Hello Folks, Anupama here, Presenting on behalf of my team for our internship project - Patients Condition Classification Using Drug Reviews. for that, we use python and machine learning algorithms and models.

1. P194-Patients Condition Classification
Using Drug Reviews
Presented By:
1.Anupama
2.Laiba
3.Somanath
4.Sunny
5.Rohan
6.Suhas

2. Contents
• Business Objective
• Project Architecture
• Data Collection & Details
• Exploratory Data Analysis
• Visualizations
• Sentimental Analysis
• Model Building
• Model Evaluation
• Depolyment

3. Business Objective:
• This is a sample dataset which consists of 161297 drug name, condition
reviews and ratings from different patients and our goal is to examine how
patients are feeling using the drugs their positive and negative experiences
so that we can recommend him a suitable drug. By analysing the reviews,
we can understand the drug effectiveness and its side effects.
• The dataset provides patient reviews on specific drugs along with related
conditions and a 10 star patient rating reflecting overall patient
satisfaction. So in this dataset, we can see many patients conditions but we
will focus only on the below, classify the below conditions from the
patients reviews
a) Depression
b) High Blood Pressure
c) Diabetes, Type 2

4. Project Architecture / Project Flow
Business
Understanding
Data
Collection
Data
Preparation
Exploratory
Data Analysis
Model
Evaluation
Model
Deployment

5. Importing libraries and Data Sets

6. Data Collection & Details
• 161297 Rows and 7 Columns
Attribute Information:
• 1. DrugName (categorical): name of drug
• 2. condition (categorical): name of condition
• 3. review (text): patient review
• 4. rating (numerical): 10 star patient rating
• 5. date (date): date of review entry
• 6. usefulCount (numerical): number of users who found review
useful

7. Exploratory Data Analysis (EDA)

8. Exploratory Data Analysis (EDA)
Data Type Column
Shape
Is Null present?
Find the Unique values
Corelation
Describe the data

9. Cleaning the data

10. EDA Visualizations

11. EDA Visualizations
Count Plot Histogram Plot

12. Pie Plot
Box Plot

13. This barplot shows the top 20 drugs with the 10/10
rating

14. This barplot shows the top 20 drugs with the
1/10 rating

15. This barplot show the top 10 conditions the people
are suffering.

16. Top 10 drugs used for depression, High
Blood Pressure, Diabetes, Type 2

17. Word cloud For Drug names

18. Word cloud For Reviews

19. Sentimental Analysis

20. Sentimental Analysis

21. Word cloud For Positive Reviews

22. Word cloud For Negative Reviews

23. Visualization of review based on date-time

24. Month wise Visualization of review

25. Day wise Visualization of review

26. Visualization of useful counts

27. Modelling

28. Modelling
Insert the Side-effect column in the data
Save the data in CSV file
From side-effects get the Results
Information of CSV file

29. Liner SVC
Classification report of logistic regression
on Liner SVC Model
Accuracy of Train and Test
Split-Train-Test-Process

30. Logistic Regression
Split-Train-Test-Process
Accuracy of Train and Test
Classification report of logistic regression
on Logistic Regression Model

31. Decision Tree
Split-Train-Test-Process
Accuracy of Train and Test
Classification report of logistic regression
on Decision Tree Model

32. XGBOOST (XGBM)
Split-Train-Test-Process Accuracy of Train and Test
Classification report of logistic regression
on XGBM Model

33. Light-GBM
Classification report of logistic regression
on Liner SVC Model
Accuracy of Train and Test
Split-Train-Test-Process

34. Model Evaluation

35. Model Evaluation
Liner SVC Model
Logistic Regression Model
Decision Tree Model
XGBOOST Model
Light-GBM Model

36. Deployment

37. Deployment

38. Challenges faced
• Research on history of Drugs and Patients Conditions
• Deciding model building technique

39. How Challenges Overcome
• As we are not much aware of the Medicines we have done a lot of
research to find out the drugs review history.
• We as a team worked so hard to get the knowledge on the previous
year gold price data.
• Which helps us to do the project more effectively.

40. Deciding Model Building Technique
• As we tried many model building techniques every model don’t have
such a significant difference in the output
• We are little bit worried about the output results that we got.
• But we again overcame this as a team, Everyone has worked really
hard on this part and we finally build a model that best suits the data