Recommendation System For Patients

Project Title

Recommendation System For Patients

Project Area of Specialization Artificial IntelligenceProject Summary

• The idea is to make an AI-Based Recommendation System for mental patients who are suffering from depression and anxiety through Content-based filtering, and after that, we display both the depression and anxiety levels of a user and show them to a user interface altogether without seeing their data.
• The project aimed is to "saves their life from suicide and drug addiction etc., but also saves their data from the other people."

Project Objectives

• The main objective of an AI-based recommendation system is to provide "A distributed platform for the patient where the patient can get a recommendation without sharing their data to any third-party.

          By making this distributed system, the user can:

• Get security where personal data is only accessible by patients.
• Get better and more reliable recommendations with a sequence of steps that could easily be followed by the patient. Save their time and money because of its open-source availability and free services. But in order to make a distributed system, there may become issues arise which are given below in the form of points.

Project Implementation Method

The methodology of this AI recommendation system is mentioned in the above section, as you can see the first module is the user login where a user is giving the answer to the questions which is followed by PHQ (Patient health questionnaire) strategy then it will move to the pre-trained model by using web API. Then the data will flow on the Scaling phase in which we find the depression and anxiety level with the help of the Hamilton Rating Scale. In we have two case studies which are a) When a user has no depression and anxiety level: In this case, we will not move forward to the next phase(I. Recommendation). Second one b) When a user has depression and anxiety level: In this case, we will move forward to the next phase (I. Recommendation). Forgiving recommendation to a patient. Then according to the given case studies as I mentioned earlier the data will go to the AI-based recommendation system which will further classify the type of recommendations as per user requirements (according to patient’s disease). As that we move to the second last part which is the Google teachable machine which is our main part of this project, it is a web-based tool that makes creating machine learning models fast, easy, and accessible to everyone. But there are still exits some requirements which is availability I discussed this on the Consequential of the website section which is Docker Container it is a virtual machine that provides a virtual environment to your system in order to provide computations and specific features into a package etc. So, by using the docker container we can deploy the ML model.

Benefits of the Project

• Time Saving-It will save time for both patients and doctor (in case the patent visit the clinic or hospital).
• No Treatment Charges-a lot of patients can get freedom from depression and anxiety without paying any treatment charges.
• Safety And Security-Get security where personal data is only accessible by patients using distributed systems.

Technical Details of Final Deliverable

This system will be based on the following technologies:

Google Teachable Machine- is a web-based tool that makes creating machine learning models fast, easy, and accessible to everyone

Web API- is an interface between client-side (react.js) or teachable machine which is being provided google servers.

React.js - is a front-end JavaScript library for building user interfaces based on UI components. Which asks some relevant questions about patients’ mental disorders in order to give their data as an input to a model which is being served from Google servers.

Docker Container- is a virtual machine that provides a virtual environment to your system in order to provide computations and specific features into a package, etc. So, by using the docker container we can deploy the ML model.

Final Deliverable of the Project Software SystemCore Industry MedicalOther Industries IT , Health Core Technology Artificial Intelligence(AI)Other Technologies Cloud InfrastructureSustainable Development Goals Good Health and Well-Being for PeopleRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	4100
printing	Miscellaneous	90	10	900
printing	Miscellaneous	90	20	1800
Report Binding	Miscellaneous	2	150	300
AWS Docker Container	Equipment	1	1100	1100