[PDF]

Could AI do a NHS (Audiology) clinicians paperwork to help create a better patient experience.


Richard Johns

11/09/2023

Supervised by Paul Goddard; Moderated by Víctor Gutiérrez Basulto

It is often reported by clinicians in the NHS that their least favorite part was the associated paperwork. Paperwork such as appointment summary notes, letters to doctors, onward referrals etc. are incredibly important. NHS Staff are trained to reject the medical model and embrace the biopsychosocial model of care. However with the growing levels of demand faced by clinicians, they are not given enough time to complete all the medical tasks and write notes and also spend time delving into a patients history to get a better understanding and therefore a better treatment plan, spending time counselling the patient on there problems and how the process is going to go. Clinicians are faced with 4 options, don’t do paper work or the medical side such as testing (which isn’t an option), do the appointment properly but overrun and deal with unhappy patients who have been waiting for, in some cases, hours to be seen and the clinicians will have to work into their unpaid own time. Leave the paperwork till the end of the day, again in there own unpaid time and likely have a poorer quality of paperwork, or don’t do the “soft skills” part of the appointment which means the clinician can leave on time but quality of their work deteriorates leading to unhappy patients and loss of passion for the job. Having to compromise in one of these ways is one of the reasons leading to massive burnout and high rates of passionate staff quitting. The solution for this is to hire more staff and have more clinical rooms, however this requires funding that is currently unavailable to the NHS, so another solution needs to be found.

What I am interested in doing my dissertation around is testing the feasibility/building a program that uses speech to text to create transcripts of a one to one hearing aid audiology appointment. I then would look at if AI could be used to analyse the transcript, maybe help identify and correct any transcription errors and generate a summary report of what had happened in the appointment. I would also be interested to see if from this initial report other “actions” could automatically take place such as letters to doctors, orders for certain tests/devices required at another appt, future appt requests etc. I believe Hearing aid audiology appts will be a good place to develop this sort of software initially as there are a limited number of outcomes that happen which I suspect will help.

This is something that could lead to tangible benefits for the healthcare workplace and beyond. In audiology, it in theory could free up 10-15 mins of time in a 1 hour appt to allow the clinician to spend more time talking and counselling there patient leading to better levels of care and better levels of patient satisfaction whilst making the job less stressful and more enjoyable for the clinician and could measure this with some form of questionnaire. I also suspect that this would also reduce the number of visits a patient needs and help with cutting down the hospitals historically long waiting lists. Another issue this could solve is the quality of the notes written by clinicians which can vary greatly from detailed typed notes to a scribble of a couple of keywords. It may help with patients complaints as it would provide an “unbiased” record of what had occurred during any appointment. Whilst I would be building it for a specific type of appointment initially I believe there is potential for it to be used across all types of hospital appts and from there is has potential to be beneficial in all sorts of situations such as meeting minutes.


Final Report (11/09/2023) [Zip Archive]

Publication Form