MétaCan
Menu
← Back to cohort
Record W2898012179 · doi:10.1093/annonc/mdy283.105

Predictive radiomics signature for treatment response to nivolumab in patients (pts) with advanced renal cell carcinoma (RCC)

2018· article· en· W2898012179 on OpenAlexaff
Hao‐Wen Sim, A. B. Stundžia, Sabrina Pierre, Ur Metser, Martin O’Malley, Elena Elimova, Srikala S. Sridhar, Aaron R. Hansen

Bibliographic record

VenueAnnals of Oncology · 2018
Typearticle
Languageen
FieldMedicine
TopicRadiomics and Machine Learning in Medical Imaging
Canadian institutionsPrincess Margaret Cancer Centre
Fundersnot available
KeywordsMedicineNivolumabRenal cell carcinomaRadiomicsRadiologyNephrectomyBiopsyImaging biomarkerClear cell renal cell carcinomaOncologyInternal medicineMagnetic resonance imagingImmunotherapyKidneyCancer

Abstract

fetched live from OpenAlex

Background: Although nivolumab has been widely adopted as a treatment for advanced RCC, only a minority of pts benefit. We aimed to use radiomics as a predictive biomarker. By extracting quantitative information from serial imaging, this non-invasive method captures the spatial and temporal heterogeneity of tumors, more than tissue biopsy. We hypothesized to find an imaging correlate of host immune recognition, characterized by infiltration of the invasive tumor margin by immune effector cells, that would identify pts to benefit from nivolumab. Methods: We retrospectively identified all advanced RCC pts treated with nivolumab at our institution from 2013-2017. Pts were labelled as responders (CR / PR / durable SD) or non-responders based on clinical data. For each pt, lesions were contoured from pre-treatment and first on-treatment CT scans. All lesions were manually contoured in tandem by two trained investigators. This information was used to train a radial basis function support vector machine classifier to learn a prediction rule to distinguish responders versus non-responders. The classifier was internally validated by 10-fold nested cross-validation. Results: 37 pts were identified. Excluded: imaging unavailable = 3, incompatible CT protocols = 7. 104 lesions were contoured from 27 pts. Median age 56 years, 78% male, 89% clear cell histology, 89% prior nephrectomy, 89% prior systemic therapy. 19 responders vs 8 non-responders. Lesions: 60% lymph nodes, 23% lung metastases, 17% renal/adrenal metastases. For the classifier trained on the baseline CT scans, 69% accuracy was achieved. For the classifier trained on the first on-treatment CT scans, 66% accuracy was achieved. Conclusions: Based on preliminary computations, the radiomics signature could discriminate nivolumab responders from non-responders. Additional texture feature analysis with over 72 billion calculations is underway to improve the classifier performance to discriminate tumor responses to immunotherapy. External validation against the comprehensive patient dataset from the International Metastatic Renal Cell Cancer Database Consortium is planned. Legal entity responsible for the study: Dr Hao-Wen Sim and Dr Aaron Hansen. Funding: Awarded $40,000 from peer-reviewed 2017 GUMOC Astellas Research Grant. Disclosure: All authors have declared no conflicts of interest.

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)0.001
metaresearch head score (Gemma)0.002
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.001
Threshold uncertainty score0.003

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.002
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0010.000

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 head0.019
GPT teacher head0.337
Teacher spread0.319 · 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.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

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
Published2018
Admission routes1
Has abstractyes

Explore more

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