Precise Insights

Advanced Data and AI for Lung Cancer

On-demand access to the largest and most sophisticated oncology data for accelerated RWE and improved patient outcomes.

Advanced Data and AI for Lung Cancer

See some of the 1000s of data elements we offer:

Structured Fields

Request a Demo

 

Structured Fields

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

Expert Abstraction

Request a Demo

 

Expert Abstraction

full ngs panel

Complete genomic report with treatment exposure and clinical outcomes

Disease Progression

Directly-observed measures of critical endpoints

Adverse Events

Different types of adverse responses

Histology

Classification into multiple categories

Enriched Data

Request a Demo

 

Enriched Data

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

AI & Model-Based Insights

Request a Demo

 

AI & Model-Based Insights

NSCLC Histology Classifier

Segment histology into four categories

Cancer Subtype

Cancer type when ICD code is unknown

ECOG

Predict oft-missing performance score

Metastatic Status

Impute missing data from unstructured notes

Date of Initial Dx

Impute index event

EGFR Status

Impute specific gene mutation

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

Request Data Count

Explore ConcertAI datasets to see how many patients are in your disease area and meet study criteria.

lung cancer

Research Studies

Our scientists regularly publish leading RWE studies in the fields of clinical development and health economics and outcomes research.

lung cancer research study

Impute Subtype

Cancer subtypes are rarely captured in structured EMR data but are important for clinical outcomes and cost analyses. ConcertAI developed an AI model to identify NSCLC patients from a heterogeneous cohort of lung cancer patients.

See Full Study
Methods

Machine Learning Model

Analysis
  • Treatment patterns
  • Clinical effectiveness
  • Progression-free survival
  • Overall survival
Patient Features
325

Patient Features

  • Lab Tests
  • Staging Information
  • Surgery Information
  • Medications Administered
Results

56,748

Patients labeled as NSCLC or not-NSCLC based on expert nurse abstraction

This Data was divided into three sets:

Train

60%

Train

Test

20%

Test

Validate

20%

Validate

The model improved accuracy:
93%

Test machine learning model

Line

88%

Best-performing rules-based model

The model had strong relevance scores:

Precision

93%

Precision

Recall

99%

Recall

Conclusion

We can develop and validate reliable machine learning models to label lung cancer subtypes. This could save substantial time and effort compared to expert manual curation.

Research for ISPOR, 2020

lung cancer research study

Predict Slow Progressors

Few clinical characteristics of patient with exceptional response to existing cancer therapies are known. ConcertAI trained a deep learning model to predict slow progression, a proxy, in aNSCLC in the second line setting. ​

See Full Study
Methods

Machine Learning Model

Patient Criteria
  • Pathologically confirmed aNSCLC without other primary cancer Dx
  • Started 2nd-line therapy between 2013 and 2017
  • Labeled slow progressors if no evidence of progression or death within 180 days of index
Results

2,205

Patients met selection criteria of the study

patients labeled slow progressors:

Train

19%

The model improved accuracy:
75%

Test machine learning model

Rectangles

66%

Best-performing logistic regression model

The model had strong relevance scores:

Precision

39%

Precision

Recall

60%

Recall

Conclusion

This deep learning model may be useful in discovering novel drivers of favorable response.​

Research for ASCO, 2020