Completed OBSERVATIONAL NCT06827132

AI medical trial: AstraZeneca evaluates "AI pathology" in real-world lung and breast cancer practice (multinational, observational)

AstraZeneca Updated 2026-09-03

A multinational observational study by AstraZeneca evaluating how computational pathology plus AI algorithms are used in the pathology workup of patients with suspected lung and breast cancer — gauging how far AI has entered routine pathology.

Trial overview (primary data)

  • StatusCompleted
  • ConditionsLung Cancer, Breast Cancer
  • SponsorAstraZeneca
  • Target enrollment603 participants
  • Period2025-10-25 〜 2026-03-19

Key points

  • AstraZeneca evaluates real-world use of AI (computational pathology) in lung/breast cancer pathology
  • An observational study of adoption, not a new-tool performance test
  • Relevant to patient selection (biomarker assessment) for cancer therapies
  • Multinational, 600 participants, 2025–2027, active (not recruiting)
  • It examines not the performance of a new AI tool but how far AI pathology has penetrated actual diagnostic practice.

1Lung and breast cancer diagnosis and pathology

AstraZeneca's clinical study (NCT06827132) evaluates how AI is used in real-world practice in the pathology workup of patients with suspected lung and breast cancer — a multinational observational study.

2Compared against current pathology practice

Per the registry summary, the goal is to evaluate "the current pathology practices and the utilization of computational pathology plus artificial intelligence algorithms in patients with suspected lung and breast cancer." It is observational (no intervention), with target enrollment 600 and a period of October 25, 2025 – May 31, 2027; status as of the check date is active, not recruiting.

3Pathology as the foundation

Pathology — examining tissue under the microscope to confirm cancer type — is central to oncology. Increasingly, slides are digitized (digital pathology) and AI algorithms assist with region extraction, classification, and quantification (computational pathology).

Rather than testing a new tool's performance, this study characterizes how AI pathology is actually adopted into clinical workflow, from a pharmaceutical-company perspective (relevant to patient selection / biomarker assessment for cancer therapies).

4Not testing performance, but examining practice

Medical AI research brings to mind measuring the performance of a new tool. That is not the purpose here.

A study testing a new AI tool's performanceA study examining how it is actually used (this study)
What is evaluated is correctnessWhat is evaluated is penetration into the diagnostic workflow
The object is an algorithm in developmentThe object is current pathology practice
The result bears on whether to adopt a deviceThe result bears on designing patient selection for a drug

Pathology, evaluating tissue under a microscope to establish the presence and type of cancer, is the foundation of cancer care. Digitising slides and using AI algorithms to assist segmentation, classification and quantification — computational pathology — has been spreading. This is a multinational observational study led by a major pharmaceutical company, targeting 600 cases from October 2025 to May 2027.

Why it matters

AI pathology is an area of regulatory approval and adoption in many markets. A major pharma company systematically characterizing its real-world use is a useful read on AI penetration in oncology and on AI for companion diagnostics / patient selection.

FAQ

What is computational (AI) pathology?
Digitizing pathology slides and using AI algorithms to assist with region extraction, classification, and quantification, supporting the pathologist.
Is this a new AI performance trial?
Its focus is characterizing real-world adoption — how widely and how AI pathology is used in practice — from a pharmaceutical-company perspective.

Sources (primary)

Source: ClinicalTrials.gov (U.S. NIH/NLM, public domain). This site does not provide medical advice. Verify the latest and exact details with the official source. This site is not endorsed or certified by the NIH/NLM.

#Medical AI#Clinical trial#AI pathology#Cancer#AstraZeneca#Digital pathology
Disclaimer: This site independently summarizes and classifies information based on official data sources. Always verify the latest and accurate information with the official sources. Content on finance, health, legal, and security is information, not advice. This site is not an official website of the U.S. government.