Topic Analysis of UK Fitness to Practise Cases: What Lessons Can Be Learnt?

Abstract

Background: Fitness to practise (FtP) impairment (failure of a healthcare professional to demonstrate skills, knowledge, character and/or health required for their job) can compromise patient safety, the profession’s reputation, and an individual’s career. In the United Kingdom (UK), various healthcare professionals’ FtP cases (documents about the panel hearing(s) and outcome(s) relating to the alleged FtP impairment) are publicly available, yet reviewing these to learn lessons may be time-consuming given the number of cases across the professions and amount of text in each. We aimed to demonstrate how machine learning facilitated the examination of such cases (at uni- and multi-professional level), involving UK dental, medical, nursing and pharmacy professionals. Methods: Cases dating from August 2017 to June 2019 were downloaded (577 dental, 481 medical, 2199 nursing and 63 pharmacy) and converted to text files. A topic analysis method (non-negative matrix factorization; machine learning) was employed for data analysis. Results: Identified topics were criminal offences; dishonesty (fraud and theft); drug possession/supply; English language; indemnity insurance; patient care (including incompetence) and personal behavior (aggression, sexual conduct and substance misuse). The most frequently identified topic for dental, medical and nursing professions was patient care whereas for pharmacy, it was criminal offences. Conclusions: While commonalities exist, each has different priorities which professional and educational organizations should strive to address.

The Ongoing Emergence of Technology in Healthcare to Enhance Patient Outcomes

“…For example, one of the authors of this chapter has demonstrated how machine learning facilitated the examination of over 3000 Fitness to Practise cases involving UK healthcare professionals. These cases were initially converted to text files, with other preprocessing steps implemented, before a topic analysis method (non-negative matrix factorisation; machine learning) was employed for data analysis (Hanna and Hanna 2019).…”

“…An educated prediction may include the hypothesis that future directions being added to the healthcare map will be exceptionally combinatorial and may well tie in with technologies which have been discussed elsewhere within this chapter, in addition to others. Drastically enhanced computing power and the ability for systems to handle, process and draw conclusions from extraordinarily large data sets have led to the emergence of "big data", which in turn can centralise hugely useful information such as patient data sets, treatment outcomes and a host of other useful clinical, management-centric and professional performance data (Dash et al 2019;Hanna and Hanna 2019) This, combined with technologies such as AI, labs-on-chip-based testing and enhancements in rapid drug and device manufacturing will accelerate the area of personalised medicine (Wu et al 2018;Jhunjhunwala and Kapil 2022;Katakam, Adiki, and Satapathy 2022), potentially allowing us to move away from population-based empirical models for the treatment of disease and, instead, toward something which is maximally targeted. It is not long ago that the suggestion that someone who had fallen ill could be tested at their bedside, and their diagnostic test results instantly generated and fed into a data set which would allow both the selection of a medication that would cater specifically to that patient's needs, and its manufacture within hours or minutes within the care setting, would be touted as something straight from a science-fiction novel.…”

Insights from Regulatory Data on Development Needs of Community Pharmacy Professionals

“…Some health profession regulators have ventured into data analysis to explore the potential for this data to help fulfill the regulatory mandate. A recent study used machine learning to examine topics of fitness-to-practice cases involving various UK health professionals including pharmacists [ 3 ]. The study identified some overlap or commonalities across professions, it also concluded that each profession has different priorities which professional associations and educational organizations should be aware of and work to address.…”