Skip to content
DraconiticResearch
Search Sources API
186,541 studies31 sourcesUpdated 55 min ago
Peer-reviewedCC BYJournal of pathology informatics

Agentic AI workflows in anatomic pathology: Opportunities and challenges.

  • Andy Ngo1
  • Roland Tian2
  • Amin Mohammad2
  • Jenny L Weon3
  • Simone Arvisais-Anhalt4
  • Jacob Minor1
  • Kenneth Youens1,2
4 affiliations
  1. 1Clinical Informatics Fellowship Program, Baylor Scott & White Health, Temple, TX, United States of America.
  2. 2Department of Pathology, Baylor Scott & White Health, Temple, TX, United States of America.
  3. 3Department of Pathology, UT Southwestern Medical Center, Dallas, TX, United States of America.
  4. 4Department of Laboratory Medicine, University of California, San Francisco, San Francisco, CA, United States of America.
Read full textPDFDOICite

Abstract

Artificial intelligence (AI) in anatomic pathology is dominated by image-based diagnostic applications, but much of the specialty's cognitive work is textual: reviewing clinical history, drafting reports, coordinating testing, and communicating results. Large language models can be useful for many of these tasks, and agentic systems extend their capabilities by retrieving external information, invoking software tools, following task-specific instructions, tracking workflow states, and carrying out complex multi-step tasks under human oversight. This conceptual review outlines key components of agentic AI systems including retrieval augmented generation, tool use, skills, and the so-called "agentic loop"-and applies them to anatomic pathology workflows. Three illustrative design sketches use reflex testing support, workload balancing and case routing, and ancillary test decision support to explain how agentic systems can combine lab information system data, trustworthy knowledge sources, local policy, and explicit human approval gates. We examine considerations for clinical deployment, including interoperability and integration challenges, lifecycle governance and validation, security and safety concerns, and cost and sustainability. Agentic AI offers a plausible and constructive near-term vision for AI in pathology: better-supported diagnosis that allows pathologists to spend more of their time on the judgment, accountability, and genuine care that remain distinctly human.

Related

  1. Agentic AI in Healthcare: Opportunities, Challenges, and Future Directions
    Mourad Gridach, Jay Nanavati, Khaldoun Zine El Abidine +2
    ACM Computing SurveysPeer-reviewedCC BY-NC-ND10 citedEpidemiology & public healthOpenAlex
  2. Current Advances in Spatial Pathology of Nasal Polyps: Challenges, Opportunities for Artificial Intelligence, and Future Directions
    Zi‐Xuan Hua, Xin Luo, Ning Kang +10
    World Journal of Otorhinolaryngology-Head and Neck SurgeryPeer-reviewedCC BYFull textSurgery & anaesthesiaDOAJ
  3. The Radiology Sparring Partner: A PoC Study of Multi-Agentic Workflows for Clinical Decision Support and Teaching
    Schewior Jonas, Ashfaq Anwerdeen Mohamed, Ertürk Birim +4
    Current Directions in Biomedical EngineeringPeer-reviewedCC BY-NC-NDFull textEpidemiology & public healthDOAJ
  4. Challenges and opportunities in emotion dynamics research: an interdisciplinary perspective
    Nikolaos Vasileiadis, Daouia Larabi, Peter de Jonge +1
    PsyArXivPreprintAll rights reservedFull textPsychiatry & mental healthOSF
  5. Editorial: Silver linings: navigating the challenges and opportunities of organ transplantation in an Ageing population
    Thierry Berney, Thierry Berney, Thierry Berney +4
    Transplant InternationalPeer-reviewedCC BYFull textEpidemiology & public healthDOAJ

Cite

BibTeXRIS
BibTeX
@article{ngo2026agentic,
  title = {{Agentic AI workflows in anatomic pathology: Opportunities and challenges.}},
  author = {Andy Ngo and Roland Tian and Amin Mohammad and Jenny L Weon and Simone Arvisais-Anhalt and Jacob Minor and Kenneth Youens},
  journal = {Journal of pathology informatics},
  year = {2026},
  month = sep,
  doi = {10.1016/j.jpi.2026.100718},
  url = {https://europepmc.org/article/MED/42894874},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Agentic AI workflows in anatomic pathology: Opportunities and challenges.
AU  - Andy Ngo
AU  - Roland Tian
AU  - Amin Mohammad
AU  - Jenny L Weon
AU  - Simone Arvisais-Anhalt
AU  - Jacob Minor
AU  - Kenneth Youens
PY  - 2026
DA  - 2026/09/12
JO  - Journal of pathology informatics
DO  - 10.1016/j.jpi.2026.100718
UR  - https://europepmc.org/article/MED/42894874
AB  - Artificial intelligence (AI) in anatomic pathology is dominated by image-based diagnostic applications, but much of the specialty's cognitive work is textual: reviewing clinical history, drafting reports, coordinating testing, and communicating results. Large language models can be useful for many of these tasks, and agentic systems extend their capabilities by retrieving external information, invoking software tools, following task-specific instructions, tracking workflow states, and carrying out complex multi-step tasks under human oversight. This conceptual review outlines key components of agentic AI systems including retrieval augmented generation, tool use, skills, and the so-called "agentic loop"-and applies them to anatomic pathology workflows. Three illustrative design sketches use reflex testing support, workload balancing and case routing, and ancillary test decision support to explain how agentic systems can combine lab information system data, trustworthy knowledge sources, local policy, and explicit human approval gates. We examine considerations for clinical deployment, including interoperability and integration challenges, lifecycle governance and validation, security and safety concerns, and cost and sustainability. Agentic AI offers a plausible and constructive near-term vision for AI in pathology: better-supported diagnosis that allows pathologists to spend more of their time on the judgment, accountability, and genuine care that remain distinctly human.
SN  - 2229-5089
SN  - 2153-3539
ER  -