The healthcare

Big Data Platform

Kythera Wayfinder

Wayfinder is the all-in-one, SaaS big data platform for Healthcare and Life Sciences - unifying data, analytics, and AI workloads into an ecosystem that accelerates the time to insights for the Healthcare and Life Sciences industries.

Big Data Infrastructure.

Big Data Insights.

Wayfinder makes it possible to find granular insights from healthcare data faster. Built on the Databricks Lakehouse Platform, Wayfinder delivers access to over 45 Terabytes of de-identified, remastered claims data and meets the unique data and processing needs of the Healthcare and Life Sciences industries at scale.

With Wayfinder, you can analyze higher-quality claims data to identify rare patients, target providers, build comprehensive patient journeys, and identify market trends, all with granular detail to inform strategies that drive differentiation and growth.

Wayfinder is your big data infrastructure, so you can stop preparing and managing your data and start analyzing.

Easily Connect

Power BI

Quickly Integrate


Your Claims Data

Claims Data



Consumer Data

Consumer Data

Effectively Protect
Security Tokens

Security Tokens

Expert Determination

Expert Determination

Efficiently Access
Quick Instance Setup

Quick Instance Setup

Transparently Invoice
Databricks & AWS on a Single Invoice

Databricks & AWS on 1 Invoice

Enriched Data.
Accurate Analysis.

Through Wayfinder, Kythera curates and delivers over 40 billion rows of de-identified claims data as remastered sources. Our subscription model supplies weekly updates to ever-expanding but not duplicative datasets that empower users to analyze a more holistic view of their market. Wayfinder combines data from disparate vendor feeds into a unified format, creating a foundational data asset for faster, simpler, and more complete analytics. This remastered source data is de-identified, conformed, unified, enriched, continuously updated, and delivered through a flexible, flat Delta data lake.

By processing the data on Wayfinder before delivery, we ensure that the data is ready for analysis — saving you time and removing processing compute costs from your budget. Processing includes:


Partnering with Datavant, Wayfinder transfers de-identified claims tokens to keep PII private.


Automatic processing conforms column naming across billions of rows of data for consistency.


Automatically joins and flattens data from various vendors into a common data lake at the lowest grain of data.


Algorithmically append claims data with additional detail and refinement from curated directories to bring insights into focus.

Curated References.

Reliable Data.

Kythera Labs

Kythera Labs creates, curates, and manages core data dimension directories to support the enrichment of Wayfinder data. These refined and derived data indexes make it possible to append data with more accurate information like provider name, specialties, and relationship to the organization based on NPI.

  • Organization
  • Facility
  • Practitioner

Wayfinder connects and manages reference codesets that support the accuracy of our remastered data and your analysis. References codesets include:

  • ICD
  • CPT
  • NDC
  • Taxonomies
  • Geographies and Markets

Using one or more of our directories and reference sources, Wayfinder uses NPI, service data, and procedure groups to accurately determine the most likely facility of care and resolve errors in rendering and referring providers. Through this data uplift, Wayfinder improves the data quality and reduces the time you spend preparing data for analysis so you can have more confidence in the insights and conclusions reached.

Refined Data Products.

Accelerated Analysis.

Kythera Data

The Most Accurate, Robust Healthcare Data.

Building upon the remastered source data, Kythera curates Patient Event Assets; these derived data products deliver patient-level transaction compilations built for targeted Healthcare and Life Sciences use cases and applications. Analyses using these products are less affected by missingness and errors in raw claims data and deliver more accurate insights faster.

Surgical Events

Surgical Events

The Surgical Events asset delivers visibility into surgical activity nationwide and by market, helping answer questions like:

  • Who is performing surgery in my market?
  • Where are surgeries being performed?
  • How many surgeries are being performed in my market by specialty/service line?
  • Who is referring to whom and for which types of procedures?

Using details from ancillary claims, proprietary data science, and imputation logic, Surgical Events more accurately reflects surgical encounter volume and delivers uplift in encounter volume compared to the analysis of raw claims data by:

  • Filling in information gaps and providing comprehensive insights for each surgical encounter, including details about the patient, procedure, surgeon, facility, immediate referral, and root Primary Care Provider.
  • Providing discharge details (e.g., home health, skilled nursing facility) and a series of binary flags to indicate major or minor surgery, Emergency Department visit related, inter-hospital transfer, or involved associated imaging.
  • Including enhanced referral logic to ensure each surgical event has a referring provider when applicable, providing an uplift in referral capture at the encounter level.
Surgical Events

Hospital Events

The Hospital Events asset delivers details about events occurring in hospitals, helping answer questions like:

  • What is the hospital volume by facility in my market?
  • Which patients are visiting hospitals by market?
  • Why are patients going to the hospital?  

Hospital Events aggregates information associated with claims that occurred in a hospital, combining records from remastered source data assets and Surgical Events to produce a rich data product with more complete insight, including details on:

  • Surgeries, inpatient stays, and other types of visits.
  • The patient, procedure, physician, facility, immediate referral, and emergency department information.
Chronic Conditions

Chronic Conditions

The Chronic Conditions asset houses longitudinal data for each patient diagnosed or treated for one or more chronic conditions helping answer questions like:

  • What chronic conditions diagnoses does a patient carry?
  • What are the affected body systems?
  • How many patients in a given Core Based Statistical Area (CBSA) have chronic conditions?
  • How does that compare to other CBSAs?

Chronic Conditions includes patients diagnosed or treated for any chronic condition defined by Healthcare Cost and Utilization Project (HCUP) and mapped to one of 18 relevant body systems, and details like the diagnosing provider(s) and treating provider(s) for each condition. Using statistical models, Chronic Conditions identifies procedures, revenue codes, diagnostic and imaging procedures, and drugs relevant to treating the chronic conditions that each patient is experiencing, in addition to treatments explicitly listed on claims.

Diagnostic Events

Diagnostic Events

The Diagnostic Events asset details diagnostic procedures and imaging scans by site of service (e.g., hospital or ambulatory) and modality, helping to answer questions like:

  • Which provider ordered the diagnostic procedure?
  • Where was the scan performed?
  • What type of procedure occurred?

Utilizing claims, Diagnostic Events tracks the diagnostic and imaging procedures a patient received, the ordering provider information, and the professional and technical portions of the claim.

Proprietary technology combines provider taxonomies and facility capability determination logic with claims data to identify and correct occurrences of missing claims data and missing information - even when entire claims are unavailable. Diagnostic Events captures a more accurate and complete view of diagnostic activity by incorporating several different types of claims.

Physical Therapy Events

Physical Therapy Events

The Physical Therapy Events asset delivers visibility into physical therapy events, encounters, and episodes, helping to answer questions like:

  • Which provider performed the therapy?
  • What type of therapy was delivered?

Physical Therapy Events focuses on the service rendered, site of care, and referring provider and contains logic to standardize and clean payer information, reducing noise and improving payer analytics use cases.

Oncology Cases

Oncology Cases

The Oncology Case Asset is an extension of the Chronic Conditions Asset focused on delivering detailed diagnostic and treatment information about cancer patients across the country, including surgical, radiation, and medical oncology, helping to answer questions like:

  • Which providers are referring cancer patients to whom?
  • Which organizations are diagnosing and treating patients with specific types of cancer?
  • Are patients coming into or leaving my market for cancer treatment?
  • Which Providers are prescribing or not prescribing a cancer treatment or drug?
  • Who is taking my drug, and what are their outcomes?

Oncology Cases identifies oncology-related ICD-10 diagnoses (as defined by the CDC), then labels cases by cancer description (e.g., lung, brain or prostate) and cancer behavior (e.g., benign, malignant, primary and secondary metastasis, or in situ). Identified cases include details about:

  • The patient, treating organization, and treating physician.
  • Diagnostic events, referral sources, and comorbidities at the time of each treatment.
  • The payer, oncology-related treatments received by each patient and non-oncology comorbidities.

Connect with us to learn more.

If you are ready to uncover hidden insights from healthcare data, we’re here to help.