International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 04 | Apr 2024
p-ISSN: 2395-0072
www.irjet.net
Disease Prediction and Doctor Recommendation System Abhinav Kandalkar1, Suraj Bute 2, Abhigyan Chhajed3, Vishnu Zanwar4 1,2,3,4 B.E. (Computer Science & Engineering), Prof. Ram Meghe Institute of Research and Technology, Badnera-
Amravati, Maharashtra, India ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Careful examination of patients’ health-related
possible to recommend and prescribe treatment according to risk profiles and patient-specific needs. This approach not only leads to better patient outcomes, but enables a more efficient use of healthcare resources and reduces healthcare costs in the long run. In brief, intelligent systems integration in healthcare will make disease control easier to achieve, wellness promotion more effective and healthcare delivery more efficient.
medical records can predict the likelihood of various diseases. In addition, having the expertise of that particular pathologist, if needed, facilitates appropriate and effective diagnosis. This paper presents a new approach that uses data mining techniques, i.e. Naive Bayes classification algorithm for disease prediction recommended by experts predicted heart rate, blood pressure by sensors, and other externally visible symptoms like fever, chills, headache The Naive Bayes algorithm measures those characteristics this and predicts the disease. Additionally, they provide all the necessary and sufficient information about the patient’s prognosis and the recommended physicians. The recommendation shows the location of the pathologists, their contacts, and other required information based on the user's chosen filter from low cost, more experience, nearby locations, and they use Stanford's The core NLP algorithm compares physician claims with survey research. Thus, users can access appropriate treatment and necessary medical advice as soon as possible. Additionally, users provide their feedback to the recommending physicians who then incorporate it into search results to provide other recommendations based on the search results. Keywords: Core NLP, Naive Recommendation, Django.
Bayes,
1.1 Prediction System The main objective of this manuscript is to mine the data and explore the inner coded structures behind the symptomdisease correlations. The disease diagnosis process involves examination of medical profiles based on key parameters like blood sugar levels, blood pressure readings, blood oxygen saturation, presence of headaches, and other symptoms possible in the context condition. An important method for disease classification which is applied is the Naive Bays classifier that is a probability model which the likelihood of a disease is calculated by different observed symptoms and the medical records. The classifier is used to enable the system to identify the seeming complication that primarily affects an individual. The combination of data mining methods with the advanced classifiers such as Naive Bayes greatly increases the disease prediction models’ accuracy and trustworthiness. It permits a more subtle comprehension of the dynamics between diseases, symptoms and background factors, helping medical professionals to make more precise diagnoses and treatment decisions. In addition, this technique helps in identifying early warning signs and risk factors to that proactive interventions being taken with preventive measures that would ensure people attain optimal health. However, a variety of data mining programmes and methods of prediction together make a real difference in disease prediction and healthcare.
Prediction,
1. INTRODUCTION Healthcare indeed produces a vast amount of data yearly; this includes medical documents that contain incredible information about the patients' health conditions. However, this task might not only be challenging but also critical due to diagnosis and disease prediction in healthcare. Analyzing all these huge data sets allow us to recognize these patterns, trends, and risks associated with a number of conditions. Through the use of advanced analytics, machine learning algorithms, and AI-based resolutions, we can predict the advent of particular diseases with increasing accuracy. Through this type of forecasting, one can achieve the goal of health protection for the society by way of preventive methods and intervention. An intelligent system for the disease prediction is of great importance for the disease control and the maintaining of health status among the people. It enables the accurate and reliable disease risk prediction based on the accumulated data analytics which in turn helps healthcare professionals to make informed decisions and direct targeted interventions. To further advance healthcare personalization, the system makes it
© 2024, IRJET
|
Impact Factor value: 8.226
1.2 Recommendation system In addition to disease operations through data mining and the use of Naive Bayes Classifier, the system gives a professional on demand via the selected filters by a user. The review-oriented recommendations are obtained by collecting and processing reviews about various physician from other users. These reviews are then processed using the CoreNLP for sentiment analysis and more valuable information extraction. The system seeks the closest experts to the user's location in a case where location-based
|
ISO 9001:2008 Certified Journal
|
Page 383