Ensemble Machine Learning methods for Hypertension Scaling in Pregnant during Trimester Periods

Author : Shreeja Vydyam

Abstract : In recent years more interest of research is taking place for analyzing risks for women during pregnancy period. Increased machine learning techniques application over medical data to identify risk factors during trimester periods provide an insight to knowledge patterns supporting good decision making. In this paper we present ensemble methods for hypertension scaling and classification of clinical features. The adoption of AI techniques and transformer encoding methods are under research. Hypertension severity estimation and trimester based mental health data is the focus carried over in this research to generate decision summaries for pregnant health care guidance in perspective of both mother and child growth harmony. Various models are adopted for improved interpretability analysis. The application of transformer learning mechanisms encouraged in this research to introduce hybrid ensemble models for hyper scaling pregnancy trimester risks.

Keywords : Machine Learning, Hypertension, Risk Analysis, Trimesters.

Conference Name : International Conference on Blockchain and Cybersecurity for Big Data Governance (ICBCBDG-26)

Conference Place : Coimbatore, India

Conference Date : 3rd Jan 2026