Critical reviewMethodology & analyticsMedicine & healthcare

AI, digital twins and organ-on-chip in preclinical research: a critical review of Gangwal and Lavecchia (2025)

Gangwal and Lavecchia review how machine learning, digital twins and organ-on-chip systems could reduce reliance on animal testing. This critique separates what has been validated from what has only been claimed, and shows where a doctoral project could add real evidence.

What you will learn

  • Summarise the scope and conclusions of Gangwal and Lavecchia (2025) accurately
  • Explain what a digital twin is in the strict sense and how it differs from a simulation model
  • Distinguish vendor statements, retrospective benchmarks and independent validation when appraising AI tools
  • Describe how the FDA and EMA currently frame the credibility of AI models and non-animal methods
  • Identify researchable gaps in validating AI-enhanced non-animal methods

What you will unlearn

  • AI can now replace animal testing in drug development.The reviewed authors themselves conclude that AI is a complementary tool and that complete replacement is unlikely in the near future.
  • Any computational model of a patient or organ is a digital twin.A digital twin in the strict sense is continuously updated from its physical counterpart through two-way data flows.
  • Generative models trained on animal data remove the need for animal data.Models such as AnimalGAN learn from legacy animal studies, so they reuse animal data rather than make it unnecessary.
  • Most drugs fail in the clinic because animal models are poor predictors.Clinical failures have several causes, including lack of efficacy, toxicity, poor drug-like properties and commercial decisions.

Skills you will practise

  • Appraising narrative reviews
  • Grading evidence for AI tools
  • Model credibility and context of use
  • Regulatory awareness
  • Gap identification
  • Critical reading of industry claims

The source and its scope

Gangwal and Lavecchia (2025) is an open-access review in Drug Discovery Today titled "Artificial intelligence in preclinical research: enhancing digital twins and organ-on-chip to reduce animal testing". It argues that machine learning, deep learning, AI-powered digital twins and AI-enhanced organ-on-a-chip platforms can simulate biological systems well enough to support early safety and efficacy decisions, in line with the 3Rs of replacement, reduction and refinement.

It is a narrative review. It brings together technologies, tools and companies across a fast-moving field, which makes it a useful map for a newcomer. It does not report a systematic search or a quantitative synthesis, so it cannot tell the reader how strong the evidence for each tool is. That is the main task of this critique.

What the review covers

The review opens with the limitations of animal studies, including species differences and false positive and false negative safety findings, and notes that the FDA Modernization Act 2.0 allows sponsors to submit non-animal data. It then surveys existing alternatives: in vitro and three-dimensional cultures, organoids, organ chips, human tissue, ex vivo slices, microdosing, molecular modelling and digital twins.

A long section describes AI tools offered as alternatives to animal studies. These include AnimalGAN and Tox-GAN, generative models from FDA scientists that produce synthetic clinical pathology and toxicogenomic data (Chen et al., 2023; Chen et al., 2022); deep learning models for drug-induced liver injury and carcinogenicity; and several commercial platforms. Separate sections cover AI-supported digital twins and organ chips, again mixing academic and company examples.

The review closes with challenges: biological complexity that models cannot fully capture; data bias, including datasets drawn mainly from young, healthy male subjects; scarce data for rare diseases; and the black-box nature of deep learning, for which it discusses explanation tools such as SHAP and LIME. Its conclusion is measured: AI is a complementary tool rather than a full replacement, and complete phasing out of animal testing is unlikely in the near future (Gangwal & Lavecchia, 2025).

Appraising the evidence behind the claims

Different kinds of evidence are presented side by side

The review's examples rest on very different foundations. Some are peer-reviewed studies with stated methods and metrics. Others are company descriptions of what a platform can do. Presenting them together, without grading, gives vendor statements the same weight as published validation. A reader should sort every example into one of the levels in the table below before citing it.

Grading claims about AI-enhanced non-animal methods
Level of evidenceTypical formWhat it can support
Vendor or press statementCompany website, funding announcementThat a product exists; not that it works
Retrospective benchmarkModel tested on historical compoundsDiscrimination on known drugs (Chen et al., 2023)
Prospective or blinded testPredictions made before outcomes knownPerformance on genuinely new compounds
Independent replicationAnother group, other compoundsTransferability beyond the developer
Regulatory acceptanceQualified for a stated context of useUse in decisions for that context (U.S. Food and Drug Administration, 2025a)

Strong examples, read carefully

The best examples are informative precisely because their limits are visible. Chen et al. (2023) trained AnimalGAN on legacy rat studies and reported that its synthetic clinical pathology data gave hepatotoxicity assessments comparable to the real data and better than conventional quantitative structure-activity relationship models. The model learns from animal data, so its contribution is to reuse existing studies and reduce new ones, not to make animal data unnecessary. Its predictions also concern rat outcomes, so their relevance to people depends on how well rat findings translate in the first place.

Organ chips have a similar profile. Ingber (2022) reviews their development for disease modelling and drug testing. In one of the largest performance studies, Ewart et al. (2022) tested 870 human Liver-Chips against 27 drugs with known hepatotoxicity and reported 87 per cent sensitivity and 100 per cent specificity. This is strong evidence for one organ, one endpoint and one platform; it does not show that a multi-organ chip, or an AI layer on top of it, performs as well.

The review itself acknowledges the practical limits of organ chips: current devices approximate particular tissue structures, physiological relevance requires stable function over long periods, and standardisation and reproducibility between laboratories remain obstacles (Gangwal & Lavecchia, 2025). These are measurable problems, and they are where much of the useful doctoral work in this area lies.

A contested statistic

The review supports the case against animal studies with a figure for the proportion of animal-tested drugs that fail to reach the market. Figures of this kind are widely repeated, but they refer to candidates entering clinical trials and do not by themselves show that animal models caused the failures. Sun et al. (2022) attribute clinical failures mainly to lack of efficacy (40% to 50%), unmanageable toxicity (about 30%), poor drug-like properties (10% to 15%) and commercial or strategic reasons (about 10%). Better preclinical models would help with some of these causes, not all.

What counts as a digital twin

The term "digital twin" is used loosely in the review and across the field. The US National Academies define a digital twin as computational models coupled to a physical counterpart and updated dynamically through two-way data flows, and stress verification, validation and uncertainty quantification as foundations (National Academies of Sciences, Engineering, and Medicine, 2024). Many preclinical "digital twins" are better described as mechanistic or statistical simulation models: they are built from data but are not continuously updated from a specific organism or patient.

A scoping review of digital twins in health found the field active but still at an early stage of adoption (Katsoulakis et al., 2024). For a doctoral researcher, the practical point is to define the term in your own work and to say which elements of a twin your model has: a physical counterpart, data flowing in, predictions flowing back, and quantified uncertainty.

Regulation in 2026: from permission to credibility

The regulatory context has moved since the review was written. In the United States, the FDA Modernization Act 2.0 of December 2022 replaced references to animal tests with "nonclinical tests", which include cell-based assays, organ chips, computer models and animal studies (Consolidated Appropriations Act, 2023). The FDA's April 2025 roadmap aims to make animal studies the exception for preclinical safety testing, beginning with monoclonal antibodies (U.S. Food and Drug Administration, 2025b), and a direct final rule in September 2026 aligned the wording of FDA drug and biologics regulations (U.S. Food and Drug Administration, 2026). In the European Union, animal procedures remain governed by Directive 2010/63/EU, which requires non-animal methods to be used wherever they are scientifically satisfactory (European Parliament & Council of the European Union, 2010).

Permission to use non-animal evidence is not the same as acceptance of a particular model. The FDA's January 2025 draft guidance on AI in drug development proposes a risk-based credibility assessment, judged against the model's context of use, defined as the specific role and scope of the AI model in addressing a question of interest (U.S. Food and Drug Administration, 2025a). It excludes AI used purely in drug discovery, but covers models whose outputs bear on the reliability of non-clinical or clinical study results. The EMA's reflection paper, adopted in September 2024, covers AI across the medicinal product lifecycle from discovery to post-authorisation (European Medicines Agency, 2024). Both expect evidence proportionate to the decision the model informs, which is exactly what a narrative review cannot supply.

Overall appraisal

Strengths

  • Broad, readable coverage that links AI methods, organ chips and digital twins in one place.
  • A balanced conclusion that does not overstate the prospect of full replacement.
  • Explicit discussion of data bias, data scarcity and interpretability as barriers.
  • Useful pointers to peer-reviewed tools from regulatory science, such as AnimalGAN and Tox-GAN (Chen et al., 2023; Chen et al., 2022).

Weaknesses

  • No reported search strategy or inclusion criteria, so coverage and selection cannot be judged.
  • Vendor claims sit beside peer-reviewed results without any grading of evidence.
  • Performance figures are reported without the information needed to interpret them, such as the test set, whether it was independent, and the prevalence of the outcome.
  • The term "digital twin" is not defined strictly enough to distinguish twins from simulation models (National Academies of Sciences, Engineering, and Medicine, 2024).
  • Validation and regulatory acceptance are mentioned but not analysed against a framework such as context of use (U.S. Food and Drug Administration, 2025a).

Worked example: appraising a claim

This example is hypothetical. Suppose a company states that its AI-enhanced liver chip "predicts human liver toxicity better than animal studies". Work through the following questions before citing it.

  1. Source. Is the claim in a peer-reviewed paper with methods, or only in marketing material?
  2. Context of use. Which decision is the model meant to inform: ranking candidates, setting a first-in-human dose, or replacing a specific study (U.S. Food and Drug Administration, 2025a)?
  3. Test set. How many drugs, with what reference classification, and were they chosen before testing?
  4. Comparator. Was the animal model tested on the same drugs, or is the comparison drawn from other studies?
  5. Metrics. Are sensitivity and specificity both reported, with uncertainty, as in Ewart et al. (2022)?
  6. Independence. Has anyone other than the developer reproduced the result?
  7. AI contribution. Does the AI layer add predictive value over the chip read-outs alone?

If most answers are missing, cite the claim as an example of a proposed approach, not as evidence of performance.

Research gaps and common mistakes

Gaps a doctoral project could address

Common mistakes

  • Citing a narrative review as proof that a technology works.
  • Repeating company performance figures as if they were peer-reviewed results.
  • Calling a simulation model a digital twin without the features that define one.
  • Assuming that regulatory permission to submit non-animal data means a given model will be accepted.

Key takeaways

Your next step

Want to apply this to your own study?

  1. 1Tell us your topic, data and deadline
  2. 2A statistician reviews your work with you
  3. 3You get a plan and a quote
Research gap identification

References

  1. Chen, X., Roberts, R., Liu, Z., & Tong, W. (2023). A generative adversarial network model alternative to animal studies for clinical pathology assessment. Nature Communications, 14, 7141. https://doi.org/10.1038/s41467-023-42933-9
  2. Chen, X., Roberts, R., Tong, W., & Liu, Z. (2022). Tox-GAN: An artificial intelligence approach alternative to animal studies. A case study with toxicogenomics. Toxicological Sciences, 186(2), 242–259. https://doi.org/10.1093/toxsci/kfab157
  3. Consolidated Appropriations Act, 2023, Pub. L. No. 117-328, div. FF, § 3209 (FDA Modernization Act 2.0), 136 Stat. 4459 (2022). https://www.congress.gov/117/plaws/publ328/PLAW-117publ328.pdf
  4. European Medicines Agency. (2024). Reflection paper on the use of artificial intelligence (AI) in the medicinal product lifecycle (EMA/CHMP/CVMP/83833/2023). https://www.ema.europa.eu/en/use-artificial-intelligence-ai-medicinal-product-lifecycle-scientific-guideline
  5. European Parliament & Council of the European Union. (2010). Directive 2010/63/EU of 22 September 2010 on the protection of animals used for scientific purposes. Official Journal of the European Union, L 276, 33–79. https://eur-lex.europa.eu/eli/dir/2010/63/oj/eng
  6. Ewart, L., Apostolou, A., Briggs, S. A., Carman, C. V., Chaff, J. T., Heng, A. R., Jadalannagari, S., Janardhanan, J., Jang, K.-J., Joshipura, S. R., Kadam, M. M., Kanellias, M., Kujala, V. J., Kulkarni, G., Le, C. Y., Lucchesi, C., Manatakis, D. V., Maniar, K. K., Quinn, M. E., . . . Levner, D. (2022). Performance assessment and economic analysis of a human Liver-Chip for predictive toxicology. Communications Medicine, 2, 154. https://doi.org/10.1038/s43856-022-00209-1
  7. Gangwal, A., & Lavecchia, A. (2025). Artificial intelligence in preclinical research: Enhancing digital twins and organ-on-chip to reduce animal testing. Drug Discovery Today, 30(5), 104360. https://doi.org/10.1016/j.drudis.2025.104360
  8. Ingber, D. E. (2022). Human organs-on-chips for disease modelling, drug development and personalized medicine. Nature Reviews Genetics, 23(8), 467–491. https://doi.org/10.1038/s41576-022-00466-9
  9. Katsoulakis, E., Wang, Q., Wu, H., Shahriyari, L., Fletcher, R., Liu, J., Achenie, L., Liu, H., Jackson, P., Xiao, Y., Syeda-Mahmood, T., Tuli, R., & Deng, J. (2024). Digital twins for health: A scoping review. npj Digital Medicine, 7, 77. https://doi.org/10.1038/s41746-024-01073-0
  10. National Academies of Sciences, Engineering, and Medicine. (2024). Foundational research gaps and future directions for digital twins. The National Academies Press. https://doi.org/10.17226/26894
  11. Sun, D., Gao, W., Hu, H., & Zhou, S. (2022). Why 90% of clinical drug development fails and how to improve it? Acta Pharmaceutica Sinica B, 12(7), 3049–3062. https://doi.org/10.1016/j.apsb.2022.02.002
  12. U.S. Food and Drug Administration. (2025a). Considerations for the use of artificial intelligence to support regulatory decision-making for drug and biological products: Draft guidance for industry and other interested parties (Docket No. FDA-2024-D-4689). https://www.fda.gov/regulatory-information/search-fda-guidance-documents/considerations-use-artificial-intelligence-support-regulatory-decision-making-drug-and-biological
  13. U.S. Food and Drug Administration. (2025b). Roadmap to reducing animal testing in preclinical safety studies. https://www.fda.gov/media/186092/download
  14. U.S. Food and Drug Administration. (2026). Nonclinical testing terminology (Direct final rule; Docket No. FDA-2026-N-5347). Federal Register, 91, 59988. https://public-inspection.federalregister.gov/2026-19350.pdf

How to cite this article

Choose your referencing style, then copy. Check your university's or journal's guide for local variations.

PhD Research Lab Academy. (2026, February 20). AI, digital twins and organ-on-chip in preclinical research: a critical review of Gangwal and Lavecchia (2025). PhD Research Lab. https://www.phdassistance.com/academy/critical-review/preclinical-research-digital-twins-organ-on-chip/

PhD Research Lab Academy. “AI, Digital Twins and Organ-on-chip in Preclinical Research: A Critical Review of Gangwal and Lavecchia (2025).” PhD Research Lab, 20 Feb. 2026, www.phdassistance.com/academy/critical-review/preclinical-research-digital-twins-organ-on-chip. Accessed [access date].

PhD Research Lab Academy (2026) AI, digital twins and organ-on-chip in preclinical research: a critical review of Gangwal and Lavecchia (2025). PhD Research Lab. Available at: https://www.phdassistance.com/academy/critical-review/preclinical-research-digital-twins-organ-on-chip/ (Accessed: [access date]).

PhD Research Lab Academy. “AI, Digital Twins and Organ-on-chip in Preclinical Research: A Critical Review of Gangwal and Lavecchia (2025).” PhD Research Lab. February 20, 2026. https://www.phdassistance.com/academy/critical-review/preclinical-research-digital-twins-organ-on-chip.

PhD Research Lab Academy, ‘AI, Digital Twins and Organ-on-chip in Preclinical Research: A Critical Review of Gangwal and Lavecchia (2025)’ (PhD Research Lab, 20 February 2026) <https://www.phdassistance.com/academy/critical-review/preclinical-research-digital-twins-organ-on-chip> accessed [access date].

PhD Research Lab Academy. AI, digital twins and organ-on-chip in preclinical research: a critical review of Gangwal and Lavecchia (2025) [Internet]. PhD Research Lab; 2026 Feb 20 [cited [access date]]. Available from: https://www.phdassistance.com/academy/critical-review/preclinical-research-digital-twins-organ-on-chip/

PhD Research Lab Academy, “AI, digital twins and organ-on-chip in preclinical research: a critical review of Gangwal and Lavecchia (2025),” PhD Research Lab, Feb. 20, 2026. [Online]. Available: https://www.phdassistance.com/academy/critical-review/preclinical-research-digital-twins-organ-on-chip. [Accessed: [access date]].

@online{preclinical_research_digital_twins_organ_on_chip_2026,
  author = {{PhD Research Lab Academy}},
  title = {{AI, digital twins and organ-on-chip in preclinical research: a critical review of Gangwal and Lavecchia (2025)}},
  organization = {PhD Research Lab},
  date = {2026-02-20},
  url = {https://www.phdassistance.com/academy/critical-review/preclinical-research-digital-twins-organ-on-chip},
  urldate = {[access date]}
}

This article is for learning. Use it to understand the method and cite the original sources above in your own work; do not copy or submit it as your own.

AI, digital twins and organ-on-chip in preclinical researchNeed help applying it to your study?
Research gap identification