Abstract:
Celiac disease is a chronic autoimmune condition that affects the small intestine in people who are genetically predisposed. Gluten, a protein present in wheat, barley, and rye, causes an inflammatory response that destroys the gut lining, triggering the illness. Early and correct diagnosis is critical for efficient care and improved patient quality of life. Machine learning (ML) approaches have showed considerable promise in a variety of medical disciplines, including celiac disease, in recent years. This review paper provides an in-depth examination of the use of machine learning techniques in the diagnosis and management of celiac disease. The study opens with an overview of celiac disease, its prevalence, and the difficulties in diagnosing it due to its varied clinical presentation and different severity levels. The sections that follow dig into the application of machine learning algorithms to various areas of celiac disease management. To begin, the research investigates ML applications in celiac disease diagnosis and classification utilizing a variety of data sources, including serological testing, genetic markers, and histo-pathological data from biopsy samples. Support vector machines, random forests, and deep learning models are investigated for their ability to enhance accuracy and speed in diagnosing celiac disease. Second, the paper looks at how machine learning can be used to anticipate illness development and associated complications. When applied to longitudinal data, machine learning algorithms can assist identify people at risk of developing refractory celiac disease or associated autoimmune illnesses, allowing for early intervention and personalized treatment plans. The article also examines how machine learning might improve gluten-free diet adherence by analyzing eating trends and monitoring patient compliance. Furthermore, ML-driven decision support systems for dieticians and patients can help discover hidden sources of gluten in foods and provide suitable replacements, delivering a balanced and nutritious diet. The review also addresses the difficulties and limitations encountered when using machine learning to celiac disease. Issues such as data privacy, model interpretability, and potential biases are highlighted, emphasizing the importance of using robust and ethical approaches when applying ML techniques. We can conclude that machine learning approaches have the potential to significantly advance celiac disease detection and management. ML-driven solutions can greatly improve patient care and outcomes by improving accuracy in early diagnosis, risk prediction, and personalized nutrition advice. More study and collaboration between physicians, researchers, and data scientists are needed, however, to fully harness the power of machine learning in addressing the complexity of celiac disease and improving patient outcomes.
Page(s):
397-397
DOI:
DOI not available
Published:
Journal: Abstract Book on International Conference on Food and Applied Sciences (ICFAS-23) 3-5 August 23, Volume: 0, Issue: 0, Year: 2023