EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Output Probabilistic Prediction of Drug Side Effects Using Classical Machine Learning Algorithms

Diego Quiguango Farias iD, Juan Sarasti Espejo iD, Marlene Arce Salcedo iD, Byron Velasquez Ron iD

Pharmaceuticals · 08.04.2026 · 19 (4) · 595

DOI: 10.3390/ph19040595 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pharmaceuticals, online erschienen am 08.04.2026. Verfasst von Diego Quiguango Farias und 3 weiteren Autor:innen. Beteiligte Einrichtung: Carrera Ciencias de la Salud, Universidad de Las Americas (UDLA), Quito 170516, Ecuador. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Drug side effects are a relevant problem for patient safety and public health, and traditional methods have limitations in capturing complex patterns between clinical and pharmacological variables.

Objective

To evaluate machine learning models to probabilistically predict multiple side effects associated with drug use. Materials and methods: A cross-sectional computational study was carried out with data from 1000 medications that included clinical condition, dosage and duration of treatment. Random Forest, Decision Tree, Support Vector Classifier and KNN were trained and optimized using Grid Search and an 80:20 split for training and testing. Chi-square tests and Principal Component Analysis were applied to explore associations and overlap between categories.

Results

Significant associations were found between side effects and clinical condition (p < 0.05) and the drug administered (p < 0.05). The PCA showed a high overlap between categories, which justified a probabilistic approach. Tree-based models showed better performance (accuracy ≈ 0.35).

Conclusions

Prediction of side effects is a multifactorial and non-deterministic problem; probabilistic machine learning models allow for estimating several plausible adverse events and can support clinical decision-making and pharmacovigilance.

Schlagwörter

Stichwörter der Autor:innen

computational pharmacologymachine learningpharmacovigilancepredictive modelsprobabilistic predictionside effects

Autor:innen und Institutionen

  • Carrera Ciencias de la Salud, Universidad de Las Americas (UDLA), Quito 170516, Ecuador.
  • Carrera de Odontología, Universidad de Las Americas (UDLA), Quito 170516, Ecuador.

ORCID-Profile: Diego Quiguango Farias, Juan Sarasti Espejo, Marlene Arce Salcedo, Byron Velasquez Ron

Zitieren

APA

Quiguango Farias, D., Sarasti Espejo, J., Arce Salcedo, M., & Velasquez Ron, B. (2026). Multi-Output Probabilistic Prediction of Drug Side Effects Using Classical Machine Learning Algorithms. Pharmaceuticals, 19(4), 595. https://doi.org/10.3390/ph19040595

Vancouver

Quiguango Farias D, Sarasti Espejo J, Arce Salcedo M, Velasquez Ron B. Multi-Output Probabilistic Prediction of Drug Side Effects Using Classical Machine Learning Algorithms. Pharmaceuticals. 2026;19(4):595. doi:10.3390/ph19040595

BibTeX
@article{QuiguangoFarias2026,
  author = {Quiguango Farias, Diego and Sarasti Espejo, Juan and Arce Salcedo, Marlene and Velasquez Ron, Byron},
  title = {Multi-Output Probabilistic Prediction of Drug Side Effects Using Classical Machine Learning Algorithms},
  journal = {Pharmaceuticals},
  year = {2026},
  volume = {19},
  number = {4},
  pages = {595},
  doi = {10.3390/ph19040595}
}
Kostenlos starten →