Abstract
Recent advances at the intersection of artificial intelligence (AI), nanotechnology, and medicine are creating new opportunities to accelerate biomedical discovery and improve the development of nanotechnology-based diagnostic and therapeutic systems. Nanomedicine has demonstrated considerable promise in areas including targeted drug delivery, medical imaging, disease detection, biosensing, and personalized treatment. Yet translation from experimental research to routine clinical practice remains slow. Nanomaterial design continues to rely heavily on iterative experimentation; manufacturing and characterization processes can be time-intensive, and many systems lack the real-time monitoring and adaptive control capabilities necessary for reliable clinical use. AI and machine-learning approaches are increasingly being incorporated across the nanomedicine development lifecycle to address these challenges. At the same time, the adoption of AI-enabled nanomedicine introduces human factors challenges involving interpretability, trust, data quality, workflow integration, reproducibility, interdisciplinary communication, and appropriate allocation of responsibility between automated systems and human experts. These issues become particularly important as technologies move from laboratory proof-of-concept toward clinical environments where system performance must be understandable, predictable, safe, and usable by clinicians and researchers. This review synthesizes 15 studies published between 2023 and 2026 to examine how AI is being used within contemporary nanomedicine and to identify opportunities and barriers relevant to eventual clinical translation. The literature was organized around three major areas: (1) optimization of nanomaterial design, (2) real-time monitoring and control of nanocarriers and manufacturing processes, and (3) diagnostic and imaging data analysis. Particular attention was given to the maturity of AI applications, the type and quality of data supporting them, evidence of experimental or clinical validation, interpretability, and challenges that may affect safe integration into healthcare systems. Across the first theme, AI-supported nanomaterial design, machine-learning methods were consistently used to reduce the traditional trial-and-error process associated with formulation development. However, the quality and quantity of available data varied substantially. For example, Noorain et al. used Gaussian Process regression to predict drug loading and encapsulation efficiency in PLGA nanoparticles. Although 275 candidate publications were initially identified, only eight contained usable data, and much of the final dataset came from a single paper. The authors specifically identified limited data availability as a major constraint on model prediction. Similar concerns emerged in studies predicting protein corona formation, where imbalanced datasets could bias models toward common proteins while underrepresenting rare but potentially biologically important proteins. Other investigations demonstrated greater integration between computational prediction and experimental validation. Zhang et al., for example, used AI to screen self-assembling drug combinations and subsequently validated predicted assembly mechanisms using computational simulation and wet-lab experiments. Li et al. applied Bayesian optimization to vaccine formulation using industrial formulation and assay data, illustrating how AI can support formulation decisions when predictions are grounded in experimentally derived information. The second and most represented theme involved real-time monitoring and control of nanocarriers and manufacturing processes. The maturity of systems varied widely, ranging from autonomous laboratory platforms to entirely simulated control frameworks. Mottafegh et al. developed a Bayesian-optimization-guided continuous-flow platform capable of autonomously modifying synthesis parameters while producing drug-loaded liposomes and polymeric nanoparticles, completing multistep synthesis with limited manual intervention. Glaubitz et al. addressed another practical bottleneck by using machine-learning models trained on dynamic light scattering and UV-Vis measurements to estimate nanoparticle size and shape that would otherwise require slower electron microscopy procedures. Their approach was evaluated during an active gold nanoparticle synthesis process. DetectNano similarly demonstrated the potential for automated characterization by using a YOLOv8-based model to size polymer nanostructures from microscopy images in under two seconds per image. AI was also used to predict nanocarrier behavior after administration. Chou et al. combined an AI-based quantitative structure-activity relationship model with physiologically based pharmacokinetic modeling to predict nanoparticle tumor delivery and evaluated the approach against 288 experimental datasets. Other models attempted to predict broader pharmacokinetic behavior or brain biodistribution. Importantly, some recent approaches incorporated interpretability mechanisms, addressing a limitation commonly associated with black-box prediction systems. In contrast, the least clinically mature systems relied primarily on synthetic simulation. A reinforcement-learning framework proposed for real-time adaptation of nanoparticle dosing, for example, was evaluated only with simulated pharmacokinetic and pharmacodynamic data rather than with patients, animals, or physical nanoparticles. This variation illustrates the importance of distinguishing technically sophisticated demonstrations from systems with evidence sufficient to support clinical decision-making. The third theme involved diagnostic and imaging data analysis. AI-enhanced nanoparticle sensing systems demonstrated encouraging diagnostic performance, although levels of validation again varied. Chen et al. combined a nanoparticle-based SERS substrate with a MobileNet V2 deep-learning model to classify lung cancer subtypes from exosome Raman spectra, reporting 95.23% accuracy and an area under the curve above 0.95 for each subtype. Other approaches used neural networks to predict MRI relaxation characteristics from nanoparticle properties or machine learning with computational simulation to optimize graphene-based biosensors for breast cancer detection. However, some reported diagnostic performance was derived exclusively from simulated systems rather than physically constructed and clinically tested devices. From a human factors perspective, the findings suggest that the principal challenge facing AI-enabled nanomedicine is not simply whether algorithms can generate accurate predictions, but whether the larger sociotechnical system can support trustworthy, interpretable, and reproducible use. The reviewed literature repeatedly identified limitations involving inconsistent datasets, lack of standardization, variable transparency of methods, limited clinical validation, and black-box model behavior. These characteristics affect how researchers and clinicians assess model reliability and determine when algorithmic recommendations should be accepted, questioned, or overridden. The findings also emphasize the importance of appropriate human–automation collaboration. AI appears most useful when functioning as an augmentation tool that reduces the number of possibilities humans must evaluate rather than independently replacing experimental judgment. In nanomaterial design, machine learning can predict toxicity, formulation characteristics, or promising design candidates, allowing researchers to concentrate experimental resources on a smaller and more promising set of alternatives. In manufacturing, automated systems can potentially connect synthesis, monitoring, and quality control. In diagnostics, AI can rapidly analyze complex biosensor and imaging signals that may be difficult or time-consuming for humans to interpret manually. Across these domains, however, humans remain responsible for determining whether predictions are biologically plausible, clinically meaningful, and sufficiently validated. The reviewed literature therefore supports a model of human-AI teaming, rather than complete automation, for the foreseeable future. This perspective also raises important design requirements for future systems. Clinical-facing AI tools should communicate uncertainty, provide interpretable evidence where feasible, and make the origin and limitations of their training data visible to users. Interfaces and workflows should support verification rather than encourage uncritical reliance on automated recommendations. In conclusion, AI is increasingly shaping nanomedicine by accelerating material design, enabling automated monitoring and manufacturing, improving nanocarrier modeling, and extracting diagnostic information from complex nanoparticle-enabled sensing and imaging systems. Across the reviewed literature, however, the dominant pattern is augmentation rather than replacement: AI reduces experimental search spaces and increases analytical efficiency, while real-world nanomedicine still requires experimental validation and human expertise. The major barriers to broader clinical adoption are therefore not exclusively technical. Inconsistent data standards, limited transparency, inadequate real-world validation, and variable interpretability create substantial challenges for trust and implementation. Progress will require collaboration among nanoscientists, clinicians, AI researchers, HFE professionals, and regulatory stakeholders to develop shared data standards, transparent evaluation practices, usable decision-support systems, and validation frameworks appropriate for clinical environments. Incorporating human factors principles early in technology development may help ensure that AI-enabled nanomedicine systems are designed not merely for computational performance, but for safe, understandable, and effective integration into the complex sociotechnical environments of healthcare.
Whitepaper forthcoming.