AI Software for Early Detection Used to Catch Breast Cancer in Patients with Cancelled Appointments Due to COVID-19
Chicago, IL, June 24, 2020—An artificial intelligence (AI)-based breast ultrasound software from Koios Medical, Inc. proven to significantly enhance the accuracy and consistency of lesion assessment for physicians across a wide range of experience levels, per a study recently published in the American Journal of Roentgenology, is now being used to diagnose breast cancer earlier for patients with appointments cancelled due to Covid-19.
Several community practices and major academic medical centers primarily in the Northeast and Midwest have adopted this first of its kind, FDA-cleared software recognizing that prior breast ultrasound images of patients whose appointments were postponed due to Covid-19 can be analyzed using the software uncovering previously missed cancers. High-risk patients can be immediately prioritized for biopsy and treatment if confirmed. Patients and providers benefit from this proactive approach taken by physicians during the Covid-19 induced slowdown that also postpones lower risk patient appointments. Up to 40% of patients scheduled for follow-up may safely defer follow-up an additional six to twelve months.
Covid-19 presented clinicians with the unique challenge of addressing patient risk while unable to attend to the specific needs of each patient while “sheltering at home”. Physicians, technologists, and office staff must also take additional precautions to mitigate the risk of exposure when patients are seeking care. Koios DS AI software for early breast cancer detection can be used to analyze recent exams without requiring any additional appointments. Patients determined to have extremely low-risk exam findings can be rescheduled and deprioritized meaning fewer patient interactions and increased safety for physicians and staff.
“We’ve always known Koios DS Breast is a valuable weapon in the fight against breast cancer” says Chad McClennan, President & CEO, “but we really had no idea it could be such an effective tool when faced with a global pandemic. Catching cancers in patients sheltered at home while protecting doctors, nurses, technologists and office staff from avoidable exposure is an unanticipated impact that has been extremely motivating to our entire team during these challenging times.”
Until effective vaccines or treatments for Covid-19 are widely available, patients are likely to continue wanting to avoid medical facilities, particularly if earlier examinations found lesions to be low-risk.
During this disruption, the accuracy of diagnosis becomes even more important, so that vital care is delivered promptly while unnecessary visits are avoided. Department leaders are addressing the large and growing backlog and prioritizing patients in a manner that balances the risk of cancer to patients and the risk of Covid-19 to both patients and healthcare providers.
Koios DS BreastTM uses patented machine learning algorithms to assist physicians analyzing breast ultrasound lesions found during routine mammograms or self-exams. Ultrasound scans are typically required for added clarity in women with dense breast tissue where traditional mammogram technology is unable to detect most cancerous tissue. An ultrasound exam is part of the diagnostic pathway whenever a mammogram uncovers something suspicious. Historically the challenge with ultrasound technology has been the manual nature of each exam making it highly variable, and interpretation is plagued by a high percentage of false positive findings yet over 130,000 missed cancers (or false negatives) occur each year in just the United States alone.
The decision support software was recently the focus of the largest, most comprehensive reader study of AI decision support analyzing ultrasound images of breast lesions. Fifteen physicians each interpreted 900 cases twice in random order. The AI system improved physician sensitivity and/or specificity for 100% of the participating physicians and for 93%, both.
Key findings of the peer-reviewed report indicated up to 6 additional malignancies were found per 100 cancers presented with a simultaneous reduction in benign biopsies of 31%, reduced BI-RADS 3 follow-up recommendations, and improved consistency of interpretation, both inter- and intra-operator. As of June 2020, over 30,000 patient cases have been analyzed using the Koios AI system with several prominent institutions and community-based health systems are expected to be activating the software in Q3.
About Koios Medical, Inc: Koios DSTM Breast is the only FDA-cleared cancer diagnosis software using AI on breast ultrasound images. Koios DS works as an expert on-demand second opinion for classifying suspicious lesions and aligning to a BI-RADS rating, while prepopulating diagnostic reports. AI algorithms are trained on nearly 500,000 ultrasound images. Software integrates into all major PACS workstation viewers and is also available on select scanners. Learn more at www.koiosmedical.com.
Founded in 1900, the American Roentgen Ray Society (ARRS) is the first and oldest radiological society in North America, dedicated to the advancement of medicine through the profession of radiology and its allied sciences. An international forum for progress in medical imaging since the discovery of the x-ray, ARRS maintains its mission of improving health through a community committed to advancing knowledge and skills with an annual scientific meeting, monthly publication of the peer-reviewed American Journal of Roentgenology (AJR), quarterly issues of InPractice magazine, AJR Live Webinars and Podcasts, topical symposia, print and online educational materials, as well as awarding scholarships via The Roentgen Fund®.