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.”

In Focus Uncategorized

Aarthi Scans: Scripting tele-radiology growth in India

The rapidly increasing need for radiology diagnostic and image interpretation services around the world has brought two major issues to light. The first is the lack of radiologists and the other is the dearth of specialized knowledge.

Building reliable communication and image transfer systems to tap into the expertise of radiologists who are not on-site can solve these issues to some extent. Hospitals, mobile imaging firms, urgent care clinics, and even some private practices all around the world are increasingly using tele-radiology. Tele-radiology improves patient care by allowing radiologists to provide services without having to be physically present at the imaging site so that the patients can receive round-the-clock access to trained specialists.

Tele-radiology is significantly less expensive than having a radiologist on-site. These services are typically priced per exam, with the cost as low as $1 per X-ray Tele-radiology has transformed the practice of many radiology clinics around the world, allowing them to provide results faster and by facilitating access to the radiologist, adding enormous value to the diagnostic process.

To set up a tele-radiology system between two centres, one requiring radiologist’s services and one providing radiologist’s services, the following elements are needed:

  1. Modality – a system that captures the medical image and has the facility to send these images in the preferred format i.e., DICOM
  2. PACS – a system that stores, sends, and receives medical images (DICOMs) and that can be identifiable by a unique address (like IP address, port number, etc.)
  3. Gateway – a medium that handles communication between the two centers (source and the destination) – receives the medical images from the source and sends back the output in the required format) using API calls. Complying with the data security and Protected Health Information (PHI) standards, de-identification and re-identification of confidential information can be performed by the Gateway.
  4. API Hub – a single place where all the Application Programming Interfaces (APIs) can be published and shared with external parties/clients by the intended service provider (tele-radiology) com

Introducing Aarthi Scans: India’s largest Tele-radiology service provider

India with its population of around 1.44 billion, right now we have around 1 radiologist for 100,000 people. Most rural India still lacks adequate radiological services and personnel, and not all imaging centers have subspecialty expertise, tele-radiology plays a significant role in quality diagnostics.

Aarthi Scans and Labs, one of the largest diagnostic centers were started in the year 2000 by Mr. Govindarajan. Today Aarthi Scans has more than 100+ branches across 10 states.It was in 2011 that they started their tele-radiology services to provide quick reporting for emergency cases and nighttime reporting and to ensure continuous reporting even when radiologists go on leave. Their radiologists’ review over 200,000 CTs, 250,000 MRIs, and 2.1 million chest X-rays annually.

“At that point of time in 2011, when we started tele-radiology, telemedicine as a concept had not evolved in India. Radiologists giving reports without being present at the scanning location was viewed with skepticism. But once the referring doctors started viewing the benefits of tele-radiology, like nighttime reports, subspecialty reporting, they were impressed. Radiologists also needed a lot of convincing to report tele-radiology images. We standardised and digitised patient history, records, improved communication channels between tele-radiologists and radiographer in scanning sites and there was a slow and steady adoption by the Radiologist community. Our PACS vendor – Mr Ravindran from Innowave Healthcare Technologies helped us a great deal in solving the workflow related issues and helping us choose the right technology for us.”

 Govindarajan, Aarthi Scans and Labs

Aarthi Scans has taken a step forward by incorporating Artificial Intelligence (AI) into their reporting procedure, demonstrating their commitment to staying on the cutting edge of technology. The ratio of one radiologist to more than 100,000 people in India has resulted from stress in radiology reporting, scan misreads and reporting delays. Any solution that might assist radiologists to relax and improve their productivity is always welcome at the technologically advanced setup at Aarthi Scans, and AI can be of immense value add in this scenario.’s qXR, a Chest X-ray interpretation software – a CE Class II certified product – has been installed in Aarthi Scans diagnostic centers. The most common application of qXR in this setting is for Radiologist assistance to triage any scans with abnormalities on the worklist. The images are scanned and interpreted in under a minute. All scans that qXR identifies some findings in, are saved as a draft in the radiology worklist for further assessment and reporting. The report is generated in a natural language, significantly reducing the typing time that constitutes a significant portion of the reporting time. The final report is released in 30% lesser time due to this triaging mechanism and reading assistance by qXR. is a leading solution provider and we validated a few solutions before choose  We chose qXR because the accuracy in categorising a study as normal or abnormal is very high (95%)!”.  “We have been using qXRin our day-to-day radiological practice across India in all our branches. We are huge fans of qXR’s accuracy and utility.”

– Dr. Arunkumar Govindarajan, Director, Aarthi Scans and Labs

Technical Integration

Qure PACS gateway for acquiring the Chest X-rays is integrated with Freedom Nano PACS which is present in every center of Aarthi Scans. Each center is authenticated with a unique token for the transmission of the studies and their corresponding results. The end-to-end transmission is supported by API calls that communicate with the Qure API hub to send the studies to the qXR AI models for processing. The AI interpretations are sent back to Freedom Nano PACS, where the radiologist can view the result from the individual centers. API and back to Freedom Nano PACS, where the radiologist can view the result from the individual centers. API and https-based communication make the data secured even on the cloud.

Since partnering with Aarthi Scans four months ago, qXR has processed over 45,000 scans, triaging 55% of scans with abnormal findings. On a daily basis, qXR processes 200 chest X-rays.

Scans that are classified as normal by qXR can be evaluated by the radiologist more quickly, giving them more time to review the abnormal scans and cutting down on overall reporting time. This has led to a reduction in the TAT by 30%. The qXR Secondary Capture output also uses contours to localize anomalies in the lungs, enabling radiologists to recognize abnormalities more accurately, without spending as much time as a regular scan.

Finalising a Chest X-ray report as ‘normal’ is like passing through the valley of uncertainty for every Radiologist and qXR is like that friendly colleague who assists you with a second opinion / confirmation without bias. qXR saves our Radiologists’ time and removes doubt while reporting.qXR has resulted in a 30% reduction in reporting time for our Radiologists.

– Dr. Aarthi, Director, Aarthi Scans and Labs

Insights into incorporating AI into the practice – Dr. Arunkumar Govindarajan

“Learning about basics of Artificial Intelligence (AI) has helped me a lot to understand the inner workings of AI and terminologies. To start and understand in deep about AI one can take Coursera courses like – “AI for Everyone" by Andrew Ng and “AI for Medical Diagnosis” by DeepLearningAI. There are a lot of AI solutions out there, one can research in google to find which will suit your patients’ and radiologist’s needs. Once you fix a good AI vendor –

  • do your own validation and provide transparent feedback
  • partner with a good IT & PACS vendor and fix a workflow suited to your organization’s needs. AI integration into PACS takes a bit of effort from the AI and PACS vendor. Be present during the meetings to ease the process and quickly resolve doubts”

What’s Next?

After successful operations with qXR in all our centers, we will be next deploying Qure’s AI solution, qER for detecting brain abnormalities from head CT scans.

“Time is Brain and quick qER report never goes in vain” Dr. Arunkumar Govindarajan, Director, Aarthi Scans and Labs