Dataset Information

Robust deep learning model for prognostic stratification of pancreatic ductal adenocarcinoma patients.

ABSTRACT: A major challenge for treating patients with pancreatic ductal adenocarcinoma (PDAC) is the unpredictability of their prognoses due to high heterogeneity. We present Multi-Omics DEep Learning for Prognosis-correlated subtyping (MODEL-P) to identify PDAC subtypes and to predict prognoses of new patients. MODEL-P was trained on autoencoder integrated multi-omics of 146 patients with PDAC together with their survival outcome. Using MODEL-P, we identified two PDAC subtypes with distinct survival outcomes (median survival 10.1 and 22.7 months, respectively, log rank p = 1 × 10-6), which correspond to DNA damage repair and immune response. We rigorously validated MODEL-P by stratifying patients in five independent datasets into these two survival groups and achieved significant survival difference, which is superior to current practice and other subtyping schemas. We believe the subtype-specific signatures would facilitate PDAC pathogenesis discovery, and MODEL-P can provide clinicians the prognoses information in the treatment decision-making to better gauge the benefits versus the risks.

SUBMITTER: Ju J

PROVIDER: S-EPMC8637475 | biostudies-literature | 2021 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Robust deep learning model for prognostic stratification of pancreatic ductal adenocarcinoma patients.

Ju Jie J Wismans Leonoor V LV Mustafa Dana A M DAM Reinders Marcel J T MJT van Eijck Casper H J CHJ Stubbs Andrew P AP Li Yunlei Y

iScience 20211110 12

A major challenge for treating patients with pancreatic ductal adenocarcinoma (PDAC) is the unpredictability of their prognoses due to high heterogeneity. We present Multi-Omics DEep Learning for Prognosis-correlated subtyping (MODEL-P) to identify PDAC subtypes and to predict prognoses of new patients. MODEL-P was trained on autoencoder integrated multi-omics of 146 patients with PDAC together with their survival outcome. Using MODEL-P, we identified two PDAC subtypes with distinct survival out ...[more]

PMID: 34901786

Similar Datasets

Project description:PurposeClinical prognostic criteria using preoperative factors were not developed for post-neoadjuvant therapy (NAT) surgery of pancreatic ductal adenocarcinoma (PDAC). We aimed to identify preoperative factors associated with overall survival (OS) in PDAC patients who underwent post-NAT curative-intent surgery and develop risk stratification criteria.Materials and methodsConsecutive PDAC patients who underwent post-NAT curative-intent surgeries between 2007 and 2020 were retrospectively analyzed. Demographic, laboratory, surgical, and histopathologic variables were collected. Baseline, preoperative, and interval changes of computed tomography (CT) findings proposed by the Society of Abdominal Radiology and the American Pancreatic Association were analyzed. Cox proportional hazard analysis was used to select preoperative variables associated with OS. We developed risk stratification criteria composed of the significant preoperative variables, i.e., post-NAT response criteria. We compared the discrimination performance of post-NAT response criteria with that of post-NAT pathological (yp) American Joint Cancer Committee TNM staging system.ResultsOne hundred forty-five PDAC patients were included. Stable or increased tumor size on CT (hazard ratio [HR], 2.58; 95% confidence interval [CI], 1.58 to 4.21; p < 0.001) and elevated preoperative carbohydrate antigen 19-9 (CA19-9) level (HR, 1.98; 95% CI, 1.11 to 3.55; p=0.021) were independent factors of OS. The OS of the patient groups stratified by post-NAT response criteria which combined changes in tumor size and CA19-9 showed significant difference (p < 0.001). Such stratification was comparable to ypTNM staging in discrimination performance (difference of C-index, 0.068; 95% CI, -0.012 to 0.142).Conclusion"Any degree of decrease in tumor size on CT" and CA19-9 normalization or staying normal were independent favorable factors of OS. The combination of the two factors discriminated OS comparably to ypTNM staging.

Project description:BackgroundPancreatic ductal carcinoma patients have a really poor prognosis given its difficult early detection and the lack of early symptoms. Digital pathology is routinely used by pathologists to diagnose the disease. However, visually inspecting the tissue is a time-consuming task, which slows down the diagnostic procedure. With the advances occurred in the area of artificial intelligence, specifically with deep learning models, and the growing availability of public histology data, clinical decision support systems are being created. However, the generalization capabilities of these systems are not always tested, nor the integration of publicly available datasets for pancreatic ductal carcinoma detection (PDAC).MethodsIn this work, we explored the performace of two weakly-supervised deep learning models using the two more widely available datasets with pancreatic ductal carcinoma histology images, The Cancer Genome Atlas Project (TCGA) and the Clinical Proteomic Tumor Analysis Consortium (CPTAC). In order to have sufficient training data, the TCGA dataset was integrated with the Genotype-Tissue Expression (GTEx) project dataset, which contains healthy pancreatic samples.ResultsWe showed how the model trained on CPTAC generalizes better than the one trained on the integrated dataset, obtaining an inter-dataset accuracy of 90.62% ± 2.32 and an outer-dataset accuracy of 92.17% when evaluated on TCGA + GTEx. Furthermore, we tested the performance on another dataset formed by tissue micro-arrays, obtaining an accuracy of 98.59%. We showed how the features learned in an integrated dataset do not differentiate between the classes, but between the datasets, noticing that a stronger normalization might be needed when creating clinical decision support systems with datasets obtained from different sources. To mitigate this effect, we proposed to train on the three available datasets, improving the detection performance and generalization capabilities of a model trained only on TCGA + GTEx and achieving a similar performance to the model trained only on CPTAC.ConclusionsThe integration of datasets where both classes are present can mitigate the batch effect present when integrating datasets, improving the classification performance, and accurately detecting PDAC across different datasets.

Dataset Information

Robust deep learning model for prognostic stratification of pancreatic ductal adenocarcinoma patients.

Publications

Robust deep learning model for prognostic stratification of pancreatic ductal adenocarcinoma patients.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets