to download project abstract

ABSTRACT

Here we propose a system that allows users to get instant guidance on their health issues through an intelligent health care system online. The system allows user to share their symptoms, issues and also he/she may directly search doctors for their medical issue with their requirements. The system has many features suggesting doctors as per the disease and system lists various expert Doctors available. System then processes user’s symptoms to check for various illnesses that could be associated with it. In this we are going to implement a system which is related to smart health prediction in order to reduce the time of a user. The main objective of developing this project is to provide a proper medical guidance to the patient for their health issues by providing accurate results . Here, the system concentrates on the symptoms of patient’s disease and based on the symptoms, the data is classified from the dataset and finally the disease name is predicted. We have 3 modules; they are patient, doctor, and admin modules. The primary step is, the user (patient/doctor) needs to register if he is new to the application or else he can directly login with his credentials. The admin authenticates the credentials and allows the user to access. There is a facility that user can upload records and there is a feedback system available to the user which is directly visible by the admin. So, the doctor can study the patient and give a proper treatment.

Keywords: Disease prediction, Doctor, Patient, Symptoms, Feedback, Appointment, Admin.

Introduction

The health industry has been growing a lot from past few years .This technique has gained a lot of importance in medical areas. It has been calculated that a care hospital may generate five terabytes of data in the year. In our day to day life we have lot of other problems to deal with and we neglect our health problems. So in order to overcome such problem we have designed user friendly website which helps users to get diagnosed from their residence at any time. We also provide an option for booking an appointment with the doctor to discuss health related problems and get diagnosed properly. Data mining is the process of discovering anomalies, patterns and correlations within Large data set using sophisticated mathematical algorithms to predict outcomes. Using techniques, you can use the information to increase revenues, cut costs, improve customer relationships, and reduce risks and more. The task of actual data mining is to automatically analyze the large quantities of data to extract previously unknown, interesting patterns such as groups of data records unusual records (anomaly detection), and dependencies.[1]In simple words, data mining is defined as a process used to extract usable data from a larger set of any raw data. It implies analyzing data patterns in large batches of data using one or more software. Data mining has applications in multiple fields, like science and research. As an application of data mining, businesses can learn more about their customers and develop more effective strategies related to various business functions and in tum leverage resources in a more optimal and insightful manner. This helps businesses be closer to their objective and make better decisions. Data mining involves effective data collection and warehousing as well as computer processing. For segmenting the data and evaluating the probability of future events, data mining uses sophisticated mathematical algorithms. Data mining is also known as Knowledge Discovery in Data (KDD).The term “data mining is in fact a inapplicable title, because the goal is the extraction of patterns and knowledge from large amounts of data, not the extraction (mining) of data itself. Many classification techniques are available in data mining. There are decision trees, K nearest neighbor, Bayesian classification, artificial neural networks (ANN), support vector machine (SVM) and so on.

Algorithms:

Naïve Bayes Algorithm

It is a classification technique based on Bayes’ Theorem with an assumption of independence among predictors. In simple terms, a Naive Bayes classifier assumes that the presence of a particular feature in a class is unrelated to the presence of any other feature. Random questions are generated related to the symptoms choose by the applicant. As per that, the user continues to opt other symptoms through the random questions and finally the class with higher posterior probability will be displayed as the disease name. Other algorithms like random forest, decision tree can also be used for predicting the diseases, but there are few drawbacks in both the algorithms. They are:

  • Random forests are highly complex in nature. They are much harder and time consuming to construct.
  • Decision trees are unstable which means if there is a small change in the data, it can lead to large change in the structure of the optimal decision tree. Decision tree requires large amount of training data in order to cover all possibilities. Results obtained in decision tree on small datasets are poor.

Drawbacks of hill climbing algorithm:

One more algorithm is also there for implementing this framework namely Hill climbing algorithm but it has some drawbacks when compared to Naïve Bayes algorithm. The following are the disadvantages of hill climbing algorithm.

  • It got failed to find a better solution.
  • Either algorithm may terminate not by finding a goal state but by getting to a state from which no better state can be generated.
  • Either algorithm may terminate not by finding a goal state but by getting to a state from which no better state can be generated.
  • Naive Bayes is used a lot in robotics and computer vision, and does quite well with those tasks. Decision trees perform very poorly in those situations.
  • Not an efficient method-it gets stuck at all peaks.

Advantages of Naïve Bayes:

  • It works well with low amount of training data and doesn’t need all the possibilities.
  • An accurate result is possible in case of large data sets and is more efficient compared to decision tree.
Leave a Comment

Comments

No comments yet. Why don’t you start the discussion?

Leave a Reply

Your email address will not be published. Required fields are marked *