A tweet from preventive cardiologist Danielle Belardo, MD

Cardiology Guidelines

Algorithm Aversion in HF Care

Developing risk prediction tools can be resource- and time-intensive. And sometimes, merely developing a working tool isn’t enough to see results. In this randomized clinical trial of heart failure patients, Yale researchers found that providing clinicians with 1-year mortality risk estimates did not improve patient outcomes nor influence decision-making. 

Researchers randomized 3k heart failure patients into “usual-care” and “alert” groups. In the interventional alert group, predicted 1-year mortality rate and other relevant risk information was displayed to clinicians when they opened the order-entry portion of patients’ medical records.

Over a 384-day median follow-up, outcomes between the alert and usual-care groups were nearly identical for: 

• 1-year mortality (27.1% vs. 26.1%).
• 30-day hospitalization (19.4% vs. 20.7%).
• Length of hospital stay (4.4 days vs. 4.3 days).
• Prescription of heart failure therapies at discharge (48.2% vs. 48.1%).
• Rates of palliative care referral (10.3% vs. 10.7%).
• Rates of advanced therapies like cardiac transplants and defibrillator implants.

One explanation for these findings could be that the risk estimates did not add substantially to clinician intuition, thus diminishing their potential benefit. But the authors believe that the null findings are more likely due to “algorithm aversion” – when clinicians favor their intuition over statistical algorithms, even if the algorithms are “objectively superior.” 

The Takeaway

Identifying high-risk patients is critical for managing heart failure. And most of us probably agree that providing risk prediction scores so clinicians can tailor patient interventions is a good thing. But this study shows that these initiatives may not always work as planned, and taking the time to evaluate their efficacy is an essential step toward enacting successful real-world solutions.

Detecting CAC and Undiagnosed CAD

Do you know how many patients in your health system are at risk for coronary artery disease but are undiagnosed? This article details how Nanox AI’s CAC solution can help clinicians identify those who often go undetected. 

When Your Company Saves Your Life

We’re happy to share a special interview detailing how Cleerly’s CCTA AI solution allowed one of its own team members to catch and treat his asymptomatic, life-threatening atherosclerosis.

The Wire

• Imaging Heart Disease in Women: A review in JACC highlighted the need to consider women’s unique cardiac imaging features and disease physiology. The authors emphasize that women have a unique ischemic heart disease phenotype (less calcified lesions, more nonobstructive plaques, higher prevalence of microvascular disease) and that imaging tests tend to have lower diagnostic accuracy in women (summarized wonderfully in this image). The authors urge clinicians to consider these differences when evaluating patients. 

• Cleerly’s New VBC Leader: Cleerly appointed its first Chief of Value-Based Care, Joseph “Joe” Jasser, MD. The new leader will develop and execute Cleerly’s value-based care go-to-market strategy and related commercial and client services teams. 

• Coronary Endothelial Dysfunction: A study out of Amsterdam found that patients with ischemia and nonobstructive coronary arteries (INOCA) commonly have endothelial dysfunction. Of 110 INOCA patients, 79% had coronary endothelial dysfunction, 62% had coronary artery spasm, and 29% had impaired adenosine-mediated vasodilation. Adding endothelial function testing to adenosine and spasm provocation testing increased diagnostic yield from 75% to 92%. 

• Dyad’s AI Echo Clearance: Cardiac image analysis company Dyad Medical has secured FDA clearance for its echocardiogram application Echo:Prio. The software, which is part of its complete cardiac platform called Libby (FDA-cleared), provides operators and physicians with a computer-assisted decision-support tool for index quantification of cardiac function. With the new clearance, Dyad will soon be able to offer physicians an immediate AI-powered second opinion when evaluating echos.

• AI Identifies Diabetes Using ECG: Authors of a BMJ-published study developed an AI algorithm that predicts diabetes and prediabetes using ECG data. Researchers trained and tested the algorithm using ECGs from 1.3k people and found that the model could predict whether an individual belonged in the no diabetes, diabetes, or prediabetes cohorts (97.1% precision, 96.2% recall, and 96.8% accuracy). Their DiaBeats algorithm has yet to be externally validated, but this study is still a promising proof of concept.

• Unrealistic Care Guidelines: Primary care providers would need over 26 hours per day to follow national care guidelines for an average number of patients, according to a study in the Journal of General Internal Medicine. That breaks down to 14.1 hours for preventive care, 7.2 hours for chronic condition management, 2.2 hours for acute care, and 3.2 hours for documentation and inbox management. While the study isn’t cardiology-specific, I bet cardiologists are able to relate to the sentiment. 

• AliveCor’s Series F: Wearable Afib device manufacturer AliveCor announced its Series F round (undisclosed amount), led by GE Healthcare. The fresh funding will go toward introducing KardiaCare and KardiaComplete (memberships that provide Kardia device wearers with personalized heart insights) and KardiaPro (a portal that triages ECG patient data for clinicians). Prior to this funding round, AliveCor had raised $154.3M. 

• Interventional Cardiologists Drive Revenue: According to an analysis from Merritt Hawkins, interventional cardiologists drive more revenue to hospitals than any other physician specialty. Interventional cardiologists surpassed orthopedic surgeons and gastroenterologists for the top spot, driving an average of $3.5M in hospital revenue per physician per year (vs. $3.3M and $3.0M).

• GE & Boston Scientific’s India Collab: Boston Scientific and Wipro GE Healthcare (GE’s India-based joint venture) are partnering to provide interventional cardiac care solutions to people in India. The new partnership combines Boston Scientific’s interventional cardiology portfolio with GE’s cardiac imaging systems and will involve joint training and education efforts. It appears that this is part of a global initiative, as the companies recently launched a similar partnership in Southeast Asia. 

• Females Fare Worse After Bicuspid TAVR: A new study of TAVR in patients with bicuspid aortic valves (BAVs) showed that women have more in-hospital adverse events than men despite being healthier at baseline. Of 510 BAV patients undergoing TAVR, women presented with fewer comorbidities and yet experienced more vascular (13% vs. 5%) and bleeding (11% vs. 5%) complications. One-year survival was comparable between the sexes. 

• Mindray’s TE X Ultrasound System: Ultrasound company Mindray unveiled its new TE X point-of-care ultrasound system. The portable device includes a rotating 23.8-inch touchscreen and uses a wireless transducer (which can be used w/ the TE X system or mobile devices). The Mindray TE X offers a suite of tools that could come in handy for cardiologists and sonographers, including ventricle strain analysis, echo capture, and automated LV ejection fraction. 

Us2.ai’s Echo Evidence

Have more echo studies than sonographers? See how Us2.ai was able to classify, segment, and annotate echocardiographic videos with similar accuracy as expert sonographers. 

User Experience and Cardiovascular Imaging Transformation

Check out this Change Healthcare video discussing the importance of user experience in the adoption of structured reporting, and how it can lead to improvements in imaging speed, quality, and cardiologist workflow.