Predicting type 1 diabetes in children using electronic health records in primary care in the UK: development and validation of a machine-learning algorithm.

BACKGROUND: Children presenting to primary care with suspected type 1 diabetes should be referred immediately to secondary care to avoid life-threatening diabetic ketoacidosis. However, early recognition of children with type 1 diabetes is challenging. Children might not present with classic symptoms, or symptoms might be attributed to more common conditions. A quarter of children present with diabetic ketoacidosis, a proportion unchanged over 25 years. Our aim was to investigate whether a machine-learning algorithm could lead to earlier detection of type 1 diabetes in primary care. METHODS: We developed the predictive algorithm using Welsh primary care electronic health records (EHRs) linked to the Brecon Dataset, a register of children newly diagnosed with type 1 diabetes. Children were included from their first primary care record within the study period of Jan 1, 2000, to Dec 31, 2016, until either type 1 diabetes diagnosis, they turned 15 years of age, or study end. We developed an ensemble learner (SuperLearner) using 26 potential predictors. Validation of the algorithm was done in English EHRs from the Clinical Practice Research Datalink (primary care) and Hospital Episode Statistics, focusing on the ability of the algorithm to identify children who went on to develop type 1 diabetes and the time by which diagnosis could be anticipated. FINDINGS: The development dataset comprised 34 754 400 primary care contacts, relating to 952 402 children, and the validation dataset comprised 43 089 103 primary care contacts, relating to 1 493 328 children. Of these, 1829 (0·19%) children younger than 15 years in the development dataset, and 1516 (0·10%) in the validation dataset had a reliable date of type 1 diabetes diagnosis. If set to give an alert in 10% of contacts, an estimated 71·6% (95% CI 68·8-74·4) of the children with type 1 diabetes would receive an alert by the algorithm in the 90 days before diagnosis, with diagnosis anticipated, on average, by an estimated 9·34 days (95% CI 7·77-10·9). INTERPRETATION: If implemented into primary care settings, this predictive algorithm could substantially reduce the proportion of patients with new-onset type 1 diabetes presenting in diabetic ketoacidosis. Acceptability of alert thresholds should be explored in primary care. FUNDING: Diabetes UK.

Association between cannabis potency and mental health in adolescence.

INTRODUCTION: In legal and illegal markets, high-potency cannabis (>10 % delta-9-tetrahydrocannabinol (THC)) is increasingly available. In adult samples higher-potency cannabis has been associated with mental health disorder but no studies have considered associations in adolescence. METHODS: A population-wide study compared no, low and high potency cannabis using adolescents (aged 13-14 years) self-reported symptoms of probable depression, anxiety, and auditory hallucinations. RESULTS: Of the 6672 participants, high-potency cannabis was used by 2.6 % (n=171) and low-potency by 0.6 % (n=38). After adjustment for sociodemographic factors, tobacco and alcohol use, in comparison to participants who had never used cannabis, people who had used high-potency but not low-potency cannabis were more likely to report symptoms of depression (odds ratio 1.59 [95 % confidence interval 1.06, 2.39), anxiety (OR 1.45, 95 % CI 0.96, 2.20), and auditory hallucinations (OR 1.56, 95 % CI 0.98, 2.47). CONCLUSIONS: High-potency cannabis use is associated with an increased risk of probable mental health disorders. Services and programming to minimise drug harms may need to be adapted to pay more attention to cannabis potency.

General population screening for type 1 diabetes using islet autoantibodies at the preschool vaccination visit: a proof-of-concept study (the T1Early study).

OBJECTIVE: Type 1 diabetes (T1D) screening programmes testing islet autoantibodies (IAbs) in childhood can reduce life-threatening diabetic ketoacidosis. General population screening is required to detect the majority of children with T1D, since in >85% there is no family history. Age 3-5 years has been proposed as an optimal age for a single screen approach. DESIGN: Capillary samples were collected from children attending their preschool vaccination and analysed for IAbs to insulin, glutamic acid decarboxylase, islet antigen-2 and zinc transporter 8 using radiobinding/luciferase immunoprecipitation system assays. Acceptability was assessed using semistructured interviews and open-ended postcard questionnaires with parents. SETTING: Two primary care practices in Oxfordshire, UK. MAIN OUTCOME MEASURES: The ability to collect capillary blood to test IAbs in children at the routine preschool vaccination (3.5-4 years). RESULTS: Of 134 parents invited, 66 (49%) were recruited (median age 3.5 years (IQR 3.4-3.6), 26 (39.4%) male); 63 provided a sample (97% successfully), and one participant was identified with a single positive IAb. Parents (n=15 interviews, n=29 postcards) were uniformly positive about screening aligned to vaccination and stated they would have been less likely to take part had screening been a separate visit. Themes identified included preparedness for T1D and the long-term benefit outweighing short-term upset. The perceived volume of the capillary sample was a potential concern and needs optimising. CONCLUSIONS: Capillary IAb testing is a possible method to screen children for T1D. Aligning collection to the preschool vaccination visit can be convenient for families without the need for an additional visit.

Integrating qualitative research within a clinical trials unit: developing strategies and understanding their implementation in contexts.

BACKGROUND/AIMS: The value of using qualitative methods within clinical trials is widely recognised. How qualitative research is integrated within trials units to achieve this is less clear. This paper describes the process through which qualitative research has been integrated within Cardiff University's Centre for Trials Research (CTR) in Wales, UK. We highlight facilitators of, and challenges to, integration. METHODS: We held group discussions on the work of the Qualitative Research Group (QRG) within CTR. The content of these discussions, materials for a presentation in CTR, and documents relating to the development of the QRG were interpreted at a workshop attended by group members. Normalisation Process Theory (NPT) was used to structure analysis. A writing group prepared a document for input from members of CTR, forming the basis of this paper. RESULTS: Actions to integrate qualitative research comprised: its inclusion in Centre strategies; formation of a QRG with dedicated funding/roles; embedding of qualitative research within operating systems; capacity building/training; monitoring opportunities to include qualitative methods in studies; maximising the quality of qualitative research and developing methodological innovation. Facilitators of these actions included: the influence of the broader methodological landscape within trial/study design and its promotion of the value of qualitative research; and close physical proximity of CTR qualitative staff/students allowing sharing of methodological approaches. Introduction of innovative qualitative methods generated interest among other staff groups. Challenges included: pressure to under-resource qualitative components of research, preference for a statistical stance historically in some research areas and funding structures, and difficulties faced by qualitative researchers carving out individual academic profiles when working across trials/studies. CONCLUSIONS: Given that CTUs are pivotal to the design and conduct of RCTs and related study types across multiple disciplines, integrating qualitative research into trials units is crucial if its contribution is to be fully realised. We have made explicit one trials unit's experience of embedding qualitative research and present this to open dialogue on ways to operationalise and optimise qualitative research in trials. NPT provides a valuable framework with which to theorise these processes, including the importance of sense-making and legitimisation when introducing new practices within organisations.

Satisfaction with remote consultations in primary care during COVID-19: a population survey of UK adults.

BACKGROUND: Mode of access to primary care changed during the COVID-19 pandemic; remote consultations became more widespread. With remote consultations likely to continue in UK primary care, it is important to understand people's perceptions of remote consultations and identify potential resulting inequalities. AIM: To assess satisfaction with remote GP consultations in the UK during the COVID-19 pandemic and identify demographic variation in satisfaction levels. DESIGN AND SETTING: A cross-sectional survey from the second phase of a large UK-based study, which was conducted during the COVID-19 pandemic. METHOD: In total, 1426 adults who self-reported having sought help from their doctor in the past 6 months completed an online questionnaire (February to March 2021). Items included satisfaction with remote consultations and demographic variables. Associations were analysed using multivariable regression. RESULTS: A novel six-item scale of satisfaction with remote GP consultations had good psychometric properties. Participants with higher levels of education had significantly greater satisfaction with remote consultations than participants with mid-level qualifications (B = -0.82, 95% confidence interval [CI] = -1.41 to -0.23) or those with low or no qualifications (B = -1.65, 95% CI = -2.29 to -1.02). People living in Wales reported significantly higher satisfaction compared with those living in Scotland (B = -1.94, 95% CI = -3.11 to -0.78), although caution is warranted due to small group numbers. CONCLUSION: These findings can inform the use and adaptation of remote consultations in primary care. Adults with lower educational levels may need additional support to improve their experience and ensure equitable care via remote consultations.