Giovanni Parmigiani

Background Pancreatic adenocarcinoma (PC) is a highly lethal malignancy with a survival rate of only 12%. Surveillance is recommended for high-risk individuals (HRIs), but it is not widely adopted. To address this unmet clinical need and drive early diagnosis research, we established the Pancreatic Cancer Early Detection (PRECEDE) Consortium. Methods PRECEDE is a multi-institutional international collaboration that has undertaken an observational prospective cohort study. Individuals (aged 18–90 years) are enrolled into 1 of 7 cohorts based on family history and pathogenic germline variant (PGV) status. From April 1, 2020, to November 21, 2022, a total of 3,402 participants were enrolled in 1 of 7 study cohorts, with 1,759 (51.7%) meeting criteria for the highest-risk cohort (Cohort 1). Cohort 1 HRIs underwent germline testing and pancreas imaging by MRI/MR …

Multi-gene panel testing allows efficient detection of pathogenic variants in cancer susceptibility genes including moderate-risk genes such as ATM and PALB2. A growing number of studies examine the risk of breast cancer (BC) conferred by pathogenic variants of such genes. A meta-analysis combining the reported risk estimates can provide an overall age-specific risk of developing BC, i.e., penetrance for a gene. However, estimates reported by case-control studies often suffer from ascertainment bias. Currently there are no methods available to adjust for such ascertainment bias in this setting. We consider a Bayesian random-effects meta-analysis method that can synthesize different types of risk measures and extend it to incorporate studies with ascertainment bias. This is achieved by introducing a bias term in the model and assigning appropriate priors. We validate the method through a simulation study and apply it to estimate BC penetrance for carriers of pathogenic variants of ATM and PALB2 genes. Our simulations show that the proposed method results in more accurate and precise penetrance estimates compared to when no adjustment is made for ascertainment bias or when such biased studies are discarded from the analysis. The estimated overall BC risk for individuals with pathogenic variants in (1) ATM is 5.77% (3.22%-9.67%) by age 50 and 26.13% (20.31%-32.94%) by age 80; (2) PALB2 is 12.99% (6.48%-22.23%) by age 50 and 44.69% (34.40%-55.80%) by age 80. The proposed method allows for meta-analyses to include studies with ascertainment bias resulting in a larger number of studies included and thereby more …

It is increasingly common to encounter prediction tasks in the biomedical sciences for which multiple datasets are available for model training. Common approaches such as pooling datasets before model fitting can produce poor out‐of‐study prediction performance when datasets are heterogeneous. Theoretical and applied work has shown multistudy ensembling to be a viable alternative that leverages the variability across datasets in a manner that promotes model generalizability. Multistudy ensembling uses a two‐stage stacking strategy which fits study‐specific models and estimates ensemble weights separately. This approach ignores, however, the ensemble properties at the model‐fitting stage, potentially resulting in performance losses. Motivated by challenges in the estimation of COVID‐attributable mortality, we propose optimal ensemble construction, an approach to multistudy stacking whereby we jointly …

In this paper, we introduce Gridsemble, a data-driven selective ensembling algorithm for estimating local false discovery rates (fdr) in large-scale multiple hypothesis testing. Existing methods for estimating fdr often yield different conclusions, yet the unobservable nature of fdr values prevents the use of traditional model selection. There is limited guidance on choosing a method for a given dataset, making this an arbitrary decision in practice. Gridsemble circumvents this challenge by ensembling a subset of methods with weights based on their estimated performances, which are computed on synthetic datasets generated to mimic the observed data while including ground truth. We demonstrate through simulation studies and an experimental application that this method outperforms three popular R software packages with their default parameter values$\unicode{x2014}$common choices given the current landscape. While our applications are in the context of high throughput transcriptomics, we emphasize that Gridsemble is applicable to any use of large-scale multiple hypothesis testing, an approach that is utilized in many fields. We believe that Gridsemble will be a useful tool for computing reliable estimates of fdr and for improving replicability in the presence of multiple hypotheses by eliminating the need for an arbitrary choice of method. Gridsemble is implemented in an open-source R software package available on GitHub at jennalandy/gridsemblefdr.

689Background: Pancreatic ductal adenocarcinoma (PDAC) is a highly lethal cancer typically discovered at incurable stages. The PRECEDE Consortium was established to accelerate early detection by using a large-scale, collaborative, innovative model, predicated on standardized collection of demographic, clinical, and imaging data from high-risk individuals (HRI). Here we report the initial pancreas imaging findings in Cohort 1, representing HRI with familial pancreatic cancer (FPC) or pathogenic germline variants (PGV) in PDAC susceptibility genes with a 1st or 2nd degree relative with PDAC. Methods: The PRECEDE Consortium (NCT04970056) began enrollment in 5/2020. HRI enrolled prospectively at centers worldwide into one of 7 cohorts based on personal and/or family history of PDAC and PGV status. PRECEDE’s planned enrollment is 10,000 patients. Data sharing is required to join PRECEDE …

Clustering, the task of partitioning data into distinct classes, is fundamental in a variety of fields and applications. For example, in genomics, clustering procedures are used for exploratory analyses, dimensionality reduction and to identify interpretable groups within high-dimensional data, such as gene expression studies.One of the difficulties in clustering, common to other techniques in unsupervised learning, is the ambiguity of the notion of success. In contrast to supervised learning, where ground truth measurements can be used to validate the performance of a learning procedure (eg, the precision of a classifier), in unsupervised learning a direct measure of success is not available. In applications it is however crucial to identify criteria to assess the reliability of these unsupervised learning methods.

In this article, I propose an approach for defining replicability for prediction rules. Motivated by a recent report by the U.S.A. National Academy of Sciences, I start from the perspective that replicability is obtaining consistent results across studies suitable to address the same prediction question, each of which has obtained its own data. I then discuss concept and issues in defining key elements of this statement. I focus specifically on the meaning of “consistent results” in typical utilization contexts, and propose a multi-agent framework for defining replicability, in which agents are neither allied nor adversaries. I recover some of the prevalent practical approaches as special cases. I hope to provide guidance for a more systematic assessment of replicability in machine learning.

Simple Summary Lynch syndrome (LS) is associated with varying cancer risks depending on which of the five causative genes harbors a pathogenic variant; however, lifestyle and medical interventions provide options to lower those risks. We developed MyLynch, a patient-facing clinical decision support (CDS) web application that applies genetically-guided personalized medicine (GPM) for individuals with LS. MyLynch informs LS patients of their personal cancer risks, educates patients on relevant interventions, and provides patients with adjusted risk estimates depending on the interventions they choose to pursue. MyLynch can improve risk communication between patients and providers while also encouraging communication among relatives with the goal of increasing cascade testing. As genetic panel testing becomes more widely available, GPM will play an increasingly important role in patient care, and CDS tools offer patients and providers tailored information to inform decision-making. MyLynch provides personalized cancer risk estimates and interventions to lower these risks for patients with LS. Abstract Lynch syndrome (LS) is a hereditary cancer susceptibility condition associated with varying cancer risks depending on which of the five causative genes harbors a pathogenic variant; however, lifestyle and medical interventions provide options to lower those risks. We developed MyLynch, a patient-facing clinical decision support (CDS) web application that applies genetically-guided personalized medicine (GPM) for individuals with LS. The tool was developed in R Shiny through a patient-focused …