Electronic Health Records (EHRs) are detailed clinical patient charts maintained by healthcare providers, focusing on "why" care decisions are made. They contain vitals, lab results, and physician notes. Conversely, claims data represents the billing and payment records submitted to insurance companies, focusing on "what" services were delivered.Key DifferencesPrimary Purpose: EHRs support direct patient care and clinical workflows. Claims data is generated for administrative billing, reimbursement, and financial tracking.Depth & Context: EHRs offer granular, patient-specific clinical data (e.g., severity of illness, specific medication dosages). Claims data summarizes encounters using standardized billing codes (e.g., ICD-10 and CPT codes).Longitudinal View: EHRs are often fragmented across different hospital networks, making it hard to track a patient who visits multiple, unconnected health systems. Claims data provides a comprehensive, cross-network view of a patient’s health journey over time.Researchers and healthcare organizations frequently integrate both data types to achieve a complete view of real-world outcomes and costs.

Claims Data vs EHRs: Distinct but United in Real-World Research
In healthcare research, real-world data from patients is invaluable for gaining insights into disease patterns, treatment effectiveness, and outcomes. Two major sources of real-world data are claims data and electronic health records (EHRs). Both data types have distinct advantages and limitations that impact their utility for different research applications. This article examines the key differences between claims data and EHR data and how researchers can leverage both data sources to answer critical healthcare questions.



What is Claims Data?
Health insurance claims data contains information submitted by healthcare providers to payers to receive reimbursement for services rendered to patients. Claims data includes demographic details about the patient such as age, gender, location, insurance details, diagnosis codes, procedure codes, prescription details, costs and reimbursement information. Claims data provides a longitudinal view of a patient’s interactions across healthcare systems, as it captures data each time a claim is filed over months or years of care (Pivovarov et al., 2019).

Large claims clearinghouses aggregate data from millions of patients across different payers, providing massive real-world datasets. For example, IBM MarketScan databases contain claims information on over 240 million US patients collected from employers, health plans and government health programs (IBM Watson Health, 2022). Other major claims aggregators include Optum Clinformatics, Premier Healthcare Database and PharMetrics Plus.



Key Details Captured in Claims Data
Patient demographics – age, gender, location, insurance details
Diagnoses – ICD diagnosis codes
Procedures – CPT and HCPCS procedure codes
Medications – NDC codes, dose, number of prescription refills
Costs – total and itemized costs, amount paid by payer and patient responsibility
Claims data is extremely valuable for comparative effectiveness research, pharmacoepidemiology, health economics and outcomes research (Berger et al., 2017). The large sample sizes and longitudinal view make claims databases ideal for studying disease incidence, treatment patterns, medication adherence, healthcare costs and utilization across different patient demographics and therapeutic areas.



Limitations of Claims Data
While claims data offers unparalleled scale and longitudinal perspective, researchers must be aware of its limitations:

Diagnosis codes are not indicative of a confirmatory diagnosis; for example, a provider might submit a claim with a diagnosis code that is being considered during a diagnostic workup.
Diagnosis and procedure codes may be inaccurate or incomplete if providers submit improper codes. Important clinical details are missing.
Prescription records lack information about whether the medication was taken as directed or refilled properly.
Available data elements are restricted to what is required for reimbursement. No additional clinical context is provided.
Inability to link family members or track individuals who change payers over time.
Variable data quality and completeness across different claims sources.
Biased sampling based on specific payer population characteristics. May not represent the general population.
Despite these limitations, claims data remains highly useful for epidemiologic studies, health economics research, population health analyses and other applications where large sample sizes are critical. Researchers should account for the nuances of claims data during study design and analysis.



What are Electronic Health Records?
Electronic health records (EHRs) are a digital documentation of patient health information generated throughout clinical care. EHRs are maintained by healthcare organizations and contain various data elements documenting patient encounters, including (Hersh et al., 2013):

Demographics – age, gender, race, ethnicity, language
Medical history – conditions, diagnoses, allergies, immunizations, procedures
Medications – prescriptions, dosing instructions
Vital signs – blood pressure, heart rate, weight, height
Lab test results
Radiology images
Clinical notes – physician progress notes, discharge summaries
A key advantage of EHR data is its rich clinical context. While claims data only captures billing codes, EHRs include detailed narratives, quantitative measures, images and comprehensive documentation of each patient visit. This facilitates better understanding of disease presentation & progression, treatment rationale & response and patient complexity.

EHR databases aggregate records across large healthcare networks to compile real-world data on millions of patients. For instance, Vanderbilt University Medical Center’s Synthetic Derivative database contains de-identified medical records for over 3.7 million subjects and their BioVU® database contains over 310,000 DNA samples linked to de-identified medical records for genomics research (Roden et al., 2008).

EHR Data


Benefits of EHR Data
EHR data enables researchers to (Cowie et al., 2017):

Obtain granular clinical details beyond billing codes
Review physician notes and narratives for patient context
Link lab results, pathology reports, radiology images for additional phenotyping
Study unstructured data through natural language processing
Identify patient cohorts based on complex inclusion/exclusion criteria
Examine longitudinal disease patterns and treatment journeys
EHR data yields insights unattainable through claims data alone. The rich clinical details enable researchers to understand nuances in patient populations, disease manifestation and therapy response.



Challenges with EHR Data
While valued for its clinical context, EHR data also has some inherent limitations:

Incomplete or missing records if providers fail to properly document encounters
Incomplete records if patient receives care at multiple, unlinked healthcare networks
Inconsistent use of structured fields vs free text notes across systems
Lack of national standards in data formats, terminologies and definitions
Biased datasets dependent on specific health system patient population
Difficulty normalizing data across disparate EHR systems
Requires data science skills to analyze unstructured notes and documents
Requires clinical background to appropriately interpret unstructured notes and documents
More resource intensive for data extraction and processing compared to claims data
EHR data analysis requires specialized skills and infrastructure, especially to interpret unstructured data. Despite limitations, EHRs remain an invaluable data source on their own or as complements to other data sources like claims for comprehensive real-world evidence generation.



Integrating Claims and EHR Datasets
Given the complementary strengths of claims data and EHRs, there is significant value in integrating these datasets to conduct robust real-world studies. This can be accomplished by (Maro et al., 2019):

Linking claims and EHR data at the patient level via unique identifiers
Building cohorts based on diagnosis codes from claims data, then reviewing clinical data for each patient in the EHR
Using natural language processing on EHR notes to extract additional details not available in claims
Applying claims analysis algorithms on EHR data to identify lapses in care, adverse events, etc.
Incorporating prescription fills from claims with medication orders in EHRs to assess adherence
Using cost data from claims combined with clinical data for health economic studies

Differences in Claims and EHRs
▪ Claims data are generated from billing codes that
physicians, pharmacies, hospitals, and other healthcare
providers submit to payers for reimbursement (e.g.,
insurance companies, Medicare).
▪ Claims capture medical services provided over time and
across different provider settings for each individual
patient, making it possible to study causal relationships
between drugs and health outcomes.
▪ Claims data provides comprehensive data across all
encounters
Healthcare Claims
▪ EHRs are electronic versions of a patient’s medical
record, that is maintained over time by a provider. EHR
data may also include, but is not limited to, clinical
data relevant to that person’s care under a particular
provider.
▪ EHRs provide detailed clinical data for a single
encounter.
Electronic Healthcare Records
Primary care
physician visit
Dispensing
Diagnosis
Hospital Visit
Procedure
Primary care
physician visit
Prescription
Diagnosis
Hospital Visit
Procedure
Vital Signs
Laboratory
results
EHR 1 EHR 2 EHR 3
Claims and EHRs differ in the depth and breadth of patient information

Considerations for Using Claims Data
Claims-based
data sources
Strengths Limits
▪ Capture healthcare received
across the care continuum
▪ Time stamped data enables
studies to follow patients
longitudinally and observe
progression of health status
▪ Can produce incidence rates,
assess risk factors, and estimate
population risk
▪ High data quality due to use for
financial transactions and
reimbursement
▪ Missing non-prescription data,
certain inpatient medications,
prescriptions paid out of pocket,
drug samples or other care not
resulting in a claim
▪ Often lacking demographics and
health behaviors
▪ Often lagged due to
adjudication processes
▪ Lack of detailed clinical
information (e.g., laboratory
results, imaging procedure
results)
Claims have been the primary source of data to study post-market safety due to reliability and ability to capture longitudinal information.
However, using claims data a

Considerations for Using EHR Data
Strengths Limits
▪ Contains clinically rich data
elements, such as
laboratory results and vital
signs
▪ Improved capture of inpatient
drug use for data that
includes in-patient EHRs
▪ Detailed time-stamped data
within a single healthcare
encounter
▪ Unable to determine if
absence of data is due to
care sought outside
the healthcare system or a
true absence of care
▪ Typically, much smaller
patient sample sizes; may
also be geographically
restricted
▪ Preparation of data for use in
studies is challenging as data
varies across providers, sites,
and systems
EHR-based
data sources
EHRs can provide key clinical information documented by providers during a patient’s healthcare visit. EHR data alone may have limited
ability to follow patient

EHR data vs. claims data and the power of combining the two real-world data sources
August 1, 2022

Author:
Verana Health
Life sciences companies traditionally have relied on medical and pharmacy claims data to gain insights into patient populations and treatment utilization in the real world. This real-world data (RWD) is used to guide the development, launch, and commercialization of new therapeutics and medical devices.

But claims data alone, while of value to clinicians and researchers, is not always the best fit datasource. Claims data captures care utilization across the health care system, yet does not include information regarding treatment outcomes, details of diagnostic evaluations, or the patient experience.

Electronic health records (EHRs), however, may contain information lacking in claims data, including a patient’s medical history, symptoms, comorbidities, treatment outcomes, and more. While EHR data provides a wealth of valuable information, it is not necessarily comprehensive or ready to use in its raw form. Limited data and manual documentation can lead to missing information or incorrect information being entered into a patient’s digital record.
With recent advances in technology and data processing capabilities, life sciences and pharmaceutical companies now have the opportunity to extract meaningful insights from linked EHR and claims databases, helping them attain a more complete view of disease trajectory and management. In a white paper titled, “Strengths and Limitations of Real-world Data from Electronic Health Records and Claims, and the Value of Combining Data from These Sources to Inform Research,” Verana Health shares the differences between EHR and claims data as well as explores several life sciences use cases for combining claims and EHR data.


Building a deeper dataset

Combining EHR and claims datasets helps offset the limitations of each as individual sources and allows clinicians and researchers to see previously undetected patterns or connections. Linking EHR and claims data can help life sciences companies stratify subsets of patients based on treatment outcomes, evaluate market performance and product safety, and better understand how physicians are prescribing a commercial drug and the post-approval treatment patterns across multiple therapeutic areas.


Combining EHR and claims data also offers opportunities to mine documentation of patient symptoms, physical exams, diagnostic evaluations, and therapeutic or device utilization to investigate more complex issues surrounding outcomes.

For life sciences companies, these clinical examples translate into deeper insights across the various stages of the drug development lifecycle, including clinical development, market opportunity, trial planning, post-approval, and commercialization.

Ensuring data quality is key

The vast majority of EHR data (estimated up to 80%) is in unstructured form, such as written progress notes by a doctor or nurse regarding a patient’s response to therapy and the disease’s progression. Capturing that data digitally is essential to applying analysis to unlock clinical and research benefits.

In order to structure this data to make it usable, it requires data cleansing, harmonization, curation, and the ability to clinically interpret text-based documentation and experience with artificial intelligence (AI), such as machine learning (ML) and natural language processing (NLP).

How to find the right source of real-world data: Claims vs. EHR data
Matthew Valko Matthew Valko

With so many types of real-world data available, it can be difficult to select the source that will meet your needs—that is, the data that will help you accurately and efficiently answer your research questions.

For behavioral health research, a field in which forward momentum has been inhibited by a lack of standardized measurements and biomarkers, choosing the right source of real-world data is especially critical in order to gain new insights into these complex conditions.

Retrospective studies are often conducted using real-world data, including:

Claims data, or data from provided healthcare services that are reimbursed by health insurance companies. Claims data are often used for retrospective research on healthcare utilization and other questions.
Data from the electronic health record (EHR), or information that is routinely collected as part of patients’ clinical care. Our NeuroBlu Database contains EHR-derived real-world data representing over 1.4 million patients.
To help you decide which real-world data you should use for your project, we break down below some of the major differences between claims and EHR data.

Representativeness

Pro of claims data:

Nationally representative
Con of claims data:
Certain individuals are not represented in claims, such as the uninsured (estimated at about 8 percent of the U.S. population as of 2022) or those who pay for healthcare out of pocket.
Pro of EHR data:
Because data is captured in routine clinical care, the data are likely to be reflective of all patients who receive care.
Cons of EHR data:
Certain individuals, such as those not receiving treatment, are not represented within EHRs.
Although national representativeness is more difficult to achieve for EHR data, it is a goal we are working toward. Our NeuroBlu Database currently represents over 30 geographically diverse treatment centers, with goals to incorporate data from every state by the end of the year.
Other data features

Pro of claims data:

Because claims data are recorded each time a claim is submitted for reimbursement, data are likely to be more complete than many EHR-derived sources, which rely on providers to accurately and completely fill in the EHR and often suffer from data missingness.
At Holmusk, we are working to improve the completeness of EHR-derived data by going straight to the source: data capture. With HolCare EHR+, our EHR platform designed specifically for behavioral health, we’ve made it easier for providers to record accurate and complete data while still focusing on patient care.

Pro of EHR data:

The type of information captured by claims forms is limited and often much less detailed than what is captured by the EHR. Claims data cover information on demographics, diagnoses, and treatments—but EHR data can often provide even more granular information that provides a more comprehensive view of the patient experience.
It’s important to remember that different sources of EHR data will vary in terms of what kinds of information they can deliver. For example, our NeuroBlu Database contains clinical features from the Mental Status Examination (MSE) such as symptoms, stressors, and outcomes—all valuable contextual data that are obtained through our natural language processing techniques and not always available via traditional EHR sources.

It is clear that both claims data and EHR data have their strengths and weaknesses. Different types of real-world data often complement each other by filling in each other’s gaps—but if you’re faced with selecting one source of real-world data, that choice should be made carefully depending on the questions you’re asking and the goals of your project.

Ready to see if the real-world data within the NeuroBlu Database can help to advance your goals? Get in touch today.

Choosing between claims data and Electronic Health Record (EHR) datasets depends entirely on your research or operational goals. Claims data is best for cross-network utilization tracking, billing, and longitudinal cost analysis, while EHRs excel in providing deep clinical granularity, vital signs, and treatment outcomes.Core ComparisonFeatureHealthcare Claims DataElectronic Health Record (EHR)Primary PurposeReimbursement, billing, and financial tracking.Clinical care, patient monitoring, and medical history.Data GranularityNarrow. Standardized codes (ICD, CPT) without narrative depth.High. Includes clinical notes, lab values, and vitals (e.g., Epic, Cerner).LongitudinalityStrong for tracking patients across multiple insurance providers/hospitals.Fragmented if a patient changes healthcare networks; otherwise deep.TimelinessDelayed. Claims require adjudication and billing cycles.Immediate. Updated continuously with every patient encounter.When to Choose Healthcare Claims DataCost & Utilization Analysis: Use claims when analyzing billed costs, resource utilization, and identifying high-cost patient segments across diverse populations.Broad Population Studies: Claims are highly standardized across insurers, making them easier to de-identify and analyze at a national scale.Medication Refills: Pharmacy claims provide an accurate representation of drug prescription fill dates and adherence patterns over time.When to Choose EHR DataClinical Research & Efficacy: EHRs provide exact measures (e.g., BMI, blood pressure) and clinical progress notes that are vital for researching treatment effectiveness and patient symptoms.Cohort Identification: Use EHR data when analyzing patient cohorts based on highly specific diagnostic evaluations, lab results, or specific physician specialties.Real-time Insights: EHRs provide rapid, point-of-care data needed for clinical decision support and immediate tracking of patient progression.The Best of Both WorldsIncreasingly, life sciences companies and researchers utilize tokenization to link claims-based longitudinal coverage with granular, EHR-derived clinical data. This hybrid approach overcomes the limitations of using either dataset in isolation, offering both cost visibility and clinical depth.