Cell-free DNA methylation markers for differential diagnosis of hepatocellular carcinoma

Background Aberrant DNA methylation may offer opportunities in revolutionizing cancer screening and diagnosis. We sought to identify a non-invasive DNA methylation-based screening approach using cell-free DNA (cfDNA) for early detection of hepatocellular carcinoma (HCC). Methods Differentially, DNA methylation blocks were determined by comparing methylation profiles of biopsy-proven HCC, liver cirrhosis, and normal tissue samples with high throughput DNA bisulfite sequencing. A multi-layer HCC screening model was subsequently constructed based on tissue-derived differentially methylated blocks (DMBs). This model was tested in a cohort consisting of 120 HCC, 92 liver cirrhotic, and 290 healthy plasma samples including 65 hepatitis B surface antigen-seropositive (HBsAg+) samples, independently validated in a cohort consisting of 67 HCC, 111 liver cirrhotic, and 242 healthy plasma samples including 56 HBsAg+ samples. Results Based on methylation profiling of tissue samples, 2321 DMBs were identified, which were subsequently used to construct a cfDNA-based HCC screening model, achieved a sensitivity of 86% and specificity of 98% in the training cohort and a sensitivity of 84% and specificity of 96% in the independent validation cohort. This model obtained a sensitivity of 76% in 37 early-stage HCC (Barcelona clinical liver cancer [BCLC] stage 0-A) patients. The screening model can effectively discriminate HCC patients from non-HCC controls, including liver cirrhotic patients, asymptomatic HBsAg+ and healthy individuals, achieving an AUC of 0.957(95% CI 0.939–0.975), whereas serum α-fetoprotein (AFP) only achieved an AUC of 0.803 (95% CI 0.758–0.847). Besides detecting patients with early-stage HCC from non-HCC controls, this model showed high capacity for distinguishing early-stage HCC from a high risk population (AUC=0.934; 95% CI 0.905–0.963), also significantly outperforming AFP. Furthermore, our model also showed superior performance in distinguishing HCC with normal AFP (< 20ng ml−1) from high risk population (AUC=0.93; 95% CI 0.892–0.969). Conclusions We have developed a sensitive blood-based non-invasive HCC screening model which can effectively distinguish early-stage HCC patients from high risk population and demonstrated its performance through an independent validation cohort. Trial registration The study was approved by the ethic committee of The Second Xiangya Hospital of Central South University (KYLL2018072) and Chongqing University Cancer Hospital (2019167). The study is registered at ClinicalTrials.gov(#NCT04383353).

Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge

Artificial intelligence (AI) has shown promise for diagnosing prostate cancer in biopsies. However, results have been limited to individual studies, lacking validation in multinational settings. Competitions have been shown to be accelerators for medical imaging innovations, but their impact is hindered by lack of reproducibility and independent validation. With this in mind, we organized the PANDA challenge—the largest histopathology competition to date, joined by 1,290 developers—to catalyze development of reproducible AI algorithms for Gleason grading using 10,616 digitized prostate biopsies. We validated that a diverse set of submitted algorithms reached pathologist-level performance on independent cross-continental cohorts, fully blinded to the algorithm developers. On United States and European external validation sets, the algorithms achieved agreements of 0.862 (quadratically weighted κ, 95% confidence interval (CI), 0.840–0.884) and 0.868 (95% CI, 0.835–0.900) with expert uropathologists. Successful generalization across different patient populations, laboratories and reference standards, achieved by a variety of algorithmic approaches, warrants evaluating AI-based Gleason grading in prospective clinical trials.

Validation of a Pancreatic Cancer Detection Test in New-Onset Diabetes Using Cell-Free DNA 5-Hydroxymethylation Signatures

BACKGROUND Pancreatic cancer (PaC) has poor (10%) 5–year overall survival, largely due to predominant late-stage diagnosis. Patients with new-onset diabetes (NOD) are at a six– to eightfold increased risk for PaC. We developed a pancreatic cancer detection test for the use in a clinical setting that employs a logistic regression model based on 5–hydroxymethylcytosine (5hmC) profiling of cell-free DNA (cfDNA). METHODS: cfDNA was isolated from plasma from 89 subjects with PaC and 596 case–control non–cancer subjects, and 5hmC libraries were generated and sequenced. These data coupled with machine–learning, were used to generate a predictive model for PaC detection, which was independently validated on 79 subjects with PaC, 163 non–cancer subjects, and 506 patients with non–PaC cancers. RESULTS: The area under the receiver operating characteristic curve for PaC classification was 0.93 across the training data. Training sensitivity was 58.4% (95% confidence interval [CI]: 47.5–68.6) after setting a classification probability threshold that resulted in 98% (95% CI: 96.5–99) specificity. The independent validation dataset sensitivity and specificity were 51.9% (95% CI: 40.4–63.3) and 100.0% (95% CI: 97.8–100.0), respectively. Early–stage (stage I and II) PaC detection was 47.6% (95% CI: 23%–58%) and 39.4% (95% CI: 32%–64%) in the training and independent validation datasets, respectively. Sensitivity and specificity in NOD patients were 55.2% [95% CI: 35.7–73.6] and 98.4% [95% CI: 91.3–100.0], respectively. The PaC signal was identified in intraductal papillary mucinous neoplasm (64%), pancreatitis (56%), and non-PaC cancers (17%). CONCLUSIONS: The pancreatic cancer detection assay showed robust performance in the tested cohorts and carries the promise of becoming an essential clinical tool to enable early detection in high–risk NOD patients.

Incidence of COVID-19 in patients treated with infliximab compared with patients treated with rituximab

ObjectiveTo determine whether patients with inflammatory autoimmune diseases treated with rituximab (RTX) have more severe forms of COVID-19 compared with patients treated with anticytokine therapies, such as Tumour Necrosis Factor (TNF) inhibitors.MethodsWe included all patients who were on either RTX or infliximab (IFX) in two Swiss cantons during the first wave of the COVID-19 pandemic. We collected self-reported symptoms compatible with COVID-19, PCR-confirmed diagnoses of COVID-19 and the evolution of COVID-19 infections. We computed the raw and propensity score-adjusted incidence of COVID-19 by treatment group.Results190 patients were enrolled, of whom 121 (64%) were in the RTX group and 69 (36%) were in the IFX group. Twenty-one patients (11%) reported symptoms compatible with COVID-19 (RTX: 10, IFX: 11, p=0.14). Among patients with COVID-19 symptoms, four developed severe forms of the disease, with life-threatening pulmonary manifestations requiring intensive mechanical ventilation (RTX: 4 of 10, IFX: 0 of 11, Fisher’s exact test p=0.04). The incidence rate of COVID-19 symptoms was 0.73 (95% CI 0.39 to 1.37) cases per 1000 patient-days on RTX vs 1.52 (95% CI 0.82 to 2.85) cases per 1000 patient-days on IFX (crude p=0.10, adjusted p=0.07). The incidence rate of severe COVID-19 was 0.28 (95% CI 0.08 to 0.7.2) cases per 1000 patient-days on RTX compared with null on IFX (95% CI 0.0 to 0.44) (p=0.13). A replication in an independent validation cohort confirmed these findings, with consistent results in the Swiss Clinical Quality Management registry.ConclusionWhile the incidence of symptoms compatible with COVID-19 was overall similar in patients receiving RTX or IFX, the incidence of severe COVID-19 tended to be higher in the RTX group.

Predicting the Prognosis of Esophageal Adenocarcinoma by a Pyroptosis-Related Gene Signature

Esophageal adenocarcinoma (EAC) is a highly malignant type of digestive tract cancers with a poor prognosis despite therapeutic advances. Pyroptosis is an inflammatory form of programmed cell death, whereas the role of pyroptosis in EAC remains largely unknown. Herein, we identified a pyroptosis-related five-gene signature that was significantly correlated with the survival of EAC patients in The Cancer Genome Atlas (TCGA) cohort and an independent validation dataset. In addition, a nomogram based on the signature was constructed with novel prognostic values. Moreover, the downregulation of GSDMB within the signature is notably correlated with enhanced DNA methylation. The pyroptosis-related signature might be related to the immune response and regulation of the tumor microenvironment. Several inhibitors including GDC-0879 and PD-0325901 are promising in reversing the altered differentially expressed genes in high-risk patients. Our findings provide insights into the involvement of pyroptosis in EAC progression and are promising in the risk assessment as well as the prognosis for EAC patients in clinical practice.

Prognostic Value of Inflammatory Indicators in Chronic Hepatitis B Patients With Significant Liver Fibrosis: A Multicenter Study in China

Diagnosis of significant liver fibrosis is essential to facilitate the optimal treatment decisions and improve prognosis in patients with chronic hepatitis B (CHB). We aimed to evaluate the value of inflammatory indicators and construct a nomogram that effectively predicts significant liver fibrosis among CHB patients. 563 CHB patients from two centers in China from 2014 to 2019 were divided into three cohorts (development, internal validation, and independent validation cohorts), assigned into cases with significant fibrosis (liver fibrosis stages ≥2) and those without. Multiple biochemical and serological inflammatory indicators were investigated. Inflammatory indicators, Alanine aminotransferase (ALT) and aspartate aminotransferase (AST), were significantly associated with significant liver fibrosis in CHB patients but limited predictive performance, and then we combined them with prothrombin time activity percentage (PTA) and liver stiffness measurement (LSM) were identified by multivariate logistic regression analysis. Based on these factors, we constructed the nomogram with excellent performance. The area under the receiver operating characteristic curve (AUROC) for the nomogram in the development, internal validation, and independent validation cohorts were 0.860, 0.877, and 0.811, respectively. Our nomogram based on ALT and AST that had excellent performance in predicting significant fibrosis of CHB patients were constructed.

Profiling of Circulating Tumor DNA for Noninvasive Disease Detection, Risk Stratification, and MRD Monitoring in Patients with CNS Lymphoma

Introduction: Clinical outcomes for patients with central nervous system lymphoma (CNSL) are remarkably heterogeneous, yet identification of patients at high risk for treatment failure remains challenging with existing methods. In addition, diagnosis of CNSL requires invasive neurosurgical biopsies that carry procedural risks and often cannot be performed in frail or elderly patients. Circulating tumor DNA (ctDNA) has shown great potential as a noninvasive biomarker in systemic lymphomas. Yet, previous studies revealed low ctDNA detection rates in blood plasma of CNSL patients. In this study, we utilized ultrasensitive targeted high-throughput sequencing technologies to explore the role of ctDNA for disease classification, MRD detection, and early prediction of clinical outcomes in patients with CNSL. Methods: We applied Cancer Personalized Profiling by Deep Sequencing (CAPP-Seq) and Phased Variant Enrichment and Detection Sequencing (PhasED-Seq, Kurtz et al, Nat Biotech 2021) to 85 tumor biopsies, 131 plasma samples, and 62 CSF specimens from 92 CNSL patients and 44 patients with other brain cancers or inflammatory cerebral diseases, targeting 794 distinct genetic regions. Concentrations of ctDNA were correlated with radiological measures of tumor burden and tested for associations with clinical outcomes at distinct clinical time points. We further developed a novel classifier to noninvasively distinguish CNS lymphomas from other CNS tumors based on their mutational landscapes in plasma and CSF, using supervised training of a machine learning approach from tumor whole genome sequencing data and own genotyping analyses, followed by its independent validation. Results: We identified genetic aberrations in 100% of CNSL tumor biopsies (n=63), with a median of 262 mutations per patient. Pretreatment plasma ctDNA was detectable in 78% of plasma samples and in 100% of CSF specimens (Fig. 1a), with ctDNA concentrations ranging from 0.0004 - 5.94% allele frequency (AF, median: 0.01%) in plasma and 0.0049 - 50.47% AF (median: 0.62%) in CSF (Fig. 1b). Compared to ctDNA concentrations in patients with systemic diffuse large B-cell lymphoma (DLBCL, data from Kurtz et al., J Clin Oncol, 2018), plasma ctDNA levels in CNSL were in median more than 200-fold lower (Fig. 1b). We observed a significant correlation of ctDNA concentrations with total radiographic tumor volumes (TRTV) measured by MRI (Fig. 1c,d), but no association with clinical risk scores (i.e., MSKCC score) or concurrent steroid treatment. Assessment of ctDNA at pretreatment time points predicted progression-free survival (PFS) and overall survival (OS), both as continuous and binary variable (Fig. 1e,f). Notably, patients could be stratified into risk groups with particularly favorable or poor prognoses by combining ctDNA and TRTV as pretreatment biomarkers (Fig. 1g). Furthermore, ctDNA positivity during curative-intent induction therapy was significantly associated with clinical outcomes, both PFS and OS (Fig. 1h). Finally, we applied our novel machine learning classifier to 207 specimens from an independent validation cohort of CNSL and Non-CNSL patients. We observed high specificity (100%) and positive predictive value (100%) for noninvasive diagnosis of CNSL, with a sensitivity of 57% for CSF and 21% for plasma, suggesting that a significant subset of CNSL patients might be able to forego invasive surgical biopsies. Conclusions: We demonstrate robust and ultrasensitive detection of ctDNA at various disease milestones in CNSL. Our findings suggest that ctDNA accurately mirrors tumor burden and serves as a valuable clinical biomarker for risk stratification, outcome prediction, and surgery-free lymphoma classification in CNSL. We foresee an important potential future role of ctDNA as a decision-making tool to guide treatment in patients with CNSL. Figure 1 Figure 1. Disclosures Esfahani: Foresight Diagnostics: Current holder of stock options in a privately-held company. Kurtz: Genentech: Consultancy; Roche: Consultancy; Foresight Diagnostics: Consultancy, Current holder of stock options in a privately-held company. Schorb: Riemser Pharma GmbH: Honoraria, Research Funding; Roche: Research Funding; AbbVie: Research Funding. Diehn: BioNTech: Consultancy; RefleXion: Consultancy; Roche: Consultancy; AstraZeneca: Consultancy; Foresight Diagnostics: Current holder of individual stocks in a privately-held company, Current holder of stock options in a privately-held company; CiberMed: Current holder of stock options in a privately-held company, Patents & Royalties; Illumina: Research Funding; Varian Medical Systems: Research Funding. Alizadeh: Foresight Diagnostics: Consultancy, Current holder of individual stocks in a privately-held company, Current holder of stock options in a privately-held company; Gilead: Consultancy; Roche: Consultancy, Honoraria; Celgene: Consultancy, Research Funding; Janssen Oncology: Honoraria; CAPP Medical: Current holder of individual stocks in a privately-held company, Current holder of stock options in a privately-held company; Forty Seven: Current holder of individual stocks in a privately-held company, Current holder of stock options in a privately-held company; Cibermed: Consultancy, Current holder of individual stocks in a privately-held company, Current holder of stock options in a privately-held company; Bristol Myers Squibb: Research Funding.

Response Prediction to Isocitrate Dehydrogenase (IDH) Inhibitors in Patients with IDH1- or IDH2-Mutated Acute Myeloid Leukemia Using Clinical and Genomic Data

Background: Ivosidenib (Servier Pharmaceuticals LLC) and enasidenib (Celgene) are inhibitors of mutant IDH1 and IDH2, respectively, approved for the treatment of relapsed/refractory (R/R) AML with an IDH1 or IDH2 mutation (ivosidenib is also approved for front-line use in patients ≥ 75 years or with comorbidities). While these drugs were approved based on durable complete remission (CR) + CR with partial hematologic recovery (CRh) rate, only 23-43% of patients responded. Thus, there is a need for a biomarker to better predict response. We previously presented a genomic model of response to enasidenib using linear discriminate analysis (Ghazanchyan et al., ASH 2018). In the two-part study presented here, we improved this modeling by adding clinical data, using machine learning-based approaches to model response to both enasidenib and ivosidenib, and generated an independent validation cohort using clinical samples. Methods: In part I, models were generated using data submitted to FDA in the marketing applications for ivosidenib and enasidenib (studies AG120-C-001 [NCT02074839] and AG221-C-001 [NCT01915498], respectively). Analysis inclusion criteria were available genomic data, IDH mutation positivity per the companion diagnostics, and receipt of at least the approved dose of IDH inhibitor. Patients in the ivosidenib cohort had untreated (n=33) or R/R AML (n=173); patients in the enasidenib cohort had R/R AML. Patients achieving a best response of CR or CRh were considered responders; all other patients were considered nonresponders. Genomic data for the ivosidenib cohorts were generated with the Foundation Medicine FoundationOne Heme panel (FMI) in dose escalation (n=38) and Brigham and Women's Hospital Rapid Heme Panel (RHP) in dose expansion (n=168); these cohorts were analyzed separately to account for differences between panels. Genomic data for the enasidenib cohort (n=75) were generated with the FMI panel. Machine learning-based feature selection approaches were used prior to modeling to identify important clinical data variables (i.e., baseline demographics and disease characteristics). Each analysis cohort was split into a training set (80% patients) and a testing set (20% patients). Machine learning modeling was performed with the decision-tree based algorithm XGBoost using repeated stratified cross validation. In part II of the study, we generated an independent validation cohort consisting of patients with IDH-mutated myeloid malignancies treated with ivosidenib or enasidenib at collaborating institutions (n=14). Bone marrow or peripheral blood samples were processed for deep whole exome sequencing to an average coverage of 441X. Custom analysis pipelines for filtering and annotation were developed to harmonize exome and panel data. Results: In part I, separate machine learning models were generated for each cohort using clinical data only, genomic data only, and clinical and genomic data together. Use of clinical and genomic data together, compared with either data type alone, resulted in improved model performance with accuracies of 89-100% in the testing sets. The most important clinical and genomic features for each cohort are shown in Figure 1. In part II, the independent validation cohort, collaborators provided response data and clinical data for variables found to be important in the models. Patient demographics and response rates are shown in Table 1. Mutational profiles for model genes mutated in ≥ 2 patients are shown in Figure 2. The models for CR+CRh response using both clinical and genomic data in the validation cohort had accuracies of 50-75% (66.7% ivosidenib BWH; 50% ivosidenib FMI; and 75% enasidenib). The combined accuracy improved to 80% when restricted to AML cases (excluding CMML and MDS) treated with ivosidenib (using the BWH model) or enasidenib (n=10). Conclusions: This study demonstrates the potential of harnessing machine learning for biomarker discovery to improve response prediction for the treatment of AML. The modeling approaches improved with inclusion of multiple data types, highlighting the importance of multi-faceted approaches for biomarker development in AML. The models presented have encouraging accuracies in a small independent validation cohort, suggesting potential clinical utility of machine learning-based biomarkers for identifying patients likely to respond to IDH inhibitors. Figure 1 Figure 1. Disclosures Kural: Senseonics: Current equity holder in publicly-traded company; NanoDimensions: Current equity holder in publicly-traded company; Bionano Genomics: Current equity holder in publicly-traded company. Ghiaur: Menarini Richerche: Research Funding; Syros Pharmaceuticals: Consultancy. Kazandjian: Arcellx: Honoraria, Membership on an entity's Board of Directors or advisory committees; BMS: Honoraria, Membership on an entity's Board of Directors or advisory committees. Lai: Macrogenics: Consultancy, Membership on an entity's Board of Directors or advisory committees; Jazz Pharma: Consultancy, Membership on an entity's Board of Directors or advisory committees; Genentech: Consultancy, Membership on an entity's Board of Directors or advisory committees; Jazz Pharma: Speakers Bureau; Astellas: Speakers Bureau; Daiichi-Sankyo: Consultancy, Membership on an entity's Board of Directors or advisory committees; Agios: Consultancy, Membership on an entity's Board of Directors or advisory committees; AbbVie: Consultancy, Membership on an entity's Board of Directors or advisory committees. Wynne: Servier Pharmaceuticals: Honoraria; Carisma Therapeutics: Patents & Royalties. OffLabel Disclosure: This presentation references off label use of enasidenib in patients with MDS and CMML.

A brain structural connectivity biomarker for diagnosis of autism spectrum disorder in early childhood

Objective: Autism spectrum disorder (ASD) is associated with altered brain development, but it is unclear which specific structural changes may serve as potential diagnostic markers. This study aimed to identify and model brain-wide differences in structural connectivity using MRI diffusion tensor imaging (DTI) in young ASD and typically developing (TD) children (3.5-6 years old). Methods: Ninety-three ASD and 26 TD children were included in a discovery dataset and 12 ASD and 9 TD children from different sites included as independent validation datasets. Brain-wide (294 regions) structural connectivity was measured using DTI (fractional anisotropy, FA) under sedation together with symptom severity and behavioral and cognitive development. A connection matrix was constructed for each child for comparisons between ASD and TD groups. Pattern classification was performed and the resulting model tested on two independent datasets. Results: Thirty-three structural connections showed increased FA in ASD compared to TD children and associated with both symptom severity and general cognitive development. The majority (29/33) involved the frontal lobe and comprised five different networks with functional relevance to default mode, motor control, social recognition, language and reward. Overall, classification accuracy is very high in the discovery dataset 96.77%, and 91.67% and 88.89% in the two independent validation datasets. Conclusions: Identified structural connectivity differences primarily involving the frontal cortex can very accurately distinguish individual ASD from TD children and may therefore represent a robust early brain biomarker.