{"title":"General context and relevant public datasets available for improving pathways in Paediatric Cancer applying Artificial Intelligence. A review","authors":"","doi":"10.1016/j.ejcped.2024.100196","DOIUrl":null,"url":null,"abstract":"<div><div>Due to the promise of transforming healthcare and medicine that Artificial Intelligence (AI) has posed, the number of applications has increased exponentially. These applications range from screening and disease diagnosis to prognosis, treatment planning, and follow-up. In complex topics such as childhood cancer, these techniques are being expanded with the ambition of improving the quality of care by allowing healthcare professionals to make more informed decisions. However, the adequate application of such techniques heavily depends on the data, which creates a set of challenges including collection, bias, and scarcity among others. Furthermore, ethical, legal, and regulatory frameworks increase even more the difficulties to develop AI-powered solutions. In this paper, we present an exhaustive literature review to identify and analyse public datasets targeting two common childhood cancer types, such as neuroblastoma and nephroblastoma. Moreover, the complex context for the development of AI- based software solutions is outlined. It includes the description of the most relevant techniques to address problems associated with data sharing and training. Finally, a set of code snippets is provided to perform exploratory analysis for the available data.</div></div>","PeriodicalId":94314,"journal":{"name":"EJC paediatric oncology","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"EJC paediatric oncology","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2772610X24000564","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Due to the promise of transforming healthcare and medicine that Artificial Intelligence (AI) has posed, the number of applications has increased exponentially. These applications range from screening and disease diagnosis to prognosis, treatment planning, and follow-up. In complex topics such as childhood cancer, these techniques are being expanded with the ambition of improving the quality of care by allowing healthcare professionals to make more informed decisions. However, the adequate application of such techniques heavily depends on the data, which creates a set of challenges including collection, bias, and scarcity among others. Furthermore, ethical, legal, and regulatory frameworks increase even more the difficulties to develop AI-powered solutions. In this paper, we present an exhaustive literature review to identify and analyse public datasets targeting two common childhood cancer types, such as neuroblastoma and nephroblastoma. Moreover, the complex context for the development of AI- based software solutions is outlined. It includes the description of the most relevant techniques to address problems associated with data sharing and training. Finally, a set of code snippets is provided to perform exploratory analysis for the available data.