Mai, Junhua

Abstract Objectives Precise literature recommendation and summarization are crucial for biomedical professionals. While the latest iteration of generative pretrained transformer (GPT) incorporates 2 distinct modes—real-time search and pretrained model utilization—it encounters challenges in dealing with these tasks. Specifically, the real-time search can pinpoint some relevant articles but occasionally provides fabricated papers, whereas the pretrained model excels in generating well-structured summaries but struggles to cite specific sources. In response, this study introduces RefAI, an innovative retrieval-augmented generative tool designed to synergize the strengths of large language models (LLMs) while overcoming their limitations. Materials and Methods RefAI utilized PubMed for systematic literature retrieval, employed a novel multivariable algorithm for article recommendation, and leveraged GPT-4 turbo for summarization. Ten queries under 2 prevalent topics (“cancer immunotherapy and target therapy” and “LLMs in medicine”) were chosen as use cases and 3 established counterparts (ChatGPT-4, ScholarAI, and Gemini) as our baselines. The evaluation was conducted by 10 domain experts through standard statistical analyses for performance comparison. Results The overall performance of RefAI surpassed that of the baselines across 5 evaluated dimensions—relevance and quality for literature recommendation, accuracy, comprehensiveness, and reference integration for summarization, with the majority exhibiting statistically significant improvements (P-values <.05). Discussion RefAI demonstrated substantial improvements in literature recommendation and summarization over existing tools, addressing issues like fabricated papers, metadata inaccuracies, restricted recommendations, and poor reference integration. Conclusion By augmenting LLM with external resources and a novel ranking algorithm, RefAI is uniquely capable of recommending high-quality literature and generating well-structured summaries, holding the potential to meet the critical needs of biomedical professionals in navigating and synthesizing vast amounts of scientific literature.

Abstract Biodistribution detection methods currently hold a central role in evaluating clinical potential of new drugs and nanomedicine in vivo, either through therapeutic efficacy or toxicity assays. However, the explorative nature of these methods makes it practically difficult to validate them for clinical studies to comply with regulations as determined by the Food and Drug Administration. This work proposes a new systematic comparison of biodistribution methods to facilitate clinical validation and employment in pre-clinical and early stage clinical studies. Several optical methods (detection through IVIS, confocal microscopy, fluorescence emission), direct detection methods (detection through ICP-OES), and radiation-based methods (detection through gamma counter) are systematically tested and validated on cGMP grade microparticles. The classification here proposed quantitatively highlights the advantages and disadvantages of each method, expressing them in terms of: limit of detection, recovery rate, reproducibility, and sensitivity. As a result, this quantitative evaluation of several preclinical biodistribution detection methods leads to a new rational and objective classification of biodistribution methods based on quantitative characteristics, which is essential to facilitate clinical translation of pre-clinical data collection. Their different characteristics and application-specific advantages are also discussed based in light of the results presented. Overall, this work proposes a new and rational quantitative comparison of biodistribution detection methods with the goal to provide a guide to facilitate clinical translation of on-going and future pre-clinical and early-stage clinical studies. Citation Format: Sara Nizzero, Feng Li, Alessandro Venuta, Guodong Zhang, Carlotta Borsoi, Joy Wolfram, Junhua Mai, Haifa Shen, Zheng Li, Elvin Blanco, Mauro Ferrari. Empowering preclinical studies: A systematic and quantitative analysis of biodistribution methods to facilitate clinical translation of new drugs [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2018; 2018 Apr 14-18; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2018;78(13 Suppl):Abstract nr LB-019.