New Findings Show Artificial Intelligence Software Improves Breast Cancer Detection and Physician Accuracy – P&T Community

CHICAGO, Dec. 19, 2019 /PRNewswire/ --A New York City based large volume private practice radiology group conducted a quality assurance review that included an 18 monthsoftware evaluation in the breast center comprised of nine (9) specialist radiologists using an FDA cleared artificial intelligence software by Koios Medical, Inc as a second opinion for analyzing and assessing lesions found during breast ultrasound examinations.

Over the evaluation period, radiologists analyzed over 6,000 diagnostic breast ultrasound exams. Radiologists used Koios DS Breast decision support software (Koios Medical, Inc.) to assist in lesion classification and risk assessment. As part of the normal diagnostic workflow, radiologists would activate Koios DS and review the software findings with clinical details to formulate the best management.

Analysis was then performed comparing the physicians' diagnostic performance to the 18-month period prior to the introduction of the AI enabled software. Comparing the two periods, physicians recommended biopsy for suspicious lesions at a similar rate (17%) and performed 14% more biopsies increasing the cancer detection rate (from 8.5 to 11.8 per 1,000 diagnostic exams) while simultaneously experiencing a significant reduction in benign biopsies (aka, false positives). Noteworthy is the aggregate nature of the findings where adoption of the software gradually increased over time during the 18-month evaluation period. Trailing 6-month results indicate a benign biopsy reduction exceeding 20% across the group. Positive predictive value, the percentage a positive test returns a positive result, improved over 20%.

"Physicians were skeptical in the beginning that software could help them given their years of training and specialization focusing on breast radiology. With experience using Koios software, however, over time and seeing the preliminary analysis they came to realize that the Koios AI software was gradually impacting patient care in a very positive way.Initially, radiologists completed internal studies that verified Koios software's accuracy, and discovered the larger impact happens gradually over time. In looking at the statistics, physicians were pleasantly surprised to see the benefit was even greater than expected. The software has the potential to make a profound impact on overall quality," says Vice President of Activations Amy Fowler.

Koios DS Breast 2.0 is artificial intelligence software designed around a dataset of over 450,000 breast ultrasound images with known results intended for use to assist physicians analyzing breast ultrasound images and aligns a machine learning-generated probability of malignancy. This probabilityis then checked against and aligned to the lesion's assigned BI-RADScategory, the scale physicians use to recommend care pathways.

"We are seeing the promise of machine learning as a physician's assistant coming to fruition. This will undoubtedly improve quality, outcomes, and patient experiencesand ultimately save lives. Koios DS Breast 2.0 is proving this within several physician groups across the US," says company CFO Graham Anderson.

Koios DS Breast 2.0 can be used in conjunction and integrated directly into most major viewing workstation platforms and is directly available on the LOGIQTME10, GE Healthcare's next generation digital ultrasound system that integrates artificial intelligence, cloud connectivity, and advanced algorithms. Artificial intelligence software generated results can be exported directly into a patient's record. Koios Medical continues to experiment with thyroid ultrasound image data and expects to add to its offering in the next year.

"We could not be more encouraged by the results these physicians are seeing. All our prior testing on historical images have consistently demonstrated high levels of system accuracy. Now, and for the first time ever, physicians using AI software as a second opinion with patients in real-time, within their practice, are delivering on the promise to measurably elevate quality of care. Catching more cancers earlier while reducing avoidable procedures and improving patient experiences is fast becoming a reality," says Koios Medical CEO Chad McClennan.

Discussing future plans during the recent Radiological Society of North America (RSNA) annual meeting in Chicago, McClennan shared, "Several major academic medical centers and community hospitals are utilizing our software and conducting studies into the quality impact for publication. We expect those results to mimic these early clinical findings and further validate the experience of our physician customers in both in New York City and across the country, and most importantly, the positive patient impact."

About KoiosMedical:

Koios Medical develops medical software to assist physicians interpreting ultrasound images and applies deep machine learning methods to the process of reaching an accurate diagnosis. The FDA cleared Koios DS platform uses advanced AI algorithms to assist in the early detection of disease while reducing recommendations for biopsy of benign tissue. Patented technology saves physicians time, helps improve patient outcomes, and reduces healthcare costs. Koios Medical is presently focused on breast and thyroid cancer diagnosis assistance market. Women with dense breast tissue (over 40% in the US) often require an alternative to mammography for diagnosis. Ultrasound is a widely available and effective alternative to mammography with no radiation and is standard of care for breast cancer diagnosis. To learn more please contact us at info@koiosmedical.comor (732) 529-5755.

Learn more about Koios at: koiosmedical.com

View original content to download multimedia:http://www.prnewswire.com/news-releases/new-findings-show-artificial-intelligence-software-improves-breast-cancer-detection-and-physician-accuracy-300978087.html

SOURCE Koios Medical

Read the rest here:

New Findings Show Artificial Intelligence Software Improves Breast Cancer Detection and Physician Accuracy - P&T Community