International journal of cancer. Journal international du cancer
-
Although immune checkpoint inhibitors (ICIs) are associated with different immune-related adverse events (irAEs), the potential effect on the skeleton is poorly defined albeit biologically plausible and assessable through pharmacovigilance. We described a case series of patients experiencing skeletal fractures while on ICIs at the National Cancer Institute of Milan. To better characterize the clinical features of skeletal irAEs reported with ICIs, we queried the FDA Adverse Event Reporting System (FAERS) and performed disproportionality analysis by means of reporting odds ratios (RORs), deemed significant by a lower limit of the 95% confidence interval (LL95% CI) > 1. ⋯ Statistically significant ROR was found for eight, two and one bone AEs respectively with PD-1, PD-L1 and CTLA-4 inhibitors, being pathological fracture (N = 46; ROR = 3.17; LL95%CI = 2.37), spinal compression fracture (42; 2.51; 1.91), and femoral neck fracture (26; 2.38; 1.62) the most common. Concomitant irAEs or drugs affecting bone metabolism were poorly reported. The increased reporting of serious vertebral fractures in patients without concomitant irAEs and no apparent preexisting risk factors could suggest a possible cause-effect relationship and calls for close clinical monitoring and implementation of dedicated guidelines.
-
High levels of microsatellite instability (MSI-H) occurs in about 15% of sporadic colorectal cancer (CRC) and is an important predictive marker for response to immune checkpoint inhibitors. To test the feasibility of a deep learning (DL)-based classifier as a screening tool for MSI status, we built a fully automated DL-based MSI classifier using pathology whole-slide images (WSIs) of CRCs. On small image patches of The Cancer Genome Atlas (TCGA) CRC WSI dataset, tissue/non-tissue, normal/tumor and MSS/MSI-H classifiers were applied sequentially for the fully automated prediction of the MSI status. ⋯ The performance of the DL-based classifier was much better than that of previously reported histomorphology-based methods. We speculated that about 40% of CRC slides could be screened for MSI status without molecular testing by the DL-based classifier. These results demonstrated that the DL-based method has potential as a screening tool to discriminate molecular alteration in tissue slides.