The title of your blog is so appropriate - you are always "on" in a TV/reporter sense, even if not necessarily in a PD sense. All your work and reports regarding many aspects of the NHS are so valuable and helpful. I am very grateful for your hard work.
Yes - I’ve always found those letters patronising (though I’ve never been described as ‘charming’ I have to say). Power to you and these campaigners - much better to write direct to the patient and copy in the GP. Who wants to read a letter about yourself written in the third person?
Interesting that Dr Rayner a renal physician put this forward. I was looked after by an amazing renal
Physician at the Churchill Hospital in Oxford for 27yrs till he retired. He always wrote the post clinic letter as if he was writing to me. With a bit at the end telling the GP off for something. There is a difference between physicians and surgeons. He used to say surgeons only like patients when they are out cold under a GA! All drs should try to make the letter helpful for the patient first.
Thank you! I have my own pile of letters from my consultants, but hadn’t realised how viscerally I dislike this way of communicating, until I read your post.
It is not only the fact that the patient is a “third person” and therefore not part of the communication. It is also that they become reduced to be a “clinical case” or if you will, an “object”, and that takes them out of the conversation about their treatment (and their own lives!).
Further, many chronic patients never get seen by their GPs, so there’s no point in the pretence of doctor-to-doctor update. Patient-engagement and patient-centricity should start with communication.
And a communication that is tailored to patient’s needs, not abusing specialised language beyond the reach of patients, which I would argue probably sometimes not even GPs might fully grasp. ;)
This is an excellent summary of the webinar and the issues discussed. Thank you, Rory. The webinar will be available for viewing for free in a week or so. I hope you can advertise it.
I managed to get a copy of my medical record, and I could see why we are not encouraged to ask for it: there was a very snarky comment by one GP about me
It would be so good for a patient to receive a letter, (or an email if they prefer,) that explains in clear language what the condition is, the symptoms being experienced, the symptoms you may experience, what the treatment is and the potential timeframe for the treatment and ongoing care.
I have had to do my best to explain letters to service users, to my mum, and my mother in law, looking up phrases where needed. It would be nice to think that by the time my son might need to explain them to me, that he won't have to because I'll be able to understand them myself!
I was once described by a surgeon as “ a fit 50 year old” ( it was a long time ago). My lovely and supportive GP couldn't stop laughing and said “ hey, it's official now”. I found it funny but it could be very irritating and demeaning for others.
I've always assumed the "pleasant" descriptor was code to indicate that we're not a troublemaker or hypochondriac etc. It does always seem weird to have some judgement on your character as the first sentence.
Clear and open communication in language that patients understand is crucial. There's no excuse for not using this during the consultation.
But there are some reasons that letters tend to be addressed to GPs. It allows for a far more succinct and efficient transfer of information, by using a shorthand that both professionals understand. Hospital appointments are often 15minutes, that of GPs on average 9minutes. In that time we need to take a history, examine, organise tests, explain and discuss with the patient, document, dictate a letter and 'outcome' the appointment on whatever software is used.
Medical terminology exists, like any taxonomy, as a shorthand. I will often put lay terms in parentheses after a medical term, and frequently amend letters when proof reading, to cater to the two separate audiences; but shifting to letters written in entirely lay terms for the patient, risks significant additional time both for the hospital doctor and the GP to interpret.
I would hope that after explaining in lay terms to patients in person, the letter serves as a summary and recap, where medical terms now become more understandable.
This hinges on the letter being promptly sent out to patients which I agree is important.
Regarding doctors giving their direct email address to patients, I often do this in particular circumstances. However bear in mind the sheer volume of patients seen, and the lack of easy access to their full medical records, which means that doctors could easily be overwhelmed with patients they cannot recall.
As always, the health service needs improved administrative infrastructure for the increasing demands
Great to have such an interesting and well informed comment. I love the readers of my Substack. The only comment I make is this I’m not convinced that my rather large and impersonal GP surgery actually reads these letters – some of which are addressed to a GP who retired 15 years ago. Certainly the one interaction I’ve had with the GP surgery over my Parkinson’s did not lead me to suspect that they had much if any knowledge of my case.
This is true. Retired GP here. Because practices receive such a lot of correspondence most of it is read by admin staff who should then pass on letters that the GP needs to see according to their protocol.
Unfortunately we are in serious danger of losing the relational aspect of general practice which is good for everyone. This is mostly the result of successive central policies and a shortage of GPs which is not being addressed.
Completely understand what the hospital doctor above is saying. However, AOMRC does set out in the guidance that this is both required by GMC & in NHS Constitution.
Your concerns about writing directly to patients are understandable and commonly voiced by doctors when this change in their well established habits is suggested. I shared the same concerns when my colleague suggested we change back in 2005.
My experience, which is shared by the majority of doctors who have changed [Goulding, R., Firth, J., Gregory, WJ., Staniland, K., McMillan, B., MacPhie, E., Dixon, WG., Sharp, CA., Writing rheumatology outpatient clinic letters directly to patients: preferences, perspectives and support to change practice, (2025), Rheumatology (In press)], is that it does not take longer to write the letter to the patient once you have got used to it, and that it doesn’t take very long to adapt.
Patients often say that they don’t take in or remember what is said during a consultation. Assuming they will have learned enough to understand a medical letter afterwards is unrealistic.
The letter written to the patient can and usually does include a section written in jargon for future reference. It is essential that the change in practice does not dumb down the content.
Regarding giving out your email address, this too is less risky in practice than many fear. The vast majority of NHS patients are fully aware of how busy doctors are and are very reluctant to waste their time. Empowering them to take more control of their health and care is likely to reduce the burden on doctors.
Finally, I would add that the personal and professional satisfaction and indeed pride gained from providing a more personal service to patients is not to be underestimated.
I urge you to give this a go. If you would like practical or moral support in doing so, please email me hughrayner@gmail.com and I would be glad to help.
Thanks for this, long iverdue as you note. I have commented in the NHS change consultation askingbthat patients have the ability to comment/ annitate too. Not so much for physical health, which as you say can be technical, but certainly for mental health where details can be misremembered by the clinician too
What a good idea! Like you Rory I’ve a number of long term conditions to deal with and having navigated the transition from one health trust to another ( moving house) which has been an absolute nightmare and is ongoing -anything to make life easier and more patient centred regarding NHS bureaucracy would be welcome
As a governor and committee chair for my NHS Foundation Trust, and with help from AI re Q&A, I have submitted the following proposal:
Q. Is it feasible for data recorded in a patient’s Electronic Patient Record to be passed through Ai so as to provide a concise, intelligible summary or synopsis for the patient of the nature of the intervention, the outcome and the next steps? If yes, how would this be best achieved?
A. Yes, it is feasible to use Ai to process data recorded in a patient’s Electronic Patient Record (EPR) to provide a concise, intelligible summary for the patient. Such a system could help patients better understand their medical interventions, outcomes, and next steps in their care. Here’s how this could be best achieved:
1. Data Collection and Structuring
Extract Relevant Data: The Ai system needs to extract relevant data from the EPR, such as the diagnosis, treatment interventions, outcomes, and recommended follow-ups. This involves identifying key sections within the EPR, like clinical notes, lab results, medications, and discharge summaries.
Natural Language Processing (NLP): NLP techniques can be used to parse and understand unstructured text within the EPR, allowing the Ai to identify important details and contextual information.
Data Structuring: Organise the extracted data into a structured format that is easier to process, categorise, and summarise.
2. Ai Model Development
Pre-trained Medical NLP Models: Utilise pre-trained models like BERT, GPT, or MedPaLM, which are already fine-tuned on medical literature and clinical notes. These models can be adapted to the specific task of summarising medical data.
Fine-tuning: Fine-tune the chosen model using a dataset of annotated EPRs, where each record is paired with a human-written summary. This will teach the model to generate concise summaries that are patient-friendly.
Incorporate Domain Knowledge: Use medical ontologies like SNOMED CT or ICD-10 to help the Ai system understand medical terminology and improve the accuracy of the summaries.
3. Patient-Centric Summarisation
Simplified Language: Ensure that the Ai system can translate medical jargon into layman’s terms. This is crucial for making the summary understandable to patients who may not have a medical background.
Personalisation: Tailor the summary to the specific patient, taking into account their medical history, literacy level, and preferences. For example, some patients might prefer a more detailed explanation, while others might want only the essentials.
Contextual Relevance: Ensure the Ai focuses on the most relevant information for the patient, like what they need to do next (e.g., take medication, attend a follow-up appointment) and what to expect in terms of outcomes.
4. Validation and Safety
Clinical Review: Before deploying the Ai-generated summaries, have them reviewed by healthcare professionals to ensure accuracy and appropriateness. This helps avoid potential misunderstandings or errors.
Patient Feedback Loop: Incorporate a feedback mechanism where patients can ask follow-up questions or clarify doubts about the summary. This helps refine the Ai’s performance over time.
5. Implementation
Integration with EPR Systems: Implement the Ai within existing EPR systems, ensuring it can access the data in real-time. The Ai should be an embedded tool that clinicians can use to generate summaries during or after a patient’s visit.
User Interface Design: Create a user-friendly interface where patients can access their summaries, either through a patient portal or a mobile app. The design should focus on clarity and ease of use.
6. Privacy and Security
Data Encryption: Ensure that all patient data is encrypted and that access is controlled to protect patient privacy.
Compliance with Regulations: The system must comply with healthcare regulations like GDPR to ensure that patient data is handled securely and ethically.
7. Continuous Learning and Improvement
Monitor and Update: Continuously monitor the Ai’s performance and update it with new data and patient feedback. Regularly retraining the model ensures it stays accurate and effective.
Collaborative Learning: Collaborate with medical professionals to periodically review and refine the summaries, keeping the Ai system aligned with evolving medical practices and patient needs.
Feasibility Considerations:
.Technical Feasibility: Current NLP technologies are advanced enough to handle this task, especially with fine-tuning. However, the quality of the output heavily depends on the quality and structure of the EPR data.
Operational Feasibility: Integrating Ai into EPR systems is technically complex but achievable. It requires collaboration between healthcare providers, IT specialists, and Ai developers.
Ethical and Legal Feasibility: Strict adherence to privacy laws and ethical guidelines is essential. The system must be designed to avoid bias and ensure fairness in how information is presented to all patients.
In summary, while challenges exist, particularly around data privacy, accuracy, and integration, using Ai to provide patient-friendly summaries from EPRs is feasible and can significantly enhance patient understanding and engagement in their healthcare.
Sharing patient-friendly summaries of treatments and outcomes should not simply be viewed as a process, but as an integral element of healthcare. With the right programming, it seems that Ai is in a perfect place to do this with both accuracy and programmed compassion, especially if the output is checked by a clinician before being given to the patient.
Perhaps now is a good time to address this issue? It may be that, with a written (or in time, voice) summary, the clinicians themselves may learn a little more about the implications for the patient of their medical and surgical interventions?
The title of your blog is so appropriate - you are always "on" in a TV/reporter sense, even if not necessarily in a PD sense. All your work and reports regarding many aspects of the NHS are so valuable and helpful. I am very grateful for your hard work.
Gillian this means a lot to me, thank you so much
Yes - I’ve always found those letters patronising (though I’ve never been described as ‘charming’ I have to say). Power to you and these campaigners - much better to write direct to the patient and copy in the GP. Who wants to read a letter about yourself written in the third person?
Interesting that Dr Rayner a renal physician put this forward. I was looked after by an amazing renal
Physician at the Churchill Hospital in Oxford for 27yrs till he retired. He always wrote the post clinic letter as if he was writing to me. With a bit at the end telling the GP off for something. There is a difference between physicians and surgeons. He used to say surgeons only like patients when they are out cold under a GA! All drs should try to make the letter helpful for the patient first.
Thank you! I have my own pile of letters from my consultants, but hadn’t realised how viscerally I dislike this way of communicating, until I read your post.
It is not only the fact that the patient is a “third person” and therefore not part of the communication. It is also that they become reduced to be a “clinical case” or if you will, an “object”, and that takes them out of the conversation about their treatment (and their own lives!).
Further, many chronic patients never get seen by their GPs, so there’s no point in the pretence of doctor-to-doctor update. Patient-engagement and patient-centricity should start with communication.
And a communication that is tailored to patient’s needs, not abusing specialised language beyond the reach of patients, which I would argue probably sometimes not even GPs might fully grasp. ;)
This is an excellent summary of the webinar and the issues discussed. Thank you, Rory. The webinar will be available for viewing for free in a week or so. I hope you can advertise it.
A fascinating piece Rory. Letters to the patient rather than the GP such a simple patient focused solution.
Mind you, here in Wales id like a first step to be actually able to access my own patient record online!
I managed to get a copy of my medical record, and I could see why we are not encouraged to ask for it: there was a very snarky comment by one GP about me
Damn! I really thought it was only me that was described in this way after each consult, so thanks for piddling on my bonfire...
It would be so good for a patient to receive a letter, (or an email if they prefer,) that explains in clear language what the condition is, the symptoms being experienced, the symptoms you may experience, what the treatment is and the potential timeframe for the treatment and ongoing care.
I have had to do my best to explain letters to service users, to my mum, and my mother in law, looking up phrases where needed. It would be nice to think that by the time my son might need to explain them to me, that he won't have to because I'll be able to understand them myself!
Some pilots have been done recently in public libraries around helping people decipher health information and use NHS app and similar. https://www.cilip.org.uk/page/health-and-digital
I was once described by a surgeon as “ a fit 50 year old” ( it was a long time ago). My lovely and supportive GP couldn't stop laughing and said “ hey, it's official now”. I found it funny but it could be very irritating and demeaning for others.
I've always assumed the "pleasant" descriptor was code to indicate that we're not a troublemaker or hypochondriac etc. It does always seem weird to have some judgement on your character as the first sentence.
A couple of points from a hospital doctor.
Clear and open communication in language that patients understand is crucial. There's no excuse for not using this during the consultation.
But there are some reasons that letters tend to be addressed to GPs. It allows for a far more succinct and efficient transfer of information, by using a shorthand that both professionals understand. Hospital appointments are often 15minutes, that of GPs on average 9minutes. In that time we need to take a history, examine, organise tests, explain and discuss with the patient, document, dictate a letter and 'outcome' the appointment on whatever software is used.
Medical terminology exists, like any taxonomy, as a shorthand. I will often put lay terms in parentheses after a medical term, and frequently amend letters when proof reading, to cater to the two separate audiences; but shifting to letters written in entirely lay terms for the patient, risks significant additional time both for the hospital doctor and the GP to interpret.
I would hope that after explaining in lay terms to patients in person, the letter serves as a summary and recap, where medical terms now become more understandable.
This hinges on the letter being promptly sent out to patients which I agree is important.
Regarding doctors giving their direct email address to patients, I often do this in particular circumstances. However bear in mind the sheer volume of patients seen, and the lack of easy access to their full medical records, which means that doctors could easily be overwhelmed with patients they cannot recall.
As always, the health service needs improved administrative infrastructure for the increasing demands
Great to have such an interesting and well informed comment. I love the readers of my Substack. The only comment I make is this I’m not convinced that my rather large and impersonal GP surgery actually reads these letters – some of which are addressed to a GP who retired 15 years ago. Certainly the one interaction I’ve had with the GP surgery over my Parkinson’s did not lead me to suspect that they had much if any knowledge of my case.
This is true. Retired GP here. Because practices receive such a lot of correspondence most of it is read by admin staff who should then pass on letters that the GP needs to see according to their protocol.
Unfortunately we are in serious danger of losing the relational aspect of general practice which is good for everyone. This is mostly the result of successive central policies and a shortage of GPs which is not being addressed.
https://www.aomrc.org.uk/wp-content/uploads/2018/09/Please_write_to_me_Guidance_010918.pdf
Completely understand what the hospital doctor above is saying. However, AOMRC does set out in the guidance that this is both required by GMC & in NHS Constitution.
It’s fine expecting the GP to explain the finer points to the patients. If only we could actually get an appointment to see the GP in the first place!
Dear Dr Vijayan.
Your concerns about writing directly to patients are understandable and commonly voiced by doctors when this change in their well established habits is suggested. I shared the same concerns when my colleague suggested we change back in 2005.
My experience, which is shared by the majority of doctors who have changed [Goulding, R., Firth, J., Gregory, WJ., Staniland, K., McMillan, B., MacPhie, E., Dixon, WG., Sharp, CA., Writing rheumatology outpatient clinic letters directly to patients: preferences, perspectives and support to change practice, (2025), Rheumatology (In press)], is that it does not take longer to write the letter to the patient once you have got used to it, and that it doesn’t take very long to adapt.
Patients often say that they don’t take in or remember what is said during a consultation. Assuming they will have learned enough to understand a medical letter afterwards is unrealistic.
The letter written to the patient can and usually does include a section written in jargon for future reference. It is essential that the change in practice does not dumb down the content.
Regarding giving out your email address, this too is less risky in practice than many fear. The vast majority of NHS patients are fully aware of how busy doctors are and are very reluctant to waste their time. Empowering them to take more control of their health and care is likely to reduce the burden on doctors.
Finally, I would add that the personal and professional satisfaction and indeed pride gained from providing a more personal service to patients is not to be underestimated.
I urge you to give this a go. If you would like practical or moral support in doing so, please email me hughrayner@gmail.com and I would be glad to help.
Best wishes and Happy New Year!
Thanks for this, long iverdue as you note. I have commented in the NHS change consultation askingbthat patients have the ability to comment/ annitate too. Not so much for physical health, which as you say can be technical, but certainly for mental health where details can be misremembered by the clinician too
Thanks Rory.
What a huge difference a sensible and small change could make
What a good idea! Like you Rory I’ve a number of long term conditions to deal with and having navigated the transition from one health trust to another ( moving house) which has been an absolute nightmare and is ongoing -anything to make life easier and more patient centred regarding NHS bureaucracy would be welcome
Great idea to write to the patient. Time for change.
I received an email direct to my NHS app, hours after a recent hospital consultation. Fabulous!
As a governor and committee chair for my NHS Foundation Trust, and with help from AI re Q&A, I have submitted the following proposal:
Q. Is it feasible for data recorded in a patient’s Electronic Patient Record to be passed through Ai so as to provide a concise, intelligible summary or synopsis for the patient of the nature of the intervention, the outcome and the next steps? If yes, how would this be best achieved?
A. Yes, it is feasible to use Ai to process data recorded in a patient’s Electronic Patient Record (EPR) to provide a concise, intelligible summary for the patient. Such a system could help patients better understand their medical interventions, outcomes, and next steps in their care. Here’s how this could be best achieved:
1. Data Collection and Structuring
Extract Relevant Data: The Ai system needs to extract relevant data from the EPR, such as the diagnosis, treatment interventions, outcomes, and recommended follow-ups. This involves identifying key sections within the EPR, like clinical notes, lab results, medications, and discharge summaries.
Natural Language Processing (NLP): NLP techniques can be used to parse and understand unstructured text within the EPR, allowing the Ai to identify important details and contextual information.
Data Structuring: Organise the extracted data into a structured format that is easier to process, categorise, and summarise.
2. Ai Model Development
Pre-trained Medical NLP Models: Utilise pre-trained models like BERT, GPT, or MedPaLM, which are already fine-tuned on medical literature and clinical notes. These models can be adapted to the specific task of summarising medical data.
Fine-tuning: Fine-tune the chosen model using a dataset of annotated EPRs, where each record is paired with a human-written summary. This will teach the model to generate concise summaries that are patient-friendly.
Incorporate Domain Knowledge: Use medical ontologies like SNOMED CT or ICD-10 to help the Ai system understand medical terminology and improve the accuracy of the summaries.
3. Patient-Centric Summarisation
Simplified Language: Ensure that the Ai system can translate medical jargon into layman’s terms. This is crucial for making the summary understandable to patients who may not have a medical background.
Personalisation: Tailor the summary to the specific patient, taking into account their medical history, literacy level, and preferences. For example, some patients might prefer a more detailed explanation, while others might want only the essentials.
Contextual Relevance: Ensure the Ai focuses on the most relevant information for the patient, like what they need to do next (e.g., take medication, attend a follow-up appointment) and what to expect in terms of outcomes.
4. Validation and Safety
Clinical Review: Before deploying the Ai-generated summaries, have them reviewed by healthcare professionals to ensure accuracy and appropriateness. This helps avoid potential misunderstandings or errors.
Patient Feedback Loop: Incorporate a feedback mechanism where patients can ask follow-up questions or clarify doubts about the summary. This helps refine the Ai’s performance over time.
5. Implementation
Integration with EPR Systems: Implement the Ai within existing EPR systems, ensuring it can access the data in real-time. The Ai should be an embedded tool that clinicians can use to generate summaries during or after a patient’s visit.
User Interface Design: Create a user-friendly interface where patients can access their summaries, either through a patient portal or a mobile app. The design should focus on clarity and ease of use.
6. Privacy and Security
Data Encryption: Ensure that all patient data is encrypted and that access is controlled to protect patient privacy.
Compliance with Regulations: The system must comply with healthcare regulations like GDPR to ensure that patient data is handled securely and ethically.
7. Continuous Learning and Improvement
Monitor and Update: Continuously monitor the Ai’s performance and update it with new data and patient feedback. Regularly retraining the model ensures it stays accurate and effective.
Collaborative Learning: Collaborate with medical professionals to periodically review and refine the summaries, keeping the Ai system aligned with evolving medical practices and patient needs.
Feasibility Considerations:
.Technical Feasibility: Current NLP technologies are advanced enough to handle this task, especially with fine-tuning. However, the quality of the output heavily depends on the quality and structure of the EPR data.
Operational Feasibility: Integrating Ai into EPR systems is technically complex but achievable. It requires collaboration between healthcare providers, IT specialists, and Ai developers.
Ethical and Legal Feasibility: Strict adherence to privacy laws and ethical guidelines is essential. The system must be designed to avoid bias and ensure fairness in how information is presented to all patients.
In summary, while challenges exist, particularly around data privacy, accuracy, and integration, using Ai to provide patient-friendly summaries from EPRs is feasible and can significantly enhance patient understanding and engagement in their healthcare.
Sharing patient-friendly summaries of treatments and outcomes should not simply be viewed as a process, but as an integral element of healthcare. With the right programming, it seems that Ai is in a perfect place to do this with both accuracy and programmed compassion, especially if the output is checked by a clinician before being given to the patient.
Perhaps now is a good time to address this issue? It may be that, with a written (or in time, voice) summary, the clinicians themselves may learn a little more about the implications for the patient of their medical and surgical interventions?
Thank you, this is a very helpful post.