RESUMO
This manuscript describes the development of a resource module that is part of a learning platform named 'NIGMS Sandbox for Cloud-based Learning' https://github.com/NIGMS/NIGMS-Sandbox. The overall genesis of the Sandbox is described in the editorial NIGMS Sandbox at the beginning of this Supplement. This module delivers learning materials on protein quantification in an interactive format that uses appropriate cloud resources for data access and analyses. Quantitative proteomics is a rapidly growing discipline due to the cutting-edge technologies of high resolution mass spectrometry. There are many data types to consider for proteome quantification including data dependent acquisition, data independent acquisition, multiplexing with Tandem Mass Tag reporter ions, spectral counts, and more. As part of the NIH NIGMS Sandbox effort, we developed a learning module to introduce students to mass spectrometry terminology, normalization methods, statistical designs, and basics of R programming. By utilizing the Google Cloud environment, the learning module is easily accessible without the need for complex installation procedures. The proteome quantification module demonstrates the analysis using a provided TMT10plex data set using MS3 reporter ion intensity quantitative values in a Jupyter notebook with an R kernel. The learning module begins with the raw intensities, performs normalization, and differential abundance analysis using limma models, and is designed for researchers with a basic understanding of mass spectrometry and R programming language. Learners walk away with a better understanding of how to navigate Google Cloud Platform for proteomic research, and with the basics of mass spectrometry data analysis at the command line. This manuscript describes the development of a resource module that is part of a learning platform named ``NIGMS Sandbox for Cloud-based Learning'' https://github.com/NIGMS/NIGMS-Sandbox. The overall genesis of the Sandbox is described in the editorial NIGMS Sandbox [1] at the beginning of this Supplement. This module delivers learning materials on the analysis of bulk and single-cell ATAC-seq data in an interactive format that uses appropriate cloud resources for data access and analyses.
Assuntos
Computação em Nuvem , Proteoma , Proteômica , Software , Proteoma/metabolismo , Proteômica/métodos , Espectrometria de Massas , HumanosRESUMO
Assay for transposase-accessible chromatin with high-throughput sequencing (ATAC-seq) generates genome-wide chromatin accessibility profiles, providing valuable insights into epigenetic gene regulation at both pooled-cell and single-cell population levels. Comprehensive analysis of ATAC-seq data involves the use of various interdependent programs. Learning the correct sequence of steps needed to process the data can represent a major hurdle. Selecting appropriate parameters at each stage, including pre-analysis, core analysis, and advanced downstream analysis, is important to ensure accurate analysis and interpretation of ATAC-seq data. Additionally, obtaining and working within a limited computational environment presents a significant challenge to non-bioinformatic researchers. Therefore, we present Cloud ATAC, an open-source, cloud-based interactive framework with a scalable, flexible, and streamlined analysis framework based on the best practices approach for pooled-cell and single-cell ATAC-seq data. These frameworks use on-demand computational power and memory, scalability, and a secure and compliant environment provided by the Google Cloud. Additionally, we leverage Jupyter Notebook's interactive computing platform that combines live code, tutorials, narrative text, flashcards, quizzes, and custom visualizations to enhance learning and analysis. Further, leveraging GPU instances has significantly improved the run-time of the single-cell framework. The source codes and data are publicly available through NIH Cloud lab https://github.com/NIGMS/ATAC-Seq-and-Single-Cell-ATAC-Seq-Analysis. This manuscript describes the development of a resource module that is part of a learning platform named ``NIGMS Sandbox for Cloud-based Learning'' https://github.com/NIGMS/NIGMS-Sandbox. The overall genesis of the Sandbox is described in the editorial NIGMS Sandbox [1] at the beginning of this Supplement. This module delivers learning materials on the analysis of bulk and single-cell ATAC-seq data in an interactive format that uses appropriate cloud resources for data access and analyses.
Assuntos
Computação em Nuvem , Sequenciamento de Nucleotídeos em Larga Escala , Software , Sequenciamento de Nucleotídeos em Larga Escala/métodos , Humanos , Biologia Computacional/métodos , Sequenciamento de Cromatina por Imunoprecipitação/métodos , Análise de Célula Única/métodos , Cromatina/genética , Cromatina/metabolismoRESUMO
This study describes the development of a resource module that is part of a learning platform named 'NIGMS Sandbox for Cloud-based Learning' https://github.com/NIGMS/NIGMS-Sandbox. The overall genesis of the Sandbox is described in the editorial NIGMS Sandbox at the beginning of this Supplement. This module is designed to facilitate interactive learning of whole-genome bisulfite sequencing (WGBS) data analysis utilizing cloud-based tools in Google Cloud Platform, such as Cloud Storage, Vertex AI notebooks and Google Batch. WGBS is a powerful technique that can provide comprehensive insights into DNA methylation patterns at single cytosine resolution, essential for understanding epigenetic regulation across the genome. The designed learning module first provides step-by-step tutorials that guide learners through two main stages of WGBS data analysis, preprocessing and the identification of differentially methylated regions. And then, it provides a streamlined workflow and demonstrates how to effectively use it for large datasets given the power of cloud infrastructure. The integration of these interconnected submodules progressively deepens the user's understanding of the WGBS analysis process along with the use of cloud resources. Through this module, we can enhance the accessibility and adoption of cloud computing in epigenomic research, speeding up the advancements in the related field and beyond. This manuscript describes the development of a resource module that is part of a learning platform named ``NIGMS Sandbox for Cloud-based Learning'' https://github.com/NIGMS/NIGMS-Sandbox. The overall genesis of the Sandbox is described in the editorial NIGMS Sandbox [1] at the beginning of this Supplement. This module delivers learning materials on the analysis of bulk and single-cell ATAC-seq data in an interactive format that uses appropriate cloud resources for data access and analyses.
Assuntos
Computação em Nuvem , Metilação de DNA , Software , Sequenciamento Completo do Genoma , Sequenciamento Completo do Genoma/métodos , Sulfitos/química , Humanos , Epigênese Genética , Biologia Computacional/métodosRESUMO
Multi-omics (genomics, transcriptomics, epigenomics, proteomics, metabolomics, etc.) research approaches are vital for understanding the hierarchical complexity of human biology and have proven to be extremely valuable in cancer research and precision medicine. Emerging scientific advances in recent years have made high-throughput genome-wide sequencing a central focus in molecular research by allowing for the collective analysis of various kinds of molecular biological data from different types of specimens in a single tissue or even at the level of a single cell. Additionally, with the help of improved computational resources and data mining, researchers are able to integrate data from different multi-omics regimes to identify new prognostic, diagnostic, or predictive biomarkers, uncover novel therapeutic targets, and develop more personalized treatment protocols for patients. For the research community to parse the scientifically and clinically meaningful information out of all the biological data being generated each day more efficiently with less wasted resources, being familiar with and comfortable using advanced analytical tools, such as Google Cloud Platform becomes imperative. This project is an interdisciplinary, cross-organizational effort to provide a guided learning module for integrating transcriptomics and epigenetics data analysis protocols into a comprehensive analysis pipeline for users to implement in their own work, utilizing the cloud computing infrastructure on Google Cloud. The learning module consists of three submodules that guide the user through tutorial examples that illustrate the analysis of RNA-sequence and Reduced-Representation Bisulfite Sequencing data. The examples are in the form of breast cancer case studies, and the data sets were procured from the public repository Gene Expression Omnibus. The first submodule is devoted to transcriptomics analysis with the RNA sequencing data, the second submodule focuses on epigenetics analysis using the DNA methylation data, and the third submodule integrates the two methods for a deeper biological understanding. The modules begin with data collection and preprocessing, with further downstream analysis performed in a Vertex AI Jupyter notebook instance with an R kernel. Analysis results are returned to Google Cloud buckets for storage and visualization, removing the computational strain from local resources. The final product is a start-to-finish tutorial for the researchers with limited experience in multi-omics to integrate transcriptomics and epigenetics data analysis into a comprehensive pipeline to perform their own biological research.This manuscript describes the development of a resource module that is part of a learning platform named ``NIGMS Sandbox for Cloud-based Learning'' https://github.com/NIGMS/NIGMS-Sandbox. The overall genesis of the Sandbox is described in the editorial NIGMS Sandbox [16] at the beginning of this Supplement. This module delivers learning materials on the analysis of bulk and single-cell ATAC-seq data in an interactive format that uses appropriate cloud resources for data access and analyses.
Assuntos
Computação em Nuvem , Epigenômica , Humanos , Epigenômica/métodos , Epigênese Genética , Transcriptoma , Biologia Computacional/métodos , Perfilação da Expressão Gênica/métodos , Software , Mineração de Dados/métodosRESUMO
BACKGROUND AND AIMS: Built environment plays an important role in the development of cardiovascular disease. Tools to evaluate the built environment using machine vision and informatic approaches have been limited. This study aimed to investigate the association between machine vision-based built environment and prevalence of cardiometabolic disease in US cities. METHODS: This cross-sectional study used features extracted from Google Street View (GSV) images to measure the built environment and link them with prevalence of coronary heart disease (CHD). Convolutional neural networks, linear mixed-effects models, and activation maps were utilized to predict health outcomes and identify feature associations with CHD at the census tract level. The study obtained 0.53 million GSV images covering 789 census tracts in seven US cities (Cleveland, OH; Fremont, CA; Kansas City, MO; Detroit, MI; Bellevue, WA; Brownsville, TX; and Denver, CO). RESULTS: Built environment features extracted from GSV using deep learning predicted 63% of the census tract variation in CHD prevalence. The addition of GSV features improved a model that only included census tract-level age, sex, race, income, and education or composite indices of social determinant of health. Activation maps from the features revealed a set of neighbourhood features represented by buildings and roads associated with CHD prevalence. CONCLUSIONS: In this cross-sectional study, the prevalence of CHD was associated with built environment factors derived from GSV through deep learning analysis, independent of census tract demographics. Machine vision-enabled assessment of the built environment could potentially offer a more precise approach to identify at-risk neighbourhoods, thereby providing an efficient avenue to address and reduce cardiovascular health disparities in urban environments.
Assuntos
Inteligência Artificial , Ambiente Construído , Doença da Artéria Coronariana , Humanos , Estudos Transversais , Doença da Artéria Coronariana/epidemiologia , Prevalência , Masculino , Feminino , Estados Unidos/epidemiologia , Pessoa de Meia-Idade , Cidades/epidemiologiaRESUMO
BACKGROUND: The capability of large language models (LLMs) to understand and generate human-readable text has prompted the investigation of their potential as educational and management tools for patients with cancer and healthcare providers. MATERIALS AND METHODS: We conducted a cross-sectional study aimed at evaluating the ability of ChatGPT-4, ChatGPT-3.5, and Google Bard to answer questions related to 4 domains of immuno-oncology (Mechanisms, Indications, Toxicities, and Prognosis). We generated 60 open-ended questions (15 for each section). Questions were manually submitted to LLMs, and responses were collected on June 30, 2023. Two reviewers evaluated the answers independently. RESULTS: ChatGPT-4 and ChatGPT-3.5 answered all questions, whereas Google Bard answered only 53.3% (Pâ <â .0001). The number of questions with reproducible answers was higher for ChatGPT-4 (95%) and ChatGPT3.5 (88.3%) than for Google Bard (50%) (Pâ <â .0001). In terms of accuracy, the number of answers deemed fully correct were 75.4%, 58.5%, and 43.8% for ChatGPT-4, ChatGPT-3.5, and Google Bard, respectively (Pâ =â .03). Furthermore, the number of responses deemed highly relevant was 71.9%, 77.4%, and 43.8% for ChatGPT-4, ChatGPT-3.5, and Google Bard, respectively (Pâ =â .04). Regarding readability, the number of highly readable was higher for ChatGPT-4 and ChatGPT-3.5 (98.1%) and (100%) compared to Google Bard (87.5%) (Pâ =â .02). CONCLUSION: ChatGPT-4 and ChatGPT-3.5 are potentially powerful tools in immuno-oncology, whereas Google Bard demonstrated relatively poorer performance. However, the risk of inaccuracy or incompleteness in the responses was evident in all 3 LLMs, highlighting the importance of expert-driven verification of the outputs returned by these technologies.
Assuntos
Neoplasias , Humanos , Estudos Transversais , Neoplasias/imunologia , Neoplasias/terapia , Oncologia/métodos , Oncologia/normas , Inquéritos e Questionários , Idioma , Imunoterapia/métodosRESUMO
PURPOSE: Large language models (LLMs) are a form of artificial intelligence (AI) that uses deep learning techniques to understand, summarize and generate content. The potential benefits of LLMs in healthcare is predicted to be immense. The objective of this study was to examine the quality of patient information leaflets (PILs) produced by 3 LLMs on urological topics. METHODS: Prompts were created to generate PILs from 3 LLMs: ChatGPT-4, PaLM 2 (Google Bard) and Llama 2 (Meta) across four urology topics (circumcision, nephrectomy, overactive bladder syndrome, and transurethral resection of the prostate). PILs were evaluated using a quality assessment checklist. PIL readability was assessed by the Average Reading Level Consensus Calculator. RESULTS: PILs generated by PaLM 2 had the highest overall average quality score (3.58), followed by Llama 2 (3.34) and ChatGPT-4 (3.08). PaLM 2 generated PILs were of the highest quality in all topics except TURP and was the only LLM to include images. Medical inaccuracies were present in all generated content including instances of significant error. Readability analysis identified PaLM 2 generated PILs as the simplest (age 14-15 average reading level). Llama 2 PILs were the most difficult (age 16-17 average). CONCLUSION: While LLMs can generate PILs that may help reduce healthcare professional workload, generated content requires clinician input for accuracy and inclusion of health literacy aids, such as images. LLM-generated PILs were above the average reading level for adults, necessitating improvement in LLM algorithms and/or prompt design. How satisfied patients are to LLM-generated PILs remains to be evaluated.
Assuntos
Inteligência Artificial , Urologia , Humanos , Educação de Pacientes como Assunto/métodos , Idioma , Doenças Urológicas/cirurgiaRESUMO
AIMS: This study compared three artificial intelligence (AI) platforms' potential to identify drug therapy communication competencies expected of a graduating medical doctor. METHODS: We presented three AI platforms, namely, Poe Assistant©, ChatGPT© and Google Bard©, with structured queries to generate communication skill competencies and case scenarios appropriate for graduating medical doctors. These case scenarios comprised 15 prototypical medical conditions that required drug prescriptions. Two authors independently evaluated the AI-enhanced clinical encounters, which integrated a diverse range of information to create patient-centred care plans. Through a consensus-based approach using a checklist, the communication components generated for each scenario were assessed. The instructions and warnings provided for each case scenario were evaluated by referencing the British National Formulary. RESULTS: AI platforms demonstrated overlap in competency domains generated, albeit with variations in wording. The domains of knowledge (basic and clinical pharmacology, prescribing, communication and drug safety) were unanimously recognized by all platforms. A broad consensus among Poe Assistant© and ChatGPT© on drug therapy-related communication issues specific to each case scenario was evident. The consensus primarily encompassed salutation, generic drug prescribed, treatment goals and follow-up schedules. Differences were observed in patient instruction clarity, listed side effects, warnings and patient empowerment. Google Bard did not provide guidance on patient communication issues. CONCLUSIONS: AI platforms recognized competencies with variations in how these were stated. Poe Assistant© and ChatGPT© exhibited alignment of communication issues. However, significant discrepancies were observed in specific skill components, indicating the necessity of human intervention to critically evaluate AI-generated outputs.
RESUMO
OBJECTIVE: Colorectal cancer (CRC) is the third leading cause of cancer death among both men and women in the United States. CRC-related events may increase media coverage and public attention, boosting awareness and prevention. This study examined associations between several types of CRC events (including unplanned celebrity cancer deaths and planned events like national CRC awareness months, celebrity screening behavior, and screening guideline changes) and news coverage, Twitter discussions, and Google search trends about CRC and CRC screening. METHODS: We analyzed data from U.S. national news media outlets, posts scraped from Twitter, and Google Trends on CRC and CRC screening during a three-year period from 2020 to 2022. We used burst detection methods to identify temporal spikes in the volume of news, tweets, and search after each CRC-related event. RESULTS: There is a high level of heterogeneity in the impact of celebrity CRC events. Celebrity CRC deaths were more likely to precede spikes in news and tweets about CRC overall than CRC screening. Celebrity screening preceded spikes in news and tweets about screening but not searches. Awareness months and screening guideline changes did precede spikes in news, tweets, and searches about screening, but these spikes were inconsistent, not simultaneous, and not as large as those events concerning most prominent public figures. CONCLUSIONS: CRC events provide opportunities to increase attention to CRC. Media and public health professionals should actively intervene during CRC events to increase emphasis on CRC screening and evidence-based recommendations.
Assuntos
Neoplasias Colorretais , Detecção Precoce de Câncer , Pessoas Famosas , Meios de Comunicação de Massa , Mídias Sociais , Humanos , Neoplasias Colorretais/mortalidade , Mídias Sociais/tendências , Estados Unidos/epidemiologia , Masculino , Feminino , Programas de Rastreamento/tendênciasRESUMO
INTRODUCTION: The emerging rise in novel computer technologies and automated data analytics has the potential to change the course of dental education. In line with our long-term goal of harnessing the power of AI to augment didactic teaching, the objective of this study was to quantify and compare the accuracy of responses provided by ChatGPT (GPT-4 and GPT-3.5) and Google Gemini, the three primary large language models (LLMs), to human graduate students (control group) to the annual in-service examination questions posed by the American Academy of Periodontology (AAP). METHODS: Under a comparative cross-sectional study design, a corpus of 1312 questions from the annual in-service examination of AAP administered between 2020 and 2023 were presented to the LLMs. Their responses were analyzed using chi-square tests, and the performance was juxtaposed to the scores of periodontal residents from corresponding years, as the human control group. Additionally, two sub-analyses were performed: one on the performance of the LLMs on each section of the exam; and in answering the most difficult questions. RESULTS: ChatGPT-4 (total average: 79.57%) outperformed all human control groups as well as GPT-3.5 and Google Gemini in all exam years (p < .001). This chatbot showed an accuracy range between 78.80% and 80.98% across the various exam years. Gemini consistently recorded superior performance with scores of 70.65% (p = .01), 73.29% (p = .02), 75.73% (p < .01), and 72.18% (p = .0008) for the exams from 2020 to 2023 compared to ChatGPT-3.5, which achieved 62.5%, 68.24%, 69.83%, and 59.27% respectively. Google Gemini (72.86%) surpassed the average scores achieved by first- (63.48% ± 31.67) and second-year residents (66.25% ± 31.61) when all exam years combined. However, it could not surpass that of third-year residents (69.06% ± 30.45). CONCLUSIONS: Within the confines of this analysis, ChatGPT-4 exhibited a robust capability in answering AAP in-service exam questions in terms of accuracy and reliability while Gemini and ChatGPT-3.5 showed a weaker performance. These findings underscore the potential of deploying LLMs as an educational tool in periodontics and oral implantology domains. However, the current limitations of these models such as inability to effectively process image-based inquiries, the propensity for generating inconsistent responses to the same prompts, and achieving high (80% by GPT-4) but not absolute accuracy rates should be considered. An objective comparison of their capability versus their capacity is required to further develop this field of study.
RESUMO
The study made a comprehensive effort to examine climatic uncertainties at both yearly and monthly scales, along with mapping flood risks based on different land use categories. Recent studies have progressively been engrossed in demonstrating regional climate variations and associated flood probability to maintain the geo-ecological balance at micro to macro-regions. To carry out this investigation, various historical remote sensing record, reanalyzed and in-situ data sets were acquired with a high level of spatial precision using the Google Earth Engine (GEE) web-based remote sensing platform. Non-parametric techniques and multi-layer integration methods were then employed to illustrate the fluctuations in climate factors alongside creating maps indicating the susceptibility to floods. The study reveals an increased pattern in LST (Land Surface Temperature) (0.03 °C/year), albeit marginal declined in southern coastal regions (-0.15 °C/year) along with uneven rainfall patterns (1.42 mm/year). Moreover, long-term LULC change estimation divulges increased trends of urbanization (16.4 km2/year) together with vegetation growth (8.7 km2/year) from 2002 to 2022. Furthermore, this inquiry involves numerous environmental factors that influence the situation (elevation data, topographic wetness index, drainage density, proximity to water bodies, slope, and soil properties) as well as socio-economic attributes (population) to assess flood risk areas through the utilization of Analytical Hierarchy Process and overlay methods with assigned weights. The outcomes reveal nearly 55 percent of urban land is susceptible to flood in 2022, which were 45 and 37 percent in 2012 and 2002 separately. Additionally, 106 km2 of urban area is highly susceptible to inundation, whereas vegetation also occupies a significant proportion (52 km2). This thorough exploration offers a significant chance to formulate flood management and mitigation strategies tailored to specific regions during the era of climate change.
Assuntos
Inundações , Urbanização , Incerteza , Probabilidade , ÍndiaRESUMO
Assessing the relative importance of climate change and human activities is important in developing sustainable management policies for regional land use. In this study, multiple remote sensing datasets, i.e. CHIRPS (Climate Hazard Group InfraRed Precipitation with Station Data) precipitation, MODIS Land Surface Temperature (LST), Enhanced Vegetation Index (EVI), Potential Evapotranspiration (PET), Soil Moisture (SM), WorldPop, and nighttime light have been analyzed to investigate the effect that climate change (CC) and regional human activities (HA) have on vegetation dynamics in eastern India for the period 2000 to 2022. The relative influence of climate and anthropogenic factors is evaluated on the basis of non-parametric statistics i.e., Mann-Kendall and Sen's slope estimator. Significant spatial and elevation-dependent variations in precipitation and LST are evident. Areas at higher elevations exhibit increased mean annual temperatures (0.22 °C/year, p < 0.05) and reduced winter precipitation over the last two decades, while the northern and southwest parts of West Bengal witnessed increased mean annual precipitation (17.3 mm/year, p < 0.05) and a slight cooling trend. Temperature and precipitation trends are shown to collectively impact EVI distribution. While there is a negative spatial correlation between LST and EVI, the relationship between precipitation and EVI is positive and stronger (R2 = 0.83, p < 0.05). Associated hydroclimatic parameters are potent drivers of EVI, whereby PET in the southwestern regions leads to markedly lower SM. The relative importance of CC and HA on EVI also varies spatially. Near the major conurbation of Kolkata, and confirmed by nighttime light and population density data, changes in vegetation cover are very clearly dominated by HA (87%). In contrast, CC emerges as the dominant driver of EVI (70-85%) in the higher elevation northern regions of the state but also in the southeast. Our findings inform policy regarding the future sustainability of vulnerable socio-hydroclimatic systems across the entire state.
Assuntos
Mudança Climática , Índia , Atividades Humanas , Humanos , Chuva , Temperatura , Monitoramento AmbientalRESUMO
INTRODUCTION: The internet is a popular source of health information including images of disease manifestations. Online photographs of skin lesions may aid patients in identifying their disease, if these pictures are of good quality and of the disease they claim to show. If not, patients may be at risk of delayed diagnosis, misdiagnosis, and suboptimal treatment. For urticaria, the mismatch rate and quality of online pictures are unknown. The objective of this study was therefore to evaluate the content and quality of online images of urticaria. METHODS: The search term "urticaria" was applied to Google Images and Shutterstock. The top 100 photographs from each search engine were retrieved on October 9th, 2022. Illustrations, drawings, and heavily edited photographs were excluded. Each image was evaluated for patient characteristics, characteristics of urticarial lesions, and image quality. RESULTS: Across 194 unique images of urticaria (after removing duplicates), 35 (18.0%) did not depict urticarial lesions, and 38 (19.6%) were ambiguous. Less than two-thirds of images 121 (62.4%) showed bona fide urticarial lesions. Pictures of urticarial lesions under-represented children and did not reflect female preponderance of the disease. Images predominantly depicted urticaria lesions on Caucasian skin (59.8%) and were typical of spontaneous rather than inducible urticaria. Only 3 (1.5%) pictures showed angioedema, a common clinical sign in patients with urticaria. The overall quality of online urticaria pictures was mostly good or very good. CONCLUSION: Physicians and patients should be aware that one in five online pictures of urticaria does not show urticarial skin lesions, and children, females, non-Caucasian patients, inducible urticaria, and angioedema are under-represented. These findings should prompt efforts to improve the accuracy and representativeness of online urticaria pictures.
Assuntos
Internet , Urticária , Humanos , Urticária/diagnóstico , Feminino , Fotografação , Masculino , CriançaRESUMO
PURPOSE: The aim of this study was to define the capability of ChatGPT-4 and Google Gemini in analyzing detailed glaucoma case descriptions and suggesting an accurate surgical plan. METHODS: Retrospective analysis of 60 medical records of surgical glaucoma was divided into "ordinary" (n = 40) and "challenging" (n = 20) scenarios. Case descriptions were entered into ChatGPT and Bard's interfaces with the question "What kind of surgery would you perform?" and repeated three times to analyze the answers' consistency. After collecting the answers, we assessed the level of agreement with the unified opinion of three glaucoma surgeons. Moreover, we graded the quality of the responses with scores from 1 (poor quality) to 5 (excellent quality), according to the Global Quality Score (GQS) and compared the results. RESULTS: ChatGPT surgical choice was consistent with those of glaucoma specialists in 35/60 cases (58%), compared to 19/60 (32%) of Gemini (p = 0.0001). Gemini was not able to complete the task in 16 cases (27%). Trabeculectomy was the most frequent choice for both chatbots (53% and 50% for ChatGPT and Gemini, respectively). In "challenging" cases, ChatGPT agreed with specialists in 9/20 choices (45%), outperforming Google Gemini performances (4/20, 20%). Overall, GQS scores were 3.5 ± 1.2 and 2.1 ± 1.5 for ChatGPT and Gemini (p = 0.002). This difference was even more marked if focusing only on "challenging" cases (1.5 ± 1.4 vs. 3.0 ± 1.5, p = 0.001). CONCLUSION: ChatGPT-4 showed a good analysis performance for glaucoma surgical cases, either ordinary or challenging. On the other side, Google Gemini showed strong limitations in this setting, presenting high rates of unprecise or missed answers.
RESUMO
BACKGROUND: Due to the spread of the coronavirus disease 2019 (COVID-19) pandemic in 2020, the interest of nutritional supplements has emerged. Limited data are available on how the COVID-19 pandemic affects the search interest in nutritional supplements in Taiwan and worldwide. The study aims to investigate changes in public search interest of nutritional supplements pre- and during the COVID-19 pandemic. METHODS: Our World in Data dataset was used to collect both global and local (Taiwan) number of COVID-19 newly confirmed cases and deaths. Google Trends search query was being used to obtain relative search volumes (RSVs) covering a timeframe between 2019 to 2022. Spearman's rank-order correlation coefficients were used to measure relationships between confirmed new cases and deaths and RSVs of nutritional supplements. Multivariate analysis was conducted to examine the effect of domestic and global new cases and deaths on the RSVs of nutritional supplements. RESULTS: The mean RSVs for nutritional supplements were higher during the COVID-19 pandemic period (between 2020 to 2022) compared to the pre-pandemic period (year of 2019) for both Taiwan and worldwide. In terms of seasonal variations, except for vitamin D, the mean RSVs of probiotics, vitamin B complex, and vitamin C in winter were significantly lower compared to other seasons in Taiwan. The RSVs of nutritional supplements were not only affected by domestic cases and deaths but also by global new cases and deaths. CONCLUSIONS: The interests in nutritional supplements had substantially increased in response to the COVID-19 pandemic. The RSVs of nutritional supplements in Taiwan were not only influenced by global and domestic pandemic severity but also by seasons.
Assuntos
COVID-19 , Pandemias , Humanos , Ferramenta de Busca , COVID-19/epidemiologia , Suplementos Nutricionais , VitaminasRESUMO
OBJECTIVE: The aim of our study is to examine the relationship between the economic activity of small firms and the mental well-being of the population in five Latin American countries in the early stages of the pandemic. METHODS: We utilize the search volume of certain keywords on Google Trends (GT), such as "boredom," "frustration," "loneliness," "sleep", "anxiety", and "depression", as an indicator of the well-being of the population. By examining the data from Facebook Business Activity Trends, we investigate how social attention reacts to the activity levels of different economic sectors. RESULTS: Increased business activity is generally associated with reduced levels of boredom, loneliness, sleep problems and anxiety. The effect on depression varies by sector, with positive associations concentrated in onsite jobs. In addition, we observe that strict Non-Pharmaceutical Interventions (NPIs) tend to exacerbate feelings of boredom and loneliness, sleep issues, and anxiety. CONCLUSIONS: Our findings suggest a strong association between different indicators of psychological well-being and the level of activity in different sectors of the economy. Given the essential role of small and medium-sized enterprises (SMEs) in generating employment, especially during crises like the pandemic, it is imperative that they remain resilient and adaptable to support economic recovery and job preservation. To accomplish this, policymakers need to focus on providing financial stability and support for SMEs, fostering social support networks within companies, and incorporating mental health services into workplace environments. This comprehensive strategy can alleviate mental health challenges and enhance public health resilience.
Assuntos
COVID-19 , Saúde Mental , Humanos , COVID-19/epidemiologia , COVID-19/psicologia , América Latina/epidemiologia , Empresa de Pequeno Porte , Pandemias , Solidão/psicologia , Ansiedade/epidemiologia , Depressão/epidemiologia , Depressão/psicologia , Tédio , Saúde PúblicaRESUMO
INTRODUCTION: Wearing a helmet reduces the risk of head injuries substantially in the event of a motorcycle crash. Countries around the world are committed to promoting helmet use, but the progress has been slow and uneven. There is an urgent need for large-scale data collection for situation assessment and intervention evaluation. METHODS: This study proposes a scalable, low-cost algorithm to estimate helmet-wearing rates. Applying the state-of-the-art deep learning technique for object detection to images acquired from Google Street View, the algorithm has the potential to provide accurate estimates at the global level. RESULTS: Trained on a sample of 3995 images, the algorithm achieved high accuracy. The out-of-sample prediction results for all three object classes (helmets, drivers, and passengers) reveal a precision of 0.927, a recall value of 0.922, and a mean average precision at 50 (mAP50) of 0.956. DISCUSSION: The remarkable model performance suggests the algorithm's capacity to generate accurate estimates of helmet-wearing rates from an image source with global coverage. The significant enhancement in the availability of helmet usage data resulting from this approach could bolster progress tracking and facilitate evidence-based policymaking for helmet wearing globally.
Assuntos
Aprendizado Profundo , Dispositivos de Proteção da Cabeça , Dispositivos de Proteção da Cabeça/estatística & dados numéricos , Humanos , Algoritmos , Acidentes de Trânsito/prevenção & controle , Traumatismos Craniocerebrais/prevenção & controleRESUMO
Saving one list of words, such as on a computer or by writing them down, can improve a person's ability to learn and remember a second list of words that are not saved. This phenomenon, known as the saving enhanced memory effect, is typically observed by comparing the recall of nonsaved items when other items are saved versus when they are not saved. In past research, the effect has been shown to occur when participants save an entire list before learning a new list. In the current research, we examined whether the effect can be observed when participants save a subset of items within a single list. The results of two experiments confirmed that partial saving can lead to a saving enhanced memory effect, with the effect observed regardless of whether participants saved items by clicking a button on the computer or writing them out by hand. The effect was observed on an item-specific cued-recall test (Experiment 1) as well as a free recall test that did not control the order of output (Experiment 2). However, the effect size did vary as a function of how participants attempted to recall the items on the final test. Specifically, participants who initiated their output by recalling nonsaved items exhibited a significantly larger saving enhanced memory effect than those who initiated their output by reproducing saved items. Together, these findings expand our understanding of the saving enhanced memory effect and shine new light on the impacts of cognitive offloading on human memory.
RESUMO
BACKGROUND: Telemedicine offers a multitude of potential advantages, such as enhanced health care accessibility, cost reduction, and improved patient outcomes. The significance of telemedicine has been underscored by the COVID-19 pandemic, as it plays a crucial role in maintaining uninterrupted care while minimizing the risk of viral exposure. However, the adoption and implementation of telemedicine have been relatively sluggish in certain areas. Assessing the level of interest in telemedicine can provide valuable insights into areas that require enhancement. OBJECTIVE: The aim of this study is to provide a comprehensive analysis of the level of public and research interest in telemedicine from 2017 to 2022 and also consider any potential impact of the COVID-19 pandemic. METHODS: Google Trends data were retrieved using the search topics "telemedicine" or "e-health" to assess public interest, geographic distribution, and trends through a joinpoint regression analysis. Bibliographic data from Scopus were used to chart publications referencing the terms "telemedicine" or "eHealth" (in the title, abstract, and keywords) in terms of scientific production, key countries, and prominent keywords, as well as collaboration and co-occurrence networks. RESULTS: Worldwide, telemedicine generated higher mean public interest (relative search volume=26.3%) compared to eHealth (relative search volume=17.6%). Interest in telemedicine remained stable until January 2020, experienced a sudden surge (monthly percent change=95.7%) peaking in April 2020, followed by a decline (monthly percent change=-22.7%) until August 2020, and then returned to stability. A similar trend was noted in the public interest regarding eHealth. Chile, Australia, Canada, and the United States had the greatest public interest in telemedicine. In these countries, moderate to strong correlations were evident between Google Trends and COVID-19 data (ie, new cases, new deaths, and hospitalized patients). Examining 19,539 original medical articles in the Scopus database unveiled a substantial rise in telemedicine-related publications, showing a total increase of 201.5% from 2017 to 2022 and an average annual growth rate of 24.7%. The most significant surge occurred between 2019 and 2020. Notably, the majority of the publications originated from a single country, with 20.8% involving international coauthorships. As the most productive country, the United States led a cluster that included Canada and Australia as well. European, Asian, and Latin American countries made up the remaining 3 clusters. The co-occurrence network categorized prevalent keywords into 2 clusters, the first cluster primarily focused on applying eHealth, mobile health (mHealth), or digital health to noncommunicable or chronic diseases; the second cluster was centered around the application of telemedicine and telehealth within the context of the COVID-19 pandemic. CONCLUSIONS: Our analysis of search and bibliographic data over time and across regions allows us to gauge the interest in this topic, offer evidence regarding potential applications, and pinpoint areas for additional research and awareness-raising initiatives.
Assuntos
Bibliometria , COVID-19 , Telemedicina , Telemedicina/estatística & dados numéricos , Telemedicina/tendências , Humanos , COVID-19/epidemiologia , Pandemias , SARS-CoV-2 , Ferramenta de Busca/tendênciasRESUMO
BACKGROUND: We queried ChatGPT (OpenAI) and Google Assistant about amblyopia and compared their answers with the keywords found on the American Association for Pediatric Ophthalmology and Strabismus (AAPOS) website, specifically the section on amblyopia. Out of the 26 keywords chosen from the website, ChatGPT included 11 (42%) in its responses, while Google included 8 (31%). OBJECTIVE: Our study investigated the adherence of ChatGPT-3.5 and Google Assistant to the guidelines of the AAPOS for patient education on amblyopia. METHODS: ChatGPT-3.5 was used. The four questions taken from the AAPOS website, specifically its glossary section for amblyopia, are as follows: (1) What is amblyopia? (2) What causes amblyopia? (3) How is amblyopia treated? (4) What happens if amblyopia is untreated? Approved and selected by ophthalmologists (GW and DL), the keywords from AAPOS were words or phrases that deemed significant for the education of patients with amblyopia. The "Flesch-Kincaid Grade Level" formula, approved by the US Department of Education, was used to evaluate the reading comprehension level for the responses from ChatGPT, Google Assistant, and AAPOS. RESULTS: In their responses, ChatGPT did not mention the term "ophthalmologist," whereas Google Assistant and AAPOS both mentioned the term once and twice, respectively. ChatGPT did, however, use the term "eye doctors" once. According to the Flesch-Kincaid test, the average reading level of AAPOS was 11.4 (SD 2.1; the lowest level) while that of Google was 13.1 (SD 4.8; the highest required reading level), also showing the greatest variation in grade level in its responses. ChatGPT's answers, on average, scored 12.4 (SD 1.1) grade level. They were all similar in terms of difficulty level in reading. For the keywords, out of the 4 responses, ChatGPT used 42% (11/26) of the keywords, whereas Google Assistant used 31% (8/26). CONCLUSIONS: ChatGPT trains on texts and phrases and generates new sentences, while Google Assistant automatically copies website links. As ophthalmologists, we should consider including "see an ophthalmologist" on our websites and journals. While ChatGPT is here to stay, we, as physicians, need to monitor its answers.