Disease Prediction using Machine Learning Algorithms

Grampurohit, Sneha; Sagarnal, Chetan

doi:10.1109/incet49848.2020.9154130

Cited by 88 publications

(17 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The proposed method had high predictive accuracy, with 87.1% for Heart Disease Detection using Logistic Regression, 85.71% for Diabetes Predictability using a Vector Support Machine (line kernel), and 98.57% for AdaBoost Cancer Screening. Grampurohit, S. & Sagarnal, C. [2] analyzes performance metrics for various types of machine learning models used in diagnostic tests. Naive Bayes, Decision Trees, and K-Nearest Neighbor are commonly used, but the Support Vector Machine (SVM) is the most effective in diagnosing kidney disease and Parkinson's disease, while Logistic Regression (LR) plays a key role in predicting heart disease.…”

Section: IImentioning

confidence: 99%

Disease Prediction and Treatment Recommendation Using Machine Learning

Mahata¹,

Kapadiya²,

Kushwaha³

et al. 2023

IJRASET

View full text Add to dashboard Cite

Despite the availability of advanced technology and easy access to information, many people still rely on traditional methods of seeking medical treatment, such as visiting hospitals and consulting doctors for even minor symptoms. However, this approach can be time-consuming and inefficient, as patients with minor illnesses can take up valuable resources that could be better used to treat more serious cases. As a result, this research proposes a new approach to disease prediction using machine learning and symptom-based analysis. The goal is to develop a predictive model that can accurately identify potential diseases based on a patient's symptoms. This model utilizes machine learning techniques to analyze and process symptom data, allowing for quick and precise disease prediction. The study uses a large dataset of patient symptoms and medical records to train and test the model, which demonstrated high accuracy in predicting diseases. The results of this study suggest that the proposed model could be a useful tool for early diagnosis and treatment of diseases, with the potential to improve healthcare outcomes. Overall, this research represents an important contribution to the field of healthcare informatics, with possible applications in disease prevention, treatment, and management.

show abstract

Section: IImentioning

confidence: 99%

Disease Prediction and Treatment Recommendation Using Machine Learning

Mahata¹,

Kapadiya²,

Kushwaha³

et al. 2023

IJRASET

View full text Add to dashboard Cite

show abstract

“…A multidisease prediction system is built using CNN and Random Forest Classifier in the study an accuracy of 95% and 96% using CNN, where the users upload their images. In the study [3], an application is built to detect, which disease the patient is suffering from, they have considered 95 features, and took 5 symptoms from the user with the help of a Decision Tree, Random Forest, and Naive Bayes model, they were able to classify, which disease the patient is suffering from out of 41 diseases, and obtained an accuracy of 95% for all the three models. The authors can detect heart disease, diabetes, and breast cancer using Logistic Regression, SVM, and AdaBoost classifiers and obtained accuracy levels of 87%, 85%, and 98% in the study [1].…”

Section: Literature Surveymentioning

confidence: 99%

Multi Disease Detection Using Machine Learning

2023

ijfans

View full text Add to dashboard Cite

Machine learning algorithms are widely used to detect the occurrence of diseases in patients. Many of the machine learning algorithms in use today are only concerned with detecting a single disease. No system exists that can detect multiple diseases in a single application, saving patients' time. Even though there are some systems that can detect a variety of diseases, the models' accuracy varies, which has a significant impact on patients' quality of life. Building a multi-disease detection system is preferable to deploying numerous applications for each disease when a health organization wants to use machine learning models. It also saves capital. We are using the Ensembling Voting Classifier (Boosting) in Logistic Regression, SVM, Naïve Bayes, and KNN algorithms, and Random Forest which is high-efficient and gives the best accuracy. We are detecting three diseases namely Thyroid, PCOS, and Liver. When a user submits their medical information, we will be able to detect which of three diseases they are likely to be suffering from.

show abstract

“…In order to address health-related issues by enabling medical professionals to identify diseases at an early stage, the authors of [15] created a prediction model that analyzes the user's symptoms and forecasts the disease using machine learning algorithms (DT classifier, RF classifier, and NB classifier). A sample of 4920 patient records with diagnoses for 41 illnesses makes up a dataset.…”

Section: Related Workmentioning

confidence: 99%

A Framework for Predictive - Diagnosis of Prevalent Illness among University Students

Isiaka

Agbogun

Kolajo

2022

J. Appl. Artif. Intell.

View full text Add to dashboard Cite

The issue of identifying the prevalence of sickness that is linked to the population of a nation, state, neighborhood, organization, or school has not been taken into consideration by the majority of prior studies on the prediction of illness among populations. They frequently merely choose any sickness based on assumption, while those that determined the prevalence of the condition before developing their framework utilized survey data or data from web repositories, which removes idiosyncrasies from those data. In order to increase performance, this research suggests an enhanced data analytics framework for the predictive diagnosis of common illnesses affecting university students. In order to do this, exploratory data analysis (EDA) using a multivariate analytic technique was conducted using a high-level model methodology using CRISP-DM stages. When the suggested strategy was evaluated on support vector machines, ensemble gradient boosting, random forest, decision tree, K-neighbors, and linear regression machine learning models, experimental findings revealed that it outperformed current methods. In comparison to other reviewed frameworks that used survey datasets, standardized or online repositories' dataset, the framework with emphasis on the ensemble Gradient Boosting classifier and regression had accuracy of 100% and mean absolute error of 0.18, respectively. It is also steady due to its ability to manage both small and big data sets without impacting the model's performance. The enhanced results through localized dataset demonstrate the benefit of including local data sources in the process of developing models for the diagnosis and prognosis of prevalent illnesses of any area with people.

show abstract

Disease Prediction using Machine Learning Algorithms

Cited by 88 publications

References 4 publications

Disease Prediction and Treatment Recommendation Using Machine Learning

Disease Prediction and Treatment Recommendation Using Machine Learning

Multi Disease Detection Using Machine Learning

A Framework for Predictive - Diagnosis of Prevalent Illness among University Students

Contact Info

Product

Resources

About