Improving Clinical Decision-Making with Polynomial Regression-Based Real Patient State Estimation

As science and technology continue to evolve, clinical decision-making has become increasingly important in the field of medicine. This process not only aids experienced clinicians in making critical decisions but also provides guidance for those who lack experience. However, in the past, clinicians had to rely solely on their own expertise and medical reports to analyze patients, resulting in a time-consuming process. To address this issue, a scoring model was developed that analyzes patient conditions based on each parameter's value using data collected by the hospital. By utilizing computer analysis, evaluations, predictions, and optimizations, a suitable model for clinicians and patients can be created. This paper proposes a nonlinear polynomial regression approach as a model for predicting patient health scores, which has been validated through computer simulations and fits multiple researches and clinical examinations. The predicted results have been consistent with actual results when using the model, making it easier for clinicians to make clinical decisions. In summary, this model not only analyzes patient conditions but also predicts patient health scores with the support of appropriate parameters, making it a valuable tool for clinicians in their clinical decision-making process in the near future.