Systematic scoping review of external validation studies of AI pathology models for lung cancer diagnosis
Abstract Clinical adoption of digital pathology-based artificial intelligence models for diagnosing lung cancer has been limited, partly due to lack of robust external validation. This review provides an overview of such tools, their performance and external validation. We systematically searched fo...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-06-01
|
| Series: | npj Precision Oncology |
| Online Access: | https://doi.org/10.1038/s41698-025-00940-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849725441420558336 |
|---|---|
| author | Soumya Arun Mariia Grosheva Mark Kosenko Jan Lukas Robertus Oleg Blyuss Rhian Gabe Daniel Munblit Judith Offman |
| author_facet | Soumya Arun Mariia Grosheva Mark Kosenko Jan Lukas Robertus Oleg Blyuss Rhian Gabe Daniel Munblit Judith Offman |
| author_sort | Soumya Arun |
| collection | DOAJ |
| description | Abstract Clinical adoption of digital pathology-based artificial intelligence models for diagnosing lung cancer has been limited, partly due to lack of robust external validation. This review provides an overview of such tools, their performance and external validation. We systematically searched for external validation studies in medical, engineering and grey literature databases from 1st January 2010 to 31st October 2024. 22 studies were included. Models performed various tasks, including classification of malignant versus non-malignant tissue, tumour growth pattern classification and subtyping of adeno- versus squamous cell carcinomas. Subtyping models were most common and performed highly, with average AUC values ranging from 0.746 to 0.999. Although most studies used restricted datasets, methodological issues relevant to the applicability of models in real-world settings included small and/or non-representative datasets, retrospective studies and case-control studies without further real-world validation. Ultimately, more rigorous external validation of models is warranted for increased clinical adoption. |
| format | Article |
| id | doaj-art-c787ca603a804ec09ee43f7e2516862a |
| institution | DOAJ |
| issn | 2397-768X |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Precision Oncology |
| spelling | doaj-art-c787ca603a804ec09ee43f7e2516862a2025-08-20T03:10:28ZengNature Portfolionpj Precision Oncology2397-768X2025-06-019111110.1038/s41698-025-00940-7Systematic scoping review of external validation studies of AI pathology models for lung cancer diagnosisSoumya Arun0Mariia Grosheva1Mark Kosenko2Jan Lukas Robertus3Oleg Blyuss4Rhian Gabe5Daniel Munblit6Judith Offman7Centre for Cancer Screening, Prevention and Early Diagnosis, Wolfson Institute of Population Health, Queen Mary University of LondonDepartment of Paediatrics and Paediatric Infectious Diseases, Institute of Child’s Health, I.M. Sechenov First Moscow State Medical University, Sechenov UniversityDepartment of Paediatrics and Paediatric Infectious Diseases, Institute of Child’s Health, I.M. Sechenov First Moscow State Medical University, Sechenov UniversityDepartment of Histopathology, Royal Brompton and Harefield, Guy’s and St Thomas’ NHS Foundation TrustCentre for Cancer Screening, Prevention and Early Diagnosis, Wolfson Institute of Population Health, Queen Mary University of LondonCentre for Evaluation and Methods, Wolfson Institute of Population Health, Queen Mary University of LondonDepartment of Paediatrics and Paediatric Infectious Diseases, Institute of Child’s Health, I.M. Sechenov First Moscow State Medical University, Sechenov UniversityCentre for Cancer Screening, Prevention and Early Diagnosis, Wolfson Institute of Population Health, Queen Mary University of LondonAbstract Clinical adoption of digital pathology-based artificial intelligence models for diagnosing lung cancer has been limited, partly due to lack of robust external validation. This review provides an overview of such tools, their performance and external validation. We systematically searched for external validation studies in medical, engineering and grey literature databases from 1st January 2010 to 31st October 2024. 22 studies were included. Models performed various tasks, including classification of malignant versus non-malignant tissue, tumour growth pattern classification and subtyping of adeno- versus squamous cell carcinomas. Subtyping models were most common and performed highly, with average AUC values ranging from 0.746 to 0.999. Although most studies used restricted datasets, methodological issues relevant to the applicability of models in real-world settings included small and/or non-representative datasets, retrospective studies and case-control studies without further real-world validation. Ultimately, more rigorous external validation of models is warranted for increased clinical adoption.https://doi.org/10.1038/s41698-025-00940-7 |
| spellingShingle | Soumya Arun Mariia Grosheva Mark Kosenko Jan Lukas Robertus Oleg Blyuss Rhian Gabe Daniel Munblit Judith Offman Systematic scoping review of external validation studies of AI pathology models for lung cancer diagnosis npj Precision Oncology |
| title | Systematic scoping review of external validation studies of AI pathology models for lung cancer diagnosis |
| title_full | Systematic scoping review of external validation studies of AI pathology models for lung cancer diagnosis |
| title_fullStr | Systematic scoping review of external validation studies of AI pathology models for lung cancer diagnosis |
| title_full_unstemmed | Systematic scoping review of external validation studies of AI pathology models for lung cancer diagnosis |
| title_short | Systematic scoping review of external validation studies of AI pathology models for lung cancer diagnosis |
| title_sort | systematic scoping review of external validation studies of ai pathology models for lung cancer diagnosis |
| url | https://doi.org/10.1038/s41698-025-00940-7 |
| work_keys_str_mv | AT soumyaarun systematicscopingreviewofexternalvalidationstudiesofaipathologymodelsforlungcancerdiagnosis AT mariiagrosheva systematicscopingreviewofexternalvalidationstudiesofaipathologymodelsforlungcancerdiagnosis AT markkosenko systematicscopingreviewofexternalvalidationstudiesofaipathologymodelsforlungcancerdiagnosis AT janlukasrobertus systematicscopingreviewofexternalvalidationstudiesofaipathologymodelsforlungcancerdiagnosis AT olegblyuss systematicscopingreviewofexternalvalidationstudiesofaipathologymodelsforlungcancerdiagnosis AT rhiangabe systematicscopingreviewofexternalvalidationstudiesofaipathologymodelsforlungcancerdiagnosis AT danielmunblit systematicscopingreviewofexternalvalidationstudiesofaipathologymodelsforlungcancerdiagnosis AT judithoffman systematicscopingreviewofexternalvalidationstudiesofaipathologymodelsforlungcancerdiagnosis |