Skip to main content
OpenTrials
Not Yet Recruiting

NCT Number: NCT06309615

Decision Impact Study of PreciseDx Breast

The investigator's developed a digital LDT to predict invasive breast cancer (IBC) recurrence within 6 years by combining histologic features extracted from an H&E image of the patients IBC with clinical data including the patients age, tumor size, stage and number of positive lymph nodes. The development of an artificial-intelligent (AI)-grade provides not only an objective, quantitative advancement of classical breast cancer grading but also improves upon the accuracy and utility of clinical risk. The investigator's sought to understand how such a PreciseDx Breast would be used in clinical practice post-surgical resection for women with early-stage IBC.

Not Yet Recruiting

Trial opening soon.

Get Notified

Key information

Age range

23 year and older

Sex eligibility

Female

Study type

Observational

About this study

Female breast cancer (BC) has surpassed lung cancer as the most commonly diagnosed cancer worldwide, which translates into 24.5% of all cancer diagnoses and 15.5% of all cancer death. In the United States, it is estimated that 290,560 Americans will be diagnosed with breast cancer in 2022 and 43,780 will die of disease. Given these statistics, the 2022 National Comprehensive Cancer Network (NCCN), American Society of Clinical Oncology (ASCO), and College of American Pathologists (CAP) clinical practice guidelines continue to stress the critical importance of the pathology assessment at diagnosis to establish extent of disease and features that reflect a biological potential for recurrence such as histologic grade and stage.

Precise Dx Breast Assay (PDxBR™) is an in vitro prognostic clinically approved test by the NYSDOH to predict breast cancer recurrence for patients diagnosed with early-stage IBC. The test utilizes a digital scan of a representative H&E-stained resection specimen from the patient. Using advances in applied artificial intelligence (AI) outcome-based image analysis, selected features of the invasive cancer are acquired and combined with clinical variables to produce a risk score predicting likelihood of having breast cancer recurrence within 6-years. With the advent of computational methods, the investigator's investigated whether AI interrogation of whole slide images (WSI) could be used to improve on the characterization and accuracy of IBC histopathology. The approach was based on the generation of quantitative, discreet morphology features within a tissue section (Morphology Feature Array, MFA) and the use of machine learning to create AI models that predict risk of recurrence in early-stage disease. The investigator's developed a test that improves risk stratification of IBC relative to the use of clinical features as well as re-classification of standard breast histologic grade into low- and high-risk groups using MFA-enabled AI models.

Who can participate

Healthy volunteers accepted: Yes

Only the study team can determine whether someone qualifies for participation.

Inclusion criteria

  • Invasive breast cancer (ductal / mixed ductal-lobular)

Exclusion criteria

  • Prior history of invasive breast cancer
  • Neoadjuvant therapy

Treatment and study plan

Standard of care

Other

To use the patients age, tumor size, grade, and lymph node status and any genomic tests (i.e. OncotypeDx, MammaPrint etc to determine risk of recurrence,

Primary outcomes

  1. Decision Impact Study of PreciseDx Breast on treating Oncologist

    Time frame: 6-12 months

    Proportion (target; 20%) of medical oncologists who utilized the PDxBR results in their management of patients with IBC including any of the following decisions / actions: i. overall confirmation or adjustment of original management plan, ii. order / defer genomic testing, iii. adjust type, dose, or regimen of endocrine therapy, iv. introduction of chemotherapy in addition to endocrine treatment, v. use radiotherapy etc.

  2. Decision Impact Study of PreciseDx Breast on Diagnostic Pathologist

    Time frame: 6-12 months

    Proportion (target: 20%) of pathologists who utilized the PDxBR results in their routine diagnostic assessment of IBC including any of the following: i. supported and or changed their diagnostic histologic grade (based on the AI-grade provided by the PDxBR assay), ii. provided additional useful information in the histologic assessment of the IBC including the presence of lymphocytes, stromal content etc. iii. found the interactive smart phone accessible digital feature display tool helpful in their understanding and use of the test results in their assessment process.

Secondary outcomes

  1. Decision Impact on long term outcomes

    Time frame: 2-5 years

    Use of NPV, PPV, Sensitivity, Specificity, HR for predicting local-regional, distant metastasis or overall survival.

Study contacts

Contact information is provided by the study sponsor or research team.

Kristian Cruz

CONTACT

[email protected]

6468189330

Michael J Donovan, PhD, MD

CONTACT

[email protected]

6468189330

Sponsors and collaborators

Lead sponsor

Precise Dx, Inc.

Industry

Collaborators

  • Mount Sinai Hospital, New York

Registry information

Official study title

Prospective Clinical Utility / Decision Support Study of an AI-enabled Digital Breast Cancer Test (Precise Dx Breast, PDxBRTM) to Predict Early-stage Breast Cancer Recurrence Within 6 Years

Acronym: PDxBRUTILITY

Important dates

Study start
2025
Primary completion
2026
Study completion
2029
First posted
Mar 13, 2024
Registry last updated
May 29, 2025

OpenTrials presents study information sourced from ClinicalTrials.gov. The official registry record should be consulted for the latest information.

View the official ClinicalTrials.gov record (opens in a new tab)

This listing is for discovery and informational purposes only. It is not medical advice, does not guarantee that a study is recruiting, and does not determine eligibility. Contact the study team and a qualified healthcare professional when considering participation.

Published trials that share one or more normalized conditions with this study.