MétaCan
Menu
← Back to cohort
Record W4416140781 · doi:10.1093/neuonc/noaf201.0924

INNV-35. Artificial intelligence in Neuro-Oncology: Mapping the field

2025· article· en· W4416140781 on OpenAlexaff
Sebastian Voigtlaender, Thomas Nelson, Philipp Karschnia, Eugene Vaios, Michelle M. Kim, Philipp Lohmann, Norbert Galldiks, Shekoofeh Azizi, Vivek Natarajan, Michelle Monje, Jörg Dietrich, Sebastian Winter

Bibliographic record

VenueNeuro-Oncology · 2025
Typearticle
Languageen
FieldMedicine
TopicRadiomics and Machine Learning in Medical Imaging
Canadian institutionsGoogle (Canada)
Fundersnot available
KeywordsMetadataField (mathematics)Deep learningPython (programming language)Precision medicineKey (lock)Generative grammar

Abstract

fetched live from OpenAlex

Abstract BACKGROUND Artificial intelligence (AI) is reshaping neuro-oncology research and clinical practice. This abstract summarizes key findings from a peer-reviewed review article (accepted, The Lancet Digital Health), which maps AI applications across the neuro-oncological care trajectory and critically examines major opportunities, challenges, and future directions. METHODS We searched PubMed, ArXiv, and Google Scholar using comprehensive MeSH term-based search strings (e.g., “glioma,” “machine learning,”, “foundation model,” “omics”) from 1/1/2020–12/7/2024. Article metadata were retrieved via Python wrappers (built around PubMed and ArXiv APIs) or manually (from Google Scholar). Records were screened and deduplicated. Studies were selected based on predefined criteria, including explicit use of machine learning (ML) as a core technology, a multicentric or independent validation cohort, and high methodological rigor. RESULTS Screening of 2,675 unique records revealed that current AI-neuro-oncology literature primarily focuses on clinical neuroimaging or omics, often using radiomics, deep learning, or traditional ML, with fewer studies investigating advanced generative models. Analysis of 52 original articles meeting inclusion criteria identified robust AI applications in medical image analysis (e.g., non-invasive diagnosis and response assessment), digital neuropathology, biomarker discovery, tumor phenotyping, patient risk stratification, personalized precision treatment, and neuro-rehabilitative devices. Exploratory approaches include generalist and agentic neuro-oncology assistants, biophysical and causal models (e.g., for neural–cancer dynamics), synthetic data, and drug (target) discovery. Barriers to full integration include major data gaps, limited clinical validation of current tools, and unresolved ethical, legal, and regulatory issues. CONCLUSIONS Promising AI use cases are emerging across the neuro-oncological care trajectory, although current data, validation, and implementation gaps limit clinical deployment and scaling beyond narrowly defined tasks, particularly for advanced generalist models. Closing these gaps will require addressing data collection, standardization and annotation challenges; prioritizing rigorous prospective validation to demonstrate improved clinical outcomes; and grounding tool development in human-centred, ethical, and agile regulatory frameworks for responsible innovation.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.011
metaresearch head score (Gemma)0.043
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesBibliometrics
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: Not applicable
GenreCandidate signal: Review · Consensus signal: none
Teacher disagreement score0.982
Threshold uncertainty score0.297

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0110.043
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0030.002
Bibliometrics0.0180.017
Science and technology studies0.0010.001
Scholarly communication0.0100.004
Open science0.0030.008
Research integrity0.0030.002
Insufficient payload (model declined to judge)0.0890.039

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.031
GPT teacher head0.354
Teacher spread0.323 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

Study designNot applicable
Domainnot available
GenreReview

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueNeuro-Oncology→Same topicRadiomics and Machine Learning in Medical Imaging→French-language works237,207→