Harnessing large language models' zero-shot and few-shot learning capabilities for regulatory research.

Large language models (LLMs) are sophisticated AI-driven models trained on vast sources of natural language data. They are adept at generating responses that closely mimic human conversational patterns. One of the most notable examples is OpenAI's ChatGPT, which has been extensively used across diverse sectors. Despite their flexibility, a significant challenge arises as most users must transmit their data to the servers of companies operating these models. Utilizing ChatGPT or similar models online may inadvertently expose sensitive information to the risk of data breaches. Therefore, implementing LLMs that are open source and smaller in scale within a secure local network becomes a crucial step for organizations where ensuring data privacy and protection has the highest priority, such as regulatory agencies. As a feasibility evaluation, we implemented a series of open-source LLMs within a regulatory agency's local network and assessed their performance on specific tasks involving extracting relevant clinical pharmacology information from regulatory drug labels. Our research shows that some models work well in the context of few- or zero-shot learning, achieving performance comparable, or even better than, neural network models that needed thousands of training samples. One of the models was selected to address a real-world issue of finding intrinsic factors that affect drugs' clinical exposure without any training or fine-tuning. In a dataset of over 700 000 sentences, the model showed a 78.5% accuracy rate. Our work pointed to the possibility of implementing open-source LLMs within a secure local network and using these models to perform various natural language processing tasks when large numbers of training examples are unavailable.

Mechanism-based organization of neural networks to emulate systems biology and pharmacology models.

Deep learning neural networks are often described as black boxes, as it is difficult to trace model outputs back to model inputs due to a lack of clarity over the internal mechanisms. This is even true for those neural networks designed to emulate mechanistic models, which simply learn a mapping between the inputs and outputs of mechanistic models, ignoring the underlying processes. Using a mechanistic model studying the pharmacological interaction between opioids and naloxone as a proof-of-concept example, we demonstrated that by reorganizing the neural networks' layers to mimic the structure of the mechanistic model, it is possible to achieve better training rates and prediction accuracy relative to the previously proposed black-box neural networks, while maintaining the interpretability of the mechanistic simulations. Our framework can be used to emulate mechanistic models in a large parameter space and offers an example on the utility of increasing the interpretability of deep learning networks.

Physiologically based modeling reveals different risk of respiratory depression after fentanyl overdose between adults and children.

Despite a rapid increase in pediatric mortality rate from prescription and illicit opioids, there is limited research on the dose-dependent impact of opioids on respiratory depression in children, the leading cause of opioid-associated death. In this article, we extend a previously developed translational model to cover pediatric populations by incorporating age-dependent pharmacokinetic, pharmacodynamic, and physiological changes compared to adults. Our model reproduced previous perioperative clinical findings that adults and children have similar risk of respiratory depression at the same plasma fentanyl concentration when specific endpoints (minute ventilation, CO2 tension in the blood) were used. However, our model points to a potential caveat that, in a perioperative setting, routine use of mechanical ventilation and supplemental oxygen maintained the blood and tissue oxygen partial pressures in patients and prevented the use of oxygen-related endpoints to evaluate the consequences of respiratory depression. In a community setting when such oxygenation procedures are not immediately available, our model suggests that the higher oxygen demand and reduced cerebrovascular reactivity could make children more susceptible to severe hypoxemia and brain hypoxia, even with the same plasma fentanyl concentration as adults. Our work indicates that when developing intervention strategies to protect children from opioid overdose in a community setting, these pediatric-specific factors may need to be considered.