Research project Improvement of Internet of Medical Things based Applications with Distributed Machine Learning
Medical devices collect huge sets of patient data every day, at every hospital, around the world. What if these data could be used to improve diagnostic tools? This PhD thesis project explores how medical data can be used in a safe way.
The internet of medical things (IoMT) can be described as an interconnected setup among different medical devices to provide certain improved healthcare services in the form of IoMT based applications. In order to ensure this improvement, effective utilization of the healthcare data is the crucial factor.
This efficient utilization could be a challenge due to the extreme heterogeneity of medical data and different data source locations with security and privacy constraints. Efficient usage of distributed machine learning could be beneficial here for successfully integrating the IoMT framework, medical data, and applications such as diagnostic tools.
In this project, various aspects of these IoMT applications will be analyzed with the vision to improve the overall diagnostic tools. We hope that successfully integrating these critical aspects will help us create a more effective IoMT based application as diagnostic helping tools for healthcare professionals.
This is Mahbub Ul Alam’ s PhD thesis project.
Rahim Rahmani is the supervisor.
The full title of the project is "Improvement of Internet of Medical Things based Applications with Distributed Machine Learning Approach".
Project description
Hospitals regularly accumulate enormous amounts of patient data using various isolated medical equipment. These data consist of diagnosis results, unstructured text, and vital signs.
Sometimes it is not possible to combine and store all of the data in an effective way so that it can be used or analyzed later. Interconnection of different medical equipment over the internet with the effective formation of a distributed platform (Internet of Medical Things or IoMT) can be a solution in this regard.
A combination and utilization of medical data from different sources can provide superior diagnoses and distinguish effective action for the patient in a fast and more effective way. Moreover, it provides the opportunity to create a wider scale health network among different hospitals or countries to improve patients’ health on a global scale and platform.
However, medical data is extremely sensitive and therefore the major concerns in IoMT need to be addressed such as reliability, safety, and security. It is therefore evident that to tackle this issue we need to focus on the effective construction of the application domain of IoMT. By doing this, IoMT can overcome the issues of reliability, safety, and security by providing a system that is adaptive, interactive, iterative, stateful, and contextual.
Efficient usage of distributed machine learning could be beneficial here for successfully integrating the IoMT framework, medical data, and applications such as diagnostic tools. In this project, various aspects of these IoMT applications will be analyzed with the vision to improve the overall diagnostic tools. We hope that successfully integrating these critical aspects will help us create a more effective IoMT based application as diagnostic helping tools for healthcare professionals.
Project members
Project managers
Rahim Rahmani
Professor
Members
Mahbub Ul Alam
Doktorand
