Large language model integrations in cancer decision-making: a systematic review and meta-analysis
Abstract Large Language Models (LLMs) are increasingly used to support cancer patients and clinicians in decision-making. This systematic review investigates how LLMs are integrated into oncology and evaluated by researchers. We conducted a comprehensive search across PubMed, Web of Science, Scopus,...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-025-01824-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849332280735039488 |
|---|---|
| author | Yuexing Hao Zhiwen Qiu Jason Holmes Corinna E. Löckenhoff Wei Liu Marzyeh Ghassemi Saleh Kalantari |
| author_facet | Yuexing Hao Zhiwen Qiu Jason Holmes Corinna E. Löckenhoff Wei Liu Marzyeh Ghassemi Saleh Kalantari |
| author_sort | Yuexing Hao |
| collection | DOAJ |
| description | Abstract Large Language Models (LLMs) are increasingly used to support cancer patients and clinicians in decision-making. This systematic review investigates how LLMs are integrated into oncology and evaluated by researchers. We conducted a comprehensive search across PubMed, Web of Science, Scopus, and the ACM Digital Library through May 2024, identifying 56 studies covering 15 cancer types. The meta-analysis results suggested that LLMs were commonly used to summarize, translate, and communicate clinical information, but performance varied: the average overall accuracy was 76.2%, with average diagnostic accuracy lower at 67.4%, revealing gaps in the clinical readiness of this technology. Most evaluations relied heavily on quantitative datasets and automated methods without human graders, emphasizing “accuracy” and “appropriateness” while rarely addressing “safety”, “harm”, or “clarity”. Current limitations for LLMs in cancer decision-making, such as limited domain knowledge and dependence on human oversight, demonstrate the need for open datasets and standardized evaluations to improve reliability. |
| format | Article |
| id | doaj-art-fa11081907f84db4bb17d79c6fa9c18d |
| institution | Kabale University |
| issn | 2398-6352 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj-art-fa11081907f84db4bb17d79c6fa9c18d2025-08-20T03:46:15ZengNature Portfolionpj Digital Medicine2398-63522025-07-018111510.1038/s41746-025-01824-7Large language model integrations in cancer decision-making: a systematic review and meta-analysisYuexing Hao0Zhiwen Qiu1Jason Holmes2Corinna E. Löckenhoff3Wei Liu4Marzyeh Ghassemi5Saleh Kalantari6Department of Radiation Oncology, Mayo ClinicCornell UniversityDepartment of Radiation Oncology, Mayo ClinicCornell UniversityDepartment of Radiation Oncology, Mayo ClinicMassachusetts Institute of TechnologyCornell UniversityAbstract Large Language Models (LLMs) are increasingly used to support cancer patients and clinicians in decision-making. This systematic review investigates how LLMs are integrated into oncology and evaluated by researchers. We conducted a comprehensive search across PubMed, Web of Science, Scopus, and the ACM Digital Library through May 2024, identifying 56 studies covering 15 cancer types. The meta-analysis results suggested that LLMs were commonly used to summarize, translate, and communicate clinical information, but performance varied: the average overall accuracy was 76.2%, with average diagnostic accuracy lower at 67.4%, revealing gaps in the clinical readiness of this technology. Most evaluations relied heavily on quantitative datasets and automated methods without human graders, emphasizing “accuracy” and “appropriateness” while rarely addressing “safety”, “harm”, or “clarity”. Current limitations for LLMs in cancer decision-making, such as limited domain knowledge and dependence on human oversight, demonstrate the need for open datasets and standardized evaluations to improve reliability.https://doi.org/10.1038/s41746-025-01824-7 |
| spellingShingle | Yuexing Hao Zhiwen Qiu Jason Holmes Corinna E. Löckenhoff Wei Liu Marzyeh Ghassemi Saleh Kalantari Large language model integrations in cancer decision-making: a systematic review and meta-analysis npj Digital Medicine |
| title | Large language model integrations in cancer decision-making: a systematic review and meta-analysis |
| title_full | Large language model integrations in cancer decision-making: a systematic review and meta-analysis |
| title_fullStr | Large language model integrations in cancer decision-making: a systematic review and meta-analysis |
| title_full_unstemmed | Large language model integrations in cancer decision-making: a systematic review and meta-analysis |
| title_short | Large language model integrations in cancer decision-making: a systematic review and meta-analysis |
| title_sort | large language model integrations in cancer decision making a systematic review and meta analysis |
| url | https://doi.org/10.1038/s41746-025-01824-7 |
| work_keys_str_mv | AT yuexinghao largelanguagemodelintegrationsincancerdecisionmakingasystematicreviewandmetaanalysis AT zhiwenqiu largelanguagemodelintegrationsincancerdecisionmakingasystematicreviewandmetaanalysis AT jasonholmes largelanguagemodelintegrationsincancerdecisionmakingasystematicreviewandmetaanalysis AT corinnaelockenhoff largelanguagemodelintegrationsincancerdecisionmakingasystematicreviewandmetaanalysis AT weiliu largelanguagemodelintegrationsincancerdecisionmakingasystematicreviewandmetaanalysis AT marzyehghassemi largelanguagemodelintegrationsincancerdecisionmakingasystematicreviewandmetaanalysis AT salehkalantari largelanguagemodelintegrationsincancerdecisionmakingasystematicreviewandmetaanalysis |