EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Machine Learning Framework for Preeclampsia Prediction at Isidro Ayora Hospital, Ecuador

Maria Perez iD, Lenin G Falconi iD, Monserrate Intriago-Pazmiño iD, Andrés Bastidas-Fuertes iD, Juan Benavides iD, Raysa A Fuertes-Arévalo iD

Diagnostics · 08.07.2026 · 16 (14) · 2147

DOI: 10.3390/diagnostics16142147 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 08.07.2026. Verfasst von Maria Perez und 5 weiteren Autor:innen. Beteiligte Einrichtung: Departamento de Informática y Ciencias de la Computación, Escuela Politécnica Nacional, Quito 170525, Ecuador. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Preeclampsia (PE) is a leading cause of maternal and perinatal morbidity, affecting 2–8% of pregnancies worldwide. In Ecuadorian public hospitals, clinical data are often fragmented, limiting the construction of complete datasets for prediction modeling. This study aimed to develop a Machine Learning (ML) framework to predict PE using demographic data from the Isidro Ayora Gynecology and Obstetrics Hospital (HGOIA), Quito, Ecuador.

Methods

We proposed a custom automated Machine Learning (C-AutoML) workflow to evaluate six models (Logistic Regression, LightGBM, XGBoost, CatBoost, Multi-Layer Perceptron, and Random Forest) and compared its performance against a weighted ensemble built with Amazon SageMaker Canvas, optimizing for the F1-score. Model interpretability was analyzed using Shapley Additive Explanations (SHAP). Due to the scarcity of clinical variables at HGOIA, a synthetic dataset based on FullPIERS predictors was also generated and modeled.

Results

On the hospital dataset, the SageMaker ensemble achieved an F1-score of 0.805, accuracy of 0.934, and AUC of 0.956, while the C-AutoML best single model (LightGBM) yielded comparable results (F1-score: 0.802, accuracy: 0.938, AUC: 0.944). SHAP analysis identified patient age as the most influential feature. On the synthetic dataset, Logistic Regression achieved perfect classification (F1-score: 1.0).

Conclusions

The proposed C-AutoML framework matched the performance of the SageMaker weighted ensemble while relying on a single, interpretable model. Despite the current dependence on demographic data, the methodology shows promise for supporting PE diagnosis in resource-limited settings; future integration of clinical variables is expected to further enhance predictive power for risk stratification.

Schlagwörter

Stichwörter der Autor:innen

LightGBMensemble modelsexplainable artificial intelligencemachine learningpredictionpreeclampsia

Autor:innen und Institutionen

  • Departamento de Informática y Ciencias de la Computación, Escuela Politécnica Nacional, Quito 170525, Ecuador.
  • Smartwork S.A., Quito 170503, Ecuador.
  • Ministerio de Salud Pública, Quito 170702, Ecuador.

ORCID-Profile: Maria Perez, Lenin G Falconi, Monserrate Intriago-Pazmiño, Andrés Bastidas-Fuertes, Juan Benavides, Raysa A Fuertes-Arévalo

Zitieren

APA

Perez, M., Falconi, L. G., Intriago-Pazmiño, M., Bastidas-Fuertes, A., Benavides, J., & Fuertes-Arévalo, R. A. (2026). A Machine Learning Framework for Preeclampsia Prediction at Isidro Ayora Hospital, Ecuador. Diagnostics, 16(14), 2147. https://doi.org/10.3390/diagnostics16142147

Vancouver

Perez M, Falconi LG, Intriago-Pazmiño M, Bastidas-Fuertes A, Benavides J, Fuertes-Arévalo RA. A Machine Learning Framework for Preeclampsia Prediction at Isidro Ayora Hospital, Ecuador. Diagnostics. 2026;16(14):2147. doi:10.3390/diagnostics16142147

BibTeX
@article{Perez2026,
  author = {Perez, Maria and Falconi, Lenin G and Intriago-Pazmiño, Monserrate and Bastidas-Fuertes, Andrés and Benavides, Juan and Fuertes-Arévalo, Raysa A},
  title = {A Machine Learning Framework for Preeclampsia Prediction at Isidro Ayora Hospital, Ecuador},
  journal = {Diagnostics},
  year = {2026},
  volume = {16},
  number = {14},
  pages = {2147},
  doi = {10.3390/diagnostics16142147}
}
Kostenlos starten →