Problem Statement - Diabetes, if left undiagnosed until later stages, becomes incurable. The delayed diagnosis of diabetes poses significant challenges in healthcare, as many individuals fail to recognize symptoms, leading to delayed treatment. Traditional diagnostic methods may miss cases due to the disease's complexity.By empowering early detection and intervention, we aim to enhance health outcomes. Utilising Big Data Analytics & Machine Learning in order to predict the risk of diabetes mellitus type 2 based on clinical parameters. This enables early detection of diabetes, eliminating the need for invasive diagnostic procedures.
Big Data Analytics is pivotal in the healthcare sector, offering significant contributions. By harnessing its power, one can delve into vast datasets, uncovering concealed insights and patterns to unearth valuable knowledge. Machine Learning emerges as a crucial tool within this framework, facilitating the prediction of outcomes with precision. Moreover, it enables the development of sophisticated algorithms capable of analyzing complex healthcare data, ultimately enhancing decision-making processes and improving patient care.
In 2019, diabetes was the direct cause of 1.5 million deaths and 48% of all deaths due to diabetes occurred before the age of 70 years. Another 460 000 kidney disease deaths were caused by diabetes, and raised blood glucose causes around 20% of cardiovascular deaths.
Diabetes is a chronic disease that occurs either when the pancreas does not produce enough insulin or when the body cannot effectively use the insulin it produces. Insulin is a hormone that regulates blood glucose. Hyperglycaemia, also called raised blood glucose or raised blood sugar, is a common effect of uncontrolled diabetes and over time leads to serious damage to many of the body's systems, especially the nerves and blood vessels.
In hospitals, current method to detect diabetes is to collect blood samples and conduct Fasting, Postprandial and HbA1c glucose level tests. To supplement them and predict the risk of diabetes beforehand, we are using Big Data Analytics & ML to predict the risk of diabetes based on certain clinical parameters like Blood glucose levels, BMI, Insulin concentration, Comorbidities etc.
Scikitlearnex
Intel® Optimization for TensorFlow: Used for building, training, and validating the disease prediction models.
XGBoost for Machine Learning
This hackathon has helped me gain practical experience and enhance my skills.
Machine Learning Fundamentals: Through the hackathon, I gained a solid understanding of machine learning concepts, including supervised learning, unsupervised learning, and possibly reinforcement learning. I learned about the importance of data preprocessing, feature engineering, model selection, and evaluation metrics.
Algorithms: I explored various machine learning algorithms, including regression, classification, clustering, and dimensionality reduction algorithms. I likely gained hands-on experience with algorithms such as linear regression, logistic regression, decision trees, random forests, support vector machines, k-nearest neighbors, k-means clustering, principal component analysis (PCA), and others.
Intel IDC and One API Toolkits: I leveraged Intel Infrastructure Development Cloud (IDC) and One API toolkits to develop machine learning models. These tools provided me with access to Intel's powerful infrastructure and optimized libraries for accelerating machine learning workloads.
Scikit-learn: I used scikit-learn, a popular machine learning library in Python, to implement machine learning algorithms, preprocess data, and evaluate models. Scikit-learn provides a wide range of tools for machine learning tasks, making it a valuable tool for practitioners.
Predictive Modeling: I learned how to build predictive models using machine learning algorithms. This involved tasks such as data preprocessing, feature selection, model training, hyperparameter tuning, and model evaluation. I gained insights into best practices for building accurate and robust predictive models.
Problem Solving and Collaboration: Participating in the hackathon provided me with opportunities to solve real-world problems using machine learning techniques. I collaborated with teammates, shared knowledge, and worked together to develop solutions. This experience honed my problem-solving skills and ability to work effectively in a team.
Communication Skills: Throughout the hackathon, I communicated my ideas, approaches, and results effectively. Whether through presentations, documentation, or discussions with teammates, me practiced articulating complex concepts in a clear and concise manner.
Overall, the Intel genAI Hackathon provided me with a comprehensive learning experience in machine learning, equipped me with practical skills, and empowered me to apply my knowledge to real-world problems. By participating in the hackathon, I've taken significant steps towards becoming a proficient machine learning practitioner.