Detecting undiagnosed atrial fibrillation in UK primary care: Validation of a machine learning prediction algorithm in a retrospective cohort study.

AIMS: To evaluate the ability of a machine learning algorithm to identify patients at high risk of atrial fibrillation in primary care. METHODS: A retrospective cohort study was undertaken using the DISCOVER registry to validate an algorithm developed using a Clinical Practice Research Datalink (CPRD) dataset. The validation dataset included primary care patients in London, England aged ≥30 years from 1 January 2006 to 31 December 2013, without a diagnosis of atrial fibrillation in the prior 5 years. Algorithm performance metrics were sensitivity, specificity, positive predictive value, negative predictive value (NPV) and number needed to screen (NNS). Subgroup analysis of patients aged ≥65 years was also performed. RESULTS: Of 2,542,732 patients in DISCOVER, the algorithm identified 604,135 patients suitable for risk assessment. Of these, 3.0% (17,880 patients) had a diagnosis of atrial fibrillation recorded before study end. The area under the curve of the receiver operating characteristic was 0.87, compared with 0.83 in algorithm development. The NNS was nine patients, matching the CPRD cohort. In patients aged ≥30 years, the algorithm correctly identified 99.1% of patients who did not have atrial fibrillation (NPV) and 75.0% of true atrial fibrillation cases (sensitivity). Among patients aged ≥65 years (n = 117,965), the NPV was 96.7% with 91.8% sensitivity. CONCLUSIONS: This atrial fibrillation risk prediction algorithm, based on machine learning methods, identified patients at highest risk of atrial fibrillation. It performed comparably in a large, real-world population-based cohort and the developmental registry cohort. If implemented in primary care, the algorithm could be an effective tool for narrowing the population who would benefit from atrial fibrillation screening in the United Kingdom.

Application of a machine learning algorithm for detection of atrial fibrillation in secondary care.

Atrial fibrillation (AF) is the most common sustained heart arrhythmia and significantly increases risk of stroke. Opportunistic AF testing in high-risk patients typically requires frequent electrocardiogram tests to capture the arrhythmia. Risk-prediction algorithms may help to more accurately identify people with undiagnosed AF and machine learning (ML) may aid in the diagnosis of AF. Here, we applied an AF-risk prediction algorithm to secondary care data linked to primary care data in the DISCOVER database in order to evaluate changes in model performance, and identify patients not previously detected in primary care. We identified an additional 5,444 patients who had an AF diagnosis only in secondary care during the data extraction period. 2,696 (49.5%) were accepted by the algorithm and the algorithm correctly assigned 2,637 (97.8%) patients to the AF cohort. Using a risk threshold of 7.4% in patients aged ≥ 30 years, algorithm sensitivity and specificity was 38% and 95%, respectively. Approximately 15% of AF patients assigned to the AF cohort by the algorithm had a secondary care diagnosis with no record of AF in primary care. These additional patients did not substantially alter algorithm performance. The additional detection of previously undiagnosed AF patients in secondary care highlights unexpected potential utility of this ML algorithm.

Neurocognitive training for children with and without AD/HD.

There is accumulating evidence that computerised cognitive training of inhibitory control and/or working memory can lead to behavioural improvement in children with AD/HD. Using a randomised waitlist control design, the present study examined the effects of combined working memory and inhibitory control training, with and without passive attention monitoring via EEG, for children with and without AD/HD. One hundred and twenty-eight children (60 children with AD/HD, 68 without AD/HD) were randomly allocated to one of three training conditions (waitlist; working memory and inhibitory control with attention monitoring; working memory and inhibitory control without attention monitoring) and completed with pre- and post-training assessments of overt behaviour (from 2 sources), trained and untrained cognitive task performance, and resting EEG activity. The two active training conditions completed 25 sessions of training at home over a 4- 5-week period. Results showed significant improvements in overt behaviour for children with AD/HD in both training conditions compared to the waitlist condition as rated by a parent and other adult. Post-training improvements in the areas of spatial working memory, ignoring distracting stimuli, and sustained attention were reported for children with AD/HD. Children without AD/HD showed behavioural improvements after training. The improvements for both groups were maintained over the 6-week period following training. The passive attention monitoring via EEG had a minor effect on training outcomes. Overall, the results suggest that combined WM/IC training can result in improved behavioural control for children with and without AD/HD.