.
