Search

Introduction: Tumor-related liver failure (TRLF) is the most common cause of death in patients with intrahepatic cholangiocarcinoma (ICC). Though we previously showed that liver radiotherapy (L-RT) for locally advanced ICC is associated with less frequent TRLF and longer overall survival (OS), the role of L-RT for patients with extrahepatic metastatic disease (M1) remains undefined. We sought to compare outcomes for M1 ICC patients treated with and without L-RT. Methods: We reviewed ICC patients found to have M1 disease at initial diagnosis at a single institution between 2010 and 2021 who received L-RT, matching them with an institutional cohort by propensity score and a National Cancer Database (NCDB) cohort by frequency technique. The median biologically effective dose (BED10) was 98 Gy (interquartile range [IQR] 80.5-97.9 Gy) for L-RT. Patients treated with other local therapies or supportive care alone were excluded. We analyzed survival with Cox proportional hazards modeling. Results: We identified 61 patients who received L-RT and 220 who received chemotherapy alone. At median follow up of 11 months after diagnosis, median OS was 9 months (95% confidence interval [CI] 8-11) and 21 months (CI 17-26) for patients receiving chemotherapy alone and L-RT, respectively. TRLF was the cause of death more often in the patients who received chemotherapy alone compared to those who received L-RT (82% vs. 47%; P=0.001). On multivariable propensity-score matched analysis, associations with lower risk of death included duration of upfront chemotherapy (hazard ratio [HR] 0.82; P=0.005) and receipt of L-RT (HR 0.40; P=0.002). The median OS from diagnosis for NCDB chemotherapy alone cohort was shorter than that of the institutional L-RT cohort (9 vs. 22 months; P

Background: Cancer of unknown primary (CUP), representing approximately 3-5% of all malignancies, is defined as metastatic cancer where a primary site of origin cannot be found despite a standard diagnostic workup. Because knowledge of a patient's primary cancer remains fundamental to their treatment, CUP patients are significantly disadvantaged and most have a poor survival outcome. Developing robust and accessible diagnostic methods for resolving cancer tissue of origin, therefore, has significant value for CUP patients. Methods: We developed an RNA-based classifier called CUP-AI-Dx that utilizes a 1D Inception convolutional neural network (1D-Inception) model to infer a tumor's primary tissue of origin. CUP-AI-Dx was trained using the transcriptional profiles of 18,217 primary tumours representing 32 cancer types from The Cancer Genome Atlas project (TCGA) and International Cancer Genome Consortium (ICGC). Gene expression data was ordered by gene chromosomal coordinates as input to the 1D-CNN model, and the model utilizes multiple convolutional kernels with different configurations simultaneously to improve generality. The model was optimized through extensive hyperparameter tuning, including different max-pooling layers and dropout settings. For 11 tumour types, we also developed a random forest model that can classify the tumour's molecular subtype according to prior TCGA studies. The optimised CUP-AI-Dx tissue of origin classifier was tested on 394 metastatic samples from 11 tumour types from TCGA and 92 formalin-fixed paraffin-embedded (FFPE) samples representing 18 cancer types from two clinical laboratories. The CUP-AI-Dx molecular subtype was also independently tested on independent ovarian and breast cancer microarray datasets Findings: CUP-AI-Dx identifies the primary site with an overall top-1-accuracy of 98.54% in cross-validation and 96.70% on a test dataset. When applied to two independent clinical-grade RNA-seq datasets generated from two different institutes from the US and Australia, our model predicted the primary site with a top-1-accuracy of 86.96% and 72.46% respectively. Interpretation: The CUP-AI-Dx predicts tumour primary site and molecular subtype with high accuracy and therefore can be used to assist the diagnostic work-up of cancers of unknown primary or uncertain origin using a common and accessible genomics platform. Funding: NIH R35 GM133562, NCI P30 CA034196, Victorian Cancer Agency Australia.