Dataset Information

A novel framework for horizontal and vertical data integration in cancer studies with application to survival time prediction models.

ABSTRACT: BACKGROUND:Recently high-throughput technologies have been massively used alongside clinical tests to study various types of cancer. Data generated in such large-scale studies are heterogeneous, of different types and formats. With lack of effective integration strategies novel models are necessary for efficient and operative data integration, where both clinical and molecular information can be effectively joined for storage, access and ease of use. Such models, combined with machine learning methods for accurate prediction of survival time in cancer studies, can yield novel insights into disease development and lead to precise personalized therapies. RESULTS:We developed an approach for intelligent data integration of two cancer datasets (breast cancer and neuroblastoma) - provided in the CAMDA 2018 'Cancer Data Integration Challenge', and compared models for prediction of survival time. We developed a novel semantic network-based data integration framework that utilizes NoSQL databases, where we combined clinical and expression profile data, using both raw data records and external knowledge sources. Utilizing the integrated data we introduced Tumor Integrated Clinical Feature (TICF) - a new feature for accurate prediction of patient survival time. Finally, we applied and validated several machine learning models for survival time prediction. CONCLUSION:We developed a framework for semantic integration of clinical and omics data that can borrow information across multiple cancer studies. By linking data with external domain knowledge sources our approach facilitates enrichment of the studied data by discovery of internal relations. The proposed and validated machine learning models for survival time prediction yielded accurate results. REVIEWERS:This article was reviewed by Eran Elhaik, Wenzhong Xiao and Carlos Loucera.

SUBMITTER: Mihaylov I

PROVIDER: S-EPMC6868770 | biostudies-literature | 2019 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A novel framework for horizontal and vertical data integration in cancer studies with application to survival time prediction models.

Mihaylov Iliyan I Kańduła Maciej M Krachunov Milko M Vassilev Dimitar D

Biology direct 20191121 1

<h4>Background</h4>Recently high-throughput technologies have been massively used alongside clinical tests to study various types of cancer. Data generated in such large-scale studies are heterogeneous, of different types and formats. With lack of effective integration strategies novel models are necessary for efficient and operative data integration, where both clinical and molecular information can be effectively joined for storage, access and ease of use. Such models, combined with machine le ...[more]

PMID: 31752974

Similar Datasets

Project description:Researchers expect a high quality of biospecimens/data and value-added services from biobanks. Therefore, the concept of "biobank 3.0" was introduced so that biobanks could better meet the needs of stakeholders and maintain sustainable operations. Theoretically, the Taiwan Biobank (TWB) has already gone through the concepts of biobank 1.0 and 2.0. However, three challenges still need to be addressed before it can be transformed into a new generation of the TWB (namely, the TWB 3.0): (1) the difficulty of integrating other biobanks' resources, (2) the efficiency and effectiveness of the release and use of biospecimens/data, and (3) the development of income and revenue models of sustainability. To address these issues, this paper proposes a framework for the TWB 3.0 transformation based on a dual-pillar approach composed of a "physically" vertical integration driven by the TWB and a "virtually" horizontal network led by the National Health Research Institutes (NHRI) of Taiwan. Using prominent biobanks such as the Biobanking and BioMolecular Resources Research Infrastructure-European Research Infrastructure Consortium (BBMRI-ERIC), the UK Biobank, and the National Institutes of Health (NIH)'s All of Us Research Program as models, the TWB can strengthen its on-going TWB 2.0 operations in regional and/or international collaboration, increase the value of data collected and develop closer relationships with biobank participants and users. To these ends, the authors highlight key issues that include, but are not limited to, the harmonization of relevant ELSI standards for various biobanks' integrations; the value-added services and the efficiency of Big Data Era related research and/or precision medicine development, and financial concerns related to biobank sustainability. This paper concludes by discussing how greater participant engagement and the uptake of Information Technology (IT) and Artificial Intelligence (AI) applications can be used in partnership with vertical and horizontal integration as part of a four-pronged approach to promote biobank sustainability, and facilitate the TWB 3.0 transformation.

Project description:BackgroundPrediction models for time-to-event outcomes are commonly used in biomedical research to obtain subject-specific probabilities that aid in making important clinical care decisions. There are several regression and machine learning methods for building these models that have been designed or modified to account for the censoring that occurs in time-to-event data. Discrete-time survival models, which have often been overlooked in the literature, provide an alternative approach for predictive modeling in the presence of censoring with limited loss in predictive accuracy. These models can take advantage of the range of nonparametric machine learning classification algorithms and their available software to predict survival outcomes.MethodsDiscrete-time survival models are applied to a person-period data set to predict the hazard of experiencing the failure event in pre-specified time intervals. This framework allows for any binary classification method to be applied to predict these conditional survival probabilities. Using time-dependent performance metrics that account for censoring, we compare the predictions from parametric and machine learning classification approaches applied within the discrete time-to-event framework to those from continuous-time survival prediction models. We outline the process for training and validating discrete-time prediction models, and demonstrate its application using the open-source R statistical programming environment.ResultsUsing publicly available data sets, we show that some discrete-time prediction models achieve better prediction performance than the continuous-time Cox proportional hazards model. Random survival forests, a machine learning algorithm adapted to survival data, also had improved performance compared to the Cox model, but was sometimes outperformed by the discrete-time approaches. In comparing the binary classification methods in the discrete time-to-event framework, the relative performance of the different methods varied depending on the data set.ConclusionsWe present a guide for developing survival prediction models using discrete-time methods and assessing their predictive performance with the aim of encouraging their use in medical research settings. These methods can be applied to data sets that have continuous time-to-event outcomes and multiple clinical predictors. They can also be extended to accommodate new binary classification algorithms as they become available. We provide R code for fitting discrete-time survival prediction models in a github repository.

Dataset Information

A novel framework for horizontal and vertical data integration in cancer studies with application to survival time prediction models.

Publications

A novel framework for horizontal and vertical data integration in cancer studies with application to survival time prediction models.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets