Author: Yvette Pyne

Posted on

Speaking at the All-Party Parliamentary Group on LGBTQIA+ Menopause

On 24 June 2025, I was invited to speak at the All-Party Parliamentary Group (APPG) on Menopause, in a session focused on the experiences of LGBTQIA+ people. The event was chaired by Carolyn Harris MP and formed part of the ongoing APPG inquiry into equitable access to menopause support for historically marginalised groups.

I spoke in my capacity as a GP with a special interest in menopause and trans healthcare, a clinical academic researching perimenopause diagnosis, and a queer woman with lived experience of perimenopause. It was an honour to join fellow speakers Laura-Rose Thorogood and Helen Juffs to share evidence, insight, and lived experience.

My contribution centred around the consistent absence of tailored menopause support for LGBTQIA+ people. From the dominance of cisgender, heterosexual narratives in public information, to exclusionary healthcare language and outdated clinical protocols, our systems still fall short of serving those outside the ‘normative’ majority.

In my remarks, I called for several urgent reforms:

  • Funded, inclusive NHS menopause education and clinical guidance for LGBTQIA+ people
  • Reforms to NHS IT systems to enable flexible, anatomy-based screening access
  • Support for grassroots LGBTQ+ health organisations already leading peer-led menopause support
  • Improved access to gender-affirming care and fertility preservation for trans people
  • Increased research funding into LGBTQIA+ menopause experiences — especially for underrepresented groups such as intersex, disabled, and global majority individuals

As someone who contributed to the Rainbow Menopause film, I also reflected on how difficult it remains for LGBTQIA+ individuals to share their stories publicly — not due to lack of insight or willingness, but fear. The current political climate in the UK has become increasingly hostile toward trans and queer people, and this was acknowledged in our discussion.

Despite this, the APPG meeting was a hopeful space. I felt heard and the atmosphere was one of mutual respect. Thank you again to Carolyn Harris MP and the Wellbeing of Women team for convening such an important conversation.

Posted on

Rainbow Menopause Film: reflections

Menopause is still under-discussed in many healthcare settings — and when it is discussed, the experiences of LGBTQ+ individuals are often overlooked. That’s why I was proud to be involved as a clinical contributor to Rainbow Menopause, a short film supported by the IRIS Prize and dedicated to telling these vital stories.

The film shares personal experiences of trans and nonbinary individuals navigating menopause, highlighting both clinical gaps and moments of resilience. It brings a powerful human voice to a subject too often handled with clinical detachment — or ignored altogether.

As a menopause specialist and gender clinician, I found this work deeply affirming. It reminds us that inclusive healthcare must go beyond terminology — it must be felt in the consulting room, in clinical education, and in policy.

Since the film’s release, I’ve participated in screening events across the UK, engaging in panel discussions and Q&As. These conversations are as important as the film itself. They reflect a growing recognition that menopause care needs to evolve — not just scientifically, but socially.

Posted on

AI and the future GP consultation

In recent years, artificial intelligence has promised much — but often feels remote from the realities of day-to-day general practice. Can it really help? Or will it just add noise?

In our BJGP Open commentary, Dr. Stuart Stewart and I explored a concept we called “augmented consulting” — the idea that AI, used thoughtfully, can support clinicians rather than replace them.

We argue that the future of AI in primary care lies not in automation, but in augmentation: using digital tools to free up time, surface insights, and allow GPs to do what they do best — listen, understand, and respond.

For example, could real-time data support help identify red flags? Could natural language models help structure notes and reduce admin? Could personalised dashboards reduce cognitive overload?

These are exciting questions, but we must tread carefully. Clinical intuition, empathy, and human context are irreplaceable. So we need systems that elevate, not erode, those core values.

Augmented consulting doesn’t mean handing over decisions to machines. It means building systems that give us more time for patients, not less. And that’s the kind of digital future I want to see in general practice.

Read the full commentary here.

Posted on

Community voices in menopause education

One of the most meaningful parts of my recent work has been co-leading community engagement workshops focused on menopause education — particularly within underserved communities in Bristol.

Thanks to some public engagement funding, we were able to run a series of workshops with Somali women, mixed-ethnicity groups, and others who are often excluded from mainstream health messaging. We didn’t go in with PowerPoints — we listened, shared, co-created.

These workshops produced more than just conversation. Together, we developed multilingual menopause information leaflets, hosted open Q&A sessions, and even co-wrote a short awareness film now featured on the Bristol Menopause Toolkit.

Too often, menopause care is designed around a narrow narrative. By giving voice to those with different cultural contexts and lived experiences, we made the information better, braver, and more accessible. And the feedback? Overwhelmingly positive. People felt heard, respected, and seen.

Education works best when it’s a dialogue, not a broadcast. I’m grateful to everyone who took part and helped shape these resources — and to the funders who trusted us to do things differently.

Posted on

NLP to summarise GP consultations: early results

As part of my Academic Clinical Fellowship, I explored whether natural language processing (NLP) could help summarise GP consultations — automatically, accurately, and meaningfully.

The motivation was simple: GPs are under immense pressure, and documentation takes time away from what matters — the patient in the room. What if we could teach a machine to extract key information from free-text consultation records and generate concise summaries or action points?

Using the “One in a Million” consultation dataset, I worked with colleagues in the Department of Engineering to develop models that could begin to understand the structure and content of primary care conversations. We predated the large language model boom, so this project was both technically challenging and conceptually ambitious at the time.

The results? Promising — but not perfect. The model could identify certain clinical elements quite well (e.g., presenting complaint, advice given), but nuance and context remain hard to encode. Medical dialogue is full of subtlety, uncertainty, and interpersonal dynamics — all things that NLP still struggles with.

Still, it was a valuable proof of concept. It showed how collaboration between clinicians and data scientists can seed tools that ease documentation burden and support better record-keeping. And with the rise of tools like HeidiAI and ScribePro, it’s clear this area will only grow.

Read the full publication in BMJ Health & Care Informatics.

Posted on

Does the computer know you have perimenopause?

One of the questions I’ve been asking through my research and clinical work is deceptively simple: could digital tools help identify when someone is going through perimenopause — even if they don’t realise it themselves?

Perimenopause often presents subtly in primary care: vague fatigue, anxiety, changing cycles, poor sleep. These symptoms are frequently documented but rarely connected unless explicitly asked about. With so much rich data in GP records, is it possible for artificial intelligence to spot patterns earlier than we do?

This isn’t science fiction. As part of my current NIHR-funded work, I’ve been exploring how we might use structured and unstructured data to support earlier, more equitable diagnoses of perimenopause in general practice. It’s exciting – and humbling – to consider what computers might notice that we, in our time-limited consultations, may miss.

But it’s not just about detection. These tools must be designed with care, clinical context, and ethics front of mind. Bias, privacy, and explainability all matter. We can’t outsource judgment — but we can augment it.

If we get this right, we could offer thousands of women earlier support, better information, and a sense of being truly heard. That, to me, is the promise of responsible digital innovation in healthcare.

This idea was also the subject of my TEDx talk in Bristol — watch it here.

Posted on

Getting Things Done with Evernote

Inspired by a recent Twitter conversation with @DrLukeOR, I thought I’d write a quick blog post about how I keep myself organised. This post starts with a short caveat that the latest version of my preferred software Evernote has a significant (but hopefully temporary?!) loss of some key functions as they rebuild it from the ground up to be more stable; I’ve downgraded to version 6.25 for now. As always, there is an inertia once your work processes are embedded in a particular tool but my organisational technique would work on many similar platforms and I’m keeping an eye on both Notion and Roam to see how their tools mature.

Getting Things Done (GTD) was originally created by David Allen back when file cards and label printers were the height of technological sophistication. It looks like his original book has been updated since I read it – I imagine it’s still the quick read that gives you a good grounding in the technique. A Google of the initials GTD will open the door to a world of enthusiasts who’ve taken his simple and effective ideas and are sharing their own personalised implementations.

My own GTD flavour has been refined and improved over more than a decade of use and gives me the right balance between the “overhead” of adding and organising my tasks, and the true value of a good system – never losing an idea and instantly finding the exact right task to do at the right time.

GTD centres around the concept of clearing every task out of your head into a reliable system; your brain is a terrible place to accurately remember lists of stuff. I have an “_Inbox” folder where everything gets thrown. I then have a set of nested “_Tasks” folders that store all my GTD tasks. Why the underscores? It keeps my GTD folders at the top and typing an underscore instantly shows only the GTD folders. Within my tasks folder, there are:

  • “_Next Actions” – where the bulk of my tasks end up
  • “_Calendar” – tasks with reminders on them that can only be actioned when they reach that reminder date (to stop me seeing them before I can do them)
  • “_Sometime/Maybe” – aspirational ideas or goals I don’t want to lose but won’t be actioning in a hurry.
  • “_Waiting For” – when I’m waiting on someone else for something before I can carry on – it can be good to add reminders to these as well.
  • “_Reading” – articles I need to read – not a typical GTD folder and could probably be a tag instead but I’ve found it easier to keep them separate

Next, I have GTD tags – this is one of the first areas where the real power of the tool kicks in – I can organise anything into an appropriate grouping with a few keystrokes:

  • Context tags start with an “@” – note that they all start with a different character.
  • Time tags start with an “~” – again, make each one start with a different character to speed things up when tagging with keystrokes.
  • Current Projects (not shown) start with a “.” – when I’m done with them, I drop the “.” and move the tag under the Archived/Shelved Projects grouping.

As an example, if I see an article I want to read, I hit the keystroke shortcut on the Evernote Chrome Extension, and simply choose the “_Reading” folder; if I’m feeling enthusiastic, I can tag it with a current project by hitting “.” and the appropriate project. Similarly, if I think of a task I need to do when out and about, I click a single shortcut on my Evernote Android Widget and type in a few words or take a picture and it will automatically save to my “_Inbox”. I will tend to tag it on the laptop as it’s slightly quicker there, and drop it into the “_Next Actions” folder.

That’s it! Building my task list is simply about clearing everything out of my brain as soon as it arrives there and, when I’m ready, adding a few tags to organise it a little. Finding the right next task to action is also easy – I just filter them to my context and the time I have*. No more endless overhead and guilt associated with the creation of overly optimistic daily task lists that I never quite complete.

As a final thought – while people might choose to implement GTD in a tool that is more purely designed for task management such as Trello or ToDoist, I find the power of using Evernote as the repository for absolutely everything means I’m not needing to maintain my “list of things I’m doing” in more than one place; the “Write notes on Wednesday’s meeting” task becomes the “Notes on Wednesday’s meeting” project resource when I’ve finished the task.

*I confess, I’ve found I slightly hack this by the addition of a simple “#” as a tag to highlight stuff I want to do urgently. You can use “Shortcuts” to pin searches, tags and folders to find things like this even more quickly.

Posted on

Tech-enhanced Academic Writing

Coronavirus has completely changed how we work across most professions including in academic research. While those impromptu conversations around the coffee machine at work, or over drinks at academic conferences seem both a distant memory and a far-flung future dream, there have been some wins for collaborative working as well. Lockdown has brought both technological improvements and culture-change around the use of video conferencing and collaboration tools. A colleague – Dr. Stuart Stewart based at the University of Manchester and I (based at the University of Bristol) have been “meeting” once a week to discuss the creation of a concept paper covering ideas that have been percolating for years after a fortuitous meeting at a conference in 2018. Both of us are tech-adept and we often discuss ways that we can use software (and other technology) to enhance our work.


Meeting

Google Meet is now our default platform to meet over – I run a “G-Suite” account which allows me to have my own domain name but use all of Google’s software such as Mail, Calendar and Drive seamlessly; I can book a meeting directly into my online calendar and add a Meet link with a single click. Most work events use Zoom and Microsoft Teams but we’ve found that Google Meet tends to be faster and more reliable than Teams and doesn’t have the 40 minute restriction that (free) Zoom has.

When we’re talking, we still use WhatsApp to send each other links or screenshots – we’ve been chatting on WhatsApp since we met and the “WhatsApp Web” platform adds additional capability to quickly share written information from your laptop to someone else’s; it’s also preserved for posterity when we need the link again.


Thinking

Our discussions not only cover what we want to learn and express but also how we try to organise our thoughts between these. It’s not fresh news to point out that our brains are both incredibly powerful at making fresh connections between source material and also terrible at compiling and remembering those sources in a systematic way. How do I effectively record all the ideas I’ve had when reading that paper ready for when I want to collate and express them later?

Stuart recommended the new platform ‘Roam‘ as a possible solution to this problem. Looking at their work and what they are trying to achieve gives me a feeling that they are genuinely creating something great that’s just on the periphery of my consciousness and it’s possibly more to do with my inability to relax and flow into this different way of working than anything to do with their solution. I tried it for a few days and still didn’t quite “get it” but that doesn’t mean I’m not excited to see where they go in the future and hope they survive these challenging economic times.

For the moment, I have taken some of the concepts around daily journaling and hyperlinking back to the software platform that I have been using for nearly 10 years now – Evernote. I found this tool during my medical degree and now have over 4000 “notes” stored there; I have everything from scans of my kids’ artwork to a hyperlinked digital portfolio/CV. I have all of my study notes that get updated and re-used regularly in my clinical work, and I keep my productivity high by using the “Getting Things Done (GTD)” method through it. It can be frustratingly buggy is some basic areas *cough*tables*cough* but its cross-platform apps and widgets and the reassurance that I have never lost a single note allows me to dump anything into it and know it’s safe.

Despite Stuart being a more avid user of Roam (maybe his brain is just bigger and fresher!), he is also a fan of Notion. This has a similar offering to Evernote and I tried it for a short while and felt that it was better looking and potentially more powerful but unfortunately, their import from Evernote is not yet fully working and their Android offering isn’t as comprehensive so I’m sticking with Evernote for now.


Writing

Stuart and I’s remote paper-writing collaboration to create a paper started with Microsoft Word with us sending the document to each other to review. Word is universal and it is one of the many platforms that have a plugin for my (new) favourite citation manager – Zotero. I am relatively new to this package having tried several others but it seems to have everything you want in a tool of this type – storing, tagging and making notes on research documents. Some of the neat tools that work particularly well with it include the Chrome extension to easily get a document from a web-page into it and sharing libraries in teams which has been vital when working so closely together.

We have now moved on from Word to far more real-time collaborative writing where we can work online on the same paper at exactly the same time. First, we tried Overleaf which I imagine could be the “go to” tool for collaborative writing if you’re working with LaTeX. I keep thinking I should learn this ‘language’ but haven’t found the initial steep learning curve has been worth it yet. Instead, we fairly quickly switched to Authorea which combines a solid online paper-writing collaboration tool with the interesting concept of being able to freely publish a paper on their platform getting that all important DOI number without the lengthy process found in more traditional peer-reviewed journals. Our plan is still to see if a more mainstream publication will take our paper but it provides a fascinating alternative to getting your ideas out into the world compared to the peer-reviewed journal route.


Delivering

Finally, in this far more online academic world, it’s important to have more than just a journal paper to express your ideas and connect with people, you need an online presence. I use Dreamhost to host my many websites and during one of our meetings, I bought a couple of domain names on Stuart’s behalf. In the space of a few minutes, he was able to transfer the money back to me using “Settle Up” through my app-based account with Starling Bank which instantly showed the money had arrived with a simple notification. Transferring money instantly and securely this way was a new experience for both of us and as someone old enough to remember my first building society account book where my changing balance was typed onto the next line each time I deposited some pocket money, it really brought home how integral technology is to how we run our world, whether it is in academic research or anything else.

Edit (29/09/2020): Ironically, soon after posting this, the bugs in Mendeley Citation Manager (the citation manager originally mentioned here) became too significant to use well. I was a long-time user of the tool but it has been well and truly overtaken for me by Zotero. I’ve thus updated this blog!

Posted on

Technology for Connection and Conservation

I was part of the organising team for the recent National GP ACF Conference (2020) in Bristol. I took on the role of finding, purchasing, configuring, deploying, and supporting a software package to use at the conference. There are a lot of potential tools on the market, ranging in price from free to many £thousands. I settled in the end on a tool by a company called “Whova”.

Our core goal initially was to remove the need for a paper programme (in keeping with the overall aim to make the conference more environmentally sustainable). It quickly became apparent that there were many other potential benefits in using a digital tool at the conference including: live polls and announcements, uploading and storage of posters and talk slides, and opportunities for attendees to communicate with each other

The live polls (shown on the big screen) added a sense of drama to the debate in a way that trying to count hands wouldn’t have done. The rating tool was also used heavily by attendees to score the speaker presentations which allowed the committee to choose the prize-winning talks easily and hopefully with less bias. Announcements enabled us to immediately update attendees of room and time changes and got lost property back to its owners. I was also pleasantly surprised at how often the app was used by attendees to communicate with each other and how even the less technically aware were able to use it fairly easily.

After the event, I received a downloadable report which, among a lot of statistical facts, showed that 80% of people who were registered as attendees at the event downloaded the app. This number, while reassuringly high, also highlights a few issues; firstly, the tickets weren’t purchased through the app and the translation between the ticket software and the app, while fairly seamless, resulted in a few ‘ghost’ attendees and a few people being missed off. Secondly, while the app was fairly intuitive, there will still be a proportion of people who will be disadvantaged by their dislike, disdain or fear of “tech”. Our robust debate on AI in medicine also highlighted this:

When is the right time to embrace (tech) solutions that work well for the vast majority of people but exclude a small minority – especially when that minority might have the greatest need?

Posted on

Health Data Science – the next key development in patient-centred research will be data-led

The breadth of conditions doctors are expected to manage continues to grow as people and society become ever more complex and it is in GP surgeries up and down the country where this is most starkly seen. The volume of work expected of GPs is taking its toll on individual doctors and the service as a whole.

My previous career designing and developing information technology (IT) systems gives me insight into the huge potential computers and machine learning have to help us in this increasingly challenging environment. Artificial Intelligence (AI) can enable us to provide the best evidence-based medicine to our patients while also freeing us from mundane administration to spend more time connecting with the human beings in front of us.

In the UK, Primary Care is already leading the way when it comes to the use of IT in our daily work. New business start-ups such as Babylon Health show how much further the boundaries can be pushed, with their attempts to employ AI technology in diagnosis and management. Matt Hancock, the current health secretary, is keen for technology to be used in the NHS to ease the pressures on an increasingly under-resourced system.

For technology to truly assist with, and perhaps even replace, some clinicians’ work on the frontline, we must understand what information the system is being given and how it is being processed. This is the role of health data science. Health data science combines maths, statistics and technology to help us to better understand diseases and conditions and can provide new ways of treating them or spotting them earlier.

As a GP Academic Clinical Fellow with one of the National Institute for Health Research (NIHR) themed posts related to health data science, I was invited to London to the launch of a new research collaboration between NIHR and Health Data Research UK (HDR UK). The aim of the day was to promote not only a relationship between the two research entities but between the clinicians, data scientists, and statisticians who have different skill sets to bring to the complex puzzle of managing patient data. Exciting research projects were discussed and speakers from across the country presented their work and their goals to an engaged audience.

Professor Colin McCowan, Professor of Health Data Science at St. Andrews University, discussed the HDR UK National Multimorbidity Platform, which is grappling with the issue of linking disparate datasets across multiple areas of health data. Not only is accessing and extracting the data complex, but overlapping datasets need to be harmonised and standardised. Governance of these datasets also needs to be thought through carefully given their scope and the sensitivity of the data.

Dr Rashmi Patel, an HDR UK fellow, showcased his work using Natural Language Processing (NLP) to ‘read’ complex and extensive clerking notes of psychiatric patients, teasing out the mesh of symptoms they describe and how these do (or in some cases perhaps do not) overlap with the patient’s formal diagnosis. His project demonstrated the complexity of extracting and analysing ‘fuzzy’ data from even more complex real people.

Professor Simon Ball, Executive Medical Director for University Hospitals Birmingham, discussed with me the Trust’s recent decision to trial an implementation of Babylon Health AI technology to run a pre-hospital triage service. The software has already proved controversial with doctors over concerns about how it seems to mis-diagnose life-threatening symptoms. However, Professor Ball wondered if perhaps bold and innovative choices such as these are the only option available when services are already stretched to their limits.

Health data science is an exciting area of research that can only work as a collaborative effort, as no individual has all the skills needed to deliver meaningful research on their own. There are also benefits and risks associated with private enterprise taking the lead. Researchers and frontline clinicians will have to find an appropriate balance between the commercial attitude towards innovation of ‘Move Fast, Break Things’ and the more traditional academic attitude of careful, sometimes years-long, thorough peer-review and publication process.

Whatever the future holds, it’s clear that this research area is only just getting started and is here to stay.