Abstract
This study analyzes the issue of disease diagnosis delay in healthcare quality management using data mining methods. The aim is to understand the relationship between several key variables and diagnosis delay for various diseases. The study focuses on the variables of Age, Symptom Duration, Physician Experience, and Diagnosis Delay. Advanced data mining methods are employed to predict and prevent disease diagnosis delays. The results of this study present the findings from the analysis of the collected dataset.
 The dataset consists of patient information, including attributes such as Patient ID, Age, Symptom Duration, Physician Experience, Diagnosis Delay, and Treatment Initiation. Each attribute plays a crucial role in understanding and predicting diagnosis delay. The approach using linear regression yields coefficients [0.03260123, 0.24605912, 0.01765057, 1.09631713], indicating the influence of each variable on Diagnosis Delay. The Mean Squared Error (MSE) value of 0.7926 signifies the model's ability to predict Diagnosis Delay accurately.
 The scatter plot illustrates the linear relationship between actual Diagnosis Delay and predicted Diagnosis Delay. The Pearson's Correlation Coefficient of 0.5222 indicates a moderate positive correlation between the two. However, the residual plot indicates a tendency for underestimation of Diagnosis Delay for higher values.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have