Ultrasound AI for Cardiovascular Disease Prevention

Key Using ultrasound AI to prevent cardiovascular diseases through early detection of atherosclerosis.

Key Highlights

  • Cardiovascular diseases (CVD) cause ~32% of deaths; the leading cause of death globally
  • qVH is the first known solution for AI-guided vascular ultrasound (carotid) that can boost disease prevention using point-of-care-ultrasound (POCUS) devices.  
  • With qVH, high-risk individuals can be screened by any clinician/ remote health worker at any convenient location 
  • Patients can be identified before symptoms appear, allowing for earlier disease management, improved patient outcomes, and reduced costs

Using AI to maximize the potential of POCUS for disease prevention has developed an AI product for vascular health called qVH. It is the first known solution that guides clinicians during a carotid artery scan. Here’s how qVH’s AI works:

Probe Navigation Guidance: Detects probe location (CCA, ICA etc.) & orientation (long/short axis) and recommends best way to reach next step of protocol.

Plaque Detection & Characterization Guidance: Auto-detects abnormalities in a live scan (video) and quantifies it when a diagnostic quality image is available

Image Quality Guidance: Tracks image quality while scanning, recommends steps to maintain diagnostic quality & auto-captures images.

Device Setting Guidance: Detects common errors in ultrasound device settings in Pulse Wave (PW) mode and recommends changes for accurate PW velocity measurements. Thereby, preventing errors that could lead to misdiagnosis. 

*qVH is not FDA approved/CE marked yet and is currently meant for investigational or research use only.

The need for qVH

~20% of strokes in adults are caused by the narrowing of the carotid artery (see image; bottom). Buildup of plaque (fatty deposits) in the arteries is the root cause for this narrowing; a condition that is known as atherosclerosis (see image; top).

Plaques can develop in different vessels leading to artery narrowing/clots and hence reduced blood flow to various parts of our body. This leads to critical events such as:

  • Stroke (Carotid artery)
  • Heart Attack (Coronary Artery)
  • Renal Ischemia (Renal Artery), etc.

Evidence suggests that ~0-3% of the general population have a severe form of this disease but without any symptoms, while ~35% of diabetic patients have carotid plaques with or without symptoms. 

However, preventive measures to reduce disease burden have been limited due to:

  • Lack of clear guidelines
  • Logistical challenges like hospital visits for USG scan
  • Depending on operator skills for accurate scanning & reporting using USG
  • High cost of vascular USG
  • Lack of sufficiently skilled clinicians to perform vascular USG. 

Significant developments in the last decade 

Price: USG machines have become cheaper (by ~80%), more portable (handheld & wireless) and easily accessible with the arrival of point-of-care ultrasounds (POCUS).

Preference: USG is gradually becoming the preferred modality for disease prevention.

  • American Heart Association (AHA) recommends carotid artery duplex scanning in patients with high-risk features undergoing coronary artery bypass graft (CABG) surgery.
  • European Society of Cardiology (ESC) recommends carotid duplex ultrasound for evaluating the extent and severity of carotid stenosis.

Proof: Real-world evidence suggests benefits in risk-stratification through carotid artery screening.

  • Reduction in mortality rates (~10%), early disease diagnosis (~4.5 yrs), reduction in patient costs (by ~50%). [VIPVIZA]
  • Re-classification of low-risk patients to mid/high-risk based on the presence of carotid plaque. [Swiss AGLA]

Advantages: Govt. backed reimbursements for using advanced ultrasound technology.

  • US Hospitals can claim NTAP reimbursement of ~$1868 per patient diagnosed using ultrasound guidance technology (Caption Guidance) for CVD prevention.
  • American Medical Association (AMA) has introduced 2 new CPT codes for quantitative USG tissue characterization with ACR proposing an additional $82/scan.

What is holding back ultrasound-based CVD prevention programs?

POCUS devices have solved problems related to accessibility and affordability. But they have amplified issues related to operator skills since these ultra-portable POCUS devices can be used in any setting (remote areas, sports ground, battlefieldetc.) by most clinicians. The existing issues are:

  • Training is needed to perform the ultrasound scan as per the defined protocol.
  • Training is needed to capture diagnostic quality images from a running video (cine loop).
  • There are chances of misdiagnosis due to errors in:
    • Performing ultrasound measurements manually. Eg: plaque length/area, PW ESV/PDV, Degree of Stenosis etc.
    • Optimizing device settings manually. Ex: gate size/angle/position, box angle.
    • Detecting & quantifying abnormalities (plaques, stenosis, etc.).
  • Inter-operator variability due to operator dependence for probe navigation, abnormality detection, image capture and for optimization of USG device settings. 

In 2020, POCUS accounted for only ~3-5% of the ultrasound market by revenues. However,  global POCUS market revenue is predicted to increase to $4B by 2030 from $2B in 2020.

qVH has been designed to address all of the issues outlined above. qVH validation has begun at 2 sites in India & Argentina and will be expanded to 8 sites across Asia, Europe and North America within the next 3 months. qVH can be used with all existing ultrasound machines. Our beta sites are using Cart and POCUS machines.

In Focus Uncategorized

Qure’s AI for detecting risk of heart failure

Every year, approximately 17.9 million lives are lost to cardiovascular diseases (CVD), the leading cause of death across the world. The rates of heart failure misdiagnosis range from 16.1% in hospitals to 68.5% in GP referral settings. In the EU alone, the economic burden of cardiovascular diseases exceeds €210 Bn.

A systematic analysis on 10 studies done across 5 countries found patients groups with comorbidities and COPD, and the elderly population in nursing homes were more likely to have unrecognized heart failure.

Turkey is known to have a higher prevalence of heart failure and Atrioventricular Septal Defect (AVSD) as compared to the western world. With millions of chest radiographs done annually for a host of reasons, a tool that could screen the data used in these studies to predict the early signs for risk of heart failure could be ground-breaking for care and patient outcomes.

Output generated by Chest X-ray AI Solution

Enlargement of heart in cases of heart failure

At the start of 2021, the Department of Cardiology at the Mersin University Faculty of Medicine initiated a study under Digital Transformation with Artificial Intelligence in Health with support from AstraZeneca Turkey to use Qure’s AI solutions to understand the role of AI in predicting heart failures early from incidental findings on Chest X-rays. Only patients who were previously not suspected or identified for signs of heart failure were included in the study.

Post risk assessment using the AI tool on chest radiographs, the department approached at-risk patients for follow-up tests. A larger number of patients were identified as at-risk but since this study was conducted during the pandemic restrictions, not all individuals came back to the hospital for follow-up. Of the high risk patients who came for follow up tests, 86% were identified to be confirmed heart failure patients. These individuals had confirmatory diagnoses with tests such as NT-proBNP and Echocardiography.

The results of this year-long exercise have the potential to change the use of AI in cardiology altogether.

Prof. Dr. Ahmet Çelik, President at Heart Failure Working Group of Turkish Society of Cardiology and the Principal Investigator in this research said,

“In this study, which was carried out for the early diagnosis of heart failure, the power of artificial intelligence to predict heart failure by looking at lung X-rays was realized with a sensitivity of 89.1 percent and a selectivity of 86.4 percent. More importantly 65.3 percent of patients diagnosed with heart failure had Preserved Ejection Fraction Heart Failure which is difficult to diagnose.”

 Qure’s AI solution has been found to have 95%+ sensitivity for both cardiomegaly and pleural effusion. It could potentially be a game-changer as a silent reader, without increasing the work burden on healthcare professionals or adding significant costs by changing care pathways. It could screen all chest radiographs done worldwide on non-suspecting cases adding thousands of undiagnosed cases onto the cardiology risk assessment, diagnosis, and eventually treatment pathway. With a well-thought-through system for detection and diagnosis, this technology could mean more lives saved with minimal additional investment.

AstraZeneca Middle East and Africa Region Medical Director Dr. Viraj Rajadhyaksha stated,

“By applying advanced artificial intelligence and machine learning approaches to patients who go to different units for many reasons, this project will enable them to touch the lives of patients who are diagnosed early and to meet the right treatments much earlier. The results of the research have the potential to create an early detection tool for heart failure for the first time in the world.”

AstraZeneca team aims to expand the project nationally and apply it to every lung x-ray taken. There has been research exploring the possibility of using AI for X-ray-based cardiac failure detection in a study setting. However, the potential impact on patients has not been demonstrated at such a scale before. This opens a world of opportunities for further focussed research evaluations to ascertain protocols of bringing in clinical practice.

Prof. Dr. Ahmet Çamsari, the Rector of Mersin University is a strong believer in the potential of AI to impact the diagnostic pathway for patients. He said,

“Our project will be one of the first projects where artificial intelligence is used in the early diagnosis of undiagnosed and suspected heart failure patients in our country and even in the world. In line with the results obtained, we aim to expand the project nationally and apply it to every lung x-ray taken. Again, we hope that these systems can be used in other fields such as radiological oncology and that artificial intelligence projects that touch the lives of patients can be implemented.”