Tag: Cohort 2

Cohort 2 student Neshika Wijewardhane publishes a paper in the Journal of Micro and Bio Robotics entitled ‘Long-term imaging and spatio-temporal control of living cells using targeted light based on closed-loop feedback’.

Neshika had the following to say about her publication: ‘This publication showcases the 2nd iteration of the DOME in my PhD project. We present a robotic device that is able to image and illuminate living cells with light at a higher intensity, with additional fluorescence imaging (Fluoro-DOME). We can image cells long-term, illuminate the leading edge of a wound over time, and autonomously alter the light pattern in real time to restructure the illumination on the wound edge.

With this iteration, we could set up the autonomous real-time frontier illumination of the leading edge of the wound. Currently, I am optimising the light irradiation regime to aid in accelerated wound healing and closure.’

Link to the paper: https://link.springer.com/article/10.1007/s12213-024-00165-0

Cohort 2 student Neshika Wijewardhane publishes in the International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS) entitled ‘Modular Wavelength Adaptation of the Dynamic Optical MicroEnvironment’.

Neshika had the following to say about the experience: ‘The DOME is a powerful and adaptable platform that facilitates the study of light-reactive systems at the microscale. While the projection module of the DOME can produce light patterns with high spatial and temporal resolution, the maximum irradiance (incident electromagnetic energy per unit area) that can be generated by its native LEDs is limited. Increasing the irradiance is crucial to enabling new biomedical applications such as inducing DNA damage. In this paper, we present a modular solution to allow general light sources to be used with the DOME. By switching to a high-powered near-UV light source, we show that DNA damage can be caused by the Epi-DOME’s projection system at a targeted location.

In a previous paper, I showed that I could image and identify the leading edge of a wound and then project light onto the wound edge. With this paper, I showed that I can target the light to cause low levels of DNA damage in a select population of cells. By putting these two pieces of work together, I should be able to selectively damage cells at the leading edge of the wound, thus initiating specific pathways that increase the migration of cells. Enabling faster wound closure.’

Cohort 2 student Harry Emerson publishes in the Journal of Biomedical Informatics entitled ‘Offline reinforcement learning for safer blood glucose control in people with type 1 diabetes’.

Harry had the following to say about his publication: ‘The publication explores how machine learning algorithms can be used to improve insulin dosing decisions for people with type 1 diabetes. Artificial pancreas devices have shown great success in reducing the burden of diabetes management, but rely on simplistic and reactive control algorithms. This work applies offline reinforcement learning as a method for learning sophisticated and safe strategies from pre-collected patient data. The method is verified in a simulation of 30 people and explores practical challenges, such as human error, device malfunction and data quality. The presented method significantly improved blood glucose control compared to current state-of-the-art control algorithms and was shown to be more robust than previous reinforcement learning approaches to the constraints of real-world data. The algorithm demonstrated the greatest benefit in children, which represent a particularly important group as they are often unable to manage their diabetes without assistance.

I implemented a selection of reinforcement learning algorithms in the type 1 diabetes simulator and created a full pipeline to perform data collection, training and evaluation. I modified the established UVA/Padova simulator to incorporate common blood glucose scenarios in which to evaluate the approach.

This represents the first demonstration of the benefits of offline reinforcement learning in blood glucose control. This work provides a basis for continued reinforcement learning research, demonstrating the potential of the approach to improve the health outcomes of people with type 1 diabetes, while highlighting the method’s shortcomings and areas of necessary future development. The publication was picked up by Wired Science, who write an article about myself and my research https://www.wired.com/story/managing-type-1-diabetes-is-tricky-can-ai-help/.

Link to Paper: https://www.sciencedirect.com/science/article/pii/S1532046423000977

Cohort 2 student Sam James published a journal article via Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems entitled ‘Chronic Care in a Life Transition: Challenges and Opportunities for Artificial Intelligence to Support Young Adults With Type 1 Diabetes Moving to University’.

Sam had the following to say about his paper: ‘The paper uses data collected in one-to-one interviews with young adults in the UK who had recently experienced the move to university and were living with type 1 diabetes (T1D). From a thematic analysis of the interviews, findings were made about this life transition and its impact on T1D management. These focused on the changes in lifestyle and the changes in support network. The changes in lifestyle included changes to drinking habits, eating habits, sleeping habits, physical
activity habits and overall schedule. The changes to support network highlighted; the increased independence, parents’ role in T1D management, explaining T1D to people and the assistive roles
people at university fill. From these findings, several opportunities and challenges for technology during the transition to university are discussed, with a focus on artificial intelligence and the closedloop system. These include automated personalisation, customisation, data limitations, the limitations of artificial intelligence in unusual scenarios and the potential of human-centred based design solutions. The paper then considers the wider implication of these findings for other chronic conditions and suggests the need for further research to allow personalised solutions to develop that consider the problems caused by life transitions.

I was first author on the paper and performed the majority of work across the process with input from my supervisors, who made up the remaining authors. The work I did included the project setup (exploring the research space and gaining ethical approval for the study), data collection (participant recruitment, online interviews and transcribing them), data analysis (thematic analysis)
and write-up (selecting the novel parts of the analysis and creating a paper to explain them).

The work aims to highlight the difficulties that life transitions cause in chronic condition management and to trigger more research into technology during these periods. This hopefully will
lead to the design of management systems that can cope with the challenges of life transitions or increase awareness of times they may be less effective and why.’

Link to Paper: https://dl.acm.org/doi/10.1145/3544548.3580901