RESUMO
Reception is an essential process for patients seeking medical care and a critical component influencing the healthcare experience. However, current communication systems rely mainly on human efforts, which are both labor and knowledge intensive. A promising alternative is to leverage the capabilities of large language models (LLMs) to assist the communication in medical center reception sites. Here we curated a unique dataset comprising 35,418 cases of real-world conversation audio corpus between outpatients and receptionist nurses from 10 reception sites across two medical centers, to develop a site-specific prompt engineering chatbot (SSPEC). The SSPEC efficiently resolved patient queries, with a higher proportion of queries addressed in fewer rounds of queries and responses (Q&Rs; 68.0% ≤2 rounds) compared with nurse-led sessions (50.5% ≤2 rounds) (P = 0.009) across administrative, triaging and primary care concerns. We then established a nurse-SSPEC collaboration model, overseeing the uncertainties encountered during the real-world deployment. In a single-center randomized controlled trial involving 2,164 participants, the primary endpoint indicated that the nurse-SSPEC collaboration model received higher satisfaction feedback from patients (3.91 ± 0.90 versus 3.39 ± 1.15 in the nurse group, P < 0.001). Key secondary outcomes indicated reduced rate of repeated Q&R (3.2% versus 14.4% in the nurse group, P < 0.001) and reduced negative emotions during visits (2.4% versus 7.8% in the nurse group, P < 0.001) and enhanced response quality in terms of integrity (4.37 ± 0.95 versus 3.42 ± 1.22 in the nurse group, P < 0.001), empathy (4.14 ± 0.98 versus 3.27 ± 1.22 in the nurse group, P < 0.001) and readability (3.86 ± 0.95 versus 3.71 ± 1.07 in the nurse group, P = 0.006). Overall, our study supports the feasibility of integrating LLMs into the daily hospital workflow and introduces a paradigm for improving communication that benefits both patients and nurses. Chinese Clinical Trial Registry identifier: ChiCTR2300077245 .
RESUMO
Relation Extraction (RE) is a natural language processing (NLP) task for extracting semantic relations between biomedical entities. Recent developments in pre-trained large language models (LLM) motivated NLP researchers to use them for various NLP tasks. We investigated GPT-3.5-turbo and GPT-4 on extracting the relations from three standard datasets, EU-ADR, Gene Associations Database (GAD), and ChemProt. Unlike the existing approaches using datasets with masked entities, we used three versions for each dataset for our experiment: a version with masked entities, a second version with the original entities (unmasked), and a third version with abbreviations replaced with the original terms. We developed the prompts for various versions and used the chat completion model from GPT API. Our approach achieved a F1-score of 0.498 to 0.809 for GPT-3.5-turbo, and a highest F1-score of 0.84 for GPT-4. For certain experiments, the performance of GPT, BioBERT, and PubMedBERT are almost the same.
RESUMO
The consistent and persuasive evidence illustrating the influence of social determinants on health has prompted a growing realization throughout the health care sector that enhancing health and health equity will likely depend, at least to some extent, on addressing detrimental social determinants. However, detailed social determinants of health (SDoH) information is often buried within clinical narrative text in electronic health records (EHRs), necessitating natural language processing (NLP) methods to automatically extract these details. Most current NLP efforts for SDoH extraction have been limited, investigating on limited types of SDoH elements, deriving data from a single institution, focusing on specific patient cohorts or note types, with reduced focus on generalizability. This study aims to address these issues by creating cross-institutional corpora spanning different note types and healthcare systems, and developing and evaluating the generalizability of classification models, including novel large language models (LLMs), for detecting SDoH factors from diverse types of notes from four institutions: Harris County Psychiatric Center, University of Texas Physician Practice, Beth Israel Deaconess Medical Center, and Mayo Clinic. Four corpora of deidentified clinical notes were annotated with 21 SDoH factors at two levels: level 1 with SDoH factor types only and level 2 with SDoH factors along with associated values. Three traditional classification algorithms (XGBoost, TextCNN, Sentence BERT) and an instruction tuned LLM-based approach (LLaMA) were developed to identify multiple SDoH factors. Substantial variation was noted in SDoH documentation practices and label distributions based on patient cohorts, note types, and hospitals. The LLM achieved top performance with micro-averaged F1 scores over 0.9 on level 1 annotated corpora and an F1 over 0.84 on level 2 annotated corpora. While models performed well when trained and tested on individual datasets, cross-dataset generalization highlighted remaining obstacles. To foster collaboration, access to partial annotated corpora and models trained by merging all annotated datasets will be made available on the PhysioNet repository.
RESUMO
Purpose: To evaluate the clinical usefulness of digital radiography dacryocystography in patients with primary acquired nasolacrimal duct obstruction prior to endoscopic dacryocystorhinostomy. Methods: All dacryocystography images from 129 patients with primary acquired nasolacrimal duct obstruction were analyzed. Each group was assessed for postoperative epiphora severity using Munk's score via telephone follow-up three years post-surgery. Receiver operating characteristic (ROC) curve was plotted to obtain a suitable cutoff value of the transverse diameter of the lacrimal sac (LS), used to categorize LS size into small (≤4.350 mm) and large (>4.350 mm). Results: Analysis of the transverse diameter of the LS among 129 patients showed a negative correlation between it and Munk's score (r = -0.282, p = 0.001). There was a statistical difference between the surgical outcomes and the sizes of the LS (p = 0.041). The ROC curve analysis showed that the transverse diameter of the LS at 4.350 mm was the ideal cutoff value for the outcome of endoscopic dacryocystorhinostomy, with a sensitivity of 42.2 %, and specificity of 92.3 %. After adjusting for the age and sex, the small LS was associated with an increased risk of postoperative failed outcome (adjusted odds ratio [95 % CI]: 8.628 [1.074, 69.335]). Conclusion: The small LS was independently associated with the failed surgical outcome. Furthermore, the preoperative measurement of the LS transverse diameter serves as one of the reliable predictors for postoperative epiphora severity.
RESUMO
Recent advancements in large language models (LLMs) such as ChatGPT and LLaMA have hinted at their potential to revolutionize medical applications, yet their application in clinical settings often reveals limitations due to a lack of specialized training on medical-specific data. In response to this challenge, this study introduces Me-LLaMA, a novel medical LLM family that includes foundation models - Me-LLaMA 13/70B, along with their chat-enhanced versions - Me-LLaMA 13/70B-chat, developed through continual pre-training and instruction tuning of LLaMA2 using large medical datasets. Our methodology leverages a comprehensive domain-specific data suite, including a large-scale, continual pre-training dataset with 129B tokens, an instruction tuning dataset with 214k samples, and a new medical evaluation benchmark (MIBE) across six critical medical tasks with 12 datasets. Our extensive evaluation using the MIBE shows that Me-LLaMA models achieve overall better performance than existing open-source medical LLMs in zero-shot, few-shot and supervised learning abilities. With task-specific instruction tuning, Me-LLaMA models outperform ChatGPT on 7 out of 8 datasets and GPT-4 on 5 out of 8 datasets. In addition, we investigated the catastrophic forgetting problem, and our results show that Me-LLaMA models outperform other open-source medical LLMs in mitigating this issue. Me-LLaMA is one of the largest open-source medical foundation LLMs that use both biomedical and clinical data. It exhibits superior performance across both general and medical tasks compared to other open-source medical LLMs, rendering it an attractive choice for medical AI applications. We release our models, datasets, and evaluation scripts at: https://github.com/BIDS-Xu-Lab/Me-LLaMA.
RESUMO
BACKGROUND: Flap transplantation is a widely used plastic repair technique in surgical procedures, aimed at addressing skin defects resulting from diverse wounds and diseases. However, due to the insufficient blood supply after flap surgery, the occurrence of ischemia-reperfusion injury, and an excessive sterile inflammatory response, flaps frequently develop complications (e.g., partial or complete ischemic necrosis). These complications have adverse effects on wound healing and repair. ß-Caryophyllene (BCP) is a bicyclic sesquiterpene that is widely present in plants. It mitigates oxidative stress and inflammatory responses, demonstrates neuroprotective and analgesic properties, and serves a protective function in organs or tissues subjected to ischemia-reperfusion injury. However, no study has confirmed whether BCP can be used in the field of flap transplantation to improve the flap survival rate. METHODS: To assess the impact of BCP on random flap survival, we constructed a modified McFarlane random flap model on the rat. After 7 consecutive days of gavage with different doses of BCP, we measured the survival area ratio, angiogenesis, blood perfusion, tissue inflammation level, apoptosis-related protein levels, and the PI3K/AKT signaling pathway expression of the random flap. RESULTS: BCP treatment increased the survival area of the flap in a dose-dependent manner after random flap transplantation in rats. BCP mainly promoted the formation of tissue blood vessels, improved flap blood perfusion, limited the local inflammatory response, and reduced apoptosis. In addition, we demonstrated that BCP works primarily by promoting the PI3K/AKT signaling expression while enhancing the phosphorylation of AKT. Administration of wortmannin, a selective inhibitor of PI3K, eliminated the effects of BCP. CONCLUSION: BCP can promote the survival of random flaps by upregulating the PI3K/AKT signaling pathway, increasing tissue blood perfusion, and limiting the inflammatory response and apoptosis.
Assuntos
Fosfatidilinositol 3-Quinases , Sesquiterpenos Policíclicos , Proteínas Proto-Oncogênicas c-akt , Ratos Sprague-Dawley , Transdução de Sinais , Retalhos Cirúrgicos , Animais , Proteínas Proto-Oncogênicas c-akt/metabolismo , Transdução de Sinais/efeitos dos fármacos , Sesquiterpenos Policíclicos/farmacologia , Fosfatidilinositol 3-Quinases/metabolismo , Masculino , Ratos , Regulação para Cima/efeitos dos fármacos , Pele/efeitos dos fármacos , Pele/irrigação sanguínea , Sesquiterpenos/farmacologia , Apoptose/efeitos dos fármacosRESUMO
Cervical cancer is a significant global health issue, its prevalence and prognosis highlighting the importance of early screening for effective prevention. This research aimed to create and validate an artificial intelligence cervical cancer screening (AICCS) system for grading cervical cytology. The AICCS system was trained and validated using various datasets, including retrospective, prospective, and randomized observational trial data, involving a total of 16,056 participants. It utilized two artificial intelligence (AI) models: one for detecting cells at the patch-level and another for classifying whole-slide image (WSIs). The AICCS consistently showed high accuracy in predicting cytology grades across different datasets. In the prospective assessment, it achieved an area under curve (AUC) of 0.947, a sensitivity of 0.946, a specificity of 0.890, and an accuracy of 0.892. Remarkably, the randomized observational trial revealed that the AICCS-assisted cytopathologists had a significantly higher AUC, specificity, and accuracy than cytopathologists alone, with a notable 13.3% enhancement in sensitivity. Thus, AICCS holds promise as an additional tool for accurate and efficient cervical cancer screening.
Assuntos
Inteligência Artificial , Detecção Precoce de Câncer , Neoplasias do Colo do Útero , Adulto , Feminino , Humanos , Pessoa de Meia-Idade , Área Sob a Curva , Colo do Útero/patologia , Detecção Precoce de Câncer/métodos , Gradação de Tumores , Estudos Prospectivos , Estudos Retrospectivos , Sensibilidade e Especificidade , Neoplasias do Colo do Útero/diagnóstico , Neoplasias do Colo do Útero/patologiaRESUMO
Lung adenocarcinoma (LUAD) is the most prevalent histological type of lung cancer. Previous studies have reported that specific long noncoding RNAs (lncRNA) are involved in cancer development and progression. The phenotype and mechanism of ENST00000440028, named MSL3P1, an lncRNA referred to as a cancer-testis gene with potential roles in tumorigenesis and progression, have not been reported. MSL3P1 is overexpressed in LUAD tumor tissues, which is significantly associated with clinical characteristics, metastasis, and poor clinical prognosis. MSL3P1 promotes the metastasis of LUAD in vitro and in vivo. The enhancer reprogramming in LUAD tumor tissue is the major driver of the aberrant expression of MSL3P1. Mechanistically, owing to the competitive binding to CUL3 mRNA with ZFC3H1 protein (a protein involved in targeting polyadenylated RNA to exosomes and promoting the degradation of target mRNA), MSL3P1 can prevent the ZFC3H1-mediated RNA degradation of CUL3 mRNA and transport it to the cytoplasm. This activates the downstream epithelial-to-mesenchymal transition signaling pathway and promotes tumor invasion and metastasis. Implications: This study indicates that lncRNA MSL3P1 regulates CUL3 mRNA stability and promotes metastasis and holds potential as a prognostic biomarker and therapeutic target in LUAD.
Assuntos
Adenocarcinoma de Pulmão , Proteínas Culina , Neoplasias Pulmonares , Metástase Neoplásica , Estabilidade de RNA , RNA Longo não Codificante , Humanos , RNA Longo não Codificante/genética , RNA Longo não Codificante/metabolismo , Proteínas Culina/metabolismo , Proteínas Culina/genética , Adenocarcinoma de Pulmão/genética , Adenocarcinoma de Pulmão/patologia , Adenocarcinoma de Pulmão/metabolismo , Neoplasias Pulmonares/genética , Neoplasias Pulmonares/patologia , Neoplasias Pulmonares/metabolismo , Neoplasias Pulmonares/secundário , Animais , Camundongos , RNA Mensageiro/genética , RNA Mensageiro/metabolismo , Masculino , Linhagem Celular Tumoral , Citoplasma/metabolismo , Prognóstico , Regulação Neoplásica da Expressão Gênica , Camundongos Nus , Feminino , Transição Epitelial-Mesenquimal/genéticaRESUMO
PubTator 3.0 (https://www.ncbi.nlm.nih.gov/research/pubtator3/) is a biomedical literature resource using state-of-the-art AI techniques to offer semantic and relation searches for key concepts like proteins, genetic variants, diseases and chemicals. It currently provides over one billion entity and relation annotations across approximately 36 million PubMed abstracts and 6 million full-text articles from the PMC open access subset, updated weekly. PubTator 3.0's online interface and API utilize these precomputed entity relations and synonyms to provide advanced search capabilities and enable large-scale analyses, streamlining many complex information needs. We showcase the retrieval quality of PubTator 3.0 using a series of entity pair queries, demonstrating that PubTator 3.0 retrieves a greater number of articles than either PubMed or Google Scholar, with higher precision in the top 20 results. We further show that integrating ChatGPT (GPT-4) with PubTator APIs dramatically improves the factuality and verifiability of its responses. In summary, PubTator 3.0 offers a comprehensive set of features and tools that allow researchers to navigate the ever-expanding wealth of biomedical literature, expediting research and unlocking valuable insights for scientific discovery.
Assuntos
PubMed , Inteligência Artificial , Humanos , Software , Mineração de Dados/métodos , Semântica , InternetRESUMO
PURPOSE: To update the Age-Related Eye Disease Study (AREDS) simplified severity scale for risk of late age-related macular degeneration (AMD), including incorporation of reticular pseudodrusen (RPD), and to perform external validation on the Age-Related Eye Disease Study 2 (AREDS2). DESIGN: Post hoc analysis of 2 clinical trial cohorts: AREDS and AREDS2. PARTICIPANTS: Participants with no late AMD in either eye at baseline in AREDS (n = 2719) and AREDS2 (n = 1472). METHODS: Five-year rates of progression to late AMD were calculated according to levels 0 to 4 on the simplified severity scale after 2 updates: (1) noncentral geographic atrophy (GA) considered part of the outcome, rather than a risk feature, and (2) scale separation according to RPD status (determined by validated deep learning grading of color fundus photographs). MAIN OUTCOME MEASURES: Five-year rate of progression to late AMD (defined as neovascular AMD or any GA). RESULTS: In the AREDS, after the first scale update, the 5-year rates of progression to late AMD for levels 0 to 4 were 0.3%, 4.5%, 12.9%, 32.2%, and 55.6%, respectively. As the final simplified severity scale, the 5-year progression rates for levels 0 to 4 were 0.3%, 4.3%, 11.6%, 26.7%, and 50.0%, respectively, for participants without RPD at baseline and 2.8%, 8.0%, 29.0%, 58.7%, and 72.2%, respectively, for participants with RPD at baseline. In external validation on the AREDS2, for levels 2 to 4, the progression rates were similar: 15.0%, 27.7%, and 45.7% (RPD absent) and 26.2%, 46.0%, and 73.0% (RPD present), respectively. CONCLUSIONS: The AREDS AMD simplified severity scale has been modernized with 2 important updates. The new scale for individuals without RPD has 5-year progression rates of approximately 0.5%, 4%, 12%, 25%, and 50%, such that the rates on the original scale remain accurate. The new scale for individuals with RPD has 5-year progression rates of approximately 3%, 8%, 30%, 60%, and 70%, that is, approximately double for most levels. This scale fits updated definitions of late AMD, has increased prognostic accuracy, seems generalizable to similar populations, but remains simple for broad risk categorization. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
RESUMO
BACKGROUND: Although obesity and heart rate (HR) were closely related to the prevalence and development of type 2 diabetes mllitus (T2DM), few studies have shown a co-association effect of them on T2DM. We aimed at assessing the interactive effects of HR and obesity with prevalence of T2DM in Chinese population, providing the exact cutpoint of the risk threshold for blood glucose with high HR. MATERIALS AND METHODS: In the Risk Evaluation of cAncers in Chinese diabeTic Individuals: a lONgitudinal study (REACTION) cohorts (N = 8398), the relationship between HR and T2DM was explored by linear regression, logistic regression, and restricted cubic spline, and odds ratios (ORs) and 95% confidence intervals (CIs) were calculated. Interaction terms between HR and body mass index (BMI) and HR and waist circumference (WC) were introduced into the logistic regression model. RESULTS: In those with HR > 88.0 beats/min, fasting plasma glucose and oral glucose tolerance tests were significantly correlated with HR, and the prevalence of T2DM was highly correlated with HR (all p < .05). There were interactive associations of HR and obesity in patients with T2DM with HR < 74 beats/min. CONCLUSION: High HR was in interaction with obesity, associating with prevalence of T2DM. The newly subdivided risk threshold for HR with T2DM might be HR > 88 beats/minute.
Assuntos
Diabetes Mellitus Tipo 2 , Humanos , Diabetes Mellitus Tipo 2/epidemiologia , Diabetes Mellitus Tipo 2/complicações , Fatores de Risco , Estudos Longitudinais , Frequência Cardíaca , Obesidade/complicações , Obesidade/epidemiologia , Índice de Massa Corporal , Circunferência da CinturaRESUMO
PURPOSE: This study aims to assess the extent to which the demand for ophthalmologic care among patients at the state level is reflected in Google Trends data, serving as an indicator of patient desire in ophthalmology. METHODS: For each state, patient interest in ophthalmologic care was estimated using the Google Trends resource measuring web search and YouTube search rates for multiple ophthalmologic terms. We compared the change in search for ophthalmologic terms over time and used ordinary least squares regression to evaluate whether search interest for ophthalmologic terms was able to predict the rate of practicing ophthalmologists in each state. We also compare the changing rates of searches across the web and YouTube to evaluate the resources patients are most likely to utilize. RESULTS: From 2008 to 2022, web search rates for general ophthalmology related terms increased by 43.98%, while search interest for retinal specific terms increased by 19.51%. YouTube specific results for general ophthalmology terms increased by 55.83% while search for retinal terms fell by 58.48%. Ophthalmologic and retinal specific search interest was not significantly associated with either outcome. CONCLUSIONS: Our findings suggest that patient information needs, demographic elements, and the educational backgrounds of residents and fellows - those important factors - are surprisingly poorly correlated with ophthalmology provider density. Furthermore, we observed no noteworthy correlation between the search interest in ophthalmology and the overall density of ophthalmologists or retinal specialists. This implies that there is a pressing need to explore and implement strategies aimed at better aligning these influencing factors the choices made by ophthalmologists in selecting their practice locations to bridge the gap between healthcare availability and public interest.
Assuntos
Oftalmologia , Humanos , Instalações de SaúdeRESUMO
MOTIVATION: Large Language Models (LLMs) have the potential to revolutionize the field of Natural Language Processing, excelling not only in text generation and reasoning tasks but also in their ability for zero/few-shot learning, swiftly adapting to new tasks with minimal fine-tuning. LLMs have also demonstrated great promise in biomedical and healthcare applications. However, when it comes to Named Entity Recognition (NER), particularly within the biomedical domain, LLMs fall short of the effectiveness exhibited by fine-tuned domain-specific models. One key reason is that NER is typically conceptualized as a sequence labeling task, whereas LLMs are optimized for text generation and reasoning tasks. RESULTS: We developed an instruction-based learning paradigm that transforms biomedical NER from a sequence labeling task into a generation task. This paradigm is end-to-end and streamlines the training and evaluation process by automatically repurposing pre-existing biomedical NER datasets. We further developed BioNER-LLaMA using the proposed paradigm with LLaMA-7B as the foundational LLM. We conducted extensive testing on BioNER-LLaMA across three widely recognized biomedical NER datasets, consisting of entities related to diseases, chemicals, and genes. The results revealed that BioNER-LLaMA consistently achieved higher F1-scores ranging from 5% to 30% compared to the few-shot learning capabilities of GPT-4 on datasets with different biomedical entities. We show that a general-domain LLM can match the performance of rigorously fine-tuned PubMedBERT models and PMC-LLaMA, biomedical-specific language model. Our findings underscore the potential of our proposed paradigm in developing general-domain LLMs that can rival SOTA performances in multi-task, multi-domain scenarios in biomedical and health applications. AVAILABILITY AND IMPLEMENTATION: Datasets and other resources are available at https://github.com/BIDS-Xu-Lab/BioNER-LLaMA.
Assuntos
Camelídeos Americanos , Aprendizado Profundo , Animais , Idioma , Processamento de Linguagem NaturalRESUMO
MOTIVATION: While large language models (LLMs) have been successfully applied to various tasks, they still face challenges with hallucinations. Augmenting LLMs with domain-specific tools such as database utilities can facilitate easier and more precise access to specialized knowledge. In this article, we present GeneGPT, a novel method for teaching LLMs to use the Web APIs of the National Center for Biotechnology Information (NCBI) for answering genomics questions. Specifically, we prompt Codex to solve the GeneTuring tests with NCBI Web APIs by in-context learning and an augmented decoding algorithm that can detect and execute API calls. RESULTS: Experimental results show that GeneGPT achieves state-of-the-art performance on eight tasks in the GeneTuring benchmark with an average score of 0.83, largely surpassing retrieval-augmented LLMs such as the new Bing (0.44), biomedical LLMs such as BioMedLM (0.08) and BioGPT (0.04), as well as GPT-3 (0.16) and ChatGPT (0.12). Our further analyses suggest that: First, API demonstrations have good cross-task generalizability and are more useful than documentations for in-context learning; second, GeneGPT can generalize to longer chains of API calls and answer multi-hop questions in GeneHop, a novel dataset introduced in this work; finally, different types of errors are enriched in different tasks, providing valuable insights for future improvements. AVAILABILITY AND IMPLEMENTATION: The GeneGPT code and data are publicly available at https://github.com/ncbi/GeneGPT.
Assuntos
Algoritmos , Benchmarking , Bases de Dados Factuais , Documentação , IdiomaRESUMO
PubTator 3.0 (https://www.ncbi.nlm.nih.gov/research/pubtator3/) is a biomedical literature resource using state-of-the-art AI techniques to offer semantic and relation searches for key concepts like proteins, genetic variants, diseases, and chemicals. It currently provides over one billion entity and relation annotations across approximately 36 million PubMed abstracts and 6 million full-text articles from the PMC open access subset, updated weekly. PubTator 3.0's online interface and API utilize these precomputed entity relations and synonyms to provide advanced search capabilities and enable large-scale analyses, streamlining many complex information needs. We showcase the retrieval quality of PubTator 3.0 using a series of entity pair queries, demonstrating that PubTator 3.0 retrieves a greater number of articles than either PubMed or Google Scholar, with higher precision in the top 20 results. We further show that integrating ChatGPT (GPT-4) with PubTator APIs dramatically improves the factuality and verifiability of its responses. In summary, PubTator 3.0 offers a comprehensive set of features and tools that allow researchers to navigate the ever-expanding wealth of biomedical literature, expediting research and unlocking valuable insights for scientific discovery.
RESUMO
IMPORTANCE: The study highlights the potential of large language models, specifically GPT-3.5 and GPT-4, in processing complex clinical data and extracting meaningful information with minimal training data. By developing and refining prompt-based strategies, we can significantly enhance the models' performance, making them viable tools for clinical NER tasks and possibly reducing the reliance on extensive annotated datasets. OBJECTIVES: This study quantifies the capabilities of GPT-3.5 and GPT-4 for clinical named entity recognition (NER) tasks and proposes task-specific prompts to improve their performance. MATERIALS AND METHODS: We evaluated these models on 2 clinical NER tasks: (1) to extract medical problems, treatments, and tests from clinical notes in the MTSamples corpus, following the 2010 i2b2 concept extraction shared task, and (2) to identify nervous system disorder-related adverse events from safety reports in the vaccine adverse event reporting system (VAERS). To improve the GPT models' performance, we developed a clinical task-specific prompt framework that includes (1) baseline prompts with task description and format specification, (2) annotation guideline-based prompts, (3) error analysis-based instructions, and (4) annotated samples for few-shot learning. We assessed each prompt's effectiveness and compared the models to BioClinicalBERT. RESULTS: Using baseline prompts, GPT-3.5 and GPT-4 achieved relaxed F1 scores of 0.634, 0.804 for MTSamples and 0.301, 0.593 for VAERS. Additional prompt components consistently improved model performance. When all 4 components were used, GPT-3.5 and GPT-4 achieved relaxed F1 socres of 0.794, 0.861 for MTSamples and 0.676, 0.736 for VAERS, demonstrating the effectiveness of our prompt framework. Although these results trail BioClinicalBERT (F1 of 0.901 for the MTSamples dataset and 0.802 for the VAERS), it is very promising considering few training samples are needed. DISCUSSION: The study's findings suggest a promising direction in leveraging LLMs for clinical NER tasks. However, while the performance of GPT models improved with task-specific prompts, there's a need for further development and refinement. LLMs like GPT-4 show potential in achieving close performance to state-of-the-art models like BioClinicalBERT, but they still require careful prompt engineering and understanding of task-specific knowledge. The study also underscores the importance of evaluation schemas that accurately reflect the capabilities and performance of LLMs in clinical settings. CONCLUSION: While direct application of GPT models to clinical NER tasks falls short of optimal performance, our task-specific prompt framework, incorporating medical knowledge and training samples, significantly enhances GPT models' feasibility for potential clinical applications.
Assuntos
Registros Eletrônicos de Saúde , Processamento de Linguagem Natural , Humanos , Mineração de Dados/métodosRESUMO
ETHNOPHARMACOLOGICAL RELEVANCE: Flap necrosis is the most common complication after flap transplantation, but its prevention remains challenging. Tetrahydropalmatine (THP) is the main bioactive component of the traditional Chinese medicine Corydalis yanhusuo, with effects that include the activation of blood circulation, the promotion of qi, and pain relief. Although THP is widely used to treat various pain conditions, its impact on flap survival is unknown. AIM OF THE STUDY: To explore the effect and mechanism of THP on skin flap survival. MATERIALS AND METHODS: In this study, we established a modified McFarlane flap model, and the flap survival rate was calculated after 7 days of THP treatment. Angiogenesis and blood perfusion were evaluated using lead oxide/gelatin angiography and laser Doppler, respectively. Flap tissue obtained from zone II was evaluated histopathologically, by hematoxylin and eosin staining, and in assays for malondialdehyde content and superoxide dismutase activity. Immunofluorescence was performed to detect interleukin (IL)-6, tumor necrosis factor (TNF)-α, hypoxia-inducible factor (HIF)-1α, Bcl-2, Bax, caspase-3, caspase-9, SQSTM1/P62, Beclin-1, and LC3 expression, and Western blot to assess PI3K/AKT signaling pathway activation and Vascular endothelial growth factor (VEGF) expression. The role played by the autophagy pathway in flap necrosis was examined using rapamycin, a specific inhibitor of mTOR. RESULTS: Experimentally, THP improved the survival rate of skin flaps, promoted angiogenesis, and improved blood perfusion. THP administration reduced the inflammatory response, oxidative stress, and apoptosis in addition to inhibiting autophagy via the PI3K/AKT/mTOR pathway. Rapamycin partially reversed these effects. CONCLUSION: THP promotes skin flap survival via the PI3K/AKT signaling pathway.
Assuntos
Alcaloides de Berberina , Fosfatidilinositol 3-Quinases , Proteínas Proto-Oncogênicas c-akt , Ratos , Animais , Proteínas Proto-Oncogênicas c-akt/metabolismo , Fosfatidilinositol 3-Quinases/metabolismo , Fator A de Crescimento do Endotélio Vascular/metabolismo , Transdução de Sinais , Serina-Treonina Quinases TOR/metabolismo , Fator de Necrose Tumoral alfa/farmacologia , Necrose , Sirolimo/farmacologia , DorRESUMO
BACKGROUND: Flap placement remains the primary method for wound repair, but postoperative ischemic flap necrosis is of major concern. This study explored whether rivaroxaban, a factor Xa inhibitor, enhanced flap survival. METHODS: Thirty-six rats were randomly divided into control, low-dose rivaroxaban (3 mg/kg/day), and high-dose rivaroxaban (7 mg/kg/day) groups. On postoperative day 7, the flap survival rate was analyzed and the average survival area calculated. After the rats were euthanized, immunological and molecular biological techniques were employed to assess vascular regeneration, pyroptosis, and inflammation. RESULTS: Rivaroxaban upregulated VEGF expression, in turn enhancing angiogenesis, and it downregulated IL-1ß, IL-6, and TNF-α expression, thereby mitigating inflammation. The drug also suppressed TLR4, NF-κB p65, NLRP3, caspase-1, and IL-18 syntheses, thus inhibiting pyroptosis. CONCLUSIONS: Rivaroxaban enhanced random flap survival by down-regulating the TLR4/NF-κB/NLRP3 signaling pathway to suppress pyroptosis, promoting vascular regeneration and inhibiting inflammation.
Assuntos
NF-kappa B , Proteína 3 que Contém Domínio de Pirina da Família NLR , Ratos , Animais , NF-kappa B/metabolismo , Proteína 3 que Contém Domínio de Pirina da Família NLR/metabolismo , Rivaroxabana , Receptor 4 Toll-Like/metabolismo , Piroptose , Transdução de Sinais , Inflamação/metabolismoRESUMO
BACKGROUND: Cataract diagnosis typically requires in-person evaluation by an ophthalmologist. However, color fundus photography (CFP) is widely performed outside ophthalmology clinics, which could be exploited to increase the accessibility of cataract screening by automated detection. METHODS: DeepOpacityNet was developed to detect cataracts from CFP and highlight the most relevant CFP features associated with cataracts. We used 17,514 CFPs from 2573 AREDS2 participants curated from the Age-Related Eye Diseases Study 2 (AREDS2) dataset, of which 8681 CFPs were labeled with cataracts. The ground truth labels were transferred from slit-lamp examination of nuclear cataracts and reading center grading of anterior segment photographs for cortical and posterior subcapsular cataracts. DeepOpacityNet was internally validated on an independent test set (20%), compared to three ophthalmologists on a subset of the test set (100 CFPs), externally validated on three datasets obtained from the Singapore Epidemiology of Eye Diseases study (SEED), and visualized to highlight important features. RESULTS: Internally, DeepOpacityNet achieved a superior accuracy of 0.66 (95% confidence interval (CI): 0.64-0.68) and an area under the curve (AUC) of 0.72 (95% CI: 0.70-0.74), compared to that of other state-of-the-art methods. DeepOpacityNet achieved an accuracy of 0.75, compared to an accuracy of 0.67 for the ophthalmologist with the highest performance. Externally, DeepOpacityNet achieved AUC scores of 0.86, 0.88, and 0.89 on SEED datasets, demonstrating the generalizability of our proposed method. Visualizations show that the visibility of blood vessels could be characteristic of cataract absence while blurred regions could be characteristic of cataract presence. CONCLUSIONS: DeepOpacityNet could detect cataracts from CFPs in AREDS2 with performance superior to that of ophthalmologists and generate interpretable results. The code and models are available at https://github.com/ncbi/DeepOpacityNet ( https://doi.org/10.5281/zenodo.10127002 ).
Cataracts are cloudy areas in the eye that impact sight. Diagnosis typically requires in-person evaluation by an ophthalmologist. In this study, a computer program was developed that can identify cataracts from specialist photographs of the eye. The computer program successfully identified cataracts and was better able to identify these than ophthalmologists. This computer program could be introduced to improve the diagnosis of cataracts in eye clinics.
RESUMO
ChatGPT has drawn considerable attention from both the general public and domain experts with its remarkable text generation capabilities. This has subsequently led to the emergence of diverse applications in the field of biomedicine and health. In this work, we examine the diverse applications of large language models (LLMs), such as ChatGPT, in biomedicine and health. Specifically, we explore the areas of biomedical information retrieval, question answering, medical text summarization, information extraction and medical education and investigate whether LLMs possess the transformative power to revolutionize these tasks or whether the distinct complexities of biomedical domain presents unique challenges. Following an extensive literature survey, we find that significant advances have been made in the field of text generation tasks, surpassing the previous state-of-the-art methods. For other applications, the advances have been modest. Overall, LLMs have not yet revolutionized biomedicine, but recent rapid progress indicates that such methods hold great potential to provide valuable means for accelerating discovery and improving health. We also find that the use of LLMs, like ChatGPT, in the fields of biomedicine and health entails various risks and challenges, including fabricated information in its generated responses, as well as legal and privacy concerns associated with sensitive patient data. We believe this survey can provide a comprehensive and timely overview to biomedical researchers and healthcare practitioners on the opportunities and challenges associated with using ChatGPT and other LLMs for transforming biomedicine and health.