The DOI matches its Crossref record; 58 of the 58 references it cites were found in a registry or an index; 52 of the 76 sources its claims cite were checked for support.
A generative AI multi-agent framework with integrated XAI governance for cancer diagnostics: from multi-omics interpretation to lifestyle risk stratification
Open accessAbstract
Background: Cancer diagnostics is being reshaped by rapid advances in artificial intelligence, yet a persistent gap separates computational performance from clinical trust. Systematic reviews confirm that 83% of XAI studies in oncology excluded clinicians from development or evaluation, 87% lacked rigorous assessment of XAI explanations, and no universally accepted quality metrics for XAI outputs currently exist. Concurrently, generative AI (GenAI) is entering oncology at an unprecedented pace, yet it operates largely without formal interpretability governance. Aim: This review aimed to (i) synthesize the documented gaps in XAI applications for cancer diagnostics from peer-reviewed literature, (ii) evaluate the state and limitations of GenAI in oncological settings, and (iii) propose a conceptual framework of three GenAI-powered, XAI-governed agents designed to address these gaps within a systems biology context. Review Findings: A narrative synthesis of peer-reviewed literature published between 2020 and 2026 across PubMed, Scopus, and Web of Science identified four critical, recurrent gaps: systematic exclusion of clinicians from XAI development, the absence of standardized evaluation metrics, incomplete cross-omics explanations, and the near absence of lifestyle-driven XAI models for cancer risk. GenAI is accelerating in oncology but introduces additional safety concerns, including hallucinations, non-deterministic outputs, and the illusion of transparency through chain-of-thought reasoning. Framework Proposal: Three specialized agents are proposed: a Multi-Omics XAI Agent (MO-XAI Agent) for cross-layer biological data interpretation, a Clinician Trust and Communication Agent (CTC Agent) for structured explanation translation and quality scoring, and a Lifestyle-Driven Cancer Risk Stratification Agent (LRS Agent) for modifiable risk factor analysis. Each agent uses a large language model as the computational backbone with SHAP, LIME, or graph-level XAI methods as governance layers. Conclusion: To our knowledge, this framework represents the first conceptual architecture to integrate agentic GenAI with systematic XAI governance for cancer diagnostics, offering a clinically grounded, biologically interpretable, and regulatorily aligned design specification for future implementation research.
Overview
CoChat Summary
TL;DR
This review synthesizes documented gaps in XAI for cancer diagnostics and GenAI limitations in oncology, then proposes a three-agent GenAI/XAI-governed conceptual framework (MO-XAI, CTC, LRS) for multi-omics interpretation, clinician communication, and lifestyle risk stratification. It is a design specification and research agenda, not an empirically validated system.
Key findings
- The narrative synthesis identified four recurrent gaps: clinician exclusion from XAI development (83% of XAI cancer studies excluded clinicians; 73% excluded them from system design), absent standardized evaluation metrics (87% lacked rigorous assessment of XAI explanations), incomplete cross-omics explanations, and near absence of lifestyle-driven XAI models for cancer risk.
- GenAI is accelerating in oncology but introduces safety and interpretability concerns, including hallucinations, non-deterministic outputs, and chain-of-thought reasoning as an illusion of transparency; cited LLM benchmarks include GPT-4 matching pathologist-level error detection (89.5% vs. 88.5%), dermatologist skin lesion classification (84.8% vs. 84.6%), and ovarian cancer staging (97% vs. 88% by radiologists).
- The proposed framework has three agents: MO-XAI for cross-layer multi-omics interpretation using SHAP/GNNExplainer and LLM pathway interpretation; CTC for explanation translation and quality scoring adapted from CLIX-M; and LRS for lifestyle risk stratification using XGBoost, SHAP, and RAG-supported causal annotation.
- Multi-agent coordination is cited as improving most likely diagnosis accuracy from 19.65% to 34.11% with GPT-4; validation pathways include TCGA across 33 cancer types and UK Biobank with approximately 500,000 participants.
Methods
- Structured narrative review, not a systematic meta-analysis, searching PubMed, Scopus, IEEE Xplore, and Web of Science primarily for 2020–2026 publications on XAI, cancer diagnostics, interpretability, SHAP, LIME, Grad-CAM, and multi-omics cancer AI.
- Inclusion required AI applications in cancer diagnosis, prognosis, or treatment decision support with explainability/interpretability; exclusions covered non-oncology, non-AI, or non-explainable predictive models. Findings were synthesized thematically across XAI methods/modalities, clinical application domain, interpretability evaluation strategies, and reported limitations/gaps.
- The framework proposal describes three modular agents sharing an LLM backbone and XAI governance layers, coordinated by an orchestration layer that aggregates intermediate outputs into a Unified Clinical Report, with regulatory alignment to EU AI Act and FDA guidance.
Limitations
- Stated: the work is conceptual and exploratory, includes no empirical datasets for statistical validation, and the framework has not been empirically validated; it should be read as a research agenda requiring multi-institutional collaboration, clinical co-design, implementation, and prospective evaluation.
- Stated: XAI method choices reflect the current evidence base but may change; fairness requires dedicated research; CTC rubric co-design is needed; LRS causal annotations require validation against Mendelian randomization and randomized lifestyle-intervention trials; economic implications have not been formally evaluated.
- Evident from the text: no standardized dataset currently exists for CTC Agent validation, no prospective clinical deployment or cost-effectiveness analysis is possible, and the paper relies on literature synthesis and proposed architecture rather than primary data.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures





Verification
Claims the paper makes
39 Valid · 6 Not valid · 16 Not checked · 47 Own results and interpretations
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“found no research that evaluated explanation fidelity, clinician trust, or usability in real-world settings”
§ A generative AI multi-agent framework with integrated XAI governance for cancer diagnostics: from multi-omics interpretation to lifestyle risk stratification > XAI in cancer diagnostics: current evidence and documented gaps > The clinician exclusion problem
What the sources say
- Disputedcites Abbas et al., 2025 sourceExperimental — accuracy not yet measured
Section 3.4 (page unavailable) reports that 18 of 62 reviewed studies included physician feedback, usability testing, or pilot deployment; a small number integrated XAI tools into clinical dashboards or EHR systems for pilot evaluation. It also describes assessments using trust and usability scales. This contradicts the categorical claim that no research evaluated these aspects in real-world settings, although the passage does not establish that any one study evaluated all three aspects together. (LLM, conf=0.86)
Checked by a reasoning model — may be wrong.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“explanation stability across cancer types remained a major unresolved challenge”
§ A generative AI multi-agent framework with integrated XAI governance for cancer diagnostics: from multi-omics interpretation to lifestyle risk stratification > XAI in cancer diagnostics: current evidence and documented gaps > Multi-omics and cross-layer gaps
What the sources say
- Disputedcites Zuo et al., 2026 sourceExperimental — accuracy not yet measured
The Results (§3.3; page unavailable) report that DeepSHAP was among the most stable methods in the cancer cohorts examined. The composite evaluation (§3.4; page unavailable) ranks it first in explanation stability, contrary to the claim that stability remained a major unresolved challenge for DeepSHAP. Stability was measured across validation folds within each cancer cohort, not as consistency of explanations between cancer types. (LLM, conf=0.86)
Checked by a reasoning model — may be wrong.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“a Graph Neural Network architecture is paired with GNNExplainer to identify the network subgraphs whose activation most strongly influences the cancer risk prediction”
§ A generative AI multi-agent framework with integrated XAI governance for cancer diagnostics: from multi-omics interpretation to lifestyle risk stratification > A proposed agentic XAI framework for cancer diagnostics > Agent 1: the multi-omics XAI agent (MO-XAI agent)
What the sources say
- Not checked — no full text of the sourcecites Zhang and Yin, 2025 source
- Disputedcites Zuo et al., 2026 sourceExperimental — accuracy not yet measured
The Model construction section describes a self-normalizing neural network for cancer survival prediction, not a graph neural network. The Discussion says the study focused exclusively on that architecture and leaves graph neural networks for future investigation; it does not report pairing one with GNNExplainer to identify influential subgraphs. Page numbers were not available in our copy. (LLM, conf=0.90)
Checked by a reasoning model — may be wrong.
- Not matchedcites Ying et al., 2019
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“No validated instrument currently exists that captures both the technical fidelity of an explanation and its clinical relevance.”
§ A generative AI multi-agent framework with integrated XAI governance for cancer diagnostics: from multi-omics interpretation to lifestyle risk stratification > XAI in cancer diagnostics: current evidence and documented gaps > The standardization deficit
What the sources say
- Partly supportedcites Brankovic et al., 2025 sourceExperimental — accuracy not yet measured
The Introduction (page unavailable) says there are no available standardized XAI evaluation metrics and guidelines informed by clinical experts or users, and describes CLIX-M as a provisional guide addressing clinical and technical attributes. That supports the claimed gap, but the paper does not establish the stronger assertion that no validated instrument capturing both attributes exists. (LLM, conf=0.84)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“high SHAP attribution for a feature in a predictive model does not imply that modifying that feature will reduce cancer risk, because SHAP captures statistical association and not causal effect”
§ A generative AI multi-agent framework with integrated XAI governance for cancer diagnostics: from multi-omics interpretation to lifestyle risk stratification > XAI in cancer diagnostics: current evidence and documented gaps > The lifestyle-driven XAI gap
What the sources say
- Supportedcites Coupland et al., 2025 source
The Introduction (page unavailable) says SHAP values relate to the predictive influence of exposures and warns against treating predictive markers as causal mechanisms. The Discussion’s “Explainability & causality” section (page unavailable) reports that SHAP can identify variables inconsistent with simulated causal pathways. Together, these support the claim that high SHAP attribution alone cannot establish that modifying a feature would reduce risk; cancer risk is the citing sentence’s application of that principle. (LLM, conf=0.90)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
48 more claims · 21 with their cited sources checked
Create a free account to see all 108 claims and to verify the 2 references still open.
- Probably not a substantial claim. 33
- It may state two separate claims as one. 30
Citations
Cites
Bray, F., Laversanne, M., Sung, H., Ferlay, J., Siegel, R. L., Soerjomataram, I., & Jemal, A. (2024) · CA: a cancer journal for clinicians · doi:10.3322/caac.21834 · Cited by 27,064 · cited 1×
“Projections from the Global Cancer Observatory indicate a 77% increase in the annual case burden by 2050, driven primarily by demographic aging and the rising prevalence of modifiable risk factors, including obesity, physical inactivity, and tobacco use (Bray et al., 2024).”
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01228-7 · Cited by 6,909
“Why Should I Trust You?”: Explaining the Predictions of Any Classifier
Ribeiro, M., Singh, S., & Guestrin, C. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations · doi:10.18653/v1/n16-3020 · Cited by 6,682
GNNExplainer: Generating Explanations for Graph Neural Networks.
Ying, R., Bourgeois, D., You, J., Žitnik, M., & Leskovec, J. (2019) · PubMed · Cited by 1,446
The imperative for regulatory oversight of large language models (or generative AI) in healthcare
Meskó, B., & Topol, E. J. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00873-0 · Cited by 1,047 · cited 1×
“…innovation in governance frameworks specifically designed for non-deterministic, broadly functional LLM-based medical devices (Ong et al., 2026; Armoundas and Singh, 2026; Meskó and Topol, 2023) provides the regulatory science context within which this framework is offered as a design contribution.”
GNNExplainer: Generating Explanations for Graph Neural Networks
Ying, R., Bourgeois, D., You, J., Zitnik, M., & Leskovec, J. (2019) · arXiv · doi:10.48550/arxiv.1903.03894 · Cited by 850
Dergaa, I., Chamari, K., Zmijewski, P., & Ben Saad, H. (2023) · Biology of Sport · doi:10.5114/biolsport.2023.125623 · Cited by 796 · cited 1×
“…settings (Boussi Rahmouni et al., 2025), and multi-domain empirical evaluations of LLM performance across health contexts (Dergaa et al., 2024a; Dergaa et al., 2024b; Dergaa et al., 2024c; Dergaa et al., 2024d; Dergaa et al., 2023; Dergaa et al., 2024e; Washif et al., 2024; Methnani et al., 2023).”
Self-citationBias recognition and mitigation strategies in artificial intelligence healthcare applications
Hasanzadeh, F., Josephson, C. B., Waters, G., Adedinsewo, D., Azizi, Z., & White, J. A. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01503-7 · Cited by 320 · cited 1×
“Bias recognition and mitigation must be addressed across the complete AI model lifecycle, from training data curation through deployment and longitudinal surveillance (Hasanzadeh et al., 2025).”
Integrative multi-omics approaches in cancer research: from biological networks to clinical subtypes
Heo, Y. J., Hwa, C., Lee, G.-H., Park, J.-M., & An, J.-Y. (2021) · Molecules and Cells · doi:10.14348/molcells.2021.0042 · Cited by 294 · cited 1×
“…the diagnostic data it processes reflects the multi-level organization of cancer: from molecular pathway disruptions captured by omics profiles, to tissue-level features captured by imaging, to organism-level behavioral and metabolic signals captured by lifestyle variables (Heo et al., 2021).”
Metadata
- Authors
- Barki, C., Chouchen, M., Sediri, A., Ceylan, H. İ., Rahmouni, H. B., Muntean, R. I., El-Seedi, H. R., Bragazzi, N. L., & Dergaa, I.
- Affiliations
- Tunis University (TN)
- Research Laboratory of Biophysics and Medical Technologies, The Higher Institute of Medical Technologies of Tunis, University of Tunis El Manar
- Department of Physical Education and Sports Teaching, Faculty of Sports Sciences, Atatürk University
- 1 Decembrie 1918 University (RO)
- Islamic University of Madinah (SA)
- Saarland University (DE)
- University of Jendouba (TN)
- Corresponding author
- Muntean, Raul Ioan
- ORCID
- Venue
- Frontiers in Systems Biology
- Publisher
- Frontiers Media SA
- Published
- 2026-08-03
- Volume
- 6
- Pages
- 1892418-1892418
- ISSN
- 2674-0702 (ISSN-L)
- PMC
- PMC13477903
- OpenAlex
- W7172285805
- Semantic Scholar
- 5809a8efe7ecd3b5ce2665ac0e5c43b12d687413
- Cited by
- 1
- References
- 49
- Citations by year
- 2026: 1
- FWCI
- 0.96
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Frontiers in Systems Biology (publishedVersion, cc-by)
- PubMed (publishedVersion)
- PubMed Central (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (acceptedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Keywords
- generative AI, multi-agent systems, cancer diagnosis, lifestyle risk factors, cancer risk stratification, large language models, SHAP, lime, hallucinations, clinician trust
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: A generative AI multi-agent framework with integrated XAI governance for cancer diagnostics: from multi-omics interpretation to lifestyle risk stratification. https://app.cochat.ai/papers/10.3389/fsysb.2026.1892418
- The paper
- Barki, C., Chouchen, M., Sediri, A., Ceylan, H. İ., Rahmouni, H. B., Muntean, R. I., El-Seedi, H. R., Bragazzi, N. L., & Dergaa, I. (2026). A generative AI multi-agent framework with integrated XAI governance for cancer diagnostics: from multi-omics interpretation to lifestyle risk stratification. Frontiers in Systems Biology. https://doi.org/10.3389/fsysb.2026.1892418
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.