Advancing Remote Cognitive Assessments through Telemedicine with Cloud Computing and AdaBoost Classifiers
I. S. Beschi, K. Helenprabha, S. Mohan Krishna, A Deepa, S. Murugan, Suresh Babu Thandullu Naganathan
Abstract
The ability to efficiently evaluate and monitor cognitive function from a distance has made remote cognitive examinations via telemedicine increasingly essential in healthcare. To make remote cognitive tests more accessible and accurate, this research explores how to combine cloud computing with AdaBoost classifiers. Using Human Cognitive Performance study dataset provides a scalable platform for securely processing and storing cognitive evaluation data. AdaBoost is an efficient ensemble learning technique that enhances diagnostic accuracy and reliability by optimizing the classification of cognitive performance measures. By integrating these technologies, medical professionals can perform thorough cognitive evaluations at a distance, providing quick intervention and personalized treatment plans. This integration improves patient care by streamlining healthcare delivery procedures and allowing for continuous monitoring and early diagnosis of cognitive loss. The practicality and efficacy of the proposed method is performed on Kaggle dataset with more than 80000 samples of real-life situations and conducting empirical assessments. With real-time processing under 2 seconds via cloud computing, AdaBoost achieved 92.5% accuracy in remote cognitive tests, hence lowering erroneous diagnosis by 18%. These results demonstrate the complementary advantages of using cloud computing and AdaBoost classifiers to improve remote cognitive tests for advanced healthcare solutions that are both affordable and flexible enough to meet the changing demands of patients and doctors.