VaxBot-HPV: A GPT-based Chatbot for Answering HPV Vaccine-related Questions.

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.

The impact of postoperative adjuvant therapy on EGFR-mutated stage IA lung adenocarcinoma with micropapillary pathological subtypes.

BACKGROUND: Micropapillary (MPP) adenocarcinoma is considered one of the most aggressive pathological types of lung adenocarcinoma (LADC). This retrospective study aimed to evaluate the prognostic significance and benefit of postoperative adjuvant therapy (PAT) in stage IA LADC patients with different proportions of MPP components. MATERIALS AND METHODS: We retrospectively examined clinical stage IA LADC patients who underwent surgical resection between August 2012 and December 2019. In terms of the proportion of MPP components (TPM), the tumors were reclassified into three categories: MPP patterns absent (TPMN); low proportions of MPP components (TPML); and high proportions of MPP components (TPMH). The dates of recurrence and metastasis were identified based on physical examinations and were confirmed by histopathological examination. RESULTS: Overall, 505 (TPMN, n = 375; TPML, n = 92; TPMH, n = 38) patients harboring EGFR mutations were enrolled in the study. Male sex (P = 0.044), high pathological stage (P < 0.001), and MPP pathological subtype (P < 0.001) were more frequent in the TPM-positive (TPMP) group than in the TPM-negative (TPMN) group. Five-year disease-free survival (DFS) rates were significantly lower in the TPMP group than in the TPMN group (84.5% vs. 93.4%, P = 0.006). In addition, patients with high proportions (greater than 10%) of MPP components had worse overall survival (OS) (91.0% vs. 98.9%, P = 0.025) than those with low proportions (5%≤ TPM ≤ 10%). However, postoperative EGFR tyrosine kinase inhibitors (TKIs) or adjuvant chemotherapy (ACT) cannot improve DFS and OS between EGFR-mutated patients with different proportions of MPP components. CONCLUSION: MPP was related to earlier recurrence and shortened survival time, even in stage IA. Further research needs a larger sample size to clarify that EGFR-mutated stage IA patients with MPP components obtain survival benefits from adjuvant therapy.

Transforming of scalp EEGs with different channel locations by REST for comparative study.

OBJECTIVE: The diversity of electrode placement systems brought the problem of channel location harmonization in large-scale electroencephalography (EEG) applications to the forefront. Therefore, our goal was to resolve this problem by introducing and assessing the reference electrode standardization technique (REST) to transform EEGs into a common electrode distribution with computational zero reference at infinity offline. METHODS: Simulation and eye-closed resting-state EEG datasets were used to investigate the performance of REST for EEG signals and power configurations. RESULTS: REST produced small errors (the root mean square error (RMSE): 0.2936-0.4583; absolute errors: 0.2343-0.3657) and high correlations (>0.9) between the estimated signals and true ones. The comparison of configuration similarities in power among various electrode distributions revealed that REST induced infinity reference could maintain a perfect performance similar (>0.9) to that of true one. CONCLUSION: These results demonstrated that REST transformation could be adopted to resolve the channel location harmonization problem in large-scale EEG applications.

Mapping vaccine names in clinical trials to vaccine ontology using cascaded fine-tuned domain-specific language models.

BACKGROUND: Vaccines have revolutionized public health by providing protection against infectious diseases. They stimulate the immune system and generate memory cells to defend against targeted diseases. Clinical trials evaluate vaccine performance, including dosage, administration routes, and potential side effects. CLINICALTRIALS: gov is a valuable repository of clinical trial information, but the vaccine data in them lacks standardization, leading to challenges in automatic concept mapping, vaccine-related knowledge development, evidence-based decision-making, and vaccine surveillance. RESULTS: In this study, we developed a cascaded framework that capitalized on multiple domain knowledge sources, including clinical trials, the Unified Medical Language System (UMLS), and the Vaccine Ontology (VO), to enhance the performance of domain-specific language models for automated mapping of VO from clinical trials. The Vaccine Ontology (VO) is a community-based ontology that was developed to promote vaccine data standardization, integration, and computer-assisted reasoning. Our methodology involved extracting and annotating data from various sources. We then performed pre-training on the PubMedBERT model, leading to the development of CTPubMedBERT. Subsequently, we enhanced CTPubMedBERT by incorporating SAPBERT, which was pretrained using the UMLS, resulting in CTPubMedBERT + SAPBERT. Further refinement was accomplished through fine-tuning using the Vaccine Ontology corpus and vaccine data from clinical trials, yielding the CTPubMedBERT + SAPBERT + VO model. Finally, we utilized a collection of pre-trained models, along with the weighted rule-based ensemble approach, to normalize the vaccine corpus and improve the accuracy of the process. The ranking process in concept normalization involves prioritizing and ordering potential concepts to identify the most suitable match for a given context. We conducted a ranking of the Top 10 concepts, and our experimental results demonstrate that our proposed cascaded framework consistently outperformed existing effective baselines on vaccine mapping, achieving 71.8% on top 1 candidate's accuracy and 90.0% on top 10 candidate's accuracy. CONCLUSION: This study provides a detailed insight into a cascaded framework of fine-tuned domain-specific language models improving mapping of VO from clinical trials. By effectively leveraging domain-specific information and applying weighted rule-based ensembles of different pre-trained BERT models, our framework can significantly enhance the mapping of VO from clinical trials.

Light at night and lung cancer risk: A worldwide interdisciplinary and time-series study.

Background: Light at night (LAN) has become a concern in interdisciplinary research in recent years. This global interdisciplinary study aimed to explore the exposure-lag-response association between LAN exposure and lung cancer incidence. Methods: LAN data were obtained from the Defense Meteorological Satellite Program's Operational Linescan System. Data of lung cancer incidence, socio-demographic index, and smoking prevalence of populations in 201 countries/territories from 1992 to 2018 were collected from the Global Burden of Disease Study. Spearman correlation tests and population-weighted linear regression analysis were used to evaluate the correlation between LAN exposure and lung cancer incidence. A distributed lag nonlinear model (DLNM) was used to assess the exposure-lag effects of LAN exposure on lung cancer incidence. Results: The Spearman correlation coefficients were 0.286-0.355 and the population-weighted linear regression correlation coefficients were 0.361-0.527. After adjustment for socio-demographic index and smoking prevalence, the Spearman correlation coefficients were 0.264-0.357 and the population-weighted linear regression correlation coefficients were 0.346-0.497. In the DLNM, the maximum relative risk was 1.04 (1.02-1.06) at LAN exposure of 8.6 with a 2.6-year lag time. After adjustment for socio-demographic index and smoking prevalence, the maximum relative risk was 1.05 (1.02-1.07) at LAN exposure of 8.6 with a 2.4-year lag time. Conclusion: High LAN exposure was associated with increased lung cancer incidence, and this effect had a specific lag period. Compared with traditional individual-level studies, this group-level study provides a novel paradigm of effective, efficient, and scalable screening for risk factors.

Relation extraction using large language models: a case study on acupuncture point locations.

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.

Development of a genome atlas for discriminating benign, preinvasive, and invasive lung nodules.

To tackle misdiagnosis in lung cancer screening with low-dose computed tomography (LDCT), we aimed to compile a genome atlas for differentiating benign, preinvasive, and invasive lung nodules and characterize their molecular pathogenesis. We collected 432 lung nodule tissue samples from Chinese patients, spanning benign, atypical adenomatous hyperplasia (AAH), adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), and invasive adenocarcinoma (IA). We performed comprehensive sequencing, examining somatic variants, gene expressions, and methylation levels. Our findings uncovered EGFR and TP53 mutations as key drivers in - early lung cancer development, with EGFR mutation frequency increasing with disease progression. Both EGFR mutations and EGF/EGFR hypo-methylation activated the EGFR pathway, fueling cancer growth. Transcriptome analysis identified four lung nodule subtypes (G1-4) with distinct molecular features and immune cell infiltrations: EGFR-driven G1, EGFR/TP53 co-mutation G2, inflamed G3, stem-like G4. Estrogen/androgen response was associated with the EGFR pathway, proposing a new therapy combining tyrosine kinase inhibitors with antiestrogens. Preinvasive nodules exhibited stem cell pathway enrichment, potentially hindering invasion. Epigenetic regulation of various genes was essential for lung cancer initiation and development. This study provides insights into the molecular mechanism of neoplastic progression and identifies potential diagnostic biomarkers and therapeutic targets for lung cancer.

Exploring the Mechanism of H2S Synthesis in Male Bactrian Camel Poll Glands Based on Data Independent Acquisition Proteomics and Non-Targeted Metabolomics.

During estrus, the poll glands of male Bactrian Camels (Camelus Bactrianus) become slightly raised, exuding a large amount of pale yellow watery secretion with a characteristic odor that may contain hydrogen sulfide (H2S). However, whether H2S can be synthesized in the poll glands of male Bactrian Camels and its role in inducing camel estrus remains unclear. This study aimed to identify differentially expressed proteins (DEPs) and signaling pathways in the poll gland tissues of male Bactrian Camels using data independent acquisition (DIA) proteomics. Additionally, gas chromatography-mass spectrometry (GC-MS) was performed to identify differentially expressed metabolites (DEMs) in the neck hair containing secretions during estrus in male Bactrian Camels, to explore the specific expression patterns and mechanisms in the poll glands of camels during estrus. The results showed that cystathionine-γ-lyase (CTH) and cystathionine-ß-synthase (CBS), which are closely related to H2S synthesis in camel poll glands during estrus, were mainly enriched in glycine, serine, and threonine metabolism, amino acid biosynthesis, and metabolic pathways. In addition, both enzymes were widely distributed and highly expressed in the acinar cells of poll gland tissues in camels during estrus. Meanwhile, the neck hair secretion contains high levels of amino acids, especially glycine, serine, threonine, and cystathionine, which are precursors for H2S biosynthesis. These results demonstrate that the poll glands of male Bactrian Camels can synthesize and secrete H2S during estrus. This study provides a basis for exploring the function and mechanism of H2S in the estrus of Bactrian Camels.

Prognostic patterns in invasion lymph nodes of lung adenocarcinoma reveal distinct tumor microenvironments.

Tumor-draining lymph nodes (TDLNs) are usually the first station of tumor metastasis in lung cancer. TDLNs+ have distinct pathomorphologic and tumor microenvironment (TME)-compositional patterns, which still need to be thoroughly investigated in lung adenocarcinoma (LUAD). Here, we enrolled 312 LUAD patients with TDLNs+ from our institution between 2015 and 2019. 3DHISTECH was used to scan all of the TDLNs+. Based on morphologic features, TDLNs+ patterns were classified as polarized-type or scattered-type, and TME-compositional patterns were classified as colloid-type, necrosis-type, specific-type, and common-type. Multivariate analysis revealed an increased risk of early recurrence associated with scattered-type (HR 2.37, 95% CI: 1.06-5.28), colloid-type (HR 1.95, 95% CI: 1.03-3.67), and necrosis-type (HR 2.21, 95% CI: 1.13-4.89). NanoString transcriptional analysis revealed an immunosuppression and vascular invasion hallmark in scattered and necrosis patterns and an immunoactivated hallmark in polarized and common patterns. According to imaging mass cytometry (IMC), the scattered and necrosis patterns revealed that germinal centers (GC) were compromised, GCB cell and T cell proliferation were deficient, tumor cells had the potential for proliferation, and the immune attack may be weaker. In this study, we present evidence that LUAD patients have distinct patterns and immune hallmarks of TDLNs+ related to their prognosis.

Adverse Events of COVID-19 Vaccines in the United States: Temporal and Spatial Analysis.

BACKGROUND: The COVID-19 pandemic, caused by SARS-CoV-2, has had a profound impact worldwide, leading to widespread morbidity and mortality. Vaccination against COVID-19 is a critical tool in controlling the spread of the virus and reducing the severity of the disease. However, the rapid development and deployment of COVID-19 vaccines have raised concerns about potential adverse events following immunization (AEFIs). Understanding the temporal and spatial patterns of these AEFIs is crucial for an effective public health response and vaccine safety monitoring. OBJECTIVE: This study aimed to analyze the temporal and spatial characteristics of AEFIs associated with COVID-19 vaccines in the United States reported to the Vaccine Adverse Event Reporting System (VAERS), thereby providing insights into the patterns and distributions of the AEFIs, the safety profile of COVID-19 vaccines, and potential risk factors associated with the AEFIs. METHODS: We conducted a retrospective analysis of administration data from the Centers for Disease Control and Prevention (n=663,822,575) and reports from the surveillance system VAERS (n=900,522) between 2020 and 2022. To gain a broader understanding of postvaccination AEFIs reported, we categorized them into system organ classes (SOCs) according to the Medical Dictionary for Regulatory Activities. Additionally, we performed temporal analysis to examine the trends of AEFIs in all VAERS reports, those related to Pfizer-BioNTech and Moderna, and the top 10 AEFI trends in serious reports. We also compared the similarity of symptoms across various regions within the United States. RESULTS: Our findings revealed that the most frequently reported symptoms following COVID-19 vaccination were headache (n=141,186, 15.68%), pyrexia (n=122,120, 13.56%), and fatigue (n=121,910, 13.54%). The most common symptom combination was chills and pyrexia (n=56,954, 6.32%). Initially, general disorders and administration site conditions (SOC 22) were the most prevalent class reported. Moderna exhibited a higher reporting rate of AEFIs compared to Pfizer-BioNTech. Over time, we observed a decreasing reporting rate of AEFIs associated with COVID-19 vaccines. In addition, the overall rates of AEFIs between the Pfizer-BioNTech and Moderna vaccines were comparable. In terms of spatial analysis, the middle and north regions of the United States displayed a higher reporting rate of AEFIs associated with COVID-19 vaccines, while the southeast and south-central regions showed notable similarity in symptoms reported. CONCLUSIONS: This study provides valuable insights into the temporal and spatial patterns of AEFIs associated with COVID-19 vaccines in the United States. The findings underscore the critical need for increasing vaccination coverage, as well as ongoing surveillance and monitoring of AEFIs. Implementing targeted monitoring programs can facilitate the effective and efficient management of AEFIs, enhancing public confidence in future COVID-19 vaccine campaigns.

Spatial whole exome sequencing reveals the genetic features of highly-aggressive components in lung adenocarcinoma.

In invasive lung adenocarcinoma (LUAD), patients with micropapillary (MIP) or solid (SOL) components had a significantly poorer prognosis than those with only lepidic (LEP), acinar (ACI) or papillary (PAP) components. It is interesting to explore the genetic features of different histologic subtypes, especially the highly aggressive components. Based on a cohort of 5,933 patients, this study observed that in different tumor size groups, LUAD with MIP/SOL components showed a different prevalence, and patients with ALK alteration or TP53 mutations had a higher probability of developing MIP/SOL components. To control individual differences, this research used spatial whole-exome sequencing (WES) via laser-capture microdissection of five patients harboring these five coexistent components and identified genetic features among different histologic components of the same tumor. In tracing the evolution of components, we found that titin (TTN) mutation might serve as a crucial intratumor potential driver for MIP/SOL components, which was validated by a cohort of 146 LUAD patients undergoing bulk WES. Functional analysis revealed that TTN mutations enriched the complement and coagulation cascades, which correlated with the pathway of cell adhesion, migration, and proliferation. Collectively, the histologic subtypes of invasive LUAD were genetically different, and certain trunk genotypes might synergize with branching TTN mutation to develop highly aggressive components.

Extracting Systemic Anticancer Therapy and Response Information From Clinical Notes Following the RECIST Definition.

PURPOSE: The RECIST guidelines provide a standardized approach for evaluating the response of cancer to treatment, allowing for consistent comparison of treatment efficacy across different therapies and patients. However, collecting such information from electronic health records manually can be extremely labor-intensive and time-consuming because of the complexity and volume of clinical notes. The aim of this study is to apply natural language processing (NLP) techniques to automate this process, minimizing manual data collection efforts, and improving the consistency and reliability of the results. METHODS: We proposed a complex, hybrid NLP system that automates the process of extracting, linking, and summarizing anticancer therapy and associated RECIST-like responses from narrative clinical text. The system consists of multiple machine learning-/deep learning-based and rule-based modules for diverse NLP tasks such as named entity recognition, assertion classification, relation extraction, and text normalization, to address different challenges associated with anticancer therapy and response information extraction. We then evaluated the system performances on two independent test sets from different institutions to demonstrate its effectiveness and generalizability. RESULTS: The system used domain-specific language models, BioBERT and BioClinicalBERT, for high-performance therapy mentions identification and RECIST responses extraction and categorization. The best-performing model achieved a 0.66 score in linking therapy and RECIST response mentions, with end-to-end performance peaking at 0.74 after relation normalization, indicating substantial efficacy with room for improvement. CONCLUSION: We developed, implemented, and tested an information extraction system from clinical notes for cancer treatment and efficacy assessment information. We expect this system will support future cancer research, particularly oncologic studies that focus on efficiently assessing the effectiveness and reliability of cancer therapeutics.

[Results of Lung Cancer Screening with Low-dose Computed Tomography 
and Exploration of Risk Factors in Guangzhou].

BACKGROUND: Both of lung cancer incidence and mortality rank first among all cancers in China. Previous lung cancer screening trials were mostly selective screening for high-risk groups such as smokers. Non-smoking women accounted for a considerable proportion of lung cancer cases in Asia. This study aimed to evaluate the outcome of community-based mass screening in Guangzhou and identify the high-risk factors for lung cancer. METHODS: Residents aged 40-74 years in Guangzhou were screened with low-dose computed tomography (LDCT) for lung cancer and the pulmonary nodules were classified and managed according to China National Lung Cancer Screening Guideline with Low-dose Computed Tomography (2018 version). The detection rate of positive nodules was calculated. Before the LDCT examination, residents were required to complete a "lung cancer risk factors questionnaire". The risk factors of the questionnaire were analyzed by least absolute shrinkage and selection operator (LASSO) penalized Logistic regression analysis. RESULTS: A total of 6256 residents were included in this study. 1228 positive nodules (19.63%) and 117 lung cancers were confirmed, including 6 cases of Tis, 103 cases of stage I (accounting for 88.03% of lung cancer). The results of LASSO penalized Logistic regression analysis indicated that age ≥50 yr (OR=1.07, 95%CI: 1.06-1.07), history of cancer (OR=3.29, 95%CI: 3.22-3.37), textile industry (OR=1.10, 95%CI: 1.08-1.13), use coal for cooking in childhood (OR=1.14, 95%CI: 1.13-1.16) and food allergy (OR=1.10, 95%CI: 1.07-1.13) were risk factors of lung cancer for female in this district. CONCLUSIONS: This study highlighted that numerous early stages of lung cancer cases were detected by LDCT, which could be applied to screening of lung cancer in women. Besides, age ≥50 yr, personal history of cancer, textile industry and use coal for cooking in childhood are risk factors for women in this district, which suggested that it's high time to raise the awareness of early lung cancer screening in this group.

RefAI: a GPT-powered retrieval-augmented generative tool for biomedical literature recommendation and summarization.

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 impact of PET/CT and brain MRI for metastasis detection among patients with clinical T1-category lung cancer: Findings from a large-scale cohort study.

PURPOSE: [18F]-FDG PET/CT and brain MRI are common approaches to detect metastasis in patients of lung cancer. Current guidelines for the use of PET/CT and MRI in clinical T1-category lung cancer lack risk-based stratification and require optimization. This study stratified patients based on metastatic risk in terms of the lesions' size and morphological characteristics. METHODS: The detection rate of metastasis was measured in different sizes and morphological characteristics (solid and sub-solid) of tumors. To confirm the cut-off value for discriminating metastasis and overall survival (OS) prediction, the receiver operating characteristic (ROC) analysis was performed based on PET/CT metabolic parameters (SUVmax/SUVmean/SULpeak/MTV/TLG), followed by Kaplan-Meier analysis for survival in post-operation patients with and without PET/CT plus MRI. RESULTS: 2,298 patients were included. No metastasis was observed in patients with solid nodules < 8.0 mm and sub-solid nodules < 10.0 mm. The cut-off of PET/CT metabolic parameters on discriminating metastasis were 1.09 (SUVmax), 0.26 (SUVmean), 0.31 (SULpeak), 0.55 (MTV), and 0.81 (TLG), respectively. Patients undergoing PET/CT plus MRI exhibited longer OS compared to those who did not receive it in solid nodules ≥ 8.0 mm & sub-solid nodules ≥ 10.0 mm (HR, 0.44; p < 0.001); in solid nodules ≥ 8.0 mm (HR, 0.12; p<0.001) and in sub-solid nodules ≥ 10.0 mm (HR; 0.61; p=0.075), respectively. Compared to patients with metabolic parameters lower than cut-off values, patients with higher metabolic parameters displayed shorter OS: SUVmax (HR, 12.94; p < 0.001), SUVmean (HR, 11.33; p <0.001), SULpeak (HR, 9.65; p < 0.001), MTV (HR, 9.16; p = 0.031), and TLG (HR, 12.06; p < 0.001). CONCLUSION: The necessity of PET/CT and MRI should be cautiously evaluated in patients with solid nodules < 8.0 mm and sub-solid nodules < 10.0 mm, however, these examinations remained essential and beneficial for patients with solid nodules ≥ 8.0 mm and sub-solid nodules ≥ 10.0 mm.

Prompt Tuning in Biomedical Relation Extraction.

Biomedical relation extraction (RE) is critical in constructing high-quality knowledge graphs and databases as well as supporting many downstream text mining applications. This paper explores prompt tuning on biomedical RE and its few-shot scenarios, aiming to propose a simple yet effective model for this specific task. Prompt tuning reformulates natural language processing (NLP) downstream tasks into masked language problems by embedding specific text prompts into the original input, facilitating the adaption of pre-trained language models (PLMs) to better address these tasks. This study presents a customized prompt tuning model designed explicitly for biomedical RE, including its applicability in few-shot learning contexts. The model's performance was rigorously assessed using the chemical-protein relation (CHEMPROT) dataset from BioCreative VI and the drug-drug interaction (DDI) dataset from SemEval-2013, showcasing its superior performance over conventional fine-tuned PLMs across both datasets, encompassing few-shot scenarios. This observation underscores the effectiveness of prompt tuning in enhancing the capabilities of conventional PLMs, though the extent of enhancement may vary by specific model. Additionally, the model demonstrated a harmonious balance between simplicity and efficiency, matching state-of-the-art performance without needing external knowledge or extra computational resources. The pivotal contribution of our study is the development of a suitably designed prompt tuning model, highlighting prompt tuning's effectiveness in biomedical RE. It offers a robust, efficient approach to the field's challenges and represents a significant advancement in extracting complex relations from biomedical texts. Supplementary Information: The online version contains supplementary material available at 10.1007/s41666-024-00162-9.

The activity and immune dynamics of PD-1 inhibition on high-risk pulmonary ground glass opacity lesions: insights from a single-arm, phase II trial.

Immune checkpoint inhibitors targeting the programmed cell death-1 (PD-1) protein significantly improve survival in patients with advanced non-small-cell lung cancer (NSCLC), but its impact on early-stage ground-glass opacity (GGO) lesions remains unclear. This is a single-arm, phase II trial (NCT04026841) using Simon's optimal two-stage design, of which 4 doses of sintilimab (200 mg per 3 weeks) were administrated in 36 enrolled multiple primary lung cancer (MPLC) patients with persistent high-risk (Lung-RADS category 4 or had progressed within 6 months) GGOs. The primary endpoint was objective response rate (ORR). T/B/NK-cell subpopulations, TCR-seq, cytokines, exosomal RNA, and multiplexed immunohistochemistry (mIHC) were monitored and compared between responders and non-responders. Finally, two intent-to-treat (ITT) lesions (pure-GGO or GGO-predominant) showed responses (ORR: 5.6%, 2/36), and no patients had progressive disease (PD). No grade 3-5 TRAEs occurred. The total response rate considering two ITT lesions and three non-intent-to-treat (NITT) lesions (pure-solid or solid-predominant) was 13.9% (5/36). The proportion of CD8+ T cells, the ratio of CD8+/CD4+, and the TCR clonality value were significantly higher in the peripheral blood of responders before treatment and decreased over time. Correspondingly, the mIHC analysis showed more CD8+ T cells infiltrated in responders. Besides, responders' cytokine concentrations of EGF and CTLA-4 increased during treatment. The exosomal expression of fatty acid metabolism and oxidative phosphorylation gene signatures were down-regulated among responders. Collectively, PD-1 inhibitor showed certain activity on high-risk pulmonary GGO lesions without safety concerns. Such effects were associated with specific T-cell re-distribution, EGF/CTLA-4 cytokine compensation, and regulation of metabolism pathways.

Ensemble pretrained language models to extract biomedical knowledge from literature.

OBJECTIVES: The rapid expansion of biomedical literature necessitates automated techniques to discern relationships between biomedical concepts from extensive free text. Such techniques facilitate the development of detailed knowledge bases and highlight research deficiencies. The LitCoin Natural Language Processing (NLP) challenge, organized by the National Center for Advancing Translational Science, aims to evaluate such potential and provides a manually annotated corpus for methodology development and benchmarking. MATERIALS AND METHODS: For the named entity recognition (NER) task, we utilized ensemble learning to merge predictions from three domain-specific models, namely BioBERT, PubMedBERT, and BioM-ELECTRA, devised a rule-driven detection method for cell line and taxonomy names and annotated 70 more abstracts as additional corpus. We further finetuned the T0pp model, with 11 billion parameters, to boost the performance on relation extraction and leveraged entites' location information (eg, title, background) to enhance novelty prediction performance in relation extraction (RE). RESULTS: Our pioneering NLP system designed for this challenge secured first place in Phase I-NER and second place in Phase II-relation extraction and novelty prediction, outpacing over 200 teams. We tested OpenAI ChatGPT 3.5 and ChatGPT 4 in a Zero-Shot setting using the same test set, revealing that our finetuned model considerably surpasses these broad-spectrum large language models. DISCUSSION AND CONCLUSION: Our outcomes depict a robust NLP system excelling in NER and RE across various biomedical entities, emphasizing that task-specific models remain superior to generic large ones. Such insights are valuable for endeavors like knowledge graph development and hypothesis formulation in biomedical research.