Precise Insights
Advanced Data and AI for Breast Cancer
On-demand access to the largest and most sophisticated oncology data for accelerated RWE and improved patient outcomes.
labs
Results from variety of patient tests
Visits
Oncology practice visits
Observations
Tumor-related observations plus vitals, biometrics, pain, and more
Procedures
Surgeries, radiation, biopsies, imaging, chemotherapy, etc.
Medications
Start and end dates, brand vs. generic codes, dosage, duration, and cycles
Diagnoses
Disease state, status, severity, and metastasis
Biomarkers
Biomarker testing, results, and timing
Disease Progression
Directly-observed measures of critical endpoints
Adverse Events
Different types of adverse responses
Histology
Classification into multiple categories
Cost & Utilization
Adjudicated costs with linked claims data
Safety, Comorbidities
Pre-cancer and claims charge events
Specialty Pharmacy & Hub
Rx acquisition status details
Payer & Formulary
Drug tiers and coverage
Social Determinants
Social and physical environment factors
HER2 Status
Positive or negative biomarker imputation
HR Status
Positive or negative biomarker imputation
Triple Negative
Positive or negative biomarker imputation
Date of Metastasis
Rules-based imputation of date of metastasis
Metastatic Status
Imputation of missing data from unstructured notes
Date of Initial Dx
Imputation of index event
Line of Therapy
Regimen or progression-based drug classes
Patient Adherence
Identify root cause of product switching
Patient Acquisition
Predict factors driving patients’ brand decision
breast cancer research study
Predict Metastatic Recurrence
Current models predict risk of distant mBC recurrence. Dynamic understanding of this risk can help guide patient care and surveillance decisions. ConcertAI tested multiple dynamic machine learning models to understand risk of recurrence at any point in the patient journey.
See Full StudyMethods
5 Machine Learning Models Were Tested
Patient Features
- Lab Tests
- Age and gender
- Biomarker status
- Surgery
- Radiation
- Tumor grade
- Stage
- Lab tests
- Care plan
- Prior regimen
- Menopausal diagnosis
Results
3,807
Patient records enriched by nurse abstractors
Within 4 Years of Diagnosis:
Patients had metastatic recurrence
The model improved accuracy:
Extremely Random Forest had best overall accuracy
Findings:
Average age at diagnosis
Years of follow-up
Results
308
Eligible Patients
primary cost drivers:
Infused or injected care
Systemic anticancer therapy
Between treatment initiation to surgery:
Monthly cost for neo
Monthly cost for neo+adj
Findings:
Patients received neoadjuvant (neo) but not adjuvant (adj) treatment
Patients received neo and adj treatment