OBJECTIVE - 3

Predict which prescribers tended to prescribe the opioid drugs.

Logistic regression is a statistical model that in its basic form uses a logistic function to model a binary dependent variable, although many more complex extensions exist. In regression analysis, logistic regression (or logit regression) is estimating the parameters of a logistic model (a form of binary regression).

Approach : Logistic Regression

Reason

In this problem, we need to find out the prescribers who are more likely to prescribe Opioid drugs to their patients and based on that to classify the Medical practitioners.

First, we tried to fit a binary Logistic regression model and try to analyze the output

Output

We have initially fitted a binary Logistic regression model and the model output is shown below.

From this model, we got an accuracy of 79.78% for the train data and the model give an AUC value of 0.890. This shows the model is Good enough to predict the Medical practitioner's prescription to opioid drugs. The sensitivity and specificity are 0.8090 and 0.7812 respectively.

The AUC curve is shown below.

Code

Availability of data, materials, and code are upon request.

Conclusion

When we fit the logistic regression, the model gives a good accuracy of 80%.
From the plot, we can see that GABAPENTIN is the most prescribed drug and most surgeons are tending to prescribe opioid drugs.

Back to Objectives