What technologies are currently at the forefront of healthcare and how can we accelerate the adoption of 5G technology & applications to help advance future healthcare innovation?

We provide end-to-end solutions across private & public sector organisations providing full mobile coverage, small cell, in-door coverage and 5G Private Networks. Together with our bespoke commercial structures, we would welcome any opportunity to explore such solutions in conjunction with CPI.

The future of hospital environments will serve to utilise advanced data sharing and visualization technology. Thus, reliant on the suitability of 5G networks as wireless technology throughout the hospital to provide interference measurements, the usability of wearable AR/VR technologies together with medical and safety-critical communication application in a clinical hospital environment.

What new sensing or processing technologies are required to bring a step change in the quality of sensing and data driven healthcare interventions?

Considering single or occasional use point of care devices, as well as wearable technologies which operate over an extended period: what are the computing and data opportunities in sensing-based approaches for patient and care support? What are the current opportunities in data processing of healthcare data and the potential for longitudinal monitoring and/or diagnosis, in healthcare or home environments?

Cirrus Logic are an international semiconductor company with more than 400 employees based at our site in Edinburgh’s Quartermile. Our expertise centres around innovation in low power, mixed-signal ICs: driving technical advancements with exceptional quality and reliable delivery. In addition to building on a strong, $B, consumer audio business, Cirrus has a clear strategy to expand into other areas. Healthcare is a key focus, with a dedicated team set up to support this effort. Telemedicine / Telehealth is inspiring for Cirrus since it has the potential to vastly improve the accessibility of healthcare worldwide, reduce the strain on healthcare providers and enable more frequent or even continuous assessment to bring early diagnosis and better patient outcomes.

How can we focus biological cells in media to the surface of a planar electrode without the use of additional liquid?

We use dielectric spectroscopy to measure the intrinsic dielectric properties of individual cells, providing them with a unique profile for subsequent downstream analysis and characterisation, without cell labelling or lasers. It is therefore critical to bring the cells as close as possible to the electric fields generated from the planar electrodes. The cells should be kept in media and presented in a continuous flow.

How do we solve the data interoperability problem in health data on a local, national and international level?

Health data can vary greatly both in structure and terminologies from one organisation to the next. Data are collected for different purposes, stored in different formats using different database systems and information models. To improve the interoperability of health data requires standardising both the structure (syntactic interoperability) and the terminologies (semantic interoperability).

The Observational Health Data Sciences and Informatics (OHDSI) is a multi-stakeholder, interdisciplinary collaborative that is striving to bring out the value of observational health data through large-scale analytics. To achieve this, it has created a mapping standard called the Observational Medical Outcomes Partnership Common Data Model (OMOP CDM) for the healthcare sector. With an active and organic growth in adopting the OMOP CDM over the past 10 years, 534 data sources from 49 counties, representing 956 million unique patient records (12% of world population) have been mapped to this common data model.

In a recent article by Health Data Research UK (HDR UK) entitled NHS Research SDE Network agrees to adopt common data model there is a focus on adopting the OMOP CDM model for NHS data, however, the focus is very much within NHS England. I believe there is a lack of awareness and adoption of the OMOP CDM within the Healthcare sector in Scotland and would really like the opportunity to explore the idea of working with academia in Scotland to focus on health data standardisation using the OMOP CDM.

How can tampons be effectively utilized for the vaginal delivery of medication, ensuring optimal absorption and targeted release?

Daye is a UK-based, female-led health start-up on a mission to close the gender
gap in product innovation through sustainable and inclusive gynaecological products. Daye’s Diagnostic Tampon Screening is the only commercially available product employing a tampon for at-home vaginal microbiome and STI screening. Using the tampon for sample collection has demonstrated superiority in accuracy and result turnaround time. Additionally, Daye’s clinical trials with over 600 participants have suggested an overwhelmingly positive preference for tampons over in-clinic methods (90%) for sample collection.

Daye recognises the utility of tampons beyond menstrual use and believes they can be repurposed even further, for the vaginal administration of medication. Using a tampon in the vaginal canal has the potential to accelerate the medication’s arrival at the intended site and achieve quicker, more substantial therapeutic effects. Furthermore, this method is familiar and comfortable to self administer, requiring minimal user education.

What is the best methodology to measure the carbon cost of in-person compared with digital service delivery in a healthcare setting?

Digital patient services are an increasing model for effective service delivery at scale and across geographies. Since the NHS has set net zero targets for operational emissions, it is an important part of the evidence base to demonstrate the carbon cost of digital versus in person services, but also to reduce the impact of digital delivery as far as possible through good IT design. GoCodeGreen has developed carbon modelling software to estimate carbon cost and reduce the impact of digital services and are interested to know how to measure the impact against in-person delivery of services.
We have an existing NHS client relationship and are in progress in assessing the digital carbon impact of a core NHS digital service. We have also spoken to the tech and climate lead about the possibility of this research project and they have confirmed that they would be supportive and agree use of the data calculations being performed by GoCodeGreen in the event that this project was successfully reviewed and approved.

Can we tune the behaviour of our Ophthalmic devices during surgery?

Our hyaluronic acid based ophthalmic viscosurgical devices require a high viscosity when injected into the eye in order to have the best surgical properties. However, this high viscosity can lead to issues post-operatively if the device is not adequately removed by the surgeon. The high viscosity means that it cannot drain from the eye quickly. We wish to know if it is possible to reduce the viscosity of the device during use so it can be naturally removed from the eye.

How can we adequately predict the behaviour of our medical devices without requiring in-vivo trials

Our devices are required to have multiple features t work in surgery; they have to be injectable, removable, maintain space and protect the corneal endothelium. Currently testing these devices requires testing on real eyes. We wish to know if we can model the behaviour of the devices in the laboratory instead.

[Closed Workshop] From a camera-based tool, what biomarkers can be found from an image of menstrual blood?

We have a health tracking app for women with abnormal menstrual conditions that uses the phone camera to scan images of blood. What are some recommendations for biomarkers or other identification metrics we can obtain from a picture of blood? The sample images we are taking will be of patient blood, and our tool is a digital health app that diagnoses women’s menstrual health conditions from blood.

[Closed Workshop] How can we develop the AI-model for our health tracking app for women’s menstrual health conditions?

We are integrating AI into our health tracking app for women with abnormal menstrual conditions. The app uses the phone camera to scan images of blood and diagnose women’s menstrual health conditions. We are aware that AI needs to be generalised to make the best predictions and have optimal accuracy and are interested in training strategies for AI with limited real-world samples. We also need to collect evidence that proves that our AI based app can reliably diagnose conditions.
We understand that AI image models need to be trained on 1000s of images. However, images of blood are difficult and expensive to obtain at this early stage. Are there any recommendations on training an AI model on limited real-world samples? The samples here are images of blood taken from women with menstrual health conditions. What are some specific biases that may arise from AI algorithms when diagnosing women’s health conditions that involve blood? How can we avoid introducing bias into this model?
How can we demonstrate the effectiveness of the AI-model while the product is in very early stages? What are recommendations to start collecting evidence that proves that our AI based app can help to predict, monitor, and screen for conditions? We are in early stages and are looking to generate evidence that can help us apply for large scale funding to begin clinical trials.

We are developing a microfluidic sensor and seek input to design and functions as well as scalable and sustainable manufacture.

Onalabs Innohub is a young start-up with the aim to improve everyone’s health in a personalized manner. We design cutting-edge wearable sensors that can be used for vital sign monitoring or to check the sportive yield. Our solution is non-invasive we measure biomarkers from sweat in a continuous fashion. We are now embarking on a new journey, where we want to detect glucose and/or insulin from sweat.
One of the technical challenges we have is the scalable design of one of our consumables that integrates microfluidic and printed sensors. We’re also interested in printed sensor development in general, as well as if there is some cutting-edge technology for the production of printed sensors for glucose detection that includes environmentally sustainable principles.

What emerging trends and new value areas are developing in the medical device industry, particularly over the next 5-10 years, for example, given recent advancements in AI, appetite for shorter supply chains, and recyclable device concepts?

What emerging trends and new value areas are developing in the medical device industry, particularly over the next 5-10 years, for example, given recent advancements in AI, appetite for shorter supply chains, and recyclable device concepts?

How can we a) optimise existing healthtech knowledge and research and b) develop new research and innovation partnerships, in order to improve sustainability and circularity within the women’s health and femtech sectors?

Oshun Labs is an innovation lab focused on women’s health. Our mission is to leverage the latest technology and expertise to create innovative solutions that empower women and improve health for people and planet.

Our objectives:
1. Advance knowledge: Undertake evidence-based research to fill existing gaps in sustainability and women’s health data and improve sustainability, gender and health equity
2. Develop solutions: Build products and services that address existing health and environmental challenges and deliver real world impact
3. Engage and inspire: Create new narratives around women’s health and sustainability that inspire and educate communities and promote sustainability, equality and empowerment through behaviour change, improved health and wellbeing
4. Action through collaboration: Mobilise companies and individuals to implement positive change through community building, collaboration and cross-sector partnerships

We develop and build out early-stage innovative ideas, nurturing projects through research and development to create pioneering new products and services that support good health and wellbeing. With a strong focus on environmental impact, our approach is multi-disciplinary and people-and-planet centred, driving sustainable change and women’s health equity through science, technology and strategic innovation, cross-sector collaborations and partnerships.

Current projects include development of a novel functional beverage to support cardiovascular health for postmenopausal women, and a project exploring circularity, recycling and reuse solutions for women’s health and femtech products. We also run The Sustainable Femtech Network, a B2B network to support the adoption and implementation of sustainable practices within the femtech sector and to drive sustainable change at industry-level.

How do we model a system as complex as health and social care in its entirety?

The model needs to take into consideration the relationships between services, demand and capacity; long term and emerging trends (e.g. climate change, demographic, disease prevalence) and service redesign (e.g. emerging technologies and workforce constraints), to support the transformative change it will require to be sustainable going forwards. The health & social care system is under major pressure and intelligence to support its transformation will be vital.

How do we model a system as complex as health and social care in its entirety?

The model needs to take into consideration the relationships between services, demand and capacity; long term and emerging trends (e.g. climate change, demographic, disease prevalence) and service redesign (e.g. emerging technologies and workforce constraints), to support the transformative change it will require to be sustainable going forwards. The health & social care system is under major pressure and intelligence to support its transformation will be vital.

[Closed Workshop] How would you approach designing a system to inspect surgical instruments for visible contamination using ai/ machine learning?

There are thousands of types, shapes and sizes of surgical instruments with multiple contaminates blood, tissue, cartilage, fat, bone, marrow, bone adhesives, ‘sticky’ residue from adhesive tape). These contaminates are on the surfaces of instruments and trapped in box joints and instrument mechanisms after being used in operations.

Instruments are inspected as they move through the decontamination process, pre-clean, wash/ disinfect. They are sterilised after the final inspection.

Following pre-clean particular instruments are inspected to ensure contaminants have been removed because the washers are not able to remove them effectively. For example, impacted bone in Exeter Rasps is compressed to the rasp teeth by the hammering of the rasp into the femur for hip replacement.

The attached images show a protein scan of a hip rasp, this system uses a fluorescent marker. Instruments must be dry, rewashed after scanning and the process is too slow to be viable for this challenge.

We are looking to create a co-bot system to scan and inspect multiple instrument sets in the workflow of a decontamination unit which processes millions of instruments per year.

A video of pre-clean process is shown here: https://1drv.ms/v/s!Ak26OUenee8371Z95Wq1mfWg7moU?e=PIzgkx

How can we use aggregated health data, individual health histories, and/or wearables data in our app that supports young people with Gastrointestinal Functional Disorders and Psychological Issues. Creating better engagement with users and better health outcomes for them.

We are running a Feasibility Study of a digital health intervention for young people with Gastrointestinal Functional Disorders and Psychological Issues working with NHS Grampian and two other NHS boards in Scotland. This CBT informed app aims to engage users in regular learning and activities that help them to live with their painful and embarrassing somatic symptoms, and manage their mental health issues.

We currently use user responses to personalise the user’s experience. What other sources of data are available and could be used to further personalise the users experience and increase their engagement with the app? EG, postcode health data, digital health records, wearables.

Further, could the data gathered be used to inform generative AI that increases user engagement in a safe and ethical way?