A systematic review of data sources for artificial intelligence applications in pediatric brain tumors in Europe: implications for bias and generalizability
IntroductionEurope works to improve cancer management through the use of artificialintelligence (AI), and there is a need to accelerate the development of AI applications for childhood cancer. However, the current strategies used for algorithm development in childhood cancer may have bias and limite...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-10-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2023.1285775/full |
| _version_ | 1827781872751476736 |
|---|---|
| author | Alberto Eugenio Tozzi Ileana Croci Paul Voicu Francesco Dotta Giovanna Stefania Colafati Andrea Carai Francesco Fabozzi Giuseppe Lacanna Roberto Premuselli Angela Mastronuzzi |
| author_facet | Alberto Eugenio Tozzi Ileana Croci Paul Voicu Francesco Dotta Giovanna Stefania Colafati Andrea Carai Francesco Fabozzi Giuseppe Lacanna Roberto Premuselli Angela Mastronuzzi |
| author_sort | Alberto Eugenio Tozzi |
| collection | DOAJ |
| description | IntroductionEurope works to improve cancer management through the use of artificialintelligence (AI), and there is a need to accelerate the development of AI applications for childhood cancer. However, the current strategies used for algorithm development in childhood cancer may have bias and limited generalizability. This study reviewed existing publications on AI tools for pediatric brain tumors, Europe's most common type of childhood solid tumor, to examine the data sources for developing AI tools.MethodsWe performed a bibliometric analysis of the publications on AI tools for pediatric brain tumors, and we examined the type of data used, data sources, and geographic location of cohorts to evaluate the generalizability of the algorithms.ResultsWe screened 10503 publications, and we selected 45. A total of 34/45 publications developing AI tools focused on glial tumors, while 35/45 used MRI as a source of information to predict the classification and prognosis. The median number of patients for algorithm development was 89 for single-center studies and 120 for multicenter studies. A total of 17/45 publications used pediatric datasets from the UK.DiscussionSince the development of AI tools for pediatric brain tumors is still in its infancy, there is a need to support data exchange and collaboration between centers to increase the number of patients used for algorithm training and improve their generalizability. To this end, there is a need for increased data exchange and collaboration between centers and to explore the applicability of decentralized privacy-preserving technologies consistent with the General Data Protection Regulation (GDPR). This is particularly important in light of using the European Health Data Space and international collaborations. |
| first_indexed | 2024-03-11T15:24:03Z |
| format | Article |
| id | doaj.art-3576878600004d74b2062c7bdbc5fb54 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-03-11T15:24:03Z |
| publishDate | 2023-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-3576878600004d74b2062c7bdbc5fb542023-10-27T22:36:28ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2023-10-011310.3389/fonc.2023.12857751285775A systematic review of data sources for artificial intelligence applications in pediatric brain tumors in Europe: implications for bias and generalizabilityAlberto Eugenio Tozzi0Ileana Croci1Paul Voicu2Francesco Dotta3Giovanna Stefania Colafati4Andrea Carai5Francesco Fabozzi6Giuseppe Lacanna7Roberto Premuselli8Angela Mastronuzzi9Predictive and Preventive Medicine Research Unit, Bambino Gesù Children’s Hospital, IRCCS, Rome, ItalyPredictive and Preventive Medicine Research Unit, Bambino Gesù Children’s Hospital, IRCCS, Rome, ItalyDepartment of Neuroscience and Imaging, “SS Annunziata” Hospital, “G. D’Annunzio” University, Chieti, ItalyImaging Department, Bambino Gesù Children’s Hospital, IRCCS, Rome, ItalyImaging Department, Bambino Gesù Children’s Hospital, IRCCS, Rome, ItalyDepartment of Neurosciences, Bambino Gesù Children’s Hospital, IRCCS, Rome, ItalyDepartment of Hematology/Oncology, Cell and Gene Therapy, Bambino Gesù Children’s Hospital, IRCCS, Rome, ItalyPredictive and Preventive Medicine Research Unit, Bambino Gesù Children’s Hospital, IRCCS, Rome, ItalyDepartment of Hematology/Oncology, Cell and Gene Therapy, Bambino Gesù Children’s Hospital, IRCCS, Rome, ItalyDepartment of Hematology/Oncology, Cell and Gene Therapy, Bambino Gesù Children’s Hospital, IRCCS, Rome, ItalyIntroductionEurope works to improve cancer management through the use of artificialintelligence (AI), and there is a need to accelerate the development of AI applications for childhood cancer. However, the current strategies used for algorithm development in childhood cancer may have bias and limited generalizability. This study reviewed existing publications on AI tools for pediatric brain tumors, Europe's most common type of childhood solid tumor, to examine the data sources for developing AI tools.MethodsWe performed a bibliometric analysis of the publications on AI tools for pediatric brain tumors, and we examined the type of data used, data sources, and geographic location of cohorts to evaluate the generalizability of the algorithms.ResultsWe screened 10503 publications, and we selected 45. A total of 34/45 publications developing AI tools focused on glial tumors, while 35/45 used MRI as a source of information to predict the classification and prognosis. The median number of patients for algorithm development was 89 for single-center studies and 120 for multicenter studies. A total of 17/45 publications used pediatric datasets from the UK.DiscussionSince the development of AI tools for pediatric brain tumors is still in its infancy, there is a need to support data exchange and collaboration between centers to increase the number of patients used for algorithm training and improve their generalizability. To this end, there is a need for increased data exchange and collaboration between centers and to explore the applicability of decentralized privacy-preserving technologies consistent with the General Data Protection Regulation (GDPR). This is particularly important in light of using the European Health Data Space and international collaborations.https://www.frontiersin.org/articles/10.3389/fonc.2023.1285775/fullartificial intelligenceCNS tumorspediatric oncologychildhood cancerdata sharing |
| spellingShingle | Alberto Eugenio Tozzi Ileana Croci Paul Voicu Francesco Dotta Giovanna Stefania Colafati Andrea Carai Francesco Fabozzi Giuseppe Lacanna Roberto Premuselli Angela Mastronuzzi A systematic review of data sources for artificial intelligence applications in pediatric brain tumors in Europe: implications for bias and generalizability Frontiers in Oncology artificial intelligence CNS tumors pediatric oncology childhood cancer data sharing |
| title | A systematic review of data sources for artificial intelligence applications in pediatric brain tumors in Europe: implications for bias and generalizability |
| title_full | A systematic review of data sources for artificial intelligence applications in pediatric brain tumors in Europe: implications for bias and generalizability |
| title_fullStr | A systematic review of data sources for artificial intelligence applications in pediatric brain tumors in Europe: implications for bias and generalizability |
| title_full_unstemmed | A systematic review of data sources for artificial intelligence applications in pediatric brain tumors in Europe: implications for bias and generalizability |
| title_short | A systematic review of data sources for artificial intelligence applications in pediatric brain tumors in Europe: implications for bias and generalizability |
| title_sort | systematic review of data sources for artificial intelligence applications in pediatric brain tumors in europe implications for bias and generalizability |
| topic | artificial intelligence CNS tumors pediatric oncology childhood cancer data sharing |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2023.1285775/full |
| work_keys_str_mv | AT albertoeugeniotozzi asystematicreviewofdatasourcesforartificialintelligenceapplicationsinpediatricbraintumorsineuropeimplicationsforbiasandgeneralizability AT ileanacroci asystematicreviewofdatasourcesforartificialintelligenceapplicationsinpediatricbraintumorsineuropeimplicationsforbiasandgeneralizability AT paulvoicu asystematicreviewofdatasourcesforartificialintelligenceapplicationsinpediatricbraintumorsineuropeimplicationsforbiasandgeneralizability AT francescodotta asystematicreviewofdatasourcesforartificialintelligenceapplicationsinpediatricbraintumorsineuropeimplicationsforbiasandgeneralizability AT giovannastefaniacolafati asystematicreviewofdatasourcesforartificialintelligenceapplicationsinpediatricbraintumorsineuropeimplicationsforbiasandgeneralizability AT andreacarai asystematicreviewofdatasourcesforartificialintelligenceapplicationsinpediatricbraintumorsineuropeimplicationsforbiasandgeneralizability AT francescofabozzi asystematicreviewofdatasourcesforartificialintelligenceapplicationsinpediatricbraintumorsineuropeimplicationsforbiasandgeneralizability AT giuseppelacanna asystematicreviewofdatasourcesforartificialintelligenceapplicationsinpediatricbraintumorsineuropeimplicationsforbiasandgeneralizability AT robertopremuselli asystematicreviewofdatasourcesforartificialintelligenceapplicationsinpediatricbraintumorsineuropeimplicationsforbiasandgeneralizability AT angelamastronuzzi asystematicreviewofdatasourcesforartificialintelligenceapplicationsinpediatricbraintumorsineuropeimplicationsforbiasandgeneralizability AT albertoeugeniotozzi systematicreviewofdatasourcesforartificialintelligenceapplicationsinpediatricbraintumorsineuropeimplicationsforbiasandgeneralizability AT ileanacroci systematicreviewofdatasourcesforartificialintelligenceapplicationsinpediatricbraintumorsineuropeimplicationsforbiasandgeneralizability AT paulvoicu systematicreviewofdatasourcesforartificialintelligenceapplicationsinpediatricbraintumorsineuropeimplicationsforbiasandgeneralizability AT francescodotta systematicreviewofdatasourcesforartificialintelligenceapplicationsinpediatricbraintumorsineuropeimplicationsforbiasandgeneralizability AT giovannastefaniacolafati systematicreviewofdatasourcesforartificialintelligenceapplicationsinpediatricbraintumorsineuropeimplicationsforbiasandgeneralizability AT andreacarai systematicreviewofdatasourcesforartificialintelligenceapplicationsinpediatricbraintumorsineuropeimplicationsforbiasandgeneralizability AT francescofabozzi systematicreviewofdatasourcesforartificialintelligenceapplicationsinpediatricbraintumorsineuropeimplicationsforbiasandgeneralizability AT giuseppelacanna systematicreviewofdatasourcesforartificialintelligenceapplicationsinpediatricbraintumorsineuropeimplicationsforbiasandgeneralizability AT robertopremuselli systematicreviewofdatasourcesforartificialintelligenceapplicationsinpediatricbraintumorsineuropeimplicationsforbiasandgeneralizability AT angelamastronuzzi systematicreviewofdatasourcesforartificialintelligenceapplicationsinpediatricbraintumorsineuropeimplicationsforbiasandgeneralizability |