USING MACHINE LEARNING AND CLINICAL REGISTRY DATA TO UNCOVER VARIATION IN CLINICAL DECISION MAKING

  • Unique Paper ID: 177791
  • Volume: 11
  • Issue: 12
  • PageNo: 2924-2929
  • Abstract:
  • Clinical decision-making in healthcare is already being impacted by predictions or suggestions generated by data-driven technologies. Machine learning applications have exploded in the most recent clinical literature, especially in the creation of outcome prediction models. Acute illnesses, cardiac arrest, and mortality are only a few of the many outcomes that are covered by these models. When it comes to forecasting patient waiting times, the PTTP (Patient Treatment Time Prediction) model is the most accurate of these models. For outcome prediction models that use data taken from electronic health records, our study offers a thorough review of the state-of-the-art in data processing, inference, and model evaluation. We also discuss the shortcomings of current modeling assumptions and suggest some directions for further study.

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 12
  • PageNo: 2924-2929

USING MACHINE LEARNING AND CLINICAL REGISTRY DATA TO UNCOVER VARIATION IN CLINICAL DECISION MAKING

Related Articles