home datasets articles

NB EHRs ODR Neuroblastoma Electronic Health Records Open Data Repository

Neuroblastoma is a rare pediatric cancer that affects thousands of children worldwide each year, and information stored in electronic health records can be a useful source of data for computational research studies about this disease.
Several open datasets of electronic health records from anonymized patients diagnosed with neuroblastoma are available on the internet, but they have been released on different websites or "forgotten" as supplementary information in peer-reviewed scientific publications, making them difficult to find. To mitigate this problem, we decided to create this Neuroblastoma Electronic Health Records Open Data Repository, a publicly free accessible website containing open neuroblastoma datasets, derived from EHRs released online under open licenses such as the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license or similar licenses.
Having all these datasets in one place can bring several advantages to the scientific community: researchers and users, in fact, can take advantage of the listed datasets to conduct any scientific analyses they want. For example, they can apply computational statistics and machine learning methods to infer new knowledge about neuroblastoma.

This data repository supports the FAIR principles for open data and was inspired by the University of California Irvine Machine Learning Repository (UC Irvine ML Repo) and by Gene Expression Omnibus (GEO).

News

2025-09-01: I added two new datasets: GSE3960 and GSE49710 SEQC NB.
2025-06-13: Our new open access article involving three datasets of our data repository was published in the BioData Mining journal: "DBSCAN and DBCV application to open medical records heterogeneous data for identifying clinically significant clusters of patients with neuroblastoma".
2025-06-06: I added two new datasets: TARGET-NBL and GSE85047 NRC.
2022-10-04: Our open access scientific survey on five datasets of our data repository was published in the Data Science Journal: "A survey on publicly available open datasets of electronic health records (EHRs) of patients with neuroblastoma".
2021-11-07: Our Neuroblastoma Electronic Health Records Open Data Repository website is online.

Submit a dataset

Do you have or do you know a dataset that should be included here? Send me an email at davidechicco(AT)davidechicco.it

Contacts

This website was created by Davide Chicco, who coordinates this project, its articles, and found 4 datasets. The other datasets listed on this website were found by Davide Cangelosi. The scientific interpretation of the clinical features of the datasets was made by Gabriel Cerono and Davide Cangelosi.

You can contact me via email at davidechicco(AT)davidechicco.it

Credits

This website was made and is maintained by Davide Chicco, and is publically available under the Attribution-NonCommercial 4.0 Unported (CC BY-NC 4.0) license. The banner was made by Davide Chicco with images from Wikimedia Commons ("Neuroblastoma cell maturation" by Jensflorian under the CC BY-SA 4.0 license and "Neuroblastoma of the Adrenal Gland" by Ed Uthman under CC BY-SA 2.0) and is available under the same CC BY-NC 4.0 license.



(Last update of this website: 5th September 2025)