The appeal of AI in this setting rests on a simple asymmetry. Clinical trials generate enormous volumes of structured and unstructured data—imaging, laboratory values, genomic profiles, clinician notes, wearable-device streams and patient-reported outcomes—yet historically only a small fraction of that information has been used systematically in trial design and conduct. Machine-learning models, particularly modern deep-learning and foundation-model architectures, excel at extracting signal from exactly these high-dimensional, heterogeneous datasets. When trained on curated clinical data, they can identify which patient subpopulations are most likely to respond to a therapeutic candidate, predict which sites will struggle with recruitment, flag data inconsistencies long before database lock, and estimate the probability that an ongoing trial will meet its primary endpoint. The result is a shift from retrospective, intuition-driven trial management toward a prospectively optimised, continuously adaptive process.

Patient recruitment illustrates the potential most vividly. Failed recruitment and poor participant retention are among the leading reasons that trials miss their timelines or terminate early. Traditional approaches rely on broad eligibility criteria, manual chart review and outreach from a limited number of academic centres, which systematically under-enrols patients from rural areas, lower-income communities and historically marginalised groups. AI-driven approaches invert this model. Natural-language processing systems can scan millions of de-identified electronic health records to locate every patient matching a complex eligibility profile, including patients whose relevant conditions are described only in free-text notes rather than coded diagnoses. Matched patients can then be connected with trial sites through their treating physicians or through decentralised trial infrastructure that brings the study to the participant rather than the reverse. When designed carefully, such tools can also be tuned to improve diversity in enrolment, addressing a long-standing scientific weakness as well as an ethical one: a trial population that does not resemble the eventual treated population limits the generalisability of the results.

Trial design itself is being recomputed. Classical phase II and phase III trials typically use fixed designs conceived months before enrolment begins, and any mid-course revision requires protocol amendments that can delay readouts by many months. AI-assisted design tools draw on large repositories of historical trial outcomes, natural-history data and simulation frameworks to model, before a single patient is enrolled, how a trial will behave under different assumptions about effect size, dropout, endpoint variability and site performance. Bayesian adaptive designs, which allow the randomisation ratio and dose allocation to shift as interim data accumulate, become far more practical when machine-learning models supply reliable predictive components. Digital twins—computational replicas of individual patients built from rich baseline data—offer an emerging complement, allowing a portion of the control information in a trial to be estimated rather than observed, and thereby reducing the number of real participants who must be randomised to achieve a given statistical power. Regulators have begun engaging with these methods, and several external control arms constructed from historical or registry data have already supported regulatory submissions in rare-disease oncology.

Once a trial is running, AI changes the economics of monitoring. Risk-based monitoring, in which scrutiny is concentrated on the sites and data elements most likely to harbour errors, depends on recognising patterns across thousands of simultaneous data streams—precisely the task that anomaly-detection algorithms perform well. Centralised statistical monitoring can flag sites whose data distributions deviate from the norm, whether because of fraud, systematic measurement error or simple process breakdown, without the cost of sending monitors to every site on a fixed schedule. Automated adverse-event signal detection can surface safety trends earlier in the data stream, shortening the interval between an emerging risk and a protocol response. Speech-recognition and summarisation models are increasingly used to draft clinical notes, assist with adjudication of endpoints that require expert review, and reduce the administrative burden that currently consumes a large share of investigator time. Because the marginal cost of applying a trained model to new data is close to zero, these efficiencies can scale across an entire portfolio rather than applying to a single study.

The pharmaceutical industry’s interest follows directly from the arithmetic. Industry analyses have repeatedly estimated that bringing a new drug to market costs on the order of one to two billion dollars, with clinical development accounting for the majority of that expenditure and with most of the cost attributable to failed trials. Even a modest improvement in the probability of technical success, achieved through better target-patient matching or earlier detection of futility, translates into hundreds of millions of dollars in expected savings per programme and, more importantly, into faster access for patients to therapies that work. Every month shaved from a development timeline extends the effective patent-protected market life of a medicine, which strengthens the commercial case, but the public-health case is at least as strong: pipelines that iterate faster can respond more quickly to emerging pathogens, to rare diseases that currently have no treatment at all, and to the individualisation of therapy in fields such as oncology where one-size-fits-all efficacy is the exception rather than the rule.

None of this means the transformation is automatic. Machine-learning models inherit the biases of the data on which they are trained, and clinical datasets under-represent precisely the populations in whom trial evidence is weakest. An algorithm trained mostly on data from large academic hospitals may perform poorly for patients managed in community settings, and a recruitment tool optimised narrowly for speed could worsen enrolment diversity if fairness constraints are not built in explicitly. The opacity of complex models also sits awkwardly with regulatory expectations: a sponsor that uses an AI-derived covariate in a statistical analysis plan, or an AI-curated external control arm, must be able to explain to reviewers how the model was built, validated and monitored. Regulators including the United States Food and Drug Administration and the European Medicines Agency have signalled that they will evaluate such tools under existing frameworks for risk-based software validation, but the guidance landscape is still maturing, and sponsors who treat AI components as unexamined black boxes do so at their own regulatory peril.

Data governance presents a second structural challenge. The models that promise the greatest gains in recruitment and design are those trained on the largest and most diverse clinical datasets, yet health data are fragmented across institutions, jurisdictions and incompatible record systems, and privacy law constrains how they can be pooled. Federated learning, in which models are trained across multiple sites without moving the underlying patient data, offers a technically elegant partial solution, but it introduces its own questions about model ownership, auditability and the equitable distribution of the value created. Standard-setting efforts, from common data models to documented provenance for training sets, will determine whether AI-enabled trials become a broadly shared capability or a competitive advantage concentrated in a handful of organisations with the largest proprietary data estates.

The most realistic near-term picture is therefore not one of autonomous AI running trials, but of a human-machine division of labour in which algorithms perform the enumeration, matching, monitoring and simulation that humans cannot do at scale, while clinicians, statisticians and regulators retain judgment over what counts as evidence. Under that division of labour, the measurable signs of change are already visible: screening times measured in days rather than months at leading sponsors, growing numbers of adaptive and model-informed designs entering regulatory review, and decentralised, data-rich trial formats that were logistically implausible a decade ago. If those trends continue, the defining feature of the next generation of clinical trials will not be any single algorithm but the integration of computation into every stage of the evidentiary pipeline—from the first patient matching query to the final submission—producing trials that are faster, smaller where possible, larger where necessary, and ultimately more representative of the patients the resulting medicines are meant to serve.

Subject of Research: AI-enabled clinical trials

Article Title: AI-enabled clinical trials

Article References: Raynaud, M., Trayanova, N., Mannon, R. B., André, F., Doraiswamy, P. M., & Loupy, A. (2026). AI-enabled clinical trials. Nature Reviews Bioengineering. https://doi.org/10.1038/s44222-026-00487-7

Image Credits: AI Generated

DOI: 10.1038/s44222-026-00487-7

Keywords: AI-enabled, clinical, trials, scientific research, peer-reviewed research, research findings

At the core of this initiative lies a novel approach that integrates comprehensive biological data from cell and gene therapies with patient response profiles. This integration aims to illuminate the complex interplay between therapy characteristics and clinical outcomes, an endeavor critical to overcoming the unique challenges posed by personalized medicine. Unlike traditional pharmaceuticals, which are manufactured in mass-produced batches, cell and gene therapies are bespoke products — crafted meticulously one patient at a time within highly controlled laboratory environments. This intricate production process restricts the scale of clinical trials and data availability, rendering conventional drug development models inadequate.

UNICORN addresses these challenges by innovating smarter methodologies for therapy design and regulatory evaluation. The project leverages state-of-the-art cell analysis technology established by USC researchers, combined with machine learning algorithms. This fusion enables the identification of subtle biological signatures and attributes of therapeutic cells that correlate strongly with treatment efficacy. The outcome is the creation of a regulatory decision-support system crafted specifically to operate effectively even when confronted with limited datasets — a frequent reality in rare pediatric diseases. Such a tool promises to expedite patient access to critical therapies while maintaining rigorous standards of safety and efficacy.

Dr. Mohamed Abou-el-Enein, MD, PhD, principal investigator and executive director of the USC/Children’s Hospital Los Angeles Cell Therapy Program, underscores the transformative nature of this work. He emphasizes how the project reimagines therapeutic development by translating complex biological signals into actionable insights, thereby refining treatment creation and clinical management. His laboratory’s prior work laid the groundwork by developing an advanced cell-analysis platform focused on chimeric antigen receptor (CAR) T cell therapies. CAR T cells, engineered to reprogram the immune system’s T cells to recognize and eliminate certain blood cancers, represent a landmark in personalized medicine.

The analytical platform developed by Abou-el-Enein’s team measures a broad spectrum of protein markers simultaneously on individual CAR T cells, capturing both functional and physical properties during the manufacturing process. This rich, multidimensional data enables the identification of key cellular characteristics predictive of therapeutic potency and durability. This foundational work was instrumental in securing ARPA-H funding and now serves as the backbone for expanding the platform’s application to a wider variety of cell and gene therapy products, broadening the potential patient impact.

One of the major technical challenges UNICORN confronts is the development of robust AI models from small, heterogeneous patient populations characteristic of rare diseases. The team’s approach involves longitudinal data collection—gathering patient samples and clinical information at multiple time points throughout treatment. This strategy alleviates data scarcity by creating richer datasets per individual patient and improving model training, ultimately enabling the system to learn dynamically and enhance predictive accuracy over time.

In collaboration with several academic partners across the United States, USC researchers will systematically collect and analyze data on manufacturing processes, therapy product attributes, and detailed patient outcomes spanning a spectrum of pediatric diseases. The therapies under study include CAR T cell treatments, hematopoietic stem cell-derived interventions which modify the progenitor cells responsible for generating the body’s array of blood cells, and gene-edited products designed to correct genetic defects directly within a child’s cells. This comprehensive approach aims to unify disparate data sources into a cohesive, interpretable framework.

The UNICORN project also incorporates Bluecord, a sophisticated electronic quality and data management system previously supported by the California Institute for Regenerative Medicine (CIRM). Bluecord facilitates standardized tracking of samples, secure integration of multicenter clinical and product data, and structured linkage crucial for rigorous data analysis. This infrastructure is critical in ensuring data integrity and enables seamless collaboration across institutions, vital for generating generalizable insights from limited datasets and heterogeneous patient groups.

Artificial intelligence plays a pivotal role in distilling the vast and complex datasets into models capable of identifying biologically meaningful patterns that predict treatment success and risk. By continuously absorbing new patient data, the framework evolves as a living, learning system — effectively becoming smarter with every additional case. This unique characteristic promises transformative implications for regulatory science, enabling more nuanced decision-making and fostering rapid iteration cycles in therapy development.

The implications of this work transcend the laboratory, reflecting an urgent real-world need: for children with rare diseases, delays in therapy access can be life-threatening. By establishing a robust scientific foundation and regulatory roadmap, UNICORN aims to ensure that when a child’s life hangs in the balance, clinicians and regulators can move forward confidently, armed with clearer evidence and more reliable predictive tools. This paradigm shift not only benefits patients and families but also sets a replicable standard for the broader field of personalized, small-batch learning systems in therapeutic development.

Moreover, the project’s innovative synergy of cell biology, advanced cytometry, gene editing technologies, and machine learning exemplifies the frontier of precision medicine. It represents a critical step towards overcoming the inherent complexity and variability of living-cell therapies and accelerates the translation of cutting-edge scientific discoveries into tangible clinical benefits. The research has recently been highlighted in a Nature Medicine Correspondence, which articulates the ambitious scientific vision and underscores the transformative potential of the UNICORN framework within the landscape of pediatric rare disease treatment.

In conclusion, the Keck School of Medicine’s UNICORN project stands as a beacon of hope and innovation in pediatric medicine, merging computational power with biological insight to redefine the future of cell and gene therapies. Supported by ARPA-H funding, this initiative is poised to not only change the way therapies are developed and regulated but also markedly improve outcomes for some of the most vulnerable patients. By charting this new course, the researchers envision a world where life-saving, personalized treatments are available faster and with greater certainty — a true revolution in rare disease medicine.

Subject of Research: Cell and Gene Therapy Development for Pediatric Rare Diseases Using AI and Advanced Cell Analytics

Article Title: Unifying AI and Cell Analysis to Revolutionize Pediatric Cell and Gene Therapy Development

News Publication Date: Not explicitly provided; inferred as recent (2024)

Web References:

• https://keck.usc.edu/faculty-search/mohamed-abou-el-enein/
• https://keck.usc.edu/cell-therapy-program/
• https://arpa-h.gov/
• http://dx.doi.org/10.1038/s41591-025-04115-6

References:

• Nature Medicine Correspondence DOI: 10.1038/s41591-025-04115-6

Image Credits: Photo/USC

Keywords: Pediatrics, Chimeric Antigen Receptor Therapy, Hematopoietic Stem Cells, Gene Therapy, Gene Editing, Flow Cytometry, Cell Therapies, Artificial Intelligence, Rare Diseases, Machine Learning, Cell Analysis, Personalized Medicine