FSE 3: A data-driven health monitoring ecosystem using artificial neural networks (ANN) and internet of medical things (IoMT) devices and sensors for proactive respiratory care and diagnoses

Faculty: Science and Engineering

Supervisors: Dr Ian van der Linde, Dr Mahdi Maktabdar Oghaz, and Dr Lakshmi Babu Saheer

Interview date: 28 March 2022

The healthcare industry is moving towards data-driven practices that rely on technologies such as the internet of medical things (IoMT), artificial intelligence, and cloud computing. One aim of these technologies is to provide proactive patient monitoring and diagnosis and promote accessible care for the public, which is particularly useful in the care of the elderly and vulnerable (Tortorella et al., 2021).

One area that can benefit from this transformation is respiratory care. Hospital admissions for respiratory diseases have risen threefold over the past seven years and COVID-19 is worsening the situation. According to the NHS, early diagnosis of respiratory diseases can reduce the severity of the condition and the cost of future medication (NHS, 2020). Studies show COVID-19 and its variants are here to stay, and their long-term impact, side effects and complications are as yet not fully known (Jabbari and Rezaei, 2021).

Technological advances in the way that we monitor, diagnose and provide care for respiratory diseases and conditions such as COVID-19, especially for the elderly and vulnerable, not only has the potential to save lives, but also reduce the cost of care and medication and improve public health.

The aim of this project is to promote public wellbeing through a data-driven, proactive respiratory monitoring and diagnosis ecosystem capable of identifying potential conditions such as asthma, bronchitis and pneumonia using ANNs and IoMT devices and sensors. This is to be aimed primarily at the elderly and vulnerable population in care homes, although such systems also have enormous potential in the wider population.

The successful candidate will:

  • Design and deploy an end-to-end data-pipeline that channels vital signs and other respiratory-related measurements from smart IoMT devices to a data analytical engine.
  • Design and develop a data analytical engine comprising a series of data-driven algorithms that exploit ANN techniques to proactively analyse users’ vital signs and respiratory-related measurements.
  • Develop a small-scale working prototype of the proposed digital ecosystem.
  • Conduct initial data collection in collaboration with care homes across Cambridge.
  • Validate the accuracy and effectiveness of the proposed ecosystem using existing clinical datasets.

The proposed system will employ commercially available IoMT devices to measure vital signs and respiratory-related readings and channel them to a central data analytical engine that exploits ANN to train a predictive model capable of providing a proactive analysis of the user’s respiratory-related measurements for potential respiratory conditions and diseases. System validation will be based on existing benchmark clinical datasets.

If you would like to discuss this research project prior to application please contact ian.vanderlinde@aru.ac.uk

Apply online by 27 February 2022.

Funding notes

This successful applicant for this project will receive a Vice Chancellor’s PhD Scholarship which covers Home tuition fees and provides a UKRI equivalent minimum annual stipend for three years. For 2022/3 this will be £15,609 per year. The award is subject to the successful candidate meeting the scholarship terms and conditions. Please note that the University asserts the right to claim any intellectual property generated by research it funds.

Download the full terms and conditions.