Early stage of diabetics prediction using machine learnin

Project

1. EARLY-STAGE DIABETES PREDICTION USING MACHINE LEARNING TECHNIQUE SUPERVISOR BATCH MEMBERS Mrs.D.HEMALATHA M.E., RAJA GOWTHAM D 210820205064   VINOTH S 210820205083   PRINCE BENJAMIN J 210820205302

2. Objective The goal is to develop a machine learning model for Diabetics prediction, to potentially replace the updatable supervised machine learning classification models by predicting results in the form of best accuracy by comparing supervised algorithm. Dibetics is one of the major factors in our healthcare domain. There are lot of patients who are actively present in the world. It is difficult to find the dibetics . So this project can easily find out the wheather the patient has dibetics or not.  

3. Abstract: Early stage diabetic prediction using machine learning is a significant research area that aims to improve the early detection and management of diabetes. Diabetes is a chronic metabolic disorder that affects a large population worldwide and can lead to severe health complications if left untreated. Machine learning algorithms have shown promise in analysing diverse datasets and identifying patterns that may indicate the presence of early signs of diabetes. This paper presents an overview of the approach to developing a machine learning model for early stage diabetic prediction. Early stage diabetic prediction using machine learning has the potential to revolutionize healthcare by enabling timely intervention and personalized treatment for individuals at risk of developing diabetes. By identifying high-risk individuals early on, healthcare providers can implement preventive measures and lifestyle interventions to mitigate the progression of the disease and reduce associated complications. Future research in this field should focus on enhancing the accuracy and interpretability of predictive models, integrating additional data sources, and expanding the scope to cover various subtypes of diabetes.

4. Existing System: People with type 1 diabetes (T1D) face the challenge of administering exogenous insulin to maintain blood glucose (BG) levels in a safe physiological range, so as to avoid (possibly severe) complications. By automatizing insulin infusion, the artificial pancreas (AP) assists patients in this challenge. While insulin can decrease BG, having another input inducing glucose increase could further improve BG control. The improvement is limited for those already well controlled by the state-of-art strategy but relevant for the others: the 25th percentile of this metric is increased from 74.75% to 79.06% in the population. This is achieved while simultaneously decreasing time spent in hypoglycaemia (from 0.5% to 0.12% in median) and with limited manual interventions (2.86 per day in median).

5. Disadvantages: They did not implement the deployment process They implemented simple method. They did not Implement Machine Learning. They did not do data preprocessing and data cleaning process. They did not do data visualization by using Heat map, Pychart . Data analysis process Histogram, Plot and Graphs. They did not compared more than an algorithms to getting better accuracy level. They did not figure out performance and confusion metrics. They did not create performance and confusion metrics graphs and diagrams. The accuracy level and performance level are low. They did not train the data to computer properly.

6. Proposed System: Develop a machine learning-based system to predict the likelihood of an individual developing diabetes in the early stages. Data Collection: Gather comprehensive data related to diabetes risk factors, including: Patient demographics (age, gender, ethnicity). Medical history (family history of diabetes, gestational diabetes, etc.). Lifestyle factors (diet, physical activity, etc.). Clinical measures (blood pressure, BMI, cholesterol levels, etc.). Blood sugar levels (fasting glucose, HbA1c, etc.). Data Pre-processing: Clean and pre-process the data to handle missing values, outliers, and standardize formats. Normalize numerical features and encode categorical variables. Split the dataset into training and testing sets. Feature Selection: Identify and select the most relevant features using techniques like feature importance, correlation analysis, or dimensionality reduction.

7. Advantages: We implemented the deployment process by using Frontend codes like Html, Css , Bootstrap and Python Framework like Django or Flask. We implemented data preprocessing and data cleaning process by removing non-null values, missing values, duplicate values, unwanted data and imbalance data. We implemented data visualization by using Heat map, Pychart . We implemented Data analysis process by using Histogram, Plot and Graphs. We compared more than a two algorithms to getting better accuracy level. We figure out performance and confusion metrics value properly. We Created performance and confusion metrics graphs and diagrams. We improved the accuracy level and performance level. We implemented Machine Learning properly. We did train the data to computer properly. The train data level is 70% or 80%

8. Literature Review Title : Diabetes Prediction using Machine Learning Algorithms Author: Aishwarya Mujumdar, Dr. Vaidehi Year : 2019 Diabetes Mellitus is among critical diseases and lots of people are suffering from this disease. Age, obesity, lack of exercise, hereditary diabetes, living style, bad diet, high blood pressure, etc. can cause Diabetes Mellitus. People having diabetes have high risk of diseases like heart disease, kidney disease, stroke, eye problem, nerve damage, etc. Current practice in hospital is to collect required information for diabetes diagnosis through various tests and appropriate treatment is provided based on diagnosis. Big Data Analytics plays an significant role in healthcare industries. Healthcare industries have large volume databases. Using big data analytics one can study huge datasets and find hidden information, hidden patterns to discover knowledge from the data and predict outcomes accordingly. In existing method, the classification and prediction accuracy is not so high. In this paper, we have proposed a diabetes prediction model for better classification of diabetes which includes few external factors responsible for diabetes along with regular factors like Glucose, BMI, Age, Insulin, etc. Classification accuracy is boosted with new dataset compared to existing dataset. Further with imposed a pipeline model for diabetes prediction intended towards improving the accuracy of classification

9. Title : A model for early prediction of diabetes Author: Talha Mahboob Alama , Muhammad Atif Iqbala Year : 2019 Diabetes is a common, chronic disease. Prediction of diabetes at an early stage can lead to improved treatment. Data mining techniques are widely used for prediction of disease at an early stage. In this research paper, diabetes is predicted using significant attributes, and the relationship of the differing attributes is also characterized. Various tools are used to determine significant attribute selection, and for clustering, prediction, and association rule mining for diabetes. Significant attributes selection was done via the principal component analysis method. Our findings indicate a strong association of diabetes with body mass index (BMI) and with glucose level, which was extracted via the Apriori method. Artificial neural network (ANN), random forest (RF) and K-means clustering techniques were implemented for the prediction of diabetes. The ANN technique provided a best accuracy of 75.7%, and may be useful to assist medical professionals with treatment decisions.

10. List of Modules: Data Pre-processing Data Analysis of Visualization Implementing Algorithm 1 Implementing Algorithm 2 Deployment

11. Environmental Requirements: Software Requirements: Operating System : Windows 10 or later Tool : Anaconda with Jupyter Notebook Hardware requirements: Processor : Intel i3 Hard disk : 10 GB RAM : 4 GB

12. System Architecture:

13. Use Case Diagram:

14. Activity Diagram :

15. Entity Relationship Diagram (ERD):

16. Module Description: Data Pre-processing: Validation techniques in machine learning are used to get the error rate of the Machine Learning (ML) model, which can be considered as close to the true error rate of the dataset. If the data volume is large enough to be representative of the population, you may not need the validation techniques. However, in real-world scenarios, to work with samples of data that may not be a true representative of the population of given dataset. To finding the missing value, duplicate value and description of data type whether it is float variable or integer. The sample of data used to provide an unbiased evaluation of a model fit on the training dataset while tuning model hyper parameters.

17. Data visualization: Data visualization It is an important skill in applied statistics and machine learning. Statistics does indeed focus on quantitative descriptions and estimations of data. Data visualization provides an important suite of tools for gaining a qualitative understanding. This can be helpful when exploring and getting to know a dataset and can help with identifying patterns, corrupt data, outliers, and much more. With a little domain knowledge, data visualizations can be used to express and demonstrate key relationships in plots and charts that are more visceral and stakeholders than measures of association or significance. Data visualization and exploratory data analysis are whole fields themselves and it will recommend a deeper dive into some the books mentioned at the end.

18. Results and Discussion Step 1: Open and install Anaconda Navigator Tool & launch Visual Studio.

19. Step 2 : After the deployment of visual studio the website will be launched, Then register your username and password for logging in to website.

20. Step 3: The login account has been registered & successfully logged in to website.

21. Step 4: Enter the values for diabetes patient current prediction level & Submit.

22. Step 5: After clicking submit button, The result for current diabetes prediction is shown.

23. Step 6: Enter the values for finding early stage diabetes level and submit.

24. Step 7: After clicking submit button, The result for early stage diabetes prediction is shown.

25. Conclusion: The analytical process started from data cleaning and processing, missing value, exploratory analysis and finally model building and evaluation. The best accuracy on public test set of higher accuracy score algorithm will be find out. The founded one is used in the application which can help to find the Diabetics of the patient.

26. Future Work: In order to streamline the deployment of the project into the cloud and optimize its functionality within the IoT system, several key steps need to be taken. Firstly, it's crucial to assess the specific requirements and constraints of the IoT environment to ensure compatibility and efficiency. This involves understanding the data flow, network architecture, and security protocols. Next, the project should be adapted to leverage cloud-based services effectively, such as scalable computing resources, storage solutions, and data analytics tools.

27. [1] L. DiMeglio, C. Evans-Molina, and R. Oram, “Type 1 diabetes,” Lancet, vol. 391, pp. 2449–2462, Jun. 2018. [2] C. Cobelli , C. D. Man, G. Sparacino , L. Magni, G. D. Nicolao, and B. Kovatchev, “Diabetes: Models, signals and control,” IEEE Rev.Biomed . Eng., vol. 2, pp. 54–96, 2009. [3] E. Bekiari et al., “Artificial pancreas treatment for outpatients with type1 diabetes: Systematic review and meta-analysis,” Brit. Med. J., vol. 361, Apr. 2018, Art. no. k1310. [4] H. Thabit and R. Hovorka , “Coming of age: The artificial pancreas for type 1 diabetes,” Diabetologia , vol. 59, no. 9, pp. 1795–1805, 2016. [5] T. Peyser , E. Dassau , M. Breton, and J. S. Skyler, “The artificial pancreas: Current status and future prospects in the management of diabetes,” Ann. New York Acad. Sci., vol. 1311, no. 1, pp. 102–123, Apr. 2014. References

28. [6] D. Shi, S. Deshpande, E. Dassau , and F. J. Doyle III, Feedback Control Algorithms for Automated Glucose Management in T1DM: The State of the Art, 1st ed. San Diego, CA, USA: Academic, 2019. [7] G. M. Steil , K. Rebrin , C. Darwin, F. Hariri, and M. F. Saad, “The effect of insulin feedback on closed loop glucose control,” J. Clin. Endocrinol. Metabolism, vol. 55, pp. 3344–3350, Dec. 2016. [8] G. M. Steil , K. Rebrin , C. Darwin, F. Hariri, and M. F. Saad, “Feasibility of automating insulin delivery for the treatment of diabetes”, Diabetes, vol. 55, no. 12, pp. 3344–3350, Dec. 2006. [9] P. Herrero, P. Georgiou, N. Oliver, D. G. Johnston, and C. Toumazou , “A bio inspired glucose controller based on pancreatic β-cell physiology,” J. Diabetes Sci. Technol., vol. 6, no. 3, pp. 606–616, May 2012. [10] E. Atlas, R. Nimri , S. Miller, E. A. Grunberg, and M. Phillip, “MD-logic artificial pancreas system: A pilot study in adults with type 1 diabetes,” Diabetes Care, vol. 33, pp. 1072–1076, May 2010.