Early Prognosis of Preeclampsia Using Machine Learning - Inria - Institut national de recherche en sciences et technologies du numérique
Communication Dans Un Congrès Année : 2022

Early Prognosis of Preeclampsia Using Machine Learning

E. Sivaram
  • Fonction : Auteur
  • PersonId : 1334340
G. Vadivu
  • Fonction : Auteur
  • PersonId : 1334341
K. Sangeetha
  • Fonction : Auteur
  • PersonId : 1334342
Vijayan Sugumaran
  • Fonction : Auteur
  • PersonId : 1334343

Résumé

Preeclampsia is a type of hypertension condition that can be induced by a variety of circumstances during pregnancy. Typically, a diagnosis is made after 20 weeks of gestation. Several investigations employing machine learning techniques have been undertaken to diagnose preeclampsia. SVM, KNN, random forest, gradient boosting methods, and deep learning approaches are examples of these. These techniques can be implemented to detect preeclampsia earlier in an efficient way for preventing the complications caused. This paper demonstrates how hyperparameter tuning of Support vector classification of the various factors involved in the classification of preeclampsia helps in efficiently separating the patients who are prone to have preeclampsia. The selection of the hyperparameter is done through the Grid Search CV algorithm by iterative trialing of the different hyperparameters.
Fichier sous embargo
Fichier sous embargo
0 3 4
Année Mois Jours
Avant la publication
mercredi 1 janvier 2025
Fichier sous embargo
mercredi 1 janvier 2025
Connectez-vous pour demander l'accès au fichier

Dates et versions

hal-04388144 , version 1 (11-01-2024)

Licence

Identifiants

Citer

E. Sivaram, G. Vadivu, K. Sangeetha, Vijayan Sugumaran. Early Prognosis of Preeclampsia Using Machine Learning. 6th International Conference on Computer, Communication, and Signal Processing (ICCCSP), Feb 2022, Chennai, India. pp.12-19, ⟨10.1007/978-3-031-11633-9_2⟩. ⟨hal-04388144⟩
23 Consultations
2 Téléchargements

Altmetric

Partager

More