Month: December 2024

Have you ever considered how artificial intelligence (AI) chatbots could revolutionise patient care? Our recent knowledge mobilisation workshops explored this very question, bringing together diverse perspectives to discuss how AI could support NHS patients on waiting lists for surgery, particularly in achieving health improvements like weight management.

What even is a chatbot?

A chatbot is a software application designed to simulate conversation with human users, typically through text or voice. Using natural language processing (NLP) and AI, chatbots can understand and respond to user queries in a conversational manner. You may have already used one, maybe without even realising it; they’re increasingly common in customer service and online shopping, providing quick, automated responses. Advanced chatbots even ‘learn’ from interactions, offering increasingly personalised assistance.

Our workshops were supported by two expert facilitators experienced in developing healthcare chatbots, who provided a beginner’s guide to chatbots, making the discussions accessible to everyone. The facilitators shared their insights from engaging with the NHS and demonstrated chatbots in action, addressing our questions in real-time (if an idea is never going to work we’d rather know sooner than later!).

Why look at health improvement on waiting lists?

With over 7 million people on NHS surgical waiting lists, the need for scalable, personalised interventions is urgent. Our workshops aimed to explore how AI could help patients improve their health while waiting for surgery, with a particular focus on weight management. We shaped our discussions to share our hopes and ideas for chatbot use while giving equal time to highlighting the concerns held about chatbots.

Participants: A Diverse and Engaged Group

Over the two workshops 27 of us met to learn, listen, share and discuss our knowledge, experience and ideas, as part of the process of knowledge mobilisation. The workshops included patients and public representatives, healthcare and public health professionals, weight management service providers, AI experts, and researchers from all sorts of fields of expertise. The diverse nature of the group ensured that we could examine the issue from multiple perspectives, integrating both the technical feasibility and the real-world needs of patients.

We held the workshops face-to-face and left plenty of time for individual conversations and networking over lunch in an organic way that isn’t often possible in the now ubiquitous video-call meeting. Participants fed back that this had made a real difference to what they had got out of attending the workshop, and the strength of connections they made.

The potential benefits of chatbots in health improvement

The ideal scenario is for healthcare professionals to have personalised conversations with every patient on a waiting list to identify their health improvement goals and then guide them to appropriate support services. However, time constraints make this challenging. Chatbots offer an alternative, being available to interact whenever it suits the patient, even at odd hours or during holidays (e.g., New Year’s Day when some of us bring our thoughts round to healthy changes we’d like to make…?). They can also operate via voice, making them accessible regardless of reading ability or visual limitations, and converse in multiple languages—an important consideration for reaching non-English speakers.

Moreover, chatbots could assist in keeping track of all available local support services, including in the voluntary and community sector, a task often overwhelming for healthcare professionals. By providing accurate, up-to-date information, chatbots could help patients find the right support more easily, reducing the barriers to engagement.

And the concerns….

We discussed concerns over data use and privacy, ethical and safe ‘decision-making’ by chatbot algorithms and the risks of bias inherent in the data on which chatbots are trained, including chatbots’ ability to give inaccurate or problematic answers to the questions they’re asked if the right protections aren’t in place. We also talked about ‘digital exclusion’ where some groups of patients miss out if they aren’t able to access the internet or a smartphone required by some new digital support tools. The group emphasised the importance of involving a wide range of stakeholders in the development process of any future research to identify and address potential problems early on.

Application: From Insights to Action

We left the workshop with a shared commitment to move forward, excited about multiple potential research ideas to explore in collaborative research proposals. The next step will be to explore funding opportunities to support this work.

Final Reflection

Reflecting on these workshops, I am proud of what we’ve achieved. The level of engagement and collaboration exceeded my expectations. As one participant said, “When we bring together different perspectives, we find innovative solutions to even the most complex health challenges.” Thanks to the Catalyst Award, we’ve taken an important step forward, and I look forward to continuing this journey of innovation and impact.

By Joanna C McLaughlin

Joanna is an Academic Clinical Lecturer in Public Health, Bristol Medical School.

Problem

Missing data is a very common problem in health and social studies. Data can be missing because people don’t want to answer some questions, or forget to give some information, or drop out of studies completely. Missing data presents a risk that results of a study will be wrong (“biased”), unless the analysis approach is chosen carefully. One statistical approach that can correct this bias is called multiple imputation (MI). The problem is that MI can be challenging and complex to use in practice, and there is little guidance available.

Developing midoc

With Kate Tilling, Jon Heron, and Rosie Cornish (Medical Research Council Integrative Epidemiology Unit at the University of

Bristol), and James Carpenter  (London School of Hygiene and Tropical Medicine), I developed software to bridge the gap between the theory and practice of MI. The software is called the “Multiple Imputation DOCtor”, or midoc (https://elliecurnow.github.io/midoc/).

Workshops

I used the Knowledge Mobilisation Catalyst Award to run three workshops this summer to demonstrate midoc. These involved groups working in clinical trials, as well as statisticians working in the NHS with large health registries, and at the Office for National Statistics. The workshops had two objectives. The first objective was that participants would understand how midoc could help them choose when and how to use MI. The second objective was for me to find out which features of midoc were useful, which needed improving, and whether any extra functions should be added.

Anyone who has ever used R software will know that perfunctory output and obscure error messages are the norm! One of the priorities when developing midoc was including clear interpretation of results as part of the output. I wanted to make midoc  as useful and accessible as possible. So I was also keen to find out whether participants in the workshops found midoc user-friendly and with the right level of detail.

Feedback

Participants gave some really positive feedback on midoc. They said they liked walking through a real example and the structured guidance. One participant said: “Thank you for the demo. I found it very useful to understand more about  Directed acyclic graphs (DAGs) and how to check the validity of imputation. I will consider more about missing data in my future studies!” However, it was sometimes surprising what participants found confusing. I have already updated some of midoc’s functionality as a result. Lack of time was often mentioned as a barrier to the in-depth approach suggested by midoc. It was also clear there was a wide range of priorities and levels of experience in missing data methods across the participants. I’m now working on ways to streamline and simplify the analysis process used in midoc. I’ve also reflected on how to incorporate time-saving tips in the workshop format.

Next steps

I’m now applying for further development funding for midoc. It’s been incredibly useful to have workshop feedback to incorporate into my funding applications. The workshops have also helped me develop future collaborations and identify suitable studies to apply midoc to. I plan to hold follow-up events with participants to showcase the improvements I’ve made to midoc as a result of their feedback.

Final reflection

Software tools are often developed alongside new statistical methods. However, obtaining user feedback on these tools is frequently over-looked. My Knowledge Mobilisation Catalyst Award has really helped me with this. As a result, I have gained valuable insight into the midoc user-experience. This will ultimately encourage wider take-up of midoc and ensure that as many users as possible are following best practice in missing data methods.

Project links:

Multiple Imputation DOCtor (midoc)

A Decision-Making System for Multiple Imputation • midoc

By Elinor Curnow

Elinor is a lecturer in Medical Statistics and a Senior Research Associate in Biostatistics / Epidemiology in Bristol Medical School