Lunit today announced abstract presentation of its AI precision medicine research portfolio at the American Society of Clinical Oncology (ASCO) Annual Meeting 2019. The meeting will be held May 31 – June 4 in Chicago.
The accepted abstract highlights the feasibility of AI-based biomarker in metastatic non-small cell lung cancer, based on the H&E analysis that predicts response to immune checkpoint inhibitors (ICI).
The abstract will be presented at ASCO poster sessions on Sunday, 2 June. Lunit will also be hosting a booth exhibition during ASCO, at booth #19129.
The study evaluated the predictive value of AI versus PD-L1, the main biomarker for ICI, in terms of both its comparative predictive value as well as additive predictive value.
According to the research conducted by Lunit, within PD-L1(+) patient group, the treatment response and progression-free survival (PFS) significantly differed depending on the AI score. The same results were obtained within the PD-L1(-) group.
According to the results, after the reclassification of PD-L1(-) patient group based on the AI score, 52% of patients with high AI score had, in fact, shown response to ICI. These patients had three times longer PFS compared to the patients who had a low AI score.
Similar outcomes were found among the PD-L1(+) patient group. Classified with AI profiling, 63% of low AI score patients were non-responsive to ICI. These patients had six times shorter PFS compared to high AI score patients.
Additionally, in an AI analysis independent of PD-L1, the team was able to identify more patients that showed response to ICI. Among PD-L1(+) patient group, 49% of the patients were responsive to ICI, whereas 65% of patients within high AI score patient group showed response.
“Our study reveals promising results that show an added value of AI analysis in cancer therapy, especially for the patient group with PD-L1(-), commonly known to be non-responsive to immune checkpoint inhibitors,” said Kyunghyun Paeng, Head of Precision Pathology at Lunit. “An enhanced treatment response is expected for those patients with high AI score within PD-L1(-) group. This signals a more precise identification of patients who are classified to be non-responsive according to the current standard of care.”
Lunit’s AI research in the field of pathology has been recognized to be world-leading in various occasions. The company had ranked world #1 in both MICCAI TUPAC Challenge 2016 and CAMELYON 2017, ahead of competitors like Microsoft and IBM.
“With our advanced deep-learning technology, we seek to push the boundary of precision medicine and navigate for opportunities that transcend current practices,” said Brandon Suh, CEO of Lunit. “We look forward to accelerating our research and development in AI biomarkers for cancer treatment and outcome prediction through various research partnerships.”
Lunit had recently presented abstracts during AACR 2019, showing the power of AI-based identification and quantification of cancer tissues as a potential prognostic & predictive biomarker for breast cancer.
The full ASCO abstract presented by Lunit can be found at: http://abstracts.asco.org/239/AbstView_239_266969.html
ASCO Poster Session Abstract by Lunit:
#9094 Deep learning-based predictive biomarker for immune checkpoint inhibitor response in metastatic non-small cell lung cancer
Poster Session: Lung Cancer - Non-Small Cell Metastatic (Board #417)
Date: Sunday, June 2, 2019
Time: 8:00am to 11:00am
Location: Hall A