Citations

Abstract Background: HPV vaccine is an effective measure to prevent and control the diseases caused by Human Papillomavirus (HPV). This study addresses the development of VaxBot-HPV, a chatbot aimed at improving health literacy and promoting vaccination uptake by providing information and answering questions about the HPV vaccine; Methods: We constructed the knowledge base (KB) for VaxBot-HPV, which consists of 451 documents from biomedical literature and web sources on the HPV vaccine. We extracted 202 question-answer pairs from the KB and 39 questions generated by GPT-4 for training and testing purposes. To comprehensively understand the capabilities and potential of GPT-based chatbots, three models were involved in this study : GPT-3.5, VaxBot-HPV, and GPT-4. The evaluation criteria included answer relevancy and faithfulness; Results: VaxBot-HPV demonstrated superior performance in answer relevancy and faithfulness compared to baselines (Answer relevancy: 0.85; Faithfulness: 0.97) for the test questions in KB, (Answer relevancy: 0.85; Faithfulness: 0.96) for GPT generated questions; Conclusions: This study underscores the importance of leveraging advanced language models and fine-tuning techniques in the development of chatbots for healthcare applications, with implications for improving medical education and public health communication.

Abstract Objective In acupuncture therapy, the accurate location of acupoints is essential for its effectiveness. The advanced language understanding capabilities of large language models (LLMs) like Generative Pre-trained Transformers (GPTs) and Llama present a significant opportunity for extracting relations related to acupoint locations from textual knowledge sources. This study aims to explore the performance of LLMs in extracting acupoint-related location relations and assess the impact of fine-tuning on GPT’s performance. Materials and Methods We utilized the World Health Organization Standard Acupuncture Point Locations in the Western Pacific Region (WHO Standard) as our corpus, which consists of descriptions of 361 acupoints. Five types of relations (“direction_of”, “distance_of”, “part_of”, “near_acupoint”, and “located_near”) (n = 3174) between acupoints were annotated. Four models were compared: pre-trained GPT-3.5, fine-tuned GPT-3.5, pre-trained GPT-4, as well as pretrained Llama 3. Performance metrics included micro-average exact match precision, recall, and F1 scores. Results Our results demonstrate that fine-tuned GPT-3.5 consistently outperformed other models in F1 scores across all relation types. Overall, it achieved the highest micro-average F1 score of 0.92. Discussion The superior performance of the fine-tuned GPT-3.5 model, as shown by its F1 scores, underscores the importance of domain-specific fine-tuning in enhancing relation extraction capabilities for acupuncture-related tasks. In light of the findings from this study, it offers valuable insights into leveraging LLMs for developing clinical decision support and creating educational modules in acupuncture. Conclusion This study underscores the effectiveness of LLMs like GPT and Llama in extracting relations related to acupoint locations, with implications for accurately modeling acupuncture knowledge and promoting standard implementation in acupuncture training and practice. The findings also contribute to advancing informatics applications in traditional and complementary medicine, showcasing the potential of LLMs in natural language processing.

Background: Conventional neoadjuvant chemoradiotherapy (nCRT) yields a pathologic complete response (pCR) rate of 15–30% for locally advanced rectal cancer (LARC). This study ventures to shift this paradigm by incorporating short-course nCRT with immunotherapy, specifically Envafolimab, to achieve improved treatment efficacy and possibly redefine the standard of care for LARC. Materials and methods: The PRECAM study is a prospective, single-arm, phase 2 clinical trial for LARC in patients with microsatellite stable (MSS) tumors. Participants received short-course radiotherapy (25Gy/5f), followed by two cycles of CAPEOX chemotherapy and six weekly doses of Envafolimab, a PD-L1 antibody, before total mesorectal excision surgery. The primary endpoint was the pCR rate. Results: From April to December 2022, 34 patients were enrolled, of whom 32 completed the study, each diagnosed with an MSS rectal adenocarcinoma. All patients underwent preoperative CRT combined with Envafolimab. Remarkably, a pCR rate of 62.5% (20/32) was attained, and a significant pathologic response rate of 75% (24/32) was achieved. Additionally, 21 of 32 participants achieved a neoadjuvant rectal (NAR) score below 8, suggesting an effective treatment response. Common adverse events included tenesmus (78.1%), diarrhea (62.5%), and leukocyte decrease (40.6%). Two Grade 3 adverse events were noted, one related to liver function abnormality and the other to a decrease in platelet count. Surgical procedures were performed in all cases, with minor complications, including ileus, infections, and anastomotic leakage. As of this report, there have been no reported cases of recurrence or death during the follow-up period, ranging from 12 to 20 months. Conclusion: In LARC patients exhibiting MSS tumors, combining short-course nCRT with Envafolimab demonstrated favorable efficacy, leading to a significant pCR rate. Minor adverse effects and surgical complications were observed. These preliminary but promising results underscore the potential of this approach and call for further exploration and validation through a randomized controlled trial.

3614 Background: Conventional neoadjuvant chemoradiotherapy (nCRT) yields a pathologic complete response (pCR) rate of about 15%–- 30% for locally advanced rectal cancer (LARC). This PRECAM study aimed to investigate the efficacy and safety of neoadjuvant short-course radiotherapy combined with CAPEOX plus Envafolimab in Patients with Microsatellite Stable (MSS) LARC, redefining the standard of care (SOC) for LARC. Methods: The study is an open-label, prospective, single-arm, phase II clinical study . Eligible patients with MSS LARC were consecutively enrolled. Participants received short-course radiotherapy (25Gy/5f) with subsequent two cycles of CAPEOX (capecitabine and oxaliplatin) and 6 cycles of Envafolimab (subcutaneous injection, 150 mg, QW ) followed by total mesorectal excision surgery. The primary endpoint was pathological complete response (pCR) rate, and the secondary endpoint was major pathologic (MPR) rate and safety. Results: From April to December 2022, 34 patients were enrolled, of whom 32 completed the study. Remarkably, The pCR rate was62.5% (20/32), and the (MPR) rate was 75% (24/32). Furthermore, 65.6% (21/32) patients achieved a neoadjuvant rectal (NAR) score below 8, suggesting an effective treatment response. Common adverse events included tenesmus (78.1%), diarrhea (62.5%), and leukocyte decrease (40.6%), with two cases of Grade 3 adverse events. Surgical procedures were performed in all 32 cases, with minor complications observed. During the follow-up period of up to 20 months, no recurrence or death were reported. Conclusions: Short-course radiotherapy combined with CAPEOX plus Envafolimab showed favorable pCR rate with manageable adverse effects and surgical complications in LARC, underscoring the potential of the combination therapy for MSS LARC. A Randomized controlled trial is warranted for further exploration and validation. Clinical trial information: NCT05216653 .

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.

The EGFR-RAS-ERK pathway is one of the most important signaling cascades in cell survival, growth, and proliferation. Aberrant activation of this pathway is a common mechanism in various cancers. Here, we report that CDK2 is a novel regulator of the ERK pathway via USP37 deubiquitinase (DUB). Mechanistically, CDK2 phosphorylates USP37, which is required for USP37 DUB activity. Further, USP37 deubiquitinates and stabilizes ERK1/2, thereby enhancing cancer cell proliferation. Thus, CDK2 is able to promote cell proliferation by activating USP37 and, in turn, stabilizing ERK1/2. Importantly, combined CDK1/2 and EGFR inhibitors have a synergetic anticancer effect through the downregulation of ERK1/2 stability and activity. Indeed, our patient-derived xenograft (PDX) results suggest that targeting both ERK1/2 stability and activity kills cancer cells more efficiently even at lower doses of these two inhibitors, which may reduce their associated side effects and indicate a potential new combination strategy for cancer therapy.

Abstract Objectives SSc is associated with increased health-care resource utilization and economic burden. The Collaborative National Quality and Efficacy Registry (CONQUER) is a US-based collaborative that collects longitudinal follow-up data on SSc patients with <5 years of disease duration enrolled at scleroderma centres in the USA. The objective of this study was to investigate the relationship between gastrointestinal tract symptoms and self-reported resource utilization in CONQUER participants. Methods CONQUER participants who had completed a baseline and 12-month Gastrointestinal Tract Questionnaire (GIT 2.0) and a Resource Utilization Questionnaire (RUQ) were included in this analysis. Patients were categorized by total GIT 2.0 severity: none-to-mild (0–0.49); moderate (0.50–1.00), and severe-to-very severe (1.01–3.00). Clinical features and medication exposures were examined in each of these categories. The 12-month RUQ responses were summarized by GIT 2.0 score categories at 12 months. Results Among the 211 CONQUER participants who met the inclusion criteria, most (64%) had mild GIT symptoms, 26% had moderate symptoms, and 10% severe GIT symptoms at 12 months. The categorization of GIT total severity score by RUQ showed that more upper endoscopy procedures and inpatient hospitalization occurred in the CONQUER participants with severe GIT symptoms. These patients with severe GIT symptoms also reported the use of more adaptive equipment. Conclusion This report from the CONQUER cohort suggests that severe GIT symptoms result in more resource utilization. It is especially important to understand resource utilization in early disease cohorts when disease activity, rather than damage, primarily contributes to health-related costs of SSc.