External validation of precisebreast, a digital prognostic test for predicting breast cancer recurrence, in an early-stage cohort from the Netherlands
Abstract Background Current clinical guidelines recommend gene expression profiling to guide treatment in early-stage breast cancer. PreciseBreast (PDxBR) is a digital prognostic tool that integrates artificial intelligence (AI)-derived features from hematoxylin and eosin (H&E) slides with clini...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-08-01
|
| Series: | Breast Cancer Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13058-025-02104-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849225764372742144 |
|---|---|
| author | Pieter J. Westenend Claudia Meurs Gerardo Fernandez Marcel Prastawa Abishek Sainath Madduri Aaron Feliz Juan Carlos Mejias Alexander Shtabsky Xiaozhu Zhang Brandon Veremis Rebecca DeAngel Michael J. Donovan |
| author_facet | Pieter J. Westenend Claudia Meurs Gerardo Fernandez Marcel Prastawa Abishek Sainath Madduri Aaron Feliz Juan Carlos Mejias Alexander Shtabsky Xiaozhu Zhang Brandon Veremis Rebecca DeAngel Michael J. Donovan |
| author_sort | Pieter J. Westenend |
| collection | DOAJ |
| description | Abstract Background Current clinical guidelines recommend gene expression profiling to guide treatment in early-stage breast cancer. PreciseBreast (PDxBR) is a digital prognostic tool that integrates artificial intelligence (AI)-derived features from hematoxylin and eosin (H&E) slides with clinicopathologic data to predict recurrence risk. This study externally validated PDxBR in an independent cohort and compared its performance to other risk models. Methods We retrospectively analyzed PDxBR in a cohort of 739 patients with early-stage hormone receptor-positive, HER2-negative breast cancer (median follow-up of 8.8 years). For each case, one H&E-stained slide was digitized and analyzed to generate recurrence risk scores using the full PDxBR model, as well as image-only and clinical-only variants. A subset of patients who underwent MammaPrint testing was also evaluated. Model performance was assessed by AUC/C-index, hazard ratios, sensitivity, specificity, and negative and positive predictive values (NPV and PPV, respectively). Results PDxBR showed prognostic accuracy in this external cohort (AUC/C-index 0.71, 95% CI: 0.66–0.75). Applying the PDxBR threshold (≥ 58 versus < 58) yielded a hazard ratio of 3.05 (95% CI: 2.1–4.4, p < 0.001), sensitivity 0.70, specificity 0.59, NPV 0.90, and PPV 0.27. PDxBR outperformed the modified Adjuvant! Online clinical model (MINDACT model, p < 0.00001) and effectively reclassified grade 2 tumors into distinct risk groups. Conclusions PDxBR demonstrated robust prognostic performance in an independent cohort, supporting its potential as a scalable, reproducible alternative to genomic assays for individualized risk stratification in early-stage breast cancer. |
| format | Article |
| id | doaj-art-5cc5bc5a6cfe4bb296f6da265e865a0d |
| institution | Kabale University |
| issn | 1465-542X |
| language | English |
| publishDate | 2025-08-01 |
| publisher | BMC |
| record_format | Article |
| series | Breast Cancer Research |
| spelling | doaj-art-5cc5bc5a6cfe4bb296f6da265e865a0d2025-08-24T11:58:43ZengBMCBreast Cancer Research1465-542X2025-08-0127111410.1186/s13058-025-02104-8External validation of precisebreast, a digital prognostic test for predicting breast cancer recurrence, in an early-stage cohort from the NetherlandsPieter J. Westenend0Claudia Meurs1Gerardo Fernandez2Marcel Prastawa3Abishek Sainath Madduri4Aaron Feliz5Juan Carlos Mejias6Alexander Shtabsky7Xiaozhu Zhang8Brandon Veremis9Rebecca DeAngel10Michael J. Donovan11Laboratory of PathologyLaboratory of PathologyPreciseDx, Inc.PreciseDx, Inc.PreciseDx, Inc.PreciseDx, Inc.PreciseDx, Inc.PreciseDx, Inc.PreciseDx, Inc.PreciseDx, Inc.PreciseDx, Inc.PreciseDx, Inc.Abstract Background Current clinical guidelines recommend gene expression profiling to guide treatment in early-stage breast cancer. PreciseBreast (PDxBR) is a digital prognostic tool that integrates artificial intelligence (AI)-derived features from hematoxylin and eosin (H&E) slides with clinicopathologic data to predict recurrence risk. This study externally validated PDxBR in an independent cohort and compared its performance to other risk models. Methods We retrospectively analyzed PDxBR in a cohort of 739 patients with early-stage hormone receptor-positive, HER2-negative breast cancer (median follow-up of 8.8 years). For each case, one H&E-stained slide was digitized and analyzed to generate recurrence risk scores using the full PDxBR model, as well as image-only and clinical-only variants. A subset of patients who underwent MammaPrint testing was also evaluated. Model performance was assessed by AUC/C-index, hazard ratios, sensitivity, specificity, and negative and positive predictive values (NPV and PPV, respectively). Results PDxBR showed prognostic accuracy in this external cohort (AUC/C-index 0.71, 95% CI: 0.66–0.75). Applying the PDxBR threshold (≥ 58 versus < 58) yielded a hazard ratio of 3.05 (95% CI: 2.1–4.4, p < 0.001), sensitivity 0.70, specificity 0.59, NPV 0.90, and PPV 0.27. PDxBR outperformed the modified Adjuvant! Online clinical model (MINDACT model, p < 0.00001) and effectively reclassified grade 2 tumors into distinct risk groups. Conclusions PDxBR demonstrated robust prognostic performance in an independent cohort, supporting its potential as a scalable, reproducible alternative to genomic assays for individualized risk stratification in early-stage breast cancer.https://doi.org/10.1186/s13058-025-02104-8Early-stage breast cancerDigital pathologyArtificial intelligenceRisk stratificationPrognostic modelRecurrence prediction |
| spellingShingle | Pieter J. Westenend Claudia Meurs Gerardo Fernandez Marcel Prastawa Abishek Sainath Madduri Aaron Feliz Juan Carlos Mejias Alexander Shtabsky Xiaozhu Zhang Brandon Veremis Rebecca DeAngel Michael J. Donovan External validation of precisebreast, a digital prognostic test for predicting breast cancer recurrence, in an early-stage cohort from the Netherlands Breast Cancer Research Early-stage breast cancer Digital pathology Artificial intelligence Risk stratification Prognostic model Recurrence prediction |
| title | External validation of precisebreast, a digital prognostic test for predicting breast cancer recurrence, in an early-stage cohort from the Netherlands |
| title_full | External validation of precisebreast, a digital prognostic test for predicting breast cancer recurrence, in an early-stage cohort from the Netherlands |
| title_fullStr | External validation of precisebreast, a digital prognostic test for predicting breast cancer recurrence, in an early-stage cohort from the Netherlands |
| title_full_unstemmed | External validation of precisebreast, a digital prognostic test for predicting breast cancer recurrence, in an early-stage cohort from the Netherlands |
| title_short | External validation of precisebreast, a digital prognostic test for predicting breast cancer recurrence, in an early-stage cohort from the Netherlands |
| title_sort | external validation of precisebreast a digital prognostic test for predicting breast cancer recurrence in an early stage cohort from the netherlands |
| topic | Early-stage breast cancer Digital pathology Artificial intelligence Risk stratification Prognostic model Recurrence prediction |
| url | https://doi.org/10.1186/s13058-025-02104-8 |
| work_keys_str_mv | AT pieterjwestenend externalvalidationofprecisebreastadigitalprognostictestforpredictingbreastcancerrecurrenceinanearlystagecohortfromthenetherlands AT claudiameurs externalvalidationofprecisebreastadigitalprognostictestforpredictingbreastcancerrecurrenceinanearlystagecohortfromthenetherlands AT gerardofernandez externalvalidationofprecisebreastadigitalprognostictestforpredictingbreastcancerrecurrenceinanearlystagecohortfromthenetherlands AT marcelprastawa externalvalidationofprecisebreastadigitalprognostictestforpredictingbreastcancerrecurrenceinanearlystagecohortfromthenetherlands AT abisheksainathmadduri externalvalidationofprecisebreastadigitalprognostictestforpredictingbreastcancerrecurrenceinanearlystagecohortfromthenetherlands AT aaronfeliz externalvalidationofprecisebreastadigitalprognostictestforpredictingbreastcancerrecurrenceinanearlystagecohortfromthenetherlands AT juancarlosmejias externalvalidationofprecisebreastadigitalprognostictestforpredictingbreastcancerrecurrenceinanearlystagecohortfromthenetherlands AT alexandershtabsky externalvalidationofprecisebreastadigitalprognostictestforpredictingbreastcancerrecurrenceinanearlystagecohortfromthenetherlands AT xiaozhuzhang externalvalidationofprecisebreastadigitalprognostictestforpredictingbreastcancerrecurrenceinanearlystagecohortfromthenetherlands AT brandonveremis externalvalidationofprecisebreastadigitalprognostictestforpredictingbreastcancerrecurrenceinanearlystagecohortfromthenetherlands AT rebeccadeangel externalvalidationofprecisebreastadigitalprognostictestforpredictingbreastcancerrecurrenceinanearlystagecohortfromthenetherlands AT michaeljdonovan externalvalidationofprecisebreastadigitalprognostictestforpredictingbreastcancerrecurrenceinanearlystagecohortfromthenetherlands |