🇬🇧 Artificial intelligence–based biomarkers of response to immunotherapy
Description
Artificial intelligence–based biomarkers of response to immunotherapy in patients with non–small-cell
lung cancer considering previous lines of treatment.
Lung cancer is one of the most prevalent types of cancer worldwide. The an accurate biomarker is needed to
select patients diagnosed with advanced disease and benefiting the most from immunotherapy. KEM
(Knowledge Extraction and Management) explainable Artificial Intelligence (xAI) was used as a tool to
systematically extract all association rules between all variables in a database, enabling the identification of
subgroups of patients with advanced NSCLC treated with immunotherapy with higher chances of overall
survival in the NIVOBIO cohort. Data was retrieved from GEO warehouse (GSE161537) and aggregated into a
consolidated database totaling 82 patients and 2,568 variables. A total of 51,306 rules were generated by KEM,
and 19 rules involving 3 genes were retained using metrics such as Support (number of examples), Confidence
(conditional probability) and Lift (relative probability) and focusing on genes with a consistent signal across
rules. This analysis identified 2 genes that were significantly associated with overall survival and previous lines
of treatment: SOS2 (p < 0.001) and LIFR (p = 0.020) high expression was associated with improved survival
among patients with at least two previous treatment lines, whereas it was associated with poor survival for other
patients.