Developed as a “co-pilot” for clinicians to improve the accuracy and timeliness of diagnosing lung abnormalities on chest radiographs, XrAI is a decision-support tool that uses machine learning to expedite the way frontline care workers identify lung-related abnormalities, which are typically associated with conditions such as COVID-19 infections, pneumonia, tumours and tuberculosis.
The tool empowers clinicians—from emergency doctors to nurses to radiologists to residents—by providing immediate analysis of a chest radiograph, enhancing their ability to form an accurate diagnosis at the time treatment is prescribed.
XrAI is the first AI tool for radiology to be approved by Health Canada as a Class III Certified Medical Device after a detailed review was performed of the outcomes from an independent, single-blind randomized control clinical trial. The landmark clinical trial was dramatically accelerated and prioritized by the health care community in response to the COVID-19 pandemic. After seeing the impact this tool has for optimizing patient care, health care organizations across Canada and internationally have mobilized to get XrAI into the hands of clinicians.
Rather than employing a traditional black box system, XrAI provides physicians with transparency into the conclusions made by the underlying algorithm and an intuitive interface through which to view accurate results and inform their final diagnoses.
XrAI integrates into existing clinical information systems with no disruption in workflow and little to no training required. The results of XrAI’s analysis are made available within a clinician’s standard X-ray viewer, displaying the machine learning algorithm’s findings along with its level of confidence in provided results.
The Confidence Dial, which allows clinicians to increase or decrease the confidence level in the identified potential abnormalities, is unique to XrAI and has been widely praised by users as a critical feature that is intuitive to the way radiologists share their opinions with medical professionals.
XrAI is built using geographically, ethnically, and demographically diverse longitudinal (over three years) data that has extensibility and applicability across Canada and around the world. The algorithm was trained on 250,000 cases taken from more than 500,000 anonymized radiograph images from Canadian health care organizations, and open subscription-based datasets. This training data covered a broad spectrum of diseases, across geographically and demographically diverse populations. The technology was tested and validated in an independent, single-blind randomized control clinical trial. The study results confirmed that XrAI improves the quality of clinical interpretation of chest X-rays by up to 20% in all physician groups inclusive of radiologists, emergency doctors, family doctors, pulmonologists, residents and medical students.
XrAI is the first AI-based Class III Certified Medical Device to be approved for radiology by Health Canada, based on its rigorous scientific groundings and technical capabilities. Class III certification indicates that the abnormalities the tool detects are found in conditions considered critical to a patient's health care situation and that immediate action is expected following analysis by the software to drive clinical or patient management.
Despite the continually improving state of standards in the health care IT industry, there remain several variations in which a clinical environment can be set up. XrAI’s modular design takes this heterogeneity into account. The integration component of XrAI performs as an adapter that bridges the rest of the components of XrAI with a given clinical environment. Our technology is vendor agnostic and is flexible in its ability to be deployed through a multitude of existing Picture Archiving and Communication Systems (PACS) and Radiological Information Systems (RIS). The rest of the XrAI machinery remains invariant from one deployment to another, as it communicates only with the adapter. This enables 1QBit to expeditiously make the AI assistance functionality available to centres across Canada and internationally, even when they have different IT environments.
XrAI can be deployed and operated through the cloud or on-premises and is accompanied by a software component that is installed on-site and subscribes to the required modules in a clinical environment. This component uses two layers of technology to ensure no patient data leaves the home data centre.
The idea for an AI-driven chest X-ray diagnostic tool originated from the ten-year vision of Canadian physician, medical innovator, and 1QBit’s CMO, Deepak Kaura, MD, FRCPC, MBA, to apply data science to solve systemic issues in health care. XrAI has been researched and developed by a deeply technical and diverse team of experts led by radiologists. XrAI’s scientists and developers have decades of R&D experience, self-organized into dynamic, multidisciplinary teams to tackle challenges in machine learning, complex optimization, and computation.
1QBit is working with partners from around the world to deploy XrAI and support them in their fight against COVID-19 and other deadly lung diseases such as tuberculosis. XrAI is the first product in 1QBit’s suite of machine learning health care solutions. Our long-term aim is to empower physicians in all imaging and lab diagnostics with intuitively designed and technically advanced tools that enhance their uniquely human ability for critical thinking and optimize their use of time and resources.
For more information on implementing XrAI into your workflow or about our other health efforts, please contact us.Get In Touch