Diabetes prediction using machine learning Domain (Health Care ) Arth 2.0 Group - 3.0

Diabetes prediction using machine learning Domain (Health Care ) Arth 2.0 Group - 3.0.

TEAM MEMBERS name and arth roll number. Prajwal Sontakke (47) Pushpa Paranjape (48) Megha Munje(50).

PROBLEM STATEMENT. Impact of Diabetes in human society (how it impacts to our society ) More time for processing & to know if patient is diabetic or not Why it is important to Predict (over a short period of time ) Why we Need machine learning ?? Human error (precise outcome ).

SOLUTION / YOUR BIG IDEA. To collect data through google form & various websites Train the model using Machine learning algorithm More attribute value gives more accuracy To identify whether a given person in dataset will be diabetic, non diabetic or pre diabetic will be done on basis of attribute values Using Matplotlib we can predict level of diabetes between values 0 to 1 I.e. less diabetic or more diabetic.

IMPACT ON SOCIETY. As we know in modern society we have seen adverse effects on human health . Now a days It would be much easier to handle serious issue like this.

HOW IS THE SOLUTION INNOVATIVE?. It Is an innovative idea as we are not giving priorities to health in this days , so after doing all the tests like insulin , blood pressure to the doc.

TECHNOLOGY YOU ARE PLANNING TO USE. Use of Machine Learning Models I. Pandas library (Array ) II. sklearn.linear_model (for linear regression ) III. matplotlib.pyplot (Graphs).

FEATURES. Easy to maintain record Can classify High level diabetes & low level diabetes Manual to computerized Enable to predict various types of diabetes of different ages More accuracy & Precise outcomes Time Saving and Efficient Also we can tell users how they prevent themselves from being diabetic patient.

FUTURE SCOPE. Improving model by giving more training data Advance regression models & techniques In the future Proposed trained model can be used to build a Web app with user friendly interface & further integrated with various features like chatbot , Doctors near you , how to minimize future risk factors (suggestions) Hybridization of Neural networks like Convolutional Neural Networks & Recurrent Neural Network & SVM (Search Vector Machine ) We can add visitor query module also We can add treatment module.

CONCLUSION. Machine learning has the great ability to revolutionize the diabetes risk prediction with the help of advanced computational methods and availability of large amount of epidemiological and genetic diabetes risk dataset. Detection of diabetes in its early stages is the key for treatment. This work has described a machine learning approach to predicting diabetes levels. The technique may also help researchers to develop an accurate and effective tool that will reach at the table of clinicians to help them make better decision about the disease status.