Interpretable machine learning models for oncotypedDX® prediction using clinicopathologic data: a brazilian cohort study

Oncotype DX® (ODX) guides adjuvant chemotherapy decisions in early breast cancer (eBC), but its high-cost limits access in resource-constrained settings. We developed and evaluated an interpretable machine learning model using routinely available clinicopathologic variables to predict ODX recurrence score (RS) and optimize genomic testing. We analyzed 935 Brazilian patients with eBC from the GBECAM cohort (2005–2024). Ridge regression was selected for its predictive performance, interpretability, and computational efficiency. Patients were stratified into risk groups based on predicted probability of RS > 25, and recurrence-free survival was estimated using the Kaplan–Meier method. The model showed good discrimination for identifying RS > 25 (AUROC 0.818 [95% CI, 0.780–0.852]), with sensitivity of 0.556 and specificity of 0.859. The highest-risk quartile contained 60.8% of all RS > 25 cases (observed probability 42.8%), whereas the lowest-risk half had an observed probability of only 4.4%. These findings suggest that up to 75% of patients could be triaged without confirmatory ODX testing, reserving genomic assays for an intermediate-risk subgroup. The Ridge model outperformed previously published clinicopathologic models and may represent a cost-effective strategy to improve ODX testing prioritization and resource allocation.

Authors

Institutions

Publication Details

Journal
npj Breast Cancer
Published
2026-10-26
DOI
https://doi.org/10.1038/s41523-026-01065-1
Primary Topic
Breast Cancer Treatment Studies
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Interpretable machine learning models for oncotypedDX® prediction using clinicopathologic data: a brazilian cohort study

Pedro Henrique Souza, Rafael Aliosha Kaliks, Thais Baccili Cury Megid, Antonio Carlos Buzaid et al.
npj Breast Cancer
Breast Cancer Treatment Studies
article

Interpretable machine learning models for oncotypedDX® prediction using clinicopathologic data: a brazilian cohort study

Pedro Henrique Souza, Rafael Aliosha Kaliks, Thais Baccili Cury Megid, Antonio Carlos Buzaid, Marcelle Goldner Cesca, Zenaide Silva de Souza, Artur Katz, Carlos Henrique dos Anjos, Júlio Antônio Pereira de Araújo, Laura Testa, Juliana Rodrigues Beal, Daniel Negrini Batista, Daniel Fontes Santos De Teive E Argolo, Larissa Matos Almeida Moura, Rudinei Diogo Marques Linck, Daniella Castro Araújo, Débora De Melo Gagliato, Letícia telles Sales, Daniele Xavier Assad, Romualdo Barroso‐Sousa, Max S. Mano, Bruna Los, Andrea Kazumi Shimada, Leandro Jonata de Carvalho Oliveira, Solange Moraes Sanches, Débora Gaudêncio, Mario Machado Lopes, Renata Colombo Bonadio, Tatiana Strava Corrêa, Daniela D. Rosa, Daniel Musse Gomes, Júlia Leal Franco Parisi Marlière, José Bines
article en

Abstract

Oncotype DX® (ODX) guides adjuvant chemotherapy decisions in early breast cancer (eBC), but its high-cost limits access in resource-constrained settings. We developed and evaluated an interpretable machine learning model using routinely available clinicopathologic variables to predict ODX recurrence score (RS) and optimize genomic testing. We analyzed 935 Brazilian patients with eBC from the GBECAM cohort (2005–2024). Ridge regression was selected for its predictive performance, interpretability, and computational efficiency. Patients were stratified into risk groups based on predicted probability of RS > 25, and recurrence-free survival was estimated using the Kaplan–Meier method. The model showed good discrimination for identifying RS > 25 (AUROC 0.818 [95% CI, 0.780–0.852]), with sensitivity of 0.556 and specificity of 0.859. The highest-risk quartile contained 60.8% of all RS > 25 cases (observed probability 42.8%), whereas the lowest-risk half had an observed probability of only 4.4%. These findings suggest that up to 75% of patients could be triaged without confirmatory ODX testing, reserving genomic assays for an intermediate-risk subgroup. The Ridge model outperformed previously published clinicopathologic models and may represent a cost-effective strategy to improve ODX testing prioritization and resource allocation.

npj Breast Cancer
Hospital Israelita Albert Einstein (BR), AC Camargo Hospital (BR), Hospital Moinhos de Vento (BR), Instituto do Câncer do Estado de São Paulo (BR), D’Or Institute for Research and Education (BR), Beneficência Portuguesa de São Paulo (BR), Hospital Universitário de Brasília (BR), Hospital Sírio-Libanês (BR)
Openalex Percentile: Top 17%
Breast Cancer Treatment Studies
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon