Artificial intelligence improves risk stratification for breast cancer recurrence and mortality in women exposed to pesticides: a call for reassessment of stratification criteria - Scorecard - MDSpire

Artificial intelligence improves risk stratification for breast cancer recurrence and mortality in women exposed to pesticides: a call for reassessment of stratification criteria

  • By

  • Isabella Cristina Cazagranda

  • Daniel Rech

  • Stefania Tagliari de Oliveira

  • Fernanda Mara Alves

  • Carolina Panis

  • Guilherme Ferreira Silveira

  • June 3, 2026

  • 0 min

Share

Clinical Scorecard: Machine Learning Enhances Risk Assessment for Breast Cancer Recurrence and Mortality in Women with Pesticide Exposure: A Proposal for Reevaluation of Stratification Standards

At a Glance

CategoryDetail
ConditionBreast Cancer
Key MechanismsIncorporation of pesticide exposure as a risk factor in predictive models.
Target PopulationWomen with breast cancer, particularly those with occupational pesticide exposure.
Care SettingClinical settings in Brazil, particularly in rural areas.

Key Highlights

  • Machine learning models improved prediction of breast cancer recurrence and mortality by 24.12% when including pesticide exposure.
  • Pesticide exposure is not currently considered in the Brazilian Diagnostic and Therapeutic Guidelines for Breast Carcinoma.
  • Women exposed to pesticides showed higher rates of disease recurrence and aggressive tumor subtypes.

Guideline-Based Recommendations

Diagnosis

  • Consider pesticide exposure as a risk factor in breast cancer diagnosis.

Management

  • Re-evaluate treatment protocols to include risk stratification based on pesticide exposure.

Monitoring & Follow-up

  • Monitor breast cancer patients for recurrence and metastasis with consideration of pesticide exposure.

Risks

  • Increased likelihood of aggressive breast cancer and higher rates of metastasis in women exposed to pesticides.

Patient & Prescribing Data

Women with breast cancer, particularly those in agricultural settings.

Tailor treatment strategies based on the inclusion of pesticide exposure in risk assessments.

Clinical Best Practices

  • Utilize machine learning algorithms to enhance predictive accuracy in breast cancer outcomes.
  • Incorporate environmental risk factors, such as pesticide exposure, into clinical guidelines.

Related Resources & Content

Original Source(s)

Related Content