Resilient Artificial Intelligence in Health: Synthesis and Research Agenda Toward Next-Generation Trustworthy Clinical Decision Support
Open accessPublished version of a preprint
The DOI matches its Crossref record; 56 of the 56 references it cites were found in a registry or an index.
Abstract
Artificial intelligence (AI)–based clinical decision support systems are gaining momentum by relying on a greater volume and variety of secondary use data. However, the uncertainty, variability, and biases in real-world data environments still pose significant challenges to the development of health AI, its routine clinical use, and its regulatory frameworks. Health AI should be resilient against real-world environments throughout its lifecycle, including the training and prediction phases and maintenance during production, and health AI regulations should evolve accordingly. Data quality issues, variability over time or across sites, information uncertainty, human-computer interaction, and fundamental rights assurance are among the most relevant challenges. If health AI is not designed resiliently with regard to these real-world data effects, potentially biased data-driven medical decisions can risk the safety and fundamental rights of millions of people. In this viewpoint, we review the challenges, requirements, and methods for resilient AI in health and provide a research framework to improve the trustworthiness of next-generation AI-based clinical decision support.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures



Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The cited source says what the claim attributes to it.
In the citing paper
“For instance, Sáez et al. [71] introduced a 'Resilient AI Framework' focused on robustness in AI for health, and Nasarian et al. [72] proposed a 'Responsible Clinician-AI Collaboration Framework.'”
From Explainable AI for Clinical Decision Support Systems: Literature Review, Key Gaps, and Research Synthesis (2025) · cites this paper as [71]
The cited source says what the claim attributes to it.
In the citing paper
“For instance, the framework by Sáez et al. [71] prioritizes system resilience, outlining principles to ensure AI is robust against real-world data challenges as a pathway to trustworthiness.”
From Explainable AI for Clinical Decision Support Systems: Literature Review, Key Gaps, and Research Synthesis (2025) · cites this paper as [71]
The cited source says what the claim attributes to it.
In the citing paper
“Sáez, Ferri and GarcíaGómez (2024) similarly locate resilience and trustworthiness at the intersection of technical performance, monitoring, and implementation design.”
From Toward Trustworthy Artificial Intelligence in Law and Public Administration: Transparency, Accountability and Decision Support (2026) · cites this paper as Sáez, Ferri and GarcíaGómez (2024)
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., et al. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.012 · Cited by 10,423
Rajkomar, A., Dean, J., & Kohane, I. (2019) · New England Journal of Medicine · doi:10.1056/nejmra1814259 · Cited by 4,579
Key challenges for delivering clinical impact with artificial intelligence
Kelly, C. J., Karthikesalingam, A., Suleyman, M., Corrado, G., & King, D. (2019) · BMC Medicine · doi:10.1186/s12916-019-1426-2 · Cited by 3,136
Continual lifelong learning with neural networks: A review
Parisi, G. I., Kemker, R., Part, J. L., Kanan, C., & Wermter, S. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.01.012 · Cited by 3,117
A review of uncertainty quantification in deep learning: Techniques, applications and challenges
Abdar, M., Pourpanah, F., Hussain, S., Rezazadegan, D., Liu, L., Ghavamzadeh, M., Fieguth, P., Cao, X., Khosravi, A., Acharya, U. R., et al. (2021) · Information Fusion · doi:10.1016/j.inffus.2021.05.008 · Cited by 3,111 · cited 2×
“In health AI, data-related uncertainty can stem from epistemic or aleatoric factors, including lacking or faulty data or from pure statistical randomness in data or information overlap [35-37].”
Wynants, L., Van Calster, B., Bonten, M. M., Collins, G. S., Debray, T. P., De Vos, M., Haller, M. C., Heinze, G., Moons, K. G., Riley, R. D., et al. (2020) · doi:10.1101/2020.03.24.20041020 · Cited by 3,070
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI
Tjoa, E., & Guan, C. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3027314 · Cited by 2,524
Foundation models for generalist medical artificial intelligence
Moor, M., Banerjee, O., Abad, Z. S. H., Krumholz, H. M., Leskovec, J., Topol, E. J., & Rajpurkar, P. (2023) · Nature · doi:10.1038/s41586-023-05881-4 · Cited by 2,028 · cited 2×
“The related techniques include, but are not limited to, deep learning, ensemble models, and statistical methods, with knowledge acquisition schemes based on learning from scratch and using pretrained or foundation models [15,16].”
Research works printed but not linked: 8
- 10.1136/bmj.m1328 · doi:10.1136/bmj.m1328 · Paper page
- European Union Agency for Fundamental RightsData quality and artificial intelligence: mitigating bias and error to protect fundamental rightsLU: Publications Office20192022-06-01https://data.europa.eu/doi/10.2811/546219 · doi:10.2811/546219
- Sáez, C, 2012, Stud Health Technol Inform, 180, 721
- Quiñonero-Candela, J, 2009, Mass: MIT Press
- Goodfellow, I, 2016, Deep learning
- BengioYDucharmeRVincentPA neural probabilistic language modelAdvances in Neural Information Processing Systems20002024-04-16https://papers.nips.cc/paper_files/paper/2000/hash/728f206c2a01bf572b5940d7d9a8fa4c-Abstract.html
- European CommissionEthics guidelines for trustworthy AIDirectorate-General for Communications Networks, Content and Technology20192024-06-12https://data.europa.eu/doi/10.2759/346720 · doi:10.2759/346720
- 10.48550/arXiv.1602.04938 · arXiv · doi:10.48550/arxiv.1602.04938 · Paper page
Cited by
Salimparsa, M., Sedig, K., Lizotte, D. J., Abdullah, S. S., Chalabianloo, N., & Muanda, F. T. (2025) · Informatics · doi:10.3390/informatics12040119 · Cited by 39
Hwang, S. H., Lee, H., Lee, J. H., Lee, M., Koyanagi, A., Smith, L., Rhee, S. Y., Yon, D. K., & Lee, J. (2024) · Journal of Medical Internet Research · doi:10.2196/52794 · Cited by 33
Bailo, P., Nittari, G., Pesel, G., Basello, E., Spasari, T., & Ricci, G. (2026) · Sci · doi:10.3390/sci8020036 · Cited by 22
Zendehbad, S. A., Ghasemi, J., & Khodadad, F. S. (2025) · Healthcare Technology Letters · doi:10.1049/htl2.70020 · Cited by 29
“The ethical ramifications of TAI will be the center of future research; the principles of transparency and explainability should be the focus of future research [19, 20].”
AI and Machine Learning in Transplantation
Vivek, K., & Papalois, V. E. (2025) · Transplantology · doi:10.3390/transplantology6030023 · Cited by 19
Sang, D., Miao, L., & Wu, Q. (2025) · Scientific Reports · doi:10.1038/s41598-025-27129-z · Cited by 17
“The personalized art therapy program generation algorithm employs a multi-dimensional analysis framework that integrates user profile data, behavioral patterns, and therapeutic objectives to create customized intervention strategies tailored to individual needs and capabilities 33 .”
Singh, A. K., Sharma, K. K., Bajpai, M. K., & Cabezuelo, A. S. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.112374 · Cited by 12
Shaik, T., Tao, X., Xie, H., Li, L., Higgins, N., & Velasquez, J. D. (2025) · Human-Centric Intelligent Systems · doi:10.1007/s44230-025-00104-7 · Cited by 12
Enabling the upgrading of security emergency technology in the AI era
Shang, Y. (2025) · Safety Emergency Science · doi:10.26599/ses.2025.9590003 · Cited by 5
Nantakeeratipat, T. (2026) · Frontiers in Digital Health · doi:10.3389/fdgth.2025.1687820 · Cited by 4
AI for Healthcare Security: The Intersection of Innovation and Resilience
Shukla, A. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-85558-0_6 · Cited by 5
Jain, R., Mungamuri, S. K., & Garg, P. (2025) · The Journal of Precision Medicine Health and Disease · doi:10.1016/j.premed.2025.100003 · Cited by 8
Fernández-Narro, D., Ferri, P., Gutiérrez‐Sacristán, A., Garcia-Gomez, J. M., & Sáez, C. (2025) · JMIR Medical Informatics · doi:10.2196/78309 · Cited by 9
“These variations in data distributions are classified as dataset shifts [11,12] and are especially relevant in a nonstationary environment, such as real-world health data [2,13].”
Self-citationRoggendorf, P., & Волков, А. А. (2025) · International Journal of Health Governance · doi:10.1108/ijhg-11-2024-0140 · Cited by 4
de-Manuel-Vicente, C., Fernández-Narro, D., Blanes-Selva, V., Garcia-Gomez, J. M., & Sáez, C. (2024) · medRxiv · doi:10.1101/2024.07.17.24310418 · Cited by 5
Self-citationFerri, P., Sáez, C., Castro, A. F.-D., Sánchez-Cuesta, P., & Garcia-Gomez, J. M. (2025) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2025.103264 · Cited by 3
Self-citationAI Systems for Physicians: A Review from Socio-technical and Human-Computer Interaction Perspectives
Young, J. W., & Nah, F. F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-13167-6_12 · Cited by 1
An Explainable Deep Learning Framework for Brain Tumor Detection Using MRI Images
Ullah, A., Akhtar, N., Hameed, S., Sajid, H. U., Noreen, H., & Hasnain, M. (2026) · VFAST Transactions on Software Engineering · doi:10.21015/vtse.v14i1.2335 · Cited by 2
Rahmani, A. H., & Sarwar, T. (2026) · Diagnostics · doi:10.3390/diagnostics16172799 · Cited by 1
Pasupuleti, M. K. (2026) · International Journal of Academic and Industrial Research Innovations(IJAIRI) · doi:10.62311/nesx/rp-1-28-30032026
Fernández-Narro, D., Ferri, P., Gutiérrez‐Sacristán, A., Garcia-Gomez, J. M., & Sáez, C. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5196124
Self-citationImpact of Artificial Intelligence on the Gastroenterology Workforce and Practice
Soroush, A., Sabnis, S. P., Mehta, S. J., & Siddique, S. M. (2025) · Clinical Gastroenterology and Hepatology · doi:10.1016/j.cgh.2025.04.023
Towards reproducible and high-impact machine learning in health: an editorial
Sun, J. (2025) · Machine Learning Health · doi:10.1088/3049-477x/adeb8d
Amalakanti, S., Avula, V. C. R., & Jillella, J. P. (2025) · Archives of Mental Health · doi:10.4103/amh.amh_35_25
Alqarni, A. (2025) · Intelligent Information Management · doi:10.4236/iim.2025.176013
Diaconescu, B. M., Gurzu, B., Sava, C., Sava, C., Sfarghiu, I., Luchian, D., & Gurzu, I. L. (2025) · Romanian Journal of Occupational Medicine · doi:10.2478/rjom-2025-0001
Yi, J., Ryu, J., Tú, T. T., Park, S., Jeong, J. C., Chin, H. J., Kim, K., & Kim, S. (2026) · Kidney Medicine · doi:10.1016/j.xkme.2026.101327
Wu, M. (2026) · Springer eBooks · doi:10.1007/978-3-032-15872-7_1
An Evidence-First Reference Model for Trustworthy AI in Business Information Systems
Tiltack, T. O., Dong, Y., Yu, K., & Chen, F. (2026) · Lecture notes in business information processing · doi:10.1007/978-3-032-26363-6_7 · Cited by 1
Iqbal, A., Arif, S., Husnain, G., & Ayouni, S. (2026) · Frontiers in Neuroinformatics · doi:10.3389/fninf.2026.1799307 · Cited by 1
Romero-García, N., Montosa-i-Micó, V., Fernández-Narro, D., García‐Gómez, J. M., Hurtado, L., PASSARIELLO, E., Taccone, F. S., Robba, C., Chandrasekhar, R., Orun, O. M., et al. (2026) · Intensive Care Medicine Experimental · doi:10.1186/s40635-026-00922-4
Self-citationClinical Artificial Intelligence Systems in Dentistry: Designing for Safe Human-AI Collaboration
Hegde, S., & Vasa, R. (2026) · Artificial intelligence · doi:10.5772/intechopen.1015701
AI for Data Cleaning, Annotation, and Curation: Trust, Transparency, and Auditability
Jain, R., Suthar, O. P., Pahuja, L., Sharma, T. K., & Sharma, M. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-8919-6.ch004
An Operational Governance Framework for Ai-Based Smart Healthcare Systems in Smart City Contexts
Hussain, S. A., Kari, M. I., Garg, D., & Uddin, A. J. (2026) · MEC International Conference on Big Data and Smart City (ICBDSC) · doi:10.1109/icadaai64945.2026.11679177
“The problems of privacy and data governance are especially intense in the context of smart cities, where healthcare information can be merged with other urban data streams and be shared among various stakeholders [17], [18], [19].”
Roychowdhury, D. (2026) · Discover Public Health · doi:10.1186/s12982-026-02789-y
Liu, W., Guo, L., Lu, X., & Zhang, H. (2026) · Smart Agricultural Technology · doi:10.1016/j.atech.2026.102596
Mulyadi, S., Supangkat, S. H., & Anggara, D. W. (2026) · International Conference on ICT for Smart Society (ICISS) · doi:10.1109/iciss71466.2026.11715528
“Rationale: a trustworthy system should abstain when confidence is insufficient, leaving the final judgment to clinicians [6].”
Influential
Metadata
- Authors
- Sáez, C., Ferri, P., & García-Gómez, J. M.
- Affiliations
- Universitat Politècnica de València (ES)
- Corresponding author
- Sáez, Carlos
- Venue
- Journal of Medical Internet Research
- Publisher
- JMIR Publications Inc.
- Published
- 2024-06-28
- Volume
- 26
- Pages
- e50295
- ISSN
- 1438-8871 (ISSN-L)
- PMC
- PMC11245653
- OpenAlex
- W4400117494
- Cited by
- 36
- References
- 56
- Citations by year
- 2026: 16 · 2025: 17 · 2024: 3
- FWCI
- 0.82
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- Journal of Medical Internet Research (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- RiuNet (Universitat Politècnica de València) (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 › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Keywords
- clinical decision support systems, health AI, trustworthy AI, real-world data, data quality, algorithmic bias, data variability, information uncertainty, human-computer interaction, fundamental rights, AI regulation, AI safety
- MeSH terms
- Artificial Intelligence, Humans, Decision Support Systems, Clinical
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
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.