Dataset Information

Distributed radiomics as a signature validation study using the Personal Health Train infrastructure.

ABSTRACT: Prediction modelling with radiomics is a rapidly developing research topic that requires access to vast amounts of imaging data. Methods that work on decentralized data are urgently needed, because of concerns about patient privacy. Previously published computed tomography medical image sets with gross tumour volume (GTV) outlines for non-small cell lung cancer have been updated with extended follow-up. In a previous study, these were referred to as Lung1 (n?=?421) and Lung2 (n?=?221). The Lung1 dataset is made publicly accessible via The Cancer Imaging Archive (TCIA; https://www.cancerimagingarchive.net ). We performed a decentralized multi-centre study to develop a radiomic signature (hereafter "ZS2019") in one institution and validated the performance in an independent institution, without the need for data exchange and compared this to an analysis where all data was centralized. The performance of ZS2019 for 2-year overall survival validated in distributed radiomics was not statistically different from the centralized validation (AUC 0.61 vs 0.61; p?=?0.52). Although slightly different in terms of data and methods, no statistically significant difference in performance was observed between the new signature and previous work (c-index 0.58 vs 0.65; p?=?0.37). Our objective was not the development of a new signature with the best performance, but to suggest an approach for distributed radiomics. Therefore, we used a similar method as an earlier study. We foresee that the Lung1 dataset can be further re-used for testing radiomic models and investigating feature reproducibility.

SUBMITTER: Shi Z

PROVIDER: S-EPMC6805885 | biostudies-literature | 2019 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Distributed radiomics as a signature validation study using the Personal Health Train infrastructure.

Shi Zhenwei Z Zhovannik Ivan I Traverso Alberto A Dankers Frank J W M FJWM Deist Timo M TM Kalendralis Petros P Monshouwer René R Bussink Johan J Fijten Rianne R Aerts Hugo J W L HJWL Dekker Andre A Wee Leonard L

Scientific data 20191022 1

Prediction modelling with radiomics is a rapidly developing research topic that requires access to vast amounts of imaging data. Methods that work on decentralized data are urgently needed, because of concerns about patient privacy. Previously published computed tomography medical image sets with gross tumour volume (GTV) outlines for non-small cell lung cancer have been updated with extended follow-up. In a previous study, these were referred to as Lung1 (n = 421) and Lung2 (n = 221). The Lung1 ...[more]

PMID: 31641134

Similar Datasets

Project description:BackgroundPrivacy should be protected in medical data that include patient information. A distributed research network (DRN) is one of the challenges in privacy protection and in the encouragement of multi-institutional clinical research. A DRN standardizes multi-institutional data into a common structure and terminology called a common data model (CDM), and it only shares analysis results. It is necessary to measure how a DRN protects patient information privacy even without sharing data in practice.ObjectiveThis study aimed to quantify the privacy risk of a DRN by comparing different deidentification levels focusing on personal health identifiers (PHIs) and quasi-identifiers (QIs).MethodsWe detected PHIs and QIs in an Observational Medical Outcomes Partnership (OMOP) CDM as threatening privacy, based on 18 Health Insurance Portability and Accountability Act of 1996 (HIPPA) identifiers and previous studies. To compare the privacy risk according to the different privacy policies, we generated limited and safe harbor data sets based on 16 PHIs and 12 QIs as threatening privacy from the Synthetic Public Use File 5 Percent (SynPUF5PCT) data set, which is a public data set of the OMOP CDM. With minimum cell size and equivalence class methods, we measured the privacy risk reduction with a trust differential gap obtained by comparing the two data sets. We also measured the gap in randomly sampled records from the two data sets to adjust the number of PHI or QI records.ResultsThe gaps averaged 31.448% and 73.798% for PHIs and QIs, respectively, with a minimum cell size of one, which represents a unique record in a data set. Among PHIs, the national provider identifier had the highest gap of 71.236% (71.244% and 0.007% in the limited and safe harbor data sets, respectively). The maximum size of the equivalence class, which has the largest size of an indistinguishable set of records, averaged 771. In 1000 random samples of PHIs, Device_exposure_start_date had the highest gap of 33.730% (87.705% and 53.975% in the data sets). Among QIs, Death had the highest gap of 99.212% (99.997% and 0.784% in the data sets). In 1000, 10,000, and 100,000 random samples of QIs, Device_treatment had the highest gaps of 12.980% (99.980% and 87.000% in the data sets), 60.118% (99.831% and 39.713%), and 93.597% (98.805% and 5.207%), respectively, and in 1 million random samples, Death had the highest gap of 99.063% (99.998% and 0.934% in the data sets).ConclusionsIn this study, we verified and quantified the privacy risk of PHIs and QIs in the DRN. Although this study used limited PHIs and QIs for verification, the privacy limitations found in this study could be used as a quality measurement index for deidentification of multi-institutional collaboration research, thereby increasing DRN safety.

Project description:BackgroundAs the need for sharing genomic data grows, privacy issues and concerns, such as the ethics surrounding data sharing and disclosure of personal information, are raised.ObjectiveThe main purpose of this study was to verify whether genomic data is sufficient to predict a patient's personal information.MethodsRNA expression data and matched patient personal information were collected from 9538 patients in The Cancer Genome Atlas program. Five personal information variables (age, gender, race, cancer type, and cancer stage) were recorded for each patient. Four different machine learning algorithms (support vector machine, decision tree, random forest, and artificial neural network) were used to determine whether a patient's personal information could be accurately predicted from RNA expression data. Performance measurement of the prediction models was based on the accuracy and area under the receiver operating characteristic curve. We selected five cancer types (breast carcinoma, kidney renal clear cell carcinoma, head and neck squamous cell carcinoma, low-grade glioma, and lung adenocarcinoma) with large samples sizes to verify whether predictive accuracy would differ between them. We also validated the efficacy of our four machine learning models in analyzing normal samples from 593 cancer patients.ResultsIn most samples, personal information with high genetic relevance, such as gender and cancer type, could be predicted from RNA expression data alone. The prediction accuracies for gender and cancer type, which were the best models, were 0.93-0.99 and 0.78-0.94, respectively. Other aspects of personal information, such as age, race, and cancer stage, were difficult to predict from RNA expression data, with accuracies ranging from 0.0026-0.29, 0.76-0.96, and 0.45-0.79, respectively. Among the tested machine learning methods, the highest predictive accuracy was obtained using the support vector machine algorithm (mean accuracy 0.77), while the lowest accuracy was obtained using the random forest method (mean accuracy 0.65). Gender and race were predicted more accurately than other variables in the samples. On average, the accuracy of cancer stage prediction ranged between 0.71-0.67, while the age prediction accuracy ranged between 0.18-0.23 for the five cancer types.ConclusionsWe attempted to predict patient information using RNA expression data. We found that some identifiers could be predicted, but most others could not. This study showed that personal information available from RNA expression data is limited and this information cannot be used to identify specific patients.

Project description:BACKGROUND:Personal health informatics have the potential to help patients discover personalized health management strategies that influence outcomes. Fibromyalgia (FM) is a complex chronic illness requiring individualized strategies that may be informed by analysis of personal health informatics data. An online health diary program with dynamic feedback was developed to assist patients with FM in identifying symptom management strategies that predict their personal outcomes, and found reduced symptom levels associated with program use. OBJECTIVE:The aim of this study was to determine longitudinal associations between program use and functional impact of FM as measured by scores on a standardized assessment instrument, the Fibromyalgia Impact Questionnaire (FIQ). METHODS:Participants were self-identified as diagnosed with FM and recruited via online FM advocacy websites. Participants used an online health diary program ("SMARTLog") to report symptom ratings, behaviors, and management strategies used. Based on single-subject analysis of the accumulated data over time, individualized recommendations ("SMARTProfile") were then provided by the automated feedback program. Indices of program use comprised of cumulative numbers of SMARTLogs completed and SMARTProfiles received. Participants included in this analysis met a priori criteria of sufficient program use to generate SMARTProfiles (ie, ?22 SMARTLogs completed). Users completed the FIQ at baseline and again each subsequent month of program use as follow-up data for analysis. Kendall tau-b, a nonparametric statistic that measures both the strength and direction of an ordinal association between two repeated measured variables, was computed between all included FIQ scores and both indices of program use for each subject at the time of each completed FIQ. RESULTS:A total of 76 users met the a priori use criteria. The mean baseline FIQ score was 61.6 (SD 14.7). There were 342 FIQ scores generated for longitudinal analysis via Kendall tau-b. Statistically significant inverse associations were found over time between FIQ scores and (1) the cumulative number of SMARTLogs completed (tau-b=-0.135, P<.001); and (2) the cumulative number of SMARTProfiles received (tau-b=-0.133, P<.001). Users who completed 61 or more SMARTLogs had mean follow-up scores of 49.9 (n=25, 33% of the sample), an 18.9% drop in FM impact. Users who generated 11 or more new SMARTProfiles had mean follow-up scores of 51.8 (n=23, 30% of the sample), a 15.9% drop. CONCLUSIONS:Significant inverse associations were found between FIQ scores and both indices of program use, with FIQ scores declining as use increased. Based on established criteria for rating FM severity, the top one-third of users in terms of use had clinically significant reductions from "severe" to "moderate" FM impact. These findings underscore the value of self-management interventions with low burden, high usability, and high perceived relevance to the user. TRIAL REGISTRATION:ClinicalTrials.gov NCT02515552; https://clinicaltrials.gov/ct2/show/NCT02515552.

Dataset Information

Distributed radiomics as a signature validation study using the Personal Health Train infrastructure.

Publications

Distributed radiomics as a signature validation study using the Personal Health Train infrastructure.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets