Executive Summary : | Since the first In Vitro Fertilisation (IVF) baby was born over 40 years ago, over 8 million infants have been born due to infertility treatment. By 2100, 400 million people, or 3% of the global population, may live due to IVF and other fertility procedures. Advancements in infertility treatment have influenced research and treatment options in other medical specialties. This research focuses on predicting Polycystic Ovarian Syndrome (PCOS) and follicular study from a home-centric environment, which enhances the chance of getting conceived naturally by monitoring individual follicle growth. Currently, current approaches and therapies are insufficient for earlier stage diagnosis, especially in a home-centric environment. No technology has been able to independently identify the presence of PCOS in the ovaries, which affects fallopian tubes and alerts patients, doctors, or nurses to take appropriate action. To address these issues, the proposed research processes information gathered from PCOS patients using a cloud computing platform integrated with medical big data mining and machine learning algorithms. The architecture combines an intra-body-based nano-sensor with a body-area network to detect Fallopian Tube activity. Preliminary simulations using a particle-oriented stochastic simulator will investigate the relationship between feasible information rates and key metrics. Apache Kafka will be used as an ingestion tool, and the Advanced Apriori algorithm will be applied to detect characteristics with strong correlations before undergoing a CatBoost Decision Tree model for optimized prediction of PCOS. This is the first assistive system providing out-of-hospital nursing monitoring of women's fertility state, with notable results in terms of scalability and computation times. |
Co-PI: | Dr. Saravanabhavan C, Kongunadu College Of Engineering And Technology, Tholurpatti, Tamil Nadu-621215, Dr. Preethi Palanisamy, Kongunadu College Of Engineering And Technology, Tholurpatti, Tamil Nadu-621215 |