Israeli biotech firm Medial EarlySign, which develops artificial intelligence (AI)-based clinical data solutions for early detection and prevention of high-burden diseases, announced this week the publication of new research impacting the early diagnosis of non-small cell lung cancer (NSCLC).
Follow Israel Hayom on Facebook and Twitter
Together with researchers from Kaiser Permanente Southern California, the Department of Health Systems Science from Kaiser Permanente Bernard J. Tyson School of Medicine, and the Department of Health Sciences, Brock University, St. Catharines, ON, Canada, study authors found that EarlySign's machine-learning model was more accurate for early diagnosis of NSCLC than either standard eligibility criteria for screening or the modified PLCOm2012, demonstrating the potential to help prevent lung cancer deaths through early detection.
The peer-reviewed retrospective data study, "Machine Learning for Early Lung Cancer Identification Using Routine Clinical and Laboratory Data," was published in the American Journal of Respiratory and Critical Care Medicine.
The rationale for the study is that most lung cancers are diagnosed at an advanced stage, while pre-symptomatic identification of high-risk individuals can prompt earlier intervention and improve long-term outcomes. The objective was to develop a model to predict a future diagnosis of lung cancer based on routine clinical and laboratory data, using machine-learning.
Results of the study indicated that based on clinical characteristics and laboratory testing performed nine to 12 months before a clinical diagnosis of cancer, the EarlySign model was able to identify lung cancer with a sensitivity and specificity of 40.3% and 95%, respectively, with a positive test result indicating a 13-fold elevation in the odds of lung cancer. With further validation and refinement, this model has the potential to help prevent lung cancer deaths through earlier diagnosis.
"Lung cancer is the leading cancer killer of both men and women in the US with over 150,000 deaths expected each year," commented Michael K. Gould, MD, MS, and a professor of Health System Science from Kaiser Permanente Bernard J. Tyson School of Medicine.
"Earlier identification of high-risk individuals has the potential to improve lung cancer survival rates by finding the disease at a localized stage when it is more likely to be curable. The machine learning models from EarlySign can help advance lung cancer identification by nine to twelve months which can lead to earlier diagnosis and treatment, when it matters the most," Gould said.
According to EarlySign VP of Clinical Research Eran Choman, "The recent pandemic has led to significant delay of diagnosis and treatment across the board, with delays in screening meaning that cancers may be more advanced and with more serious consequences."
Choman noted that "the collaborative efforts with the research team have been extraordinary in revealing how advanced AI predictive modeling can increase the predictive power of a model that could have a significant beneficial impact leading to additional early diagnosis and treatment of this serious disease."
Ori Geva, co-founder and CEO of EarlySign, said the company was "seeking to harness these results to further establish the value of this model to partner with providers, payers and life cciences and augment the identification of lung cancer and thus the treatment and better outcome for patients."
Subscribe to Israel Hayom's daily newsletter and never miss our top stories!
