Could dementia be detected from UK primary care patients’ records by simple automated methods earlier than by the treating physician? A retrospective case-control study
Abstract:Background: Timely diagnosis of dementia is a policy priority in the United Kingdom (UK). Primary care physicians receive incentives to diagnose dementia; however, 33% of patients are still not receiving a diagnosis. We explored automating early detection of dementia using data from patients’ electronic health records (EHRs). We investigated: a) how early a machine-learning model could accurately identify dementia before the physician; b) if models could be tuned for dementia subtype; and c) what the best clin… Show more
“…At the beginning of the interview, a hypothetical example of a dementia early detection tool was introduced. This was chosen because there is a large body of work on developing automated dementia risk prediction work, some of which focuses on using primary care data [ 20 , 37 – 42 ]. However, prediction or detection of dementia is still controversial because of a lack of treatment available which makes any different to the disease trajectory [ 43 ], because of the high risk of false positives [ 44 ], and due to the patient’s “right not to know” [ 45 ].…”
Background
Well-established electronic data capture in UK general practice means that algorithms, developed on patient data, can be used for automated clinical decision support systems (CDSSs). These can predict patient risk, help with prescribing safety, improve diagnosis and prompt clinicians to record extra data. However, there is persistent evidence of low uptake of CDSSs in the clinic. We interviewed UK General Practitioners (GPs) to understand what features of CDSSs, and the contexts of their use, facilitate or present barriers to their use.
Methods
We interviewed 11 practicing GPs in London and South England using a semi-structured interview schedule and discussed a hypothetical CDSS that could detect early signs of dementia. We applied thematic analysis to the anonymised interview transcripts.
Results
We identified three overarching themes: trust in individual CDSSs; usability of individual CDSSs; and usability of CDSSs in the broader practice context, to which nine subthemes contributed. Trust was affected by CDSS provenance, perceived threat to autonomy and clear management guidance. Usability was influenced by sensitivity to the patient context, CDSS flexibility, ease of control, and non-intrusiveness. CDSSs were more likely to be used by GPs if they did not contribute to alert proliferation and subsequent fatigue, or if GPs were provided with training in their use.
Conclusions
Building on these findings we make a number of recommendations for CDSS developers to consider when bringing a new CDSS into GP patient records systems. These include co-producing CDSS with GPs to improve fit within clinic workflow and wider practice systems, ensuring a high level of accuracy and a clear clinical pathway, and providing CDSS training for practice staff. These recommendations may reduce the proliferation of unhelpful alerts that can result in important decision-support being ignored.
“…At the beginning of the interview, a hypothetical example of a dementia early detection tool was introduced. This was chosen because there is a large body of work on developing automated dementia risk prediction work, some of which focuses on using primary care data [ 20 , 37 – 42 ]. However, prediction or detection of dementia is still controversial because of a lack of treatment available which makes any different to the disease trajectory [ 43 ], because of the high risk of false positives [ 44 ], and due to the patient’s “right not to know” [ 45 ].…”
Background
Well-established electronic data capture in UK general practice means that algorithms, developed on patient data, can be used for automated clinical decision support systems (CDSSs). These can predict patient risk, help with prescribing safety, improve diagnosis and prompt clinicians to record extra data. However, there is persistent evidence of low uptake of CDSSs in the clinic. We interviewed UK General Practitioners (GPs) to understand what features of CDSSs, and the contexts of their use, facilitate or present barriers to their use.
Methods
We interviewed 11 practicing GPs in London and South England using a semi-structured interview schedule and discussed a hypothetical CDSS that could detect early signs of dementia. We applied thematic analysis to the anonymised interview transcripts.
Results
We identified three overarching themes: trust in individual CDSSs; usability of individual CDSSs; and usability of CDSSs in the broader practice context, to which nine subthemes contributed. Trust was affected by CDSS provenance, perceived threat to autonomy and clear management guidance. Usability was influenced by sensitivity to the patient context, CDSS flexibility, ease of control, and non-intrusiveness. CDSSs were more likely to be used by GPs if they did not contribute to alert proliferation and subsequent fatigue, or if GPs were provided with training in their use.
Conclusions
Building on these findings we make a number of recommendations for CDSS developers to consider when bringing a new CDSS into GP patient records systems. These include co-producing CDSS with GPs to improve fit within clinic workflow and wider practice systems, ensuring a high level of accuracy and a clear clinical pathway, and providing CDSS training for practice staff. These recommendations may reduce the proliferation of unhelpful alerts that can result in important decision-support being ignored.
“…The largest European register-based studies report mean age at the time of AD diagnosis to be 80-83 years (Tolppanen et al, 2016;Zakarias et al, 2019;Ford et al, 2020;Ponjoan et al, 2020). Based on age-specific dementia incidence rates (Prince et al, 2015) and Finnish population predictions for 2029 [Official Statistics of Finland (OSF) 2019], the majority (71%) of new AD diagnoses will occur among those aged 70-89 years, followed by those aged >90 years (21%); the phenomenon is expected to be even more pronounced during the 2030s.…”
Section: Discussionmentioning
confidence: 99%
“…An increasing number of studies are based on data from very large registers. In the AD field, register-based data have been used, e.g., to investigate incidence and prevalence of AD/dementia (Tolppanen et al, 2016;Kivimäki et al, 2018;Zakarias et al, 2019;Ponjoan et al, 2020), and AD classification (Ford et al, 2020). Registry-based data have also been used to evaluate medication use, healthcare service use (Tolppanen et al, 2016), and quality of diagnostic processes (Zakarias et al, 2019).…”
We aimed to evaluate the feasibility of using real-world register data for identifying persons with mild Alzheimer’s disease (AD) and to describe their cognitive performance at the time of diagnosis. Patients diagnosed with AD during 2010–2013 (aged 60–81 years) were identified from the Finnish national health registers and enlarged with a smaller private sector sample (total n = 1,268). Patients with other disorders impacting cognition were excluded. Detailed clinical and cognitive screening data (the Consortium to Establish a Registry for Alzheimer’s Disease neuropsychological battery [CERAD-nb]) were obtained from local health records. Adequate cognitive data were available for 389 patients with mild AD (31%) of the entire AD group. The main reasons for not including patients in analyses of cognitive performance were AD diagnosis at a moderate/severe stage (n = 266, 21%), AD diagnosis given before full register coverage (n = 152, 12%), and missing CERAD-nb data (n = 139, 11%). The cognitive performance of persons with late-onset AD (n = 284), mixed cerebrovascular disease and AD (n = 51), and other AD subtypes (n = 54) was compared with that of a non-demented sample (n = 1980) from the general population. Compared with the other AD groups, patients with late-onset AD performed the worst in word list recognition, while patients with mixed cerebrovascular disease and AD performed the worst in constructional praxis and clock drawing tests. A combination of national registers and local health records can be used to collect data relevant for cognitive screening; today, the process is laborious, but it could be improved in the future with refined search algorithms and electronic data.
“…In 22 studies of this ICD-10 classifications addressing six health conditions [28,45,[89][90][91][92][93][94][95][96][97]119,81,120,121,[82][83][84][85][86][87][88], the involved population were from eight countries, mainly the US and the UK (n=14). These studies were published since 2013 with the highest number of studies in 2020 (44.4%).…”
Aim: With the rapid advances in technology and data science, machine learning (ML) is being adopted by the health care sector; but there is a lack of literature addressing the health conditions targeted by the ML prediction models within primary health care (PHC). To fill this gap in knowledge, we conducted a systematic review following the PRISMA guidelines to identify the health conditions targeted by ML in PHC.
Methods: We searched the Cochrane Library, Web of Science, PubMed, Elsevier, BioRxiv, Association of Computing Machinery (ACM), and IEEE Xplore databases for studies published from January 1990 to January 2022. We included any primary study addressing ML diagnostic or prognostic predictive models that were supplied completely or partially by real-world PHC data. We performed literature screening, data extraction, and risk of bias assessment. Health conditions were categorized according to international classification of diseases. Extracted date were analyzed quantitatively and qualitatively.
Results: We identified 109 studies investigating 42 health conditions. These studies included 273 ML prediction models supplied by the PHC data of 24.2 million participants from 19 countries. We found that 82% of the studies were retrospective. 76.6% of the studies reported diagnostic predictive ML models. 77% of all reported models aimed for models’ development without external validation. Risk of bias assessment revealed that 90.8% of the studies were of high or unclear risk of bias. The most frequently reported health conditions were Alzheimer’s disease and diabetes mellitus.
Conclusions: To the best of our knowledge, this is the first review to investigate the extent of the health conditions targeted by the ML prediction models within PHC settings. Our study provides an important summary on the presently available ML models in PHC, which can be used in further research and implementation efforts.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.