Almost half of all adults in the U.S. have at least one form of cardiovascular disease (CVD), making it hard to find someone that hasn't been affected by the disease in one way or another.[1] The U.S. spends $225 billion on CVD every year, and yet it remains the leading cause of death in the U.S. and around the world[2],[3]. Cardiovascular disease is deemed a "silent killer" because so many people aren't aware they have it, and it often shows its first symptom as a major cardiac event like a stroke or heart attack.
Historically, healthcare delivery has been reactive with patients primarily seeking care when a symptom or issue arises. With 51 percent of cardiovascular deaths worldwide attributed to strokes and 45 percent to coronary artery disease (CAD), there is an urgent need to preventatively — and proactively —identify and address cardiovascular disease.[4]
Proactive efforts could include establishing healthcare workflows that enable preventative care for patients. For example, coronary artery calcium (CAC) has been established as the most reliable measurement for a patient's future risk of cardiovascular events.[5] CAC levels can be detected in CT scans and are an important way to stratify a patient's risk for coronary artery disease and suggest next steps in their care pathway. Today, new artificial intelligence solutions can identify CAC levels and empower radiologists and cardiologists with the data they need to intercept some forms of heart disease, like CAD, before it's too late. AI has gone from making predictions about patient outcomes or data sets to becoming part of a fully actionable preventative healthcare intervention.
Projections from the Association of American Medical Colleges predict a shortage of 120,000 cardiologists by 2030 and a shortage of 17,000 to 42,000 radiologists and other clinical specialists by 2033. That means the healthcare industry needs to act now to meet growing demand for imaging care and mitigate the strain placed on overworked specialists. In addition to shortages, radiologists today are faced with technologies that, while improved, push out more and more images per scan — increasing their workload and time spent per patient.
When reading a routine CT scan, a radiologist may or may not acknowledge the presence of CAC as an incidental finding, as they are unlikely to have the time and resources available to act on it. Even when radiologists create a thoroughly detailed report to share with the patient's care providers, more often than not, this kind of incidental finding gets put toward the bottom of the report. Unless CAC is assigned an "action item" on the report, the patient won't move forward with any follow-up visit or treatment plan.
CVD isn't the only disease associated these incidental findings. Routine imaging can pick up incidental findings across vertebral compression fractures and low bone mineral density (potential osteoporosis) and other chronic conditions that can get lost in a radiology report. That means no next steps are initiated for the patient to address these health conditions.
Nanox AI has developed a tool that is geared entirely toward creating the right action item in an imaging report, so a patient is directed to the correct care provider. Leveraging the use of routine CT scans, the AI tool integrates seamlessly within a radiologist's workflow, empowering them with clear, easy-to-interpret visual identifications of CAC. This AI tool can proactively identify patients at risk of a cardiovascular event, promoting appropriate risk assessment and follow up treatment. The tool can improve the quality of the radiology report in a way that is convenient for radiologists and their workflows, while also providing cardiologists with the information they need to better understand which patients are at high risk for a cardiac event and to identify those who may need preventative intervention. Routine medical imaging can provide incredibly valuable and actionable clinical insights — some completely unrelated to the reason the image was ordered. Physicians just need to be armed with the right tools to extract them.
As an example, let’s look at a patient care pathway with and without AI technology. Someone can go to the emergency room experiencing chest and back pain. They could receive normal laboratory results, normal EKG scan, and a CT scan to examine the root cause of the pain. A CT scan report would normally address the lungs and potential source of back pain such as a vertebral fracture. Typically, the degree of coronary artery calcium is not mentioned. Using AI to screen for incidental finding, high levels of CAC would be detected and that patient would subsequently be flagged to their primary care provider who could opt for a cardiology consultation. They then would be prescribed statin therapy, an inexpensive generic drug that could significantly reduce the chance of a cardiovascular event and save this patient's life, all because of an incidental AI screening of their original CT scan they obtained in an ER visit for back pain. More invasive cardiology intervention such as angioplasty or coronary stenting may also be recommended in the right clinical scenario.
This same scenario would play out differently in today's standard of care. After all the patients’ scans determined they didn’t have any notable pathologies in their CT except for a vertebral compression fracture, they probably would be discharged without attention to their CAC. Their CVD risk factors might go unnoticed, and they could have a potentially preventable major future cardiac event. The unfortunate and often "silent" reality of CVD is that the person's first indication and noticeable symptom of heart disease would likely have been a cardiac event.
Simply put, opportunistic screening for coronary artery calcium has the potential to save lives. Nearly everyone in the healthcare system, from patient to radiologist to cardiologist to payer would benefit from early detection of CAC and intervention, as it would improve patient care while reducing costs and risk of future cardiac events. Without requiring patients to get another scan and be exposed to additional radiation, AI can leverage underutilized data that's already within the healthcare system, flagging at-risk patients and getting them on a care pathway that addresses their condition, chronic or otherwise, before it's too late.
[1] Cardiovascular Disease: Types, Causes & Symptoms (clevelandclinic.org)
[2] Heart Disease and Stroke Statistics—2022 Update: A Report From the American Heart Association | Circulation (ahajournals.org)
[3] Cardiovascular diseases (CVDs) (who.int)
[4] Cardiovascular Diseases (CVD) | NCD Alliance
[5] Coronary Artery Calcium Score - A Reliable Indicator of Coronary Artery Disease? - PMC (nih.gov)