Background Cardiovascular outcomes for people with familial hypercholesterolaemia can be improved with diagnosis and medical management. However, 90% of individuals with familial hypercholesterolaemia remain undiagnosed in the USA. We aimed to accelerate early diagnosis and timely intervention for more than 1•3 million undiagnosed individuals with familial hypercholesterolaemia at high risk for early heart attacks and strokes by applying machine learning to large health-care encounter datasets. MethodsWe trained the FIND FH machine learning model using deidentified health-care encounter data, including procedure and diagnostic codes, prescriptions, and laboratory findings, from 939 clinically diagnosed individuals with familial hypercholesterolaemia (395 of whom had a molecular diagnosis) and 83 136 individuals presumed free of familial hypercholesterolaemia, sampled from four US institutions. The model was then applied to a national health-care encounter database (170 million individuals) and an integrated health-care delivery system dataset (174 000 individuals). Individuals used in model training and those evaluated by the model were required to have at least one cardiovascular disease risk factor (eg, hypertension, hypercholesterolaemia, or hyperlipidemia). A Health Insurance Portability and Accountability Act of 1996-compliant programme was developed to allow providers to receive identification of individuals likely to have familial hypercholesterolaemia in their practice. Findings Using a model with a measured precision (positive predictive value) of 0•85, recall (sensitivity) of 0•45, area under the precision-recall curve of 0•55, and area under the receiver operating characteristic curve of 0•89, we flagged 1 331 759 of 170 416 201 patients in the national database and 866 of 173 733 individuals in the health-care delivery system dataset as likely to have familial hypercholesterolaemia. Familial hypercholesterolaemia experts reviewed a sample of flagged individuals (45 from the national database and 103 from the health-care delivery system dataset) and applied clinical familial hypercholesterolaemia diagnostic criteria. Of those reviewed, 87% (95% Cl 73-100) in the national database and 77% (68-86) in the health-care delivery system dataset were categorised as having a high enough clinical suspicion of familial hypercholesterolaemia to warrant guideline-based clinical evaluation and treatment.Interpretation The FIND FH model successfully scans large, diverse, and disparate health-care encounter databases to identify individuals with familial hypercholesterolaemia. FundingThe FH Foundation funded this study. Support was received from Amgen, Sanofi, and Regeneron.

Objectives: To determine the effectiveness of the cardiopulmonary resuscitation (CPR) audio prompts in an automatic external defibrillator in 24 lay subjects, before and after CPR training. Methods: Untrained subjects were asked to perform CPR on a manikin with and without the assistance of audio prompts. All subjects were then trained in CPR, and retested them eight weeks later. Results: Untrained subjects who performed CPR first without audio prompts performed poorly, with only (mean (SD)) 24.5% (32%) of compressions at the correct site and depth, a mean compression rate of 52 (31) per minute, and with 15% (32%) of ventilatory attempts adequate. Repeat performance by this group with audio prompts resulted in significant improvements in compression rate (91(12), p = 0.0002, paired t test), and percentage of correct ventilations (47% (40%), p = 0.01 paired t test), but not in the percentage correct compressions (23% (29%)). Those who performed CPR first with audio prompts performed significantly better in compression rate (87 (19), p = 003, unpaired t test), and the percentage of correct ventilations (51 (34), p = 0.003 unpaired t test), but not in the percentage of correct compressions (18 (27)) than those without audio prompts. After training, CPR performance was significantly better than before training, but there was no difference in performance with or without audio prompts, although 73% of subjects commented that they felt more comfortable performing CPR with audio prompts. Conclusions: For untrained subjects, the quality of CPR may be improved by using this device, while for trained subjects the willingness to perform CPR may be increased.

No abstract