Multi Disease Detection Using Deep Learning

Abstract

Chronic diseases are the main reason for increase in mortality rate. Heart disease, cancer, diabetes, stroke, and arthritis all are chronic diseases. NCDs have a more mortality rate than other diseases. Each year, approximately 5.8 million Indians die from NCDs; globally, 41 million die from chronic diseases. Investment and prevention are two important needs for chronic diseases. It is important to discover the solution for chronic diseases. The management of these types of illnesses includes early detection, patient care, and related services. Because of the explosion of medical data, data management will become a difficult challenge. Deep learning [9] is important in big data fields such as the medical industry. Deep learning is a advancement of machine learning that is capable of performing different tasks. Chronic diseases are diagnosed using different technologies, and that is why deep learning is used to provide the best treatment to patients, resulting in a low mortality rate.

Introduction

I. INTRODUCTION

As time passes, environmental conditions, societal progress, and people's lifestyles change, all of which have a significant impact on health. Chronic diseases have a more effect all over the world. Looking only at cardiovascular diseases, the annual death rate in India is 27%. The main purpose of disease detection and stage prediction are basically to reduce mortality rate by detecting diseases at early stages using Deep Learning [5]. A large number of data are generated in the medical field [6]. But in the medical industry, the complexity level of data is different compared to other fields. They are very vulnerable to impact.Existing deep learning systems only focuses on one disease detection per testing. There is a need for one common system that will work simultaneously on many diseases. We are giving a system that will solve this problem.

In this proposed model, we examine chronic diseases such as heart disease, cancer, diabetes, etc. To perform multiple disease prediction,we using   machine learning algorithms [1]. In this system, parameters are added while analyzing the diseases. Various disease detection is done by machine learning algorithms, for example, Lung Cancer [2]. As we said parameters to the system, we could detect the disease efficiently, at early stages [3] and the accuracy of the diagnosis also increased. This system is an efficient alternative to manual diagnosis techniques [8]. Doctors can cross-verify the test results .The cost of testing for NCDs can be reduced by using this system. The experience of doctors will also increase because of this model.

II. SYSTEM ARCHITECTURE

System uses machine learning and deep learning algorithms for disease prediction[7]. In Multi Disease Prediction System using Deep learning, several phases are shown in Fig. 1. The initial step is to collect the patient's data. After we import the dataset, on each input pre-processing will occur. At the end of visualization, data pre-processing starts. In this step, the system checks for outliers and missing values and scales the dataset.

Following the completion of data pre-processing, the system used KNN, random forest, naive Bayes, and logistic regression algorithms. Using a test dataset, this system selects the best algorithm for correct accuracy for each NCD. After that, the system integrated the file with the Django framework. This helps export the model to the web.

III. METHODOLOGY/ALGORITHM DETAILS

For the detection and prediction of multi-disease using deep learning our system uses various methodologies [4]. Data collection and data analysis, Algorithm techniques, evaluation of accuracies, and model comparison are the steps of this system.

A. Data Collection And Analysis

Data collection and analysis include datasets, training data, testing data, and balanced data. For the dataset, we collect data from Kaggle. Training data is an important aspect of the deep learning model. Training data is used for the accurate prediction of diseases. Testing data is used for performance evaluation collection.

Conclusion

The primary goal of this system is to detect and predict chronic diseases at an early stage to reduce mortality rates. Given the explosion of medical data and its complexity, deep learning plays a major role in disease detection. This is used to create a more precise prediction of diseases. This model will help doctors cross-verify the test results provided by the labs. This system can be used by doctors to enhance their experience with diseases. By using this model, we will be able to reduce the cost of the tests that need to be carried out for the detection of chronic disease

References

[1] D. Dahiwade, G.Patle, and E. Meshram, “Designing disease prediction model using machine learning approach,” 2019 3rd International Conference on Computing Methodologies and Communication 2019, pp 1211-1215, doi:10.1109/ICCMC.2019.8819782. [2] K. Karthick, S. Rajakumar, N. Selvanathan, U.K, B. Saravanan, M. Murali, and B. Dhiyanesh, “Analysis of Lung Cancer Detection Based on the Machine Learning Algorithm and IOT,” 2021 6th International Conference on Communication and Electronic System (ICCES), 2021.9489084. [3] R. Katarya and P. Srinivas, “Predicting Heart Disease at Early Stages using Machine Learning: ASurvey,’’ 2020 International Conference on Electronics and Communication System (ICESC), 2020, pp.302-305, doi: 10.1109/ICESC48915.2020.9155586. [4] G. Sruthi, C. L. Ram, M. K. Singh, N. Malhotra, and N. Sharma, “ Cancer Prediction Using Machine Learning,” 2022 2nd International Conference on Innovative Practices in Technology And Management (ICIPTM),2022, pp.217-221,doi:10.1109/ICIPTM54933.2022.9754059. [5] B. Lalithadevi and S. Krishnaveni, \"Efficient Disease Risk Prediction based on Deep Learning Approach,\" 2022 6th International Conference on Computing Methodologies and Communication (ICCMC), Erode, India, 2022,pp. 1197-1204, doi:10.1109/ICCMC53470.2022.9753851. [6] Prof. Reshma Totare, Anjali Singh, Vishakha Swamy, Tejaswini Yadav “Advanced Database Update and Security Using Markov Decision Policy,” 2021. [7] K. Vayadande et al., \"Heart disease prediction using machine learning and deep learning algorithms,\" 2022 International Conference on Computational Intelligence and Sustainable Engineering Solutions (CISES), Greater Noida, India, 2022, pp. 393-401, doi: 10.1109/CISES54857.2022.9844406. [8] P. M, Y. B, S. S, and S. M, \"Cardiovascular disease prediction using deep learning,\" 2022 6th International Conference on Trends in Electronics and Informatics (ICOEI), Tirunelveli, India, 2022, pp. 1399-1404, doi: 10.1109/ICOEI53556.2022.9777135. [9] M. Chen, Y. Hao, K. Hwang, L. Wang, and L. Wang, \"Disease prediction by machine learning Over Big Data From Healthcare Communities,\" in IEEE Access, vol. 5, pp. 8869-8879, 2017, doi: 10.1109/ACCESS.2017.2694446. [10] A. S. N. Zainab, I. Soesanti and D. R. Utomo, \"Detection of COVID-19 using CNN\'s Deep Learning Method: Review,\" 2022 4th International Conference on Biomedical Engineering (IBIOMED), Yogyakarta, Indonesia, 2022, pp. 59-64, doi: 10.1109/IBIOMED56408.2022.9988533.

Copyright

Copyright © 2023 Prof. R.Y. Totare, Ishwari Ambre, Samruddhi Deore, Aryan Ingle, Akanksha Vetal. 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.