Intraocular Pressure Monitoring System for Glaucoma Patients Using IoT and Machine Learning

Glaucoma is a condition characterized by unwarranted aqueous humor in the eye, leading to elevated intraocular pressure that can cause damage to the optic nerve. Current treatments for glaucoma are not highly effective and may have significant side effects. Monitoring intraocular pressure in real-time and with accuracy is crucial, particularly for patients with severe glaucoma. Therefore, the development of wearable devices for continuous and precise intraocular pressure monitoring is a promising approach for diagnosing and treating glaucoma. However, existing intraocular pressure measurement and monitoring technologies face challenges in terms of scope, exactness, power feasting, and astuteness, which limit their suitability for glaucoma patients. To address these needs, this study focuses on the design and fabrication of an implantable, flexible intraocular pressure sensor capable of long-term continuous monitoring. This research investigates the working principle, structural design, fabrication process, measurement and control system, characterization, and performance testing of the intraocular pressure sensor. This research holds significant importance regarding achieving personalized and accurate treatment for glaucoma patients. Predictions are undertaken using Random forest, and results are obtained. Random forest has the highest accuracy when compared with other state-of-the-art models.