Actionable absolute risk prediction of atherosclerotic cardiovascular disease based on the UK Biobank.

Cardiovascular diseases (CVDs) are the primary cause of all death globally. Timely and accurate identification of people at risk of developing an atherosclerotic CVD and its sequelae is a central pillar of preventive cardiology. One widely used approach is risk prediction models; however, currently available models consider only a limited set of risk factors and outcomes, yield no actionable advice to individuals based on their holistic medical state and lifestyle, are often not interpretable, were built with small cohort sizes or are based on lifestyle data from the 1960s, e.g. the Framingham model. The risk of developing atherosclerotic CVDs is heavily lifestyle dependent, potentially making many occurrences preventable. Providing actionable and accurate risk prediction tools to the public could assist in atherosclerotic CVD prevention. Accordingly, we developed a benchmarking pipeline to find the best set of data preprocessing and algorithms to predict absolute 10-year atherosclerotic CVD risk. Based on the data of 464,547 UK Biobank participants without atherosclerotic CVD at baseline, we used a comprehensive set of 203 consolidated risk factors associated with atherosclerosis and its sequelae (e.g. heart failure). Our two best performing absolute atherosclerotic risk prediction models provided higher performance, (AUROC: 0.7573, 95% CI: 0.755-0.7595) and (AUROC: 0.7544, 95% CI: 0.7522-0.7567), than Framingham (AUROC: 0.680, 95% CI: 0.6775-0.6824) and QRisk3 (AUROC: 0.725, 95% CI: 0.7226-0.7273). Using a subset of 25 risk factors identified with feature selection, our reduced model achieves similar performance (AUROC 0.7415, 95% CI: 0.7392-0.7438) while being less complex. Further, it is interpretable, actionable and highly generalizable. The model could be incorporated into clinical practice and might allow continuous personalized predictions with automated intervention suggestions.

How accurate are digital symptom assessment apps for suggesting conditions and urgency advice? A clinical vignettes comparison to GPs.

OBJECTIVES: To compare breadth of condition coverage, accuracy of suggested conditions and appropriateness of urgency advice of eight popular symptom assessment apps. DESIGN: Vignettes study. SETTING: 200 primary care vignettes. INTERVENTION/COMPARATOR: For eight apps and seven general practitioners (GPs): breadth of coverage and condition-suggestion and urgency advice accuracy measured against the vignettes' gold-standard. PRIMARY OUTCOME MEASURES: (1) Proportion of conditions 'covered' by an app, that is, not excluded because the user was too young/old or pregnant, or not modelled; (2) proportion of vignettes with the correct primary diagnosis among the top 3 conditions suggested; (3) proportion of 'safe' urgency advice (ie, at gold standard level, more conservative, or no more than one level less conservative). RESULTS: Condition-suggestion coverage was highly variable, with some apps not offering a suggestion for many users: in alphabetical order, Ada: 99.0%; Babylon: 51.5%; Buoy: 88.5%; K Health: 74.5%; Mediktor: 80.5%; Symptomate: 61.5%; Your.MD: 64.5%; WebMD: 93.0%. Top-3 suggestion accuracy was GPs (average): 82.1%±5.2%; Ada: 70.5%; Babylon: 32.0%; Buoy: 43.0%; K Health: 36.0%; Mediktor: 36.0%; Symptomate: 27.5%; WebMD: 35.5%; Your.MD: 23.5%. Some apps excluded certain user demographics or conditions and their performance was generally greater with the exclusion of corresponding vignettes. For safe urgency advice, tested GPs had an average of 97.0%±2.5%. For the vignettes with advice provided, only three apps had safety performance within 1 SD of the GPs-Ada: 97.0%; Babylon: 95.1%; Symptomate: 97.8%. One app had a safety performance within 2 SDs of GPs-Your.MD: 92.6%. Three apps had a safety performance outside 2 SDs of GPs-Buoy: 80.0% (p<0.001); K Health: 81.3% (p<0.001); Mediktor: 87.3% (p=1.3×10-3). CONCLUSIONS: The utility of digital symptom assessment apps relies on coverage, accuracy and safety. While no digital tool outperformed GPs, some came close, and the nature of iterative improvements to software offers scalable improvements to care.