Page 151 - Emerging Trends and Innovations in Web-Based Applications and Technologies

International Journal of Trend in Scientific Research and Development (IJTSRD)
Special Issue on Emerging Trends and Innovations in Web-Based Applications and Technologies
Available Online: www.ijtsrd.com e-ISSN: 2456 – 6470

Advancing Horizons in Chronic Diseases:
Research Innovation Insights

3
Vaishnavi Watkar , Shivani Ayyagari , Prof. Anupam Chaube
2
1
1,2,3 Department of Science and Technology,
1,2,3 G H Raisoni College of Engineering and Management, Nagpur, Maharashtra, India

ABSTRACT illnesses. This could be achieved by using a cutting-edge
Technological development, including machine learning, machine learning technique to ensure that this
has a huge impact on health through an effective analysis of categorization reliably identifies persons with chronic
various chronic diseases for more accurate diagnosis and diseases. The prediction of diseases is also a challenging task.
successful treatment. In the field of biomedical and Hence, data mining plays a critical role in disease prediction.
healthcare communities the accurate prediction plays the With ML models, it can also be possible to improve quality of
major role to find out the risk of the disease in the patient. medical data, reduce variation in patient rates, and save in
The only way to overcome with the mortality due to chronic medical costs.
diseases is to predict it earlier so that the disease
prevention can be done. Such model is a Patient’s need in Machine learning examine the study and construction of
which Machine Learning is highly recommendable. But the algorithms that can learn from and make predictions on data.
precise prediction on the basis of symptoms becomes too It is closely related to (and often overlaps with)
difficult for doctor. The correct prediction of disease is the computational statistics, which also focuses on prediction-
most stretching task. To overcome this problem data making through the use of computers.
mining plays an important role to predict the disease. We
use Heart disease, Kidney disease, Cancer disease and The preprocessing handling we discuss includes missing
Diabetes disease datasets, In order to build reliable values, outliers, feature selection, normalization, and
prediction models for these chronic diseases using data imbalance. The final discussions of this paper are open
mining techniques. The most relevant features are selected issues, and the potential future works in improving the
from the dataset for improved accuracy and reduced prediction performance for chronic diseases using a data
training time. The system analyzes the symptoms provided preprocessing handling and machine learning methods.
by the user as input and gives the probability of the disease Our project mainly focusses on the following mentioned
as an output Disease by using, random forest and decision outcomes:-
tree we are predicting diseases like Diabetes, Heart, Cancer 1. Early Detection of Chronic Diseases
and Kidney. For each chronic disease, diverse models, 2. Personalized Treatment Plans
techniques, and algorithms are used for predicting and 3. Enhanced Medical Data Quality
analyzing. The common prediction objective is to minimize 4. Smarter Health Decision-Making
the prediction error as low as possible. The final 5. Customizing Health Plans for Individuals
discussions of this paper are works in improving the
prediction performance for chronic diseases using a data By using machine learning and deep learning algorithms this
particular research paper manages to ensure chronic disease
preprocessing handling.
management in order to improve predictions and also

advancing overall healthcare efficiency, ultimately benefiting
KEYWORDS: Chronic Diseases, Machine Learning, Diseases both patients and healthcare systems.
Prediction, Accuracy, Prediction performance
II. RELATED WORK
I. INTRODUCTION This section describes the related works that are performed
“Advancing Horizons in Chronic Diseases: Research in developing the proposed model for predicting chronic
Innovation Insights “refers to discovering new opportunities diseases. The following are the discussions made by
and solutions for managing long-term illnesses such as reviewing the existing literature that helps develop the
diabetes, heart disease, and cancer. It emphasizes how proposed system efficiently and effectively.
advanced research methods and modern technologies, like AI Different machine-learning techniques have been used for
and data analysis, are transforming how these diseases are effective classification of chronic kidney disease from
diagnosed, treated, and prevented. The focus is on exploring patients’ data which are described as follows:-
the latest developments and sharing knowledge to improve
healthcare outcomes. Nowadays, humans face various Charleonnan et al. [8] did comparison of the predictive
diseases due to the current environmental condition and models such as K-nearest neighbors (KNN), support vector
their living habits. machine (SVM), logistic regression (LR), and decision tree
(DT) on Indians Chronic Kidney Disease (CKD) dataset in
The identification and prediction of such diseases at their order to select best classifier for predicting chronic kidney
earlier stages are much important, so as to prevent the disease. Tey have identified that SVM has the highest
extremity of it. It is difficult for doctors to manually identify classification accuracy of 98.3% and highest sensitivity of
the diseases accurately most of the time. The goal of is to 0.99
identify and predict the patients with more common chronic

IJTSRD | Special Issue on Emerging Trends and Innovations in Web-Based Applications and Technologies Page 141