CoChat
Sign Up
Cited by 27Artificial Intelligence in Healthcare and EducationArtificial Intelligence ApplicationsArtificial Intelligence in Healthcare

Artificial intelligence agents in healthcare research: A scoping review

Open access
Njei, Basile, Al-Ajlouni, Yazan A., Sidney Kanmounye, Ulrick, Boateng, Sarpong, Loic Nguefang, Guy, Njei, Nelvis, Hamouri, Shadi, Al-Ajlouni, Ahmad F.·2026·PLOS One
DOI 10.1371/journal.pone.0342182PMC PMC12890167
Open this paper in CoChat — free accountOpen PDF

Abstract

Introduction: Artificial Intelligence (AI) agents are rapidly transforming healthcare delivery, enabling real-time decision support and sophisticated patient interaction at scale. However, the scientific landscape of this rapidly growing, multidisciplinary field remains fragmented, with technical innovation outpacing translational research and the establishment of ethical governance frameworks. To address this gap, we conducted a comprehensive scoping review analysis of AI agent research in healthcare. Methods: We followed scoping review methodology (PRISMA-ScR guidelines). Searches across PubMed, Web of Science, arXiv, and medRxiv were conducted from January 2015 to December 7, 2025. Results: The search identified 1,070 records, of which 43 studies were ultimately included after full-text review. Of these 43 included studies, 36 were published in 2025. Systems were categorized into 8 conversational agents, 17 workflow/automation assistants, and 18 multimodal decision support agents. The core mechanism across all archetypes was external tool use (e.g., retrieval-augmented generation or code execution) for grounding and iterative self-correction (e.g., multi-agent debate or self-debugging loops) for refinement. Evaluation settings were predominantly simulated environments or laboratory studies, with few clinical pilots or real-world deployments. Primary reported outcomes focused on process measures (efficiency) and diagnostic accuracy; clinical outcomes and safety endpoints were rarely addressed. Conclusion: Agentic AI systems are rapidly evolving from conceptual frameworks to functional prototypes, primarily targeting complex decision-making and workflow automation. While agentic capabilities are increasingly integrated, research heavily favors simulated evaluations. Future research must prioritize clinical trials and the robust assessment of safety, usability, and clinical efficacy before widespread adoption.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1371/journal.pone.0342182

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Most current biomedical studies of agentic systems fall within conceptual/architectural proposals or controlled evaluations of prototypes, and only a limited subset provides robust external validation or analysis of generalizability across institutions.

    “Most current biomedical studies fall within the first two levels, and only a limited subset provides robust external validation or analysis of generalizability across institutions [26, 38, 41].”

    From The next paradigm in bioinformatics: a review of multi-agent systems and foundational models for end-to-end scientific discovery (2026) · cites this paper as [38]

    Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.

    Experimental — accuracy not yet measured

  • The four PARM components allow a structured comparison of heterogeneous agents, whose maturity varies substantially depending on study design, validation setting, and external reproducibility.

    “The four components allow for a structured comparison of heterogeneous agents, whose maturity varies substantially depending on study design, validation setting, and external reproducibility [26, 38, 41]:”

    From The next paradigm in bioinformatics: a review of multi-agent systems and foundational models for end-to-end scientific discovery (2026) · cites this paper as [38]

    The Methods section, “Classification of agent characteristics and evaluation settings” (page unavailable), classifies heterogeneous agents and distinguishes simulated studies, laboratory studies, clinical pilots, and real-world deployments. The Discussion’s “Limitations” and the Conclusion (pages unavailable) describe differences in study design and validation, with most evaluations still confined to simulated or laboratory settings. The copy does not assess external reproducibility as a dimension of agent maturity; the four PARM components appear to be the citing authors’ framework, not a finding attributed to this review. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

  • Recent advances in biomedical artificial intelligence increasingly highlight the importance of systems capable of coordinating reasoning and tool use in complex, multistage workflows.

    “Recent advances in biomedical artificial intelligence increasingly highlight the importance of systems capable of coordinating reasoning and tool use in complex, multistage workflows [17, 26, 38, 41].”

    From The next paradigm in bioinformatics: a review of multi-agent systems and foundational models for end-to-end scientific discovery (2026) · cites this paper as [38]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

The citation lists haven’t been fetched yet

References 45 · Cited by 27

Research works printed but not linked: 50

  1. [1]Ertel W. Introduction to artificial intelligence. Springer Nature. 2024.
  2. [2]Li Y, Liang S, Zhu B, Liu X, Li J, Chen D, et al. Feasibility and effectiveness of artificial intelligence-driven conversational agents in healthcare interventions: A systematic review of randomized controlled trials. Int J Nurs Stud. 2023; 143: 104494. doi: 10.1016/j.ijnurstu.2023.104494 37146391 · DOI
  3. [3]Tudor Car L, Dhinagaran DA, Kyaw BM, Kowatsch T, Joty S, Theng Y-L, et al. Conversational agents in health care: Scoping review and conceptual analysis. J Med Internet Res. 2020; 22(8):e17158. doi: 10.2196/17158 32763886 PMC7442948 · DOI · Paper page
  4. [4]Xu S, Zhou Y, Liu Z, Wu Z, Zhong T, Zhao H, et al. Towards Next-Generation Medical Agent: How o1 is Reshaping Decision-Making in Medical Scenarios. 2024. doi: 10.48550/arXiv.2411.14461 · DOI
  5. [5]Mahajan A, Powell D. Transforming healthcare delivery with conversational AI platforms. NPJ Digit Med. 2025; 8(1): 581. doi: 10.1038/s41746-025-01968-6 41028209 PMC12484644 · DOI
  6. [6]Martinengo L, Lin X, Jabir AI, Kowatsch T, Atun R, Car J, et al. Conversational agents in health care: Expert interviews to inform the definition, classification, and conceptual framework. J Med Internet Res. 2023; 25:e50767. doi: 10.2196/50767 37910153 PMC10652195 · DOI
  7. [9]Parmar P, Ryu J, Pandya S, Sedoc J, Agarwal S. Health-focused conversational agents in person-centered care: A review of apps. NPJ Digit Med. 2022; 5(1): 21. doi: 10.1038/s41746-022-00560-6 35177772 PMC8854396 · DOI · Paper page
  8. [10]Karunanayake N. Next-generation agentic AI for transforming healthcare. Inf Health. 2025; 2(2): 73– 83. doi: 10.1016/j.infoh.2025.03.001 · DOI · Paper page
  9. [11]Arksey H, O’Malley L. Scoping studies: Towards a methodological framework. Int J Soc Res Methodology. 2005; 8(1): 19– 32. doi: 10.1080/1364557032000119616 · DOI · Paper page
  10. [13]Sejnowski TJ. The Deep Learning Revolution. MIT Press. 2018.
  11. [14]He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. 770– 8. https://openaccess.thecvf.com/content_cvpr_2016/html/He_Deep_Residual_Learning_CVPR_2016_paper.html
  12. [15]Zhao X, Liu W, Yue S, Chen J, Xia D, Bing K, et al. Factors influencing medical students’ adoption of AI educational agents: An extended UTAUT model. BMC Med Educ. 2025; 25(1): 1678. doi: 10.1186/s12909-025-08234-z 41350656 PMC12681116 · DOI
  13. [16]Zisquit M, Shoa A, Oliva R, Perry S, Spanlang B, Brunstein Klomek A, et al. AI-Enhanced virtual reality self-talk for psychological counseling: Formative qualitative study. JMIR Form Res. 2025; 9:e67782. doi: 10.2196/67782 40173447 PMC12004015 · DOI
  14. [17]Kim H, Lee S-Y, You SC, Huh S, Kim J-E, Kim S-T, et al. A bilingual on-premises ai agent for clinical drafting: Implementation report of seamless electronic health records integration in the Y-KNOT project. JMIR Med Inform. 2025; 13:e76848. doi: 10.2196/76848 41284981 PMC12643392 · DOI
  15. [18]Niu Z, Xiao X, Wu W, Cai Q, Jiang Y, Jin W, et al. PharmaBench: Enhancing ADMET benchmarks with large language models. Sci Data. 2024; 11(1): 985. doi: 10.1038/s41597-024-03793-0 39256394 PMC11387650 · DOI
  16. [19]Altermatt FR, Neyem A, Sumonte N, Mendoza M, Villagran I, Lacassie HJ. Performance of single-agent and multi-agent language models in Spanish language medical competency exams. BMC Med Educ. 2025; 25(1): 666. doi: 10.1186/s12909-025-07250-3 40336004 PMC12057199 · DOI
  17. [20]Wang Q, Wang Z, Li M, Ni X, Tan R, Zhang W, et al. A feasibility study of automating radiotherapy planning with large language model agents. Phys Med Biol. 2025; 70(7):10.1088/1361-6560/adbff1. doi: 10.1088/1361-6560/adbff1 40073507 · DOI · Paper page
  18. [22]Soman G, Judy MV, Abou AM. Human guided empathetic AI agent for mental health support leveraging reinforcement learning-enhanced retrieval-augmented generation. Cognitive Systems Research. 2025; 90: 101337. doi: 10.1016/j.cogsys.2025.101337 · DOI
  19. [23]Saini A, Farnoud A. QSP-Copilot: An AI-Augmented platform for accelerating quantitative systems pharmacology model development. CPT Pharmacometrics Syst Pharmacol. 2025; 14(11): 1775– 86. doi: 10.1002/psp4.70127 41159846 PMC12625087 · DOI · Paper page
  20. [24]Chang Y, Li Z, Pham HA, Saju GA. Intelligent agent planning for optimizing parallel MRI reconstruction via a large language model. Annu Int Conf IEEE Eng Med Biol Soc. 2024; 2024: 1– 4. doi: 10.1109/EMBC53108.2024.10782629 40031503 · DOI
  21. [25]Ngo H. Translating Natural Language Questions into SNOMED Expression Constraint Language. Stud Health Technol Inform. 2025; 333: 58– 63. doi: 10.3233/SHTI251576 41235493 · DOI
  22. [26]Cammarota S, Ferrante M, Toschi N. Towards intelligent agents for radiotherapy: Integrating exploration-exploitation with foundation models. Annu Int Conf IEEE Eng Med Biol Soc. 2025; 2025: 1– 7. doi: 10.1109/EMBC58623.2025.11254435 41335754 · DOI
  23. [27]Zhang X, Zayed A, Rehn Hamrin J, Güneysu A, Kuoppamäki S. Exploring Body Image Awareness With a Large Language Model-Based Conversational Agent: Qualitative Study With Young Adults. J Med Internet Res. 2025; 27:e78829. doi: 10.2196/78829 41248495 PMC12670058 · DOI
  24. [28]Luo Y, Shi L, Li Y, Zhuang A, Gong Y, Liu L, et al. From intention to implementation: Automating biomedical research via LLMs. Sci China Inf Sci. 2025; 68(7). doi: 10.1007/s11432-024-4485-0 · DOI
  25. [29]Kumari M, Chauhan R, Jain R, Garg P. A novel context-aware retrieval framework for biomedical knowledge integration with large language models. Information Fusion. 2026; 127: 103902. doi: 10.1016/j.inffus.2025.103902 · DOI
  26. [30]Chen H, Zeng W, Chen C, Cai L, Wang F, Shi Y, et al. EEG Emotion Copilot: Optimizing lightweight LLMs for emotional EEG interpretation with assisted medical record generation. Neural Netw. 2025; 192: 107848. doi: 10.1016/j.neunet.2025.107848 40683189 · DOI
  27. [31]Ferber D, El Nahhas OSM, Wölflein G, Wiest IC, Clusmann J, Leßmann M-E, et al. Development and validation of an autonomous artificial intelligence agent for clinical decision-making in oncology. Nat Cancer. 2025; 6(8): 1337– 49. doi: 10.1038/s43018-025-00991-6 40481323 PMC12380607 · DOI · Paper page
  28. [33]Gorenshtein A, Weisblat Y, Khateb M, Kenan G, Tsirkin I, Fayn G, et al. AI-Based EMG Reporting: A Randomized Controlled Trial. J Neurol. 2025; 272(9): 586. doi: 10.1007/s00415-025-13261-3 40844612 PMC12373542 · DOI
  29. [34]Liu S, Huang SS, McCoy AB, Wright AP, Horst S, Wright A. Optimizing order sets with a large language model-powered multiagent system. JAMA Netw Open. 2025; 8(9):e2533277. doi: 10.1001/jamanetworkopen.2025.33277 40986301 PMC12457977 · DOI
  30. [35]Wang S, Ye Q. Enhancing large language models with AI agents for chronic gastritis management: comprehensive comparative study. JMIR Med Inform. 2025; 13:e73857. doi: 10.2196/73857 41236204 PMC12617012 · DOI
  31. [36]Wang Z, Jin Q, Wei C-H, Tian S, Lai P-T, Zhu Q, et al. GeneAgent: Self-verification language agent for gene-set analysis using domain databases. Nat Methods. 2025; 22(8): 1677– 85. doi: 10.1038/s41592-025-02748-6 40721871 PMC12328209 · DOI
  32. [37]Giske CG, Bressan M, Fiechter F, Hinic V, Mancini S, Nolte O, et al. GPT-4-based AI agents-the new expert system for detection of antimicrobial resistance mechanisms?. J Clin Microbiol. 2024; 62(11):e0068924. doi: 10.1128/jcm.00689-24 39417635 PMC11559085 · DOI
  33. [38]Imaezue GC, Marampelly H. ABCD: A Simulation Method for Accelerating Conversational Agents With Applications in Aphasia Therapy. J Speech Lang Hear Res. 2025; 68(7): 3322– 36. doi: 10.1044/2025_JSLHR-25-00003 40512969 PMC12263185 · DOI
  34. [39]Han S, Choi W. Development of a large language model-based multi-agent clinical decision support system for Korean triage and acuity scale (KTAS)-based triage and treatment planning in emergency departments. 2024. doi: 10.48550/ARXIV.2408.07531 · DOI
  35. [42]Lin W-C, Tseng M-H. Autonomous epidemic and geographic disaster mapping: Assessing the performance of large language models in spatial information integration. JDR. 2025; 20(3): 386– 95. doi: 10.20965/jdr.2025.p0386 · DOI
  36. [43]Lu MY, Chen B, Williamson DFK, Chen RJ, Zhao M, Chow AK, et al. A multimodal generative AI copilot for human pathology. Nature. 2024; 634(8033): 466– 73. doi: 10.1038/s41586-024-07618-3 38866050 PMC11464372 · DOI · Paper page
  37. [44]Matsumoto N, Choi H, Moran J, Hernandez ME, Venkatesan M, Li X, et al. ESCARGOT: An AI agent leveraging large language models, dynamic graph of thoughts, and biomedical knowledge graphs for enhanced reasoning. Bioinformatics. 2025; 41(2):btaf031. doi: 10.1093/bioinformatics/btaf031 39842860 PMC11796095 · DOI
  38. [45]Öğdü ÇU, Arslanoğlu K, Karaköse M. An Adaptive Multi-Agent LLM-Based Clinical Decision Support System Integrating Biomedical RAG and Web Intelligence. IEEE Access. 2025; 13: 167390– 404. doi: 10.1109/access.2025.3613340 · DOI
  39. [46]Pais C, Liu J, Voigt R, Gupta V, Wade E, Bayati M. Large language models for preventing medication direction errors in online pharmacies. Nat Med. 2024; 30(6): 1574– 82. doi: 10.1038/s41591-024-02933-8 38664535 PMC11186789 · DOI
  40. [47]Ruiz Mejia JM, Rawat DB. MedScrubCrew: A medical multi-agent framework for automating appointment scheduling based on patient-provider profile resource matching. Healthcare (Basel). 2025; 13(14): 1649. doi: 10.3390/healthcare13141649 40724673 PMC12294997 · DOI
  41. [48]Wang Y, Hou Y, Yang L, Li S, Tang W, Tang H, et al. Accelerating primer design for amplicon sequencing using large language model-powered agents. Nat Biomed Eng. 2025;:10.1038/s41551-025-01455-z. doi: 10.1038/s41551-025-01455-z 40738975 · DOI
  42. [49]Wang Y, Song H, Teng Y, Huang G, Qian J, Wang H, et al. A generative artificial intelligence copilot for biomedical nanoengineering. ACS Nano. 2025; 19(20): 19394– 407. doi: 10.1021/acsnano.5c03454 40367350 · DOI
  43. [50]Yang E-W, Waldrup B, Velazquez-Villarreal E. Conversational AI agent for precision oncology: AI-HOPE-WNT integrates clinical and genomic data to investigate WNT pathway dysregulation in colorectal cancer. Front Artif Intell. 2025; 8: 1624797. doi: 10.3389/frai.2025.1624797 40860720 PMC12375649 · DOI
  44. [51]Li R, Wang X, Berlowitz D, Mez J, Lin H, Yu H. CARE-AD: A multi-agent large language model framework for Alzheimer’s disease prediction using longitudinal clinical notes. npj Digit Med. 2025; 8(1). doi: 10.1038/s41746-025-01940-4 PMC12375024 40849361 · DOI
  45. [52]Arowolo MO, Abdulsalam SO, Isiaka RM, Igulu KT, Balogun BF, Popescu M, et al. Agentic RAG-Driven Multi-Omics Analysis for PI3K/AKT Pathway Deregulation in Precision Medicine. Algorithms. 2025; 18(9): 545. doi: 10.3390/a18090545 · DOI
  46. [53]Alghamdi HM, Mostafa A. Towards reliable healthcare LLM Agents: A case study for pilgrims during Hajj. Information. 2024; 15(7): 371. doi: 10.3390/info15070371 · DOI
  47. [54]Yang E-W, Waldrup B, Velazquez-Villarreal E. AI-HOPE-TP53: A conversational artificial intelligence agent for pathway-centric analysis of TP53-driven molecular alterations in early-onset colorectal cancer. Cancers (Basel). 2025; 17(17): 2865. doi: 10.3390/cancers17172865 40940961 PMC12427220 · DOI
  48. [55]Vieira-Vieira CH, Kulkarni SS, Zalewski A, Löffler J, Münch J, Kreuchwig A. From data silos to insights: The PRINCE multi-agent knowledge engine for preclinical drug development. Front Artif Intell. 2025; 8: 1636809. doi: 10.3389/frai.2025.1636809 40904819 PMC12401995 · DOI
  49. [56]Yang E-W, Waldrup B, Velazquez-Villarreal E. AI-HOPE-TGFbeta: A Conversational AI Agent for Integrative Clinical and Genomic Analysis of TGF-β Pathway Alterations in Colorectal Cancer to Advance Precision Medicine. AI. 2025; 6(7): 137. doi: 10.3390/ai6070137 · DOI
  50. [57]Deng L, Hu H, Lu K, He P. LLM-augmented multi-agent cooperative framework for medical case retrieval in cardiology. J King Saud Univ Comput Inf Sci. 2025; 37(9). doi: 10.1007/s44443-025-00311-z · DOI · Paper page

Authors
Njei, B., Al-Ajlouni, Y. A., Sidney Kanmounye, U., Boateng, S., Loic Nguefang, G., Njei, N., Hamouri, S., & Al-Ajlouni, A. F.
Affiliations
  • Euclid University (GM)
  • Jordan University of Science and Technology (JO)
Corresponding author
Njei, Basile
ORCID
Venue
PLOS One
Publisher
Public Library of Science (PLoS)
Published
2026-02-10
Volume
21
Issue
2
Pages
e0342182
ISSN
1932-6203 (ISSN-L)
DOI
10.1371/journal.pone.0342182
PMC
PMC12890167
OpenAlex
W7128548038
Cited by
27
References
45
Citations by year
2026: 27
FWCI
16.57
Type
journal article
Language
en
Open access
Licence
Locations
  • PLoS ONE (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • PubMed Central (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
Keywords
AI agents, health care research, chatbots, workflow automation, retrieval-augmented generation, multi-agent debate, self-correction, clinical deployment, AI safety, clinical decision support
MeSH terms
Intelligent Systems, Artificial Intelligence, Delivery of Health Care, Health Services Research, Humans

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review