MétaCan
Menu
← Back to cohort

Abstract P1-08-41: Pathologic response prediction to neoadjuvant chemotherapy utilizing pretreatment near infrared imaging and tumor pathologic criteria

2013· article· en· W2091615985 on OpenAlexaff
Quing Zhu, L Wang, Stacey L. Tannenbaum, Andrew Ricci, Patricia DeFusco, Poornima Hegde

Bibliographic record

VenueCancer Research · 2013
Typearticle
Languageen
FieldMedicine
TopicRadiomics and Machine Learning in Medical Imaging
Canadian institutionsUniversity of Manitoba
Fundersnot available
KeywordsMedicineChemotherapyReceiver operating characteristicBiopsyArea under the curveNuclear medicineInternal medicineOncologyPathologyRadiology

Abstract

fetched live from OpenAlex

Abstract Purpose: In previous studies, the utilization of ultrasound guided near infrared diffused light imaging (US-NIR) has shown great potential in predicting and monitoring the pathologic tumor response to neoadjuvant chemotherapy (NAC). The purpose of the current study is to develop a prediction model utilizing pretreatment tumor hemoglobin content measured by US-NIR in conjunction with standard pathologic tumor characteristics to predict pathologic response even before NAC is given. Utilizing a multiple logistic regression model, the sensitivity, specificity, positive and negative predictive values (PPV and NPV), and the area under the receiver operating characteristic curve (AUC) are determined for the models. Materials and Methods: 34 patients’ data were retrospectively analyzed using a multiple logistic regression model to predict response. These patients were split into a training group (23 patients of 24 tumors) and testing group (11 patients of 12 tumors). Tumor vascularity was assessed pre-NAC using US-NIR and measurements of total hemoglobin (tHb), oxygenated (oxyHb), and deoxygenated hemoglobin concentrations (deoxyHb) as well as tumor reduced scatter coefficients acquired before treatment. Tumor pathologic variables including the estrogen (ER) and progesterone (PR) receptors, human epidermal growth factor receptor 2 (HER2) and Nottingham score (mitotic index and grade) were acquired before NAC in biopsy specimens and were also used in the prediction model. The patients’ pathologic response was graded based on the Miller-Payne system as non- and partial-responders (grades 1-3) and near-complete and complete responders (grades 4-5). Results: Utilizing initial tumor pathologic characteristics (grade and receptor status) a sensitivity of 100%, specificity of 73.3%, PPV and NPV of 69.5% and 100%, and AUC of 0.83(95% CI: 0.637-963) were obtained from training data. When pretreatment hemoglobin parameters and reduced scatter coefficients were included as additional predictors in training data, sensitivity, specificity, PPV and NPV improved to 100% and AUC of 1.0 (95% CI: 1.0-1.0). The performance of the predictive models were validated on testing data and corresponding values were 100%, 66.7%, 75.0% and 100%, and AUC of 0.83 (CI: 0.56-1.0) when tumor pathologic parameters alone were used as predictors. While the corresponding values were 100% and AUC of 1.0 (CI: 1.0-1.0) when hemoglobin and reduced scatter parameters were added as predictors. Discussion: These initial findings indicate that combining widely used tumor pathologic variables with hemoglobin and optical scatter functional parameters determined by NIR provides a powerful tool for predicting patient response to preoperative chemotherapy before the initiation of the treatment. With the current trend to treat in the neoadjuvant setting, such a tool will be invaluable for response assessment. Plans are underway to validate this model in larger patient settings and its applicability to non-chemotherapeutic regimens. Citation Information: Cancer Res 2013;73(24 Suppl): Abstract nr P1-08-41.

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)0.003
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 score0.004
Threshold uncertainty score0.012

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.003
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)0.0040.001

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 head0.042
GPT teacher head0.399
Teacher spread0.357 · 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
Published2013
Admission routes1
Has abstractyes

Explore more

Same venueCancer Research→Same topicRadiomics and Machine Learning in Medical Imaging→French-language works237,207→