Select a Region
North America

Advanced Analytics

EVERSANA’s Advanced Data & Analytics Support Real World Evidence (RWE) Research

Advanced Data & Analytics Capabilities

Areas of Research:

  • Weighted comparator cohorts using entropy balancing
    Weighted comparator cohorts using entropy balancing
  • Target & Control cohort development using diagnosis, drug and procedure codes, based on knowledge of clinical manifestation
    Target & Control cohort development using diagnosis, drug and procedure codes, based on knowledge of clinical manifestation
  • Weighted comparator cohorts using entropy balancing
    Weighted comparator cohorts using entropy balancing
  • Longitudinal patient journey; patient journey using mutual information
    Longitudinal patient journey; patient journey using mutual information
  • Machine-learning and predictive modeling to find undiagnosed or rare disease patients (without ICD-10 codes), to predict treatment switch, and risk of disease progression
    Machine-learning and predictive modeling to find undiagnosed or rare disease patients (without ICD-10 codes), to predict treatment switch, and risk of disease progression
  • Cost of illness studies identifying individual cost contributors
    Cost of illness studies identifying individual cost contributors
  • 2-step ML based HEOR identifying risk factors and model association
    2-step ML based HEOR identifying risk factors and model association

In Rare Disease, EVERSANA is Leading the Way

  • +25
    Experience with Different Disease States
  • 7
    Exclusive Rare Disease Products In Market
  • 4
    Active Commercial Engagements in Cell and Gene Therapy

Advanced Analytics Case Studies

  • Identifying Rare Disease HCPs with Omnichannel Targeting

    How A Machine Learning Model Identified Potential Switch Targets Generating ~80% of New Patients For the Brand

    Learn More
  • Finding APDS Patients Using Predictive Models
    Finding APDS Patients Using Predictive Models

    Utilizing Machine Learning to Predict Patients Without a Specific ICD Code

    Learn More
  • Assess MPS II Diagnosis and Treatment Referral Pathways and Identify Potential Patients via Predictive Modeling
    Assess MPS II Diagnosis and Treatment Referral Pathways and Identify Potential Patients via Predictive Modeling

    Machine Learning and Algorithmic Network Mapping in Rare Diseases

    Learn More
  • Predictive Modeling for Treatment of Relapsing-Remitting Multiple Sclerosis
    Predictive Modeling for Treatment of Relapsing-Remitting Multiple Sclerosis

    Understanding First-Line Treatment and Factors Leading to Treatment Switching via Machine Learning

    Learn More
  • Assessing the Telehealth Treatment Landscape and Building Predictive Models to Identify Patients/Providers Most Likely to Use Telehealth
    Assessing the Telehealth Treatment Landscape and Building Predictive Models to Identify Patients/Providers Most Likely to Use Telehealth

    Strengthen the Robustness of a Machine Learning Model by Incorporating EMR Data

    Learn More
  • Identifying Potential High-Risk Factor Arrhythmia Patients Using Predictive Modeling
    Identifying Potential High-Risk Factor Arrhythmia Patients Using Predictive Modeling

    A Robust Approach Combining Clinical, Demographic and Social Determinants of Health Data

    Learn More
  • Scoring and Segmenting Key Opinion Leader Physicians With Innovative and Customizable Machine Learning Techniques
    Scoring and Segmenting Key Opinion Leader Physicians With Innovative and Customizable Machine Learning Techniques

    Influence Mapping for Healthcare Providers in Oncology

    Learn More
  • Improving an AATD Predictive Model Using EMR Data
    Improving an AATD Predictive Model Using EMR Data

    Strengthen the Robustness of a Machine Learning Model by Incorporating EMR Data

    Learn More
  • Use of Machine Learning to Identify Gastroparesis Patients Suitable for Nasal Spray Metoclopramide

    Utilizing Supervised and Unsupervised Learning, With Hierarchical Patient Embeddings to Build Predictive Models

    Learn More
  • Predictive Modeling for Treatment Switching in Paroxysmal Nocturnal Hemoglobinuria Patients
    Predictive Modeling for Treatment Switching in Paroxysmal Nocturnal Hemoglobinuria Patients

    Designing Machine Learning Models From Both Patient and Physician Perspectives

    Learn More

Contact Us

Schedule time with one of our experts to see a demo and learn more about EVERSANA's suite of Data & Analytics Solutions