Microsoft Healthcare United States

Pangaea Data

Enterprise Knowledge Search · Security and Compliance

Both industries have tried applying AI to resolve this, but due to privacy regulations, they are limited to collaborating on ad-hoc projects with de-identified datasets, which does not help find such missed patients and treat them at scale.

Read the original story Explore all use cases

For instance, Pangaea Data worked with two global pharmaceuticals and the UK’s National Health Service (NHS) to find 6x more (200,000) undiagnosed and miscoded cachectic cancer patients for therapies and trials, which led to improved outcomes for patients halving treatment costs for the NHS (saving £1 billion) and a six-fold increase in revenue for the pharmaceutical sponsors.

Millions of patients across 7,000 hard-to-diagnose conditions remain undiagnosed, for example, up to 90% of patients with Chronic Kidney Disease (CKD) are currently undiagnosed.

Pangaea Data also uses Azure Virtual Machines, Container Instances, Blob Storage, Key Vaults, Microsoft Defender, and Azure Health Data Services for its product development, testing, and deployment which helped ensure the robustness, security, and efficiency of its product.

Pangaea Data has partnered with Microsoft since 2021, joining Microsoft for Startups Founders Hub.

Reported impact

Business outcome

This challenge combined with the limitations of characterizing patients through manual reviews by clinicians ( which has shown to take up to 52% of clinicians’ work days ) or by applying technology based on symptoms using natural language processing (NLP) methods, results in high rates of patients reported to be undiagnosed, misdiagnosed or miscoded across hard-to-diagnose conditions, which leads to .

Solution

Millions of patients across 7,000 hard-to-diagnose conditions remain undiagnosed, for example, up to 90% of patients with Chronic Kidney Disease (CKD) are currently undiagnosed. Both industries have tried applying AI to resolve this, but due to privacy regulations, they are limited to collaborating on ad-hoc projects with de-identified datasets, which does not help find such missed patients and treat them at scale. With the help of Microsoft Azure, Pangaea Data built a scalable AI-powered product platform to discover such missed patients and connect to them. This challenge combined with the limitations of characterizing patients through manual reviews by clinicians ( which has shown to take up to 52% of clinicians’ work days ) or by applying technology based on symptoms using natural language processing (NLP) methods, results in high rates of patients reported to be undiagnosed, misdiagnosed or miscoded across hard-to-diagnose conditions, which leads to .

Solution architecture

6 components · 3 layers

Compute
- Azure AI Provides AI services used by the solution.
- Azure Virtual Machines Runs custom workloads that support the solution.
- Azure Provides the secure, scalable cloud foundation for the solution.
- Azure Container Instances Runs packaged application components in Azure.
Storage
- Azure Blob Storage Stores documents and files used by the application.
Governance
- Azure Key Vault Protects secrets and keys used by the application.

Architecture clues

Both industries have tried applying AI to resolve this, but due to privacy regulations, they are limited to collaborating on ad-hoc projects with de-identified datasets, which does not help find such missed patients and treat them at scale.
However, this collaboration is challenged by strict privacy regulations, which limit partnerships to a project-by-project basis and restrict sharing to de-identified, retrospective datasets only.
Pangaea Data also uses Azure Virtual Machines, Container Instances, Blob Storage, Key Vaults, Microsoft Defender, and Azure Health Data Services for its product development, testing, and deployment which helped ensure the robustness, security, and efficiency of its product.
Recognizing these challenges, Pangaea Data partnered with Microsoft Azure to ensure that patients’ data stays secure and private, while enabling clinicians from healthcare and pharmaceutical providers to efficiently characterize patients based on their records and clinical guidelines, to discover more patients at scale and direct them for appropriate care involving commercial therapies and clinical trials.
Richard Skipworth, Oncologist and Surgeon, NHS Lothian To provide the most appropriate care for patients, healthcare and pharmaceutical providers must collaborate at scale to characterize patients in a financially sustainable and privacy-preserving manner.
Strategic partnership enabled innovative solution The primary challenge Pangaea Data faced was how to locally deploy its product for healthcare providers and pharmaceutical companies at scale, without transacting data to preserve patient privacy.
Through this partnership, Pangaea Data leveraged the Microsoft Commercial Marketplace to scale their go-to-market efforts and create a transactable solution for customers to apply their pre-committed Azure cloud spend to optimize budgets and get faster time-to-value.
With the help of Microsoft Azure, Pangaea Data built a scalable AI-powered product platform to discover such missed patients and connect to them.

Evidence from the source

Both industries have tried applying AI to resolve this, but due to privacy regulations, they are limited to collaborating on ad-hoc projects with de-identified datasets, which does not help find such missed patients and treat them at scale.

Recognizing these challenges, Pangaea Data partnered with Microsoft Azure to ensure that patients’ data stays secure and private, while enabling clinicians from healthcare and pharmaceutical providers to efficiently characterize patients based on their records and clinical guidelines, to discover more patients at scale and direct them for appropriate care involving commercial therapies and clinical trials.

This challenge combined with the limitations of characterizing patients through manual reviews by clinicians ( which has shown to take up to 52% of clinicians’ work days ) or by applying technology based on symptoms using natural language processing (NLP) methods, results in high rates of patients reported to be undiagnosed, misdiagnosed or miscoded across hard-to-diagnose conditions, which leads to .

With the help of Microsoft Azure, Pangaea Data built a scalable AI-powered product platform to discover such missed patients and connect to them.

Transparency Evidence & methodology 90/100 reference value · 87% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value90/100

Problem clarity20/20
Measures whether the customer's operational problem is specific enough to compare.
Implementation depth15/25
Rewards named components, data flow, integrations, and architecture detail.
Outcome specificity20/20
Measures whether the reported benefit is concrete rather than a generic claim.
Quantified impact25/25
3 metrics describe measurable impact.
Deployment scale10/10
Rewards evidence of a live or scaled deployment and meaningful integration scope.

Evidence confidence87%

Source authority20/25
The main evidence is an official vendor-published customer story.
Claim traceability21/25
10 of 12 key fields link to a named source.
Direct evidence20/20
4 direct source quotes retained.
Date provenance10/10
The publication date comes from the source page or publisher.
Source transparency8/10
1 source reference document publisher, URL, authority, retrieval, and supported fields.
Implementation specificity8/10
Rewards source-backed components, data flow, quantified impact, and a specific outcome.

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

Microsoft
Pangaea Data customer story

First-party
https://www.microsoft.com/en/customers/story/1698113064434230412-pangaeadata-azure-openai-service-us

Source type
Vendor-published customer story

Published
Nov 2, 2023
Supports
- Customer
- Business problem
- Solution
- Products
- Solution components
- Data flow
- Integrations
- technical area
- use case category
- Business outcome
- outcome category
- Metrics
- Architecture
- evidence quotes
- Publication date

Date evidence

Published on source page Nov 2, 2023 · Microsoft · First-party
Open date source

Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Similar use cases

See all like this

Microsoft Sep 30, 2024 Buckinghamshire Council Healthcare United Kingdom Tony Ellis, Service Director for IT at Buckinghamshire Council, explains the approach: “As a leading local authority, we wanted to engage sooner rather than later. 10-20% time savings Helping staff to be more productive With the pressure on all public sector organisations to… Customer Service AutomationEnterprise Knowledge Search Microsoft 365 Copilot · Microsoft Copilot Studio · Microsoft Copilot for Microsoft 365

Microsoft Jun 28, 2024 University of Sydney Healthcare United States UofS, however, quickly realized they needed a secure AI solution that individual professors could customize and contextualize to their unique needs. By using Azure OpenAI, UofS can access the latest AI models such as GPT-4 and ensure the prompts and responses… Enterprise Knowledge SearchReal-time Analytics Azure · Azure AI Search · Azure AI Studio

Databricks Sep 11, 2026 Helix Healthcare United States Helix needed to replace a fragmented research environment and niche tooling that made it difficult to search petabytes of genomic and patient data efficiently and securely across teams. petabytes of clinical genomic data Enterprise Knowledge SearchSecurity and Compliance Databricks Data + AI Platform · Genie · Unity Catalog