A Survey on Publicly Available Open Datasets Derived From Electronic Health Records (EHRs) of Patients with Neuroblastoma. (4th October 2022)

• Record Type: Journal Article
• Authors: Chicco, Davide; Cerono, Gabriel; Cangelosi, Davide
• Is Part Of: Data science journal. Volume 21(2022)
• Publication Date: 2022-10-04
• Subjects: neuroblastoma -- electronic health records -- EHR -- datasets -- data -- open data -- neuro-oncology -- childhood cancer -- pediatric oncology; Science -- Data processing -- Periodicals; Database management -- Periodicals; 502.85
• DOI: 10.5334/dsj-2022-017
• Languages: English
• ISSNs: 1683-1470

Abstract

Background: Neuroblastoma is a rare pediatric cancer that affects thousands of children worldwide. Information stored in electronic health records can be a useful source of data for in silico scientific studies about this disease, carried out both by humans and by computational machines. Several open datasets derived from electronic health records of anonymized patients diagnosed with neuroblastoma are available in the internet, but they were released on different websites or as supplementary information of peer-reviewed scientific publications, making them difficult to find. Methods: To solve this problem, we present here this survey of five open public datasets derived from electronic health records of patients diagnosed with neuroblastoma, all collected in a single website called Neuroblastoma Electronic Health Records Open Data Repository. Results: The five open datasets presented in this survey can be used by researchers worldwide who want to carry on scientific studies on neuroblastoma, including machine learning and computational statistics analyses. Conclusions: We believe our survey and our open data resource can have a strong impact in oncology research, allowing new scientific discoveries that can improve our understanding of neuroblastoma and therefore improve the conditions of patients. We release the five open datasets reviewed here publicly and freely on our Neuroblastoma Electronic Health Records Open Data Repository under the CC BY 4.0 license at: https://davidechicco.github.io/neuroblastoma_EHRs_data or at https://doi.org/10.5281/zenodo.6915403