Predictive Analytics for Early Disease Detection: Machine Learning Approaches using Clinical Data

@article{1704160,
      author = {Praggnya Kanungo},
      title = {Predictive Analytics for Early Disease Detection: Machine Learning Approaches using Clinical Data},
      journal = {Iconic Research And Engineering Journals},
      year = {2023},
      volume = {6},
      number = {9},
      pages = {448-455},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1704160.pdf},
      abstract = {Early disease detection is crucial for improving patient outcomes and reducing healthcare costs. This research explores the application of machine learning techniques for predictive analytics in early disease detection using clinical data. We evaluated multiple supervised and unsupervised machine learning algorithms on a large clinical dataset to predict the onset of five common diseases: diabetes, heart disease, stroke, lung cancer, and breast cancer. Our results demonstrate that ensemble methods like random forests and gradient boosting achieved the highest predictive performance, with AUC scores ranging from 0.82 to 0.91 across the different diseases. We also identified key clinical features that were most predictive for each disease. This study highlights the potential of machine learning approaches to leverage clinical data for early disease risk assessment and screening.},
      keywords = {Predictive Analytics, Machine Learning, Early Disease Detection, Clinical Data, Healthcare},
      month = {March},
  }