Tiny Machine Learning (TinyML) Based Self Diagnostic Kit for Respiratory Diseases

Abstract

The World Health Organization (WHO) 2022 statistics show that over 3 million deaths globally result from chronic respiratory diseases yearly. Interestingly 90% of these deaths are reported from middle- and low-income countries. This may be attributed to the poor health care systems with few medical experts to enable early diagnosis and treatment of the diseases. There is therefore a need for cheap and accessible solutions to help solve the problems. The use of the latest technologies of Machine Learning (ML) and Internet of Things (IoT) provide capabilities that can enable cheap and convenient detection and monitoring of respiratory diseases. However, existing solutions are cloud-based and thus depend on the availability of internet connectivity to function. This poses privacy, security, and even connectivity challenges, especially in Africa. The concept of using an emerging ML technique for inferencing on resource-constrained devices known as Tiny ML was used as a solution enabling the development of a self diagnostic kit. The system captures breath Volatile Organic Compounds (VOC) the collected data will be processed on the device and a Tiny ML algorithm used to detect if the sample is infected or not. The designed prototype was used to collect from healthy and unhealthy volunteers. The collected data was then used to train the prediction model. The ML model predicts respiratory diseases with an accuracy of 95.4% using less than 20% of the device resources. The proposed solution will reduce the dependency on medical experts and healthcare facilities and enable early detection of respiratory diseases.