Allotey, Loretta K.

Abstract Gallbladder cancer (GBC) is one of the deadliest cancers, with a 5-year-survival-rate of less than 5 percent for late-stage disease. The response rate to chemotherapy among GBC patients is generally poor. Recent research has attempted to identify diagnostic, prognostic, and predictive biomarkers, however, currently, no biomarkers can accurately diagnose GBC and predict patients’ prognosis. Integrative analysis of molecular and clinical characterization has not been fully established, and minimal improvement has been made to the survival of these patients, in part due to the heterogeneity of GBC. Machine learning techniques have been proven to empower analysis of big data in oncology, allowing for improvement in the generation of biomarkers to predict patient outcomes. Using machine learning, we can utilize high-throughput RNA sequencing with clinicopathologic data to develop a predictive tool for GBC prognosis. Current predictive models for GBC outcomes often utilize clinical data only, with the highest C-statistic reported being 0.71. C-statistic values over 0.7 generally indicate good models, however 0.8 is the threshold for strong predictive models. We aim to build a superior algorithm to predict overall survival in GBC patients with advanced disease, using machine learning approaches to prioritize biomarkers for GBC prognosis. We have identified over 80 fresh frozen GBC tissue samples from Mayo Clinic Rochester, Dongsan Medical Center in Daegu, Korea, University of the Witwatersrand, in Johannesburg, South Africa, Lithuanian University of Health Science in Vilnius, Lithuania, and University of Calgary in Calgary, Canada, from patients enrolled between 2012 and 2021. We will perform next-generation RNA sequencing on these tissue samples. The patients’ clinical, pathologic and survival data will be abstracted from the medical record uniformly across sites. Feature engineering and dimensionality reduction will be performed. Then random forests, support vector machines, and gradient boosting machines will be applied to train the data. Variable importance will prioritize multi-omic markers. Standard 5-fold cross validation will be used to assess performance of each ML algorithm. If overall survival can be better predicted with the addition patients’ transcriptional sequencing data compared to using clinical profiles alone, we can gain a greater understanding of key biomarkers driving the tumor phenotype. Citation Format: Linsey Jackson, Loretta Allotey, Valles Kenneth, Gavin Oliver, Asha Nair, Daniel O'Brien, Rondell Graham, Mitesh Borad, Arjun Athreya, Lewis Roberts. Prognostic biomarkers for gallbladder cancer: A machine learning approach [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 1944.

Abstract Background: The GALAD score is a serum biomarker–based model that predicts the probability of having hepatocellular carcinoma (HCC) in patients with chronic liver disease. We aimed to assess the performance of the GALAD score in comparison with liver ultrasound for detection of HCC. Methods: A single-center cohort of 111 HCC patients and 180 controls with cirrhosis or chronic hepatitis B and a multicenter cohort of 233 early HCC and 412 cirrhosis patients from the Early Detection Research Network (EDRN) phase II HCC Study were analyzed. Results: The area under the ROC curve (AUC) of the GALAD score for HCC detection was 0.95 [95% confidence interval (CI), 0.93–97], which was higher than the AUC of ultrasound (0.82, P <0.01). At a cutoff of −0.76, the GALAD score had a sensitivity of 91% and a specificity of 85% for HCC detection. The AUC of the GALAD score for early-stage HCC detection remained high at 0.92 (95% CI, 0.88–0.96; cutoff −1.18, sensitivity 92%, specificity 79%). The AUC of the GALAD score for HCC detection was 0.88 (95% CI, 0.85–0.91) in the EDRN cohort. The combination of GALAD and ultrasound (GALADUS score) further improved the performance of the GALAD score in the single-center cohort, achieving an AUC of 0.98 (95% CI, 0.96–0.99; cutoff −0.18, sensitivity 95%, specificity 91%). Conclusions: The performance of the GALAD score was superior to ultrasound for HCC detection. The GALADUS score further enhanced the performance of the GALAD score. Impact: The GALAD score was validated in the United States.

Abstract Background: In Minnesota, the 2012 Cancer Report by the Department of Health reported both the incidence of liver cancer and mortality rates due to liver cancer among Blacks were significantly higher than Caucasians. African immigration to Minnesota is the third highest by percentage of state population in the US. Given that viral hepatitis disproportionately affects sub-Saharan Africans and that these individuals are emigrating from countries where childhood HBV vaccination has only recently been implemented on a national scale, we speculate that this unique immigrant community may be a major contributor to the increased burden of viral hepatitis and liver cancer complications in the state. Limited research exists on the burden of viral hepatitis and hepatocellular carcinoma among African immigrants. Thus, we conducted a prospective community-wide screening to assess the rates of chronic HBV and HCV infections among Somali, Liberian and Kenyan immigrants in Minnesota. Methods: Several African community health centers and organizations in Minnesota were selected for the study. Individuals of Somali, Liberian or Kenyan descent were enrolled in a prospective screening study for chronic HBV and HCV infection. Blood samples were collected and tested for hepatitis B surface antigen (HBsAg), hepatitis B core antibody (HBcAb), hepatitis B surface antibody (HBsAb), and anti-hepatitis C virus antibody (anti-HCV). Follow-up testing, health education, counseling, and referral were provided to participants. Results: 853 participants provided blood specimens. 13.5% of participants had chronic HBV infection while 32.4% had prior HBV exposure with spontaneous viral clearance. 7% of participants had chronic HCV infection. Follow up and linkage to care were provided to participants with chronic hepatitis while preventive advice was provided to those who were negative for both infections. In particular, participants susceptible to HBV were informed about the availability of HBV vaccine in order to protect against future HBV infection. Conclusions: Chronic HBV and HCV are major health problems among recent African immigrants in Minnesota. Community-based screening is an effective way to identify and provide health education and linkage to care for individuals with or at risk for viral hepatitis. Citation Format: Essa A. Mohamed, Nasra H. Giama, Hassan M. Shaleh, Abdul M. Oseini, Hager Ahmed Mohammed, Jessica Cvinar, Ibrahim A. Waaeys, Hamdi A. Ali, Loretta K. Allotey, Lewis R. Roberts. Community-wide outreach and screening to reduce hepatitis B, hepatitis C and liver cancer disparities among African immigrants in Minnesota. [abstract]. In: Proceedings of the Ninth AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2016 Sep 25-28; Fort Lauderdale, FL. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2017;26(2 Suppl):Abstract nr C76.

AbstractGenetic risk factors for cholangiocarcinoma (CCA) remain poorly understood. We assessed the effect of single‐nucleotide polymorphisms (SNPs) of genes modulating inflammation or carcinogenesis on CCA risk and survival. We conducted a case‐control, candidate gene association study of 370 CCA patients and 740 age‐, sex‐, and residential area‐matched healthy controls. Eighteen functional or putatively functional SNPs in nine genes were genotyped. The log‐additive genotype effects of SNPs on CCA risk and survival were determined using logistic regression and the log‐rank test, respectively. Initial analysis identified significant associations between SNP rs2143417 and rs689466 in cyclooxygenase 2 (COX‐2) and CCA risk, after adjusting for multiple comparisons (cutoff of P = 0.0028). However, these findings were not replicated in another independent cohort of 212 CCA cases and 424 matched controls. No significant association was found between any SNP and survival of CCA patients. Although COX‐2 has been shown to contribute to cholangiocarcinogenesis, the COX‐2 SNPs tested were not associated with risk of CCA. This study shows a lack of association between variants of genes related to inflammation and carcinogenesis and CCA risk and survival. Other factors than these genetic variants may play more important roles in CCA risk and survival.