This week’s edition looks at an interesting study on a new blood pressure monitoring technique usable on a smartphone, a study debunking the “July effect,” and a paper looking at an AI-enabled ECG that was successful at teasing out AFib.
Blood Pressure Monitoring by Selfie?
A new study in Circulation: Cardiovascular Imaging examined the accuracy of a smartphone imaging app that takes two-minute videos of the face and can use the data to measure blood pressure. The study results suggested that the technique was close to the accuracy of cuff-based blood pressure monitoring. “If future studies could confirm this exciting result in hypertensive patients and with video camera measurements made during daily life, then obtaining blood pressure information with a click of a camera may become reality,” an accompanying editorial on the study results said.
No “July Effect” for Cardiac Surgery Outcomes
The myth goes that medical and procedural errors go up in July due to the influx and changeover of new medical students working on the patients. A new study in the Annals of Thoracic Surgery threw some cold water on that, looking at hundreds of thousands of interventional procedures such as coronary artery bypass graft (CABG), aortic valve replacement, mitral valve repair, and others. The results showed that in-hospital mortality did no vary between months for the various cardiac procedures. “While the perception of the ‘July effect’ persists culturally among health care providers, we hope that this study reinforces the fact that hospital systems have in place processes that help provide the highest level of care and ensure patient safety,” one of the study authors said.
AI-enabled ECG Detects AFib
A new artificial intelligence (AI)-infused ECG algorithm was effective at detecting atrial fibrillation (AFib), a new Mayo Clinic study suggested. The results showed that a single AI-enabled ECG could identify AFib with a sensitivity, specificity, F1 score and overall accuracy that was comparable to standard. “Rather than finding the needle in the haystack by prolonged monitoring, authors basically suggest that AI will be able to judge by looking at the haystack if it has a needle hidden in it,” they wrote.
