Automated Prediction of Preeclampsia Using Artificial Intelligence

@article{1707427,
      author = {Frank Edughom Ekpar},
      title = {Automated Prediction of Preeclampsia Using Artificial Intelligence},
      journal = {Iconic Research And Engineering Journals},
      year = {2025},
      volume = {8},
      number = {9},
      pages = {267-274},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1707427.pdf},
      abstract = {This paper presents a system that builds artificial intelligence models for the automated prediction of the likelihood of occurrence of preeclampsia in pregnant women based on a suite of clinical measurements during the course of the pregnancy including proteinuria, amniotic fluid levels, fetal weight, gravida, parity, body mass index, systolic blood pressure, diastolic blood pressure, gestational age, presence or absence of diabetes, hemoglobin, history of hypertension and the age of the pregnant woman. The system is trained on publicly accessible preeclampsia datasets that could be augmented with locally sourced data for mitigation of bias, balance and robustness. The trained artificial intelligence models could be fine-tuned and integrated into preeclampsia prediction modules in a comprehensive artificial intelligence-driven healthcare system, saving lives and improving outcomes in pregnancy.},
      keywords = {Preeclampsia, Automated Disease Prediction, Artificial Intelligence (AI), Deep Learning (DL), Artificial Neural Network (ANN), TensorFlow, Healthcare System.},
      month = {March},
  }