KFAR MALAL, Israel, October 2, 2017 /PRNewswire/ --
Medial EarlySign (http://www.earlysign.com
The peer-reviewed study, Early Colorectal Cancer Detected by Machine Learning Model Using Gender, Age, and Complete Blood Count Data, published in Digestive Diseases and Sciences, sought to validate a machine learning risk stratification model for CRC, a lower GI malignancy, on a US-based adult population. It follows successful studies conducted in Israel and the United Kingdom.
The analysis was based on data collected from blood samples and demographic information from 17,095 Kaiser Permanente Northwest patients, including a random sample of 900 CRC patients. ColonFlag[TM] analyzed patients' complete blood count (CBC) results and factored in age and gender to create a CRC risk score for stratification of each patient.
"Colorectal cancer is the second-highest cause of all cancer-related deaths in the USA, responsible for 49,190 deaths in 2016 alone," said Mark C. Hornbrook, PhD, retired Chief Scientist of Kaiser Permanente Center for Health Research. "Early screening for CRC significantly improves the survival rate. The ability to identify people at high risk for colon cancer and refer them for further testing could help to reduce mortality and prove integral to reducing the overall CRC burden."
This study is the first in the U.S. that utilizes ColonFlag[TM] to identify individuals at increased risk of having CRC, based on demographics and existing lab test results. CRC cases identified by ColonFlag[TM] were compared with those detected by low hemoglobin (Hgb) levels alone in two adjacent time windows - 0-180, and 181-360 days prior to diagnosis. For the 0-180-day window, ColonFlag[TM] demonstrated a 34% and 36% improvement in identifying CRC cases, compared to low Hgb levels for the 50-75 and 40-89-year-old age groups, respectively. In the 181-360-day window, ColonFlag[TM] detection was 47% higher for the 50-75-year age group, and 84% higher for the 40-89-year-old group.
Further analysis revealed that ColonFlag[TM] performed best in detecting CRC tumors in the cecum and ascending colon. The odds ratio for detecting CRC in the cecum was 93.4 at 99% specificity level. The odds ratios for detection in the ascending colon were 40.3 at 95% specificity and 28.0 at 90% specificity.
"Colonoscopy resources are limited, and screening programs are being challenged by the need for active participation of asymptomatic individuals," said Dr. Ran Goshen, Chief Medical Officer of Medial EarlySign. "ColonFlag's ability to passively identify those at high-risk among non-participating individuals 180-360 days prior to diagnosis may allow healthcare providers to better allocate colonoscopy resources."
View the full study here .
ColonFlag[TM] is not cleared by the FDA for commercial use in the USA.
About Medial EarlySign Medial EarlySign's advanced AI-based algorithm platform helps healthcare organizations accurately predict and stratify individuals at high risk for developing serious health conditions, by leveraging routine blood test results and EHR data. The company creates actionable opportunities for early intervention to delay progression of illness, improve patient outcomes, focus financial resources, and reduce overall costs. Medial EarlySign is developing a number of clinically supported AlgoMarker™ risk predictors to identify patients with a high probability for harboring or developing specific illnesses, including cancers, diabetes and other life-threatening conditions. The company's platform has been supported by peer-reviewed research published by internationally recognized health organizations and hospitals. Founded in 2009, Medial EarlySign is headquartered in Kfar Malal, Israel. For more information, please visit http://www.earlysign.com.
Follow Medial EarlySign on LinkedIn: Medial EarlySign and Twitter: @MedialEarlySign
Media Relations Contact: Glenn Jasper Finn Partners +972-929-222-8002 email@example.com
SOURCE Medial EarlySign
Subscribe to our Free Newsletters!
Some drugs or therapeutic agents cause undesirable reactions in lungs, known as drug-induced ...
Sleep disorders are collectively known as ''Somnipathy.'' There are over 70 different medically ...
Unintended pregnancies are very common these days, and so one in about four pregnant women go for ...View All