Machine Learning for Health Predictor Using Cloud Storage

Abstract

There Are Many ML Models For Medical Sector Analysis Focus On A Single Disease. For Example, One Analysis Could Be For Diabetes, Another For Cancer, And Another For Skin Problems. There Is No Universal Approach That Can Forecast Multiple Diseases Using A Single Analysis. By Utilizing The Flask API, This Project Proposes A System That Can Forecast Different Diseases. Diabetes, Heart Disease, And Breast Cancer Were All Examined In This Investigation. Other Disorders, Such As Skin Conditions, Fever Analysis, And A Variety Of Others, Can Be Added Later. Using Machine Learning Methods, Tensor Flow, And The Flask API, Numerous Illness Analyses Was Implemented. The Model Behavior Is Saved Using Python Pickling, And It Is Loaded Using Python Unpicking. As We Are Using Various Kinds Of Vast Health Data Sets, This Leads To Need For A Cloud For Accessing The Data So Here We Use Cloud For Our Data Access, Then The Remaining Process Get Held By Using The Various ML Algorithms

Introduction

I. INTRODUCTION

Machine Learning Models[1] Are Used In Various Sectors For Several Uses, In Medical Sector This Plays An Crucial Role By Performing Various Analysis On Diseases And Predicting The Intensity Of Diseases. This Can Leads To The Awareness Over The Patients ,Timely Checkups May Increases The Number Of Patients In Hospitals, By Using These ML Techniques To Find The Intensity Of The Corresponding Diseases And By Analyzing The Dialogized  Reports We Can Predict The Intensity Weather To Consult A Doctor Or To Take The Simple Medication. According To WHO Doctor To Patient Ratio Is 1:1456 By Implementing These Advanced Machine Learning Techniques[2] We Can Get Some Advantage Of Unnecessary Consultation Of Doctors. So We Can Save Our Time As Well As Increase The Mortality Ratio.

II. Literacy Survey

CAD (Computer Aided Diagnosis) Is A Rapidly Evolving And Diversified Discipline Of Medical Analysis. Now-A-Days, Significant Trials Have Made To Build Computer-Aided Diagnostic Applications, As Mistakes In Medical Diagnosis Processes Can Result In Profoundly False Medical Therapies. In A Computer-Aided Diagnostic Exam, Machine Learning (ML) Is Critical. Body Organs, For Example, Cannot Be Appropriately Identified Using A Simple Equation.

Bio As A Result, Pattern Recognition Essentially Necessitates Instance-Based Training. Pattern Detection And Machine Learning Have The Potential To Improve The Accuracy Of Disease Identification And Approach In The Biomedical Field.

They Also Value The Technique Of Decision-Impartiality. Making's ML Offers A Respectable Service.

When Used To Visual, Text, And Speech Data In Diverse Fields, Deep Neural Networks Have Had A Lot Of Success. The Multi-Layer Design And In-Model Feature Translation Of Deep Learning Models Are Key Factors In These Results. Other Sub-Fields Of Machine Learning, Such As Ensemble Learning, Have Been Inspired By These Design Concepts. In Recent Years, Some Deep Homogeneous Ensemble Models With A Large Number Of Classifiers In Each Layer Have Been Introduced. As A Result, These Models Necessitate A Time-Consuming Computational Classification. Furthermore, Present Deep Ensemble Models Use All Classifiers, Including Those That Aren't Needed, Which Can Reduce The Number Of Classifiers Used.

III. PROPOSED SYSTEM

We Propose A System With A User Interface That Is Both Simple And Elegant, As Well As Time Efficient. We Are Looking For A More Particular Questionnaire That Will Be Followed By The System In Order To Make It Less Time Demanding. The Goal Of This System Is To Serve As A Link Between Patients And Doctors For Consultation.

The Main Feature Will Be Machine Learning, In Which We Will Use Various Algorithms Such As The K-Nearest Algorithm, Decision Tree Algorithm, Convolution Neural Networks, Random Forest Algorithm, And Support Vector Machine To Give Us Accurate Predictions. We Will Compare Which Algorithm Gives The Efficient And Accurate Result. Doctor's Consultation Is Another Element That Will Be Included In Our System. Following The Delivery Of The Findings, Our System Will Advise The User To Seek Medical Advice On The Report. We Will Also Earn Their Faith In The System By Demonstrating That It Is Not Impacting Their Business.

IV. IMPLEMENTATION

A. Cloud Storage: AWS S3

As We Are Using Medical Dataset Which Are Huge Amount So We Are Using Cloud  For The Storage Purpose AWS  S3(Simple Storage Service)S3 Is Interduce In 2006 In Our Region S3 Having Several Advanced Features Like Scalability , Availability , Internet Storage Can Be Extendable To Store Huge Amount Of Data

S3 Store Each Data In 3 Copies Data Can Be Available Even If Any Software Or Hardware Clash Occurs

We Access The Data From Anywhere In The World

Where We Are Having Internet Facility

Conclusion

Data This Project Is The One The Implementation Of The ML Techniques In The Medical Sector As We Are Predicting Several Diseases Like Heart, Liver, Malaria, Pneumonia, Diabetes Etc. This Is Use Full For The Health Condition Of The Patient For The Corresponding Disease Intensity Otherwise To Consult A Doctor In Bad Condition We Are Having The High Accuracy Rate For Each Disease Model So The User Can Get The Accurate Results According To Their Dialogized Reports.

References

[1] Bala Brahmeswara Kadaru And B. Raja Srinivasa Reddy, A Novel Ensemble Decision Tree Classifier Using Hybrid Feature Selection Measures For Parkinson’s Disease Prediction, Int. J. Data Science 3(4) (2018), 289-307. [2] Bala Brahmeswara Kadaru And B. Raja Srinivasa Reddy, An Improved Parallel PSO-FS Based N-SVM Technique For Medical Disease Prediction, J. Adv. Res. Dynam. Control Sys. 10 (2018), 723-737. [3] R. Manne, S.C. Kantheti, Application Of Arti?cial Intelligence In Healthcare:Chances And Challenges, Curr. J. Appl. Sci. Technol. 40 (6) (2021) 78–89. [4] M. Seera, C.P. Lim, A Hybrid Intelligent System For Medical Data Classi?cation, Expert Syst. Appl. 41 (5) (2014) 2239–2249. [5] S. Grampurohit, C. Sagarnal, Disease Prediction Using Machine Learning Algorithms, 2020 Int. Conf. Emerg. Technol. (INCET) (2020) 1–7. [6] P. Deepika, S. Sasikala. Enhanced Model For Prediction And Classi?cation Of Cardiovascular Disease Using Decision Tree With Particle Swarm Optimization, 2020 4th International Conference On Electronics, Communication And Aerospace Technology (ICECA), 2020, Pp. 1068-1072, Doi: 10.1109/ ICECA49313.2020.9297398.

Copyright

Copyright © 2023 Dr. P. Pedd Sadhu Naik, R. Sai Sowmya. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.