North Carolina man, MaxPaul Franklin, who used his Tesla’s “Full Self-Driving” mode to get him to the ED after suffering a mild heart attack.

Artificial Intelligence

Cedars-Sinai Detects AFib with Echo AI

A Cedars-Sinai-led team developed an echocardiography AI model that accurately detects patients with atrial fibrillation – including asymptomatic patients – potentially revealing a new “opportunistic screening” method to drive earlier AFib detection and treatment.

• Transthoracic echo (TTE) is the most common cardiovascular imaging exam, and is increasingly being combined with AI to support image acquisition, interpretation, and reporting.
• AFib detection has historically relied on ECG exams, and although ECG AI has shown promise, many patients who undergo ECGs were already either suspected to have AFib or already experienced a major cardiac event.

The researchers trained their deep learning algorithm using 111k TTE videos, including 39k exams from patients who were in AFib and 72k exams from patients with normal sinus rhythm at the time of their echos… although 6,654 of those “normal” exams were from patients who actually had paroxysmal AFib.

• When tested against an internal Cedars-Sinai TTE dataset, the model identified patients who were in AFib with “high accuracy” (AUC: 0.96) and patients with normal sinus rhythm but paroxysmal AFib “moderately well” (AUC: 0.74).
• When tested against 10k TTEs from an external Stanford dataset, the model achieved a decent 0.69 AUC identifying patients with a history of AFib.

That performance was consistent across genders, older patients, and patients with higher AFib risks, and perhaps more notably, it outperformed AFib detection based on clinical risk factors, TTE measurements, LA size, and CHA2DS2VASc Scores (AUCs: 0.64, 0.64, 0.62, 0.61).

They then combined the TTE AI model with an ECG-based deep learning model, finding that the combined TTE/ECG system detected patients with AFib better than the ECG model on its own (AUC 0.81 vs. 0.79), potentially because structural information from TTEs might complement ECG-based analysis. 

The Takeaway

There are about 6 million people in the United States living with AFib, and nearly a quarter of them are currently undiagnosed. Although Cedars-Sinai’s echo AI AFib model is still in its early stages, this study makes a solid case for how AI could be used to proactively analyze the 7 million echo exams that are performed in the US each year to help identify more undiagnosed AFib patients while their treatment would be most effective.

Can AI Prevent Heart Disease Progression?

Tune in to Cleerly’s on-demand webinar where study leaders will discuss how the landmark TRANSFORM randomized controlled trial will test whether an AI-personalized care strategy can outperform traditional risk factor management and prevent cardiovascular events.

PIA Medical Processes It All

Need an analysis like calcium scoring, strain or even FFR? PIA Medical began as a Core Lab and can handle creative cardiac research and clinical trials along with the full breadth of clinical analyses available today.

The Wire

• TAVR Safe in Low-Risk Cases: The DEDICATE trial added more support for TAVR in patients with severe aortic stenosis and low surgical risks. Among 1,414 low-to-intermediate risk patients, one-year rates of primary outcome events (all-cause mortality or stroke) were far lower among TAVR patients than SAVR patients (5.4% vs. 10%). TAVR also had far lower rates of major bleeding (4.3% vs. 17.2%), but slightly higher post-procedure complication rates (1.5% vs. 1%). 

• Mass General’s CT-FFR Impact: A new study out of Mass General highlighted how FFR-CT can avoid unnecessary interventional procedures. The researchers analyzed 2,985 patients who received coronary CTA exams, including 284 patients referred for HeartFlow’s FFR-CT analysis after their CCTA showed significant blockages/narrowing. The FFR-CT patients had lower rates of invasive coronary angiography (26% vs. 75%) and were less likely to undergo PCI (21% vs. 79%).

• Abbott HeartMate Recall: Abbott’s HeartMate II and HeartMate 3 Left Ventricular Assist Systems (LVAS) are the target of a Class 1 FDA recall after an issue called Extrinsic Outflow Graft Obstruction (EOGO) led to 273 reported injuries and 14 reported deaths. EOGO occurs when biological material builds up, potentially obstructing the device and making it less effective. The recall comes almost exactly a month after Abbott’s connected HeartMate Touch Communication System was also recalled.

• Cardiologists Still Compensation Leaders: Cardiologists were once again well positioned in Medscape’s 2024 Physician Compensation Report, with the third highest earnings across 29 specialties (+3.5% to $525k), following only orthopedics and plastic surgery ($558k & $536k). However, only 48% of cardiologists reported being satisfied with their compensation (14th highest).

• Telemedicine’s ACS Advantage: A new JACC study highlighted telemedicine’s benefits among recovering acute coronary syndrome patients. The TELE-ACS trial randomized 337 post-ACS patients for either telemedicine monitoring or standard care, finding that after six months the telemedicine group had far lower risks of readmission and ED attendance (hazard ratios: 0.24 & 0.59), fewer unplanned coronary revascularizations (3% vs. 9%), and less occurrence of key symptoms like chest pain, breathlessness, and dizziness (9% vs. 24%, 21% vs. 39%, 6% vs. 18%).

• Severe Baseline TR Tanks TMVR Outcomes: A new AJC study highlighted the significance of early intervention in patients with moderate to severe baseline tricuspid regurgitation. Among 135 patients who underwent TMVR, those with moderate/severe baseline TR had a far higher risk of mortality 3 years after transcatheter mitral valve replacement (adjusted HR=3.37), despite no significant differences in in-hospital events between the study’s TR severity groups.

• Self Driving MI Care: We cover a lot of futuristic healthcare news, but few can match the story of North Carolina’s MaxPaul Franklin, who used his Tesla’s “Full Self-Driving” mode to bring him 13 miles to the nearest emergency room after suffering a mild heart attack and seeing his blood glucose level spike to 670. Franklin added Full Self-Driving capabilities to his Tesla just the day before this event, and although the feature shouldn’t be used instead of an ambulance, the car did park itself after dropping him off at the ED.

• No SGLT2is After Acute MI: Results from the EMPACT-MI trial do not support routine use of SGLT2is in patients hospitalized for acute MI and at risk for heart failure. Among 3,262 patients, those taking the SGLT2i empagliflozin (Boehringer Ingelheim/Eli Lilly’s Jardiance) had similar rates of the composite primary endpoint (first HF hospitalization, all-cause deaths) as those taking a placebo (8.2% vs. 9.1%). However, Jardiance did (logically) reduce rates of first HF hospitalizations (3.6% vs. 4.7%).

• Racial Disparities in CAC Scoring: We just learned that CAC scoring’s tremendous growth has effectively erased gender disparities, but the same apparently isn’t true for racial disparities. University of Louisville analysis of 1.4k patients who underwent CAC scoring from 2019 to 2022, revealed that White patients were 8.3X more likely to get CAC scoring, even though far more Black patients in the study had high ASCVD risks (70% vs. 56%). White patients were also far more likely to receive post-CAC testing and treatment.

• No Chelation Evidence: Patients with prior MI and diabetes may not achieve cardiovascular benefits from EDTA chelation therapy to reduce lead levels. In the NIH-funded TACT2 study of 1,000 patients, there was a non-significant -7% benefit for EDTA infusions over placebo for the composite primary endpoint (time to first MI, stroke, angina hospitalization, revascularization, all deaths). Chelation therapy showed modest benefits in the prior TACT1 trial, but population lead levels have improved since then.

• Cardiologist Fraud in NJ: There are only 24 hours in a day, but that didn’t stop a New Jersey-based cardiologist from charging for 27.9 hours worth of office visits in a single day, as part of a scheme that led to $1.9M in fraudulent reimbursements over several years. The cardiologist was also found to have billed for office visits that never occurred, including visits while he was out of the country and visits that were limited to patients picking up prescriptions from the clinic’s front desk.

Advance Your Vessel Analysis

Ready to advance your EVAR planning? See how you could leverage TeraRecon’s EVAR (Vessel Analysis) package to streamline and enhance your complex aortic intervention planning.

Us2.ai’s Next Gen AI

Us2.ai recently scored FDA clearance for Us2.v2, the newest version of its flagship software featuring 45 automated echocardiography parameters, including strain analysis. See how the new version automates echo exams and improves cardiovascular disease detection.

The Resource Wire

• Reducing ECG Background Noise: Monebo’s Kinitec Rhythms ECG Algorithm separates true ECG signals from background noise, leading to more accurate diagnoses and improved operator efficiency. See for yourself how the algorithm measured up to a gold standard.

• Experience the future of learning: Medtronic Academy 2.0 is here! Unlock your ultimate destination for structural heart medical education with the newly redesigned Medtronic Academy 2.0. Gain access to expert-led courses, webinars, and a wealth of resources to stay ahead in cardiovascular care. Visit now!

• Transform CVIS Workflows: See why Merge Cardio is a 2024 Best in KLAS cardiology solution, and how it can help improve your cardiology workflows, simplify data collection, and automate cardiology reporting.

• HeartFlow FFRCT’s Real World Impact: See how HeartFlow FFRCT Analysis significantly improved NHS England’s patient outcomes and clinical efficiency in a massive real world implementation across 90k patients in this presentation by Newcastle University’s Professor Vijay Kunadian.