Key points
Many new technologies and methods are increasingly being integrated into quantitative microbial risk assessment (QMRA).
These emerging tools offer opportunities for more sophisticated modeling that addresses interconnectedness (One Health) and trade-offs (e.g., cost–benefit).
Artificial intelligence is a linchpin that will facilitate the integration of emerging food safety tools into QMRA.
The scientific community should be cautiously optimistic about the promises of advanced QMRA modeling, with due consideration of both strengths and limitations.
As it enters its fifth decade, the application of quantitative microbial risk assessment (QMRA) to food safety has undergone a rich evolution (1). In their recent Frontiers in Science lead article, Wiedmann et al. (2) called for the development of a new generation of QMRA modeling that incorporates (i) emerging scientific analytical tools [e.g., genomics, geographic information systems (GIS), and agent-based modeling (ABM)] and (ii) a shift toward modeling frameworks that explicitly consider unintended consequences and trade-offs, using approaches such as multi-criteria decision analysis (MCDA), risk–benefit analysis, and life-cycle assessment (LCA). Similar calls have been made by others (3, 4), with specific reference to predictive microbiology.
Emerging tools and systems thinking in next-generation QMRA
The tools and approaches highlighted by Wiedmann et al. (2) share several important commonalities. First, they are systems-focused, analyzing how individual components of a system interact to form a functional unit. This represents a departure from modeling events or phenomena in isolation, the so-called siloed approach. Second, whether operating at the micro (e.g., microbial signaling) or macro scale (e.g., LCA to jointly characterize environmental and safety impacts across the lifespan of a food product), these methods are designed to capture dynamic processes, often incorporating temporal and spatial dimensions. Third, the effective use of these tools depends on vast volumes of diverse data. While food safety professionals have touted the value of “big data” for some time, practical applications within QMRA are scant. In short, these newer scientific tools promise larger and more sophisticated mathematical modeling, but that promise has yet to be realized.
At its core, QMRA is an early form of predictive analytics that historically relied on defined datasets and statistical modeling to forecast scenarios, supporting systematic risk evaluation and risk-based control strategies. As computing power increased exponentially, predictive analytics evolved to include machine learning (ML), which enables forecasting based on historical data without explicit programming. For instance, ML has been an integral bioinformatics tool, facilitating the analysis of large whole-genome sequencing datasets (4). Its application to food microbiology has been described by Taiwo et al. (3). Now a subset of the larger concept of artificial intelligence (AI, i.e., using machines to mimic human thinking), ML has immense power to handle larger and more complex datasets, quickly identify patterns that may otherwise be missed by statistical analysis alone, and interface directly with users, thereby reducing the time for risk-based, data-driven decision-making from months or years down to days or weeks. In this context, AI serves as a key enabler of integrating emerging food safety tools into QMRA and using them in tandem.
Early applications of AI- and data-enabled approaches in QMRA
Interestingly, a search for citations that include food safety, ML/AI, and QMRA leads to a near dead end, despite frequent discussion of their combined potential. The few existing specific applications are primarily related to genome sequence analysis, where ML-assisted approaches are beginning to inform QMRA. An example is the work of Pouzou et al. (5), who developed a refined hazard characterization model incorporating genomically determined differences in non-typhoidal Salmonella virulence. The authors used this model in a QMRA to estimate salmonellosis attributable to ground beef. Scenario analysis enabled the evaluation of candidate microbiological criteria related to testing, pathogen prevalence, and product diversion. This work is currently informing proposed regulatory changes in meat and poultry policy in the United States. Although not directly linked to food safety, Alberts et al. (6) trained and validated different ML-derived predictive models to identify host species using RNA sequence data from the hemagglutinin gene of H3-type influenza viruses. The authors proposed that this “rapid risk assessment” approach could eventually be adapted to detect species jumps in near real time, with implications for both basic science (strain evolution) and public health (strain emergence).
Rohrs et al. (7) developed an MCDA-based assessment framework for the European Union food safety incident reports that could be integrated into an AI-supported database for automated risk categorization. The general approach was to identify categories (relevance, signal category, reason, and health risk), associated subcategories (e.g., related to safety/compliance/public perception or disease severity), and weighting schemes, which were integrated into a simple ordinal risk categorization algorithm. Hommels et al. (8) used expert elicitation and a standard MCDA platform to rank key “drivers of change” (delineated as social, technological, economic, environmental, and political) impacting emerging food safety risks. These drivers were categorized in a 2x2 matrix based on degree (high or low) of controllability and severity. Interestingly, two specific drivers, namely, environmental contamination and geopolitical conflict, were identified as both difficult to manage and highly likely to cause severe health impacts, highlighting long-term planning challenges. While neither model has yet to be implemented on AI-driven platforms, the authors articulate a clear vision in which MCDA could be operationalized to support autonomous prediction, early detection, rapid response, and risk prioritization for high-impact food safety issues.
Implications and risks for the future of QMRA
At its core, the strength of QMRA lies in its systematic use of data and mathematical tools to predict risk. The incorporation of larger datasets, advanced analytic tools, and new platforms should, theoretically, lead to more sophisticated, accurate, and accessible models. While this discussion focuses almost exclusively on food safety, for which QMRA is often used to inform governmental actions, its relevance extends to a broad range of stakeholders, including industry scientists and mathematical modelers.
Driven by the merging of advanced analytical tools (such as genomics, GIS, and MCDA) with ML and AI, the interconnectedness of food safety with public health, environmental sciences, and veterinary medicine (One Health), as well as sustainability, will become more apparent. In theory, the possibilities are almost limitless. One can envision ML- or AI-driven visual analytic platforms that allow users to manipulate data and conduct near real-time scenario analyses through web-based interfaces (9). In other words, the potential exists for QMRAs to behave like a computer game (e.g., ABM in which the user controls agent behavior). These approaches could result in rapid and intricate pattern recognition and prediction, supporting faster responses and more well-informed solutions that consider both costs and benefits. They also hold promise for resource- and risk-based prioritization, potentially establishing a new foundation for science-based risk management.
Lest we get ahead of ourselves, it is important to be cautiously optimistic about the future of such advanced QMRA modeling. While more sophisticated models may improve predictive accuracy and responsiveness, the challenges must also be considered. AI- and ML-based systems can be costly and inaccessible, especially for smaller organizations and stakeholders with limited financial resources. Concerns about data quality, crosstalk between diverse datasets, and data-sharing constraints related to legal or regulatory considerations have been part of the “big data” debate for some time now. Privacy and ethical issues associated with AI are already emerging, while regulatory oversight remains limited. Building these models requires substantial expertise as well as, perhaps more importantly, collaboration between experts across diverse fields, who often speak different technical languages. Rigorous validation will be essential to ensure credibility, accuracy, and reliability. Even then, strong technical expertise will be necessary for interpretation of any output. These are but a smattering of limitations and constraints, which are further discussed in Singh (10).
As an educator, I enter this era with some trepidation. To responsibly use these tools, both creators and users must be deeply rooted in the underlying science. Nothing can replace knowledge of the fundamental principles and how they are put into practice or the use of critical-thinking skills, often peppered with real-world experience. We must continue to teach and model these for our young people. Food safety is a “wicked problem”. Advanced QMRA tools may give us greater precision and perhaps facilitate a faster response, but they do not remove the complexity or nuances associated with implementing risk management and prioritization in the real world. Human intelligence may be enhanced by a machine, but human sensibility, judgment, and compassion can never be replaced. A child is born in a day and matures over a lifetime. Let us remember to be good parents to the new generation of QMRAs that we are only now conceiving.
Statements
Author contributions
LAJ: Conceptualization, Writing – original draft, Writing – review & editing.
Funding
The author declared that financial support was not received for this work and/or its publication.
Conflict of interest
The author declared that this work was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
The handling editor DWS declared a past collaboration with the author.
Generative AI statement
The author declared that generative AI was not used in the creation of this manuscript.
Publisher’s note
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.
References
1
WuFRodricksJV. Forty years of food safety risk assessment: a history and analysis. Risk Anal (2020) 40(S1):2218–30. doi: 10.1111/risa.13624
2
WiedmannMSunilSMoreno-SwittAIVongkamjanKJohlerS. Balancing food safety and sustainability: trade-off risk assessments and predictive modeling. Front Sci (2026) 4:1720772. doi: 10.3389/fsci.2026.1720772
3
TaiwoOROnyeakaHOladipoEKOlokeJKChukwugozieDC. Advancements in predictive microbiology: integrating new technologies for efficient food safety models. Int J Microbiol (2024) 17:6612162. doi: 10.1155/2024/6612162
4
OkoyeCOAbhadiomhenSEEzenwanneBCChenXJiangHWuYet al. Machine learning-based predictive modeling of foodborne pathogens and antimicrobial resistance in food microbiomes using omics techniques: a systematic review. Food Res Int (2025) 221(Pt 1):117255. doi: 10.1016/j.foodres.2025.117255
5
PouzouJGCostardSCPouillotRTaylorDZagmuttFJ. Incorporating genomic virulence in a quantitative microbial risk assessment to assess the public health impact of alternative microbiological criteria for Salmonella. Microbial Risk Anal (2025) 30:100358 doi: 10.1016/j.mran.2025.100358
6
AlbertsFBerkeOMaboniGPetukhovaTPoljakZ. Utilizing machine learning and hemagglutinin sequences to identify likely hosts of influenza H3Nx viruses. Prev Vet Med (2024) 233:106351. doi: 10.1016/j.prevetmed.2024.106351
7
RohrsSRohnSPfeiferY. Risk classification of food incidents using a risk evaluation matrix for use in artificial intelligence-supported risk identification. Foods (2024) 13:3675. doi: 10.3390/foods13223675
8
HommelsNMCMouritsMCMFockerMvan der Fels-KlerxHJ. Categorization of drivers of change for emerging food safety risks. Curr Res Food Sci (2025) 10:101098. doi: 10.1016/j.crfs.2025.101098
9
ChenYWuCZhangQWuD. Review of visual analytics methods for food safety risks. NPJ Sci Food (2023) 7(1):49. doi: 10.1038/s41538-023-00226-x
10
SinghD. Harnessing artificial intelligence to safeguard food quality and safety. J Food Prot (2025) 88(11):100621. doi: 10.1016/j.jfp.2025.100621
Summary
Keywords
artificial intelligence, food safety, QMRA, risk management, risk modeling
Citation
Jaykus L-A (2026) Toward the next generation of quantitative microbial risk assessment. Front Sci 4:1813401. doi: 10.3389/fsci.2026.1813401
Received
18 February 2026
Accepted
05 March 2026
Published
17 March 2026
Volume
4 - 2026
Edited and reviewed by
Donald W. Schaffner, Rutgers, The State University of New Jersey, United States
Updates
Copyright
© 2026 Jaykus.
This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
*Correspondence: Lee-Ann Jaykus, lajaykus@ncsu.edu
Disclaimer
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.