The Performance of Chatbots and the AAPOS Website as a Tool for Amblyopia Education

PURPOSE

To evaluate the understandability, actionability, and readability of responses provided by the website of the American Association for Pediatric Ophthalmology and Strabismus (AAPOS), ChatGPT-3.5, Bard, and Bing Chat about amblyopia and the appropriateness of the responses generated by the chatbots.

METHOD

Twenty-five questions provided by the AAPOS website were directed three times to fresh ChatGPT-3.5, Bard, and Bing Chat interfaces. Two experienced pediatric ophthalmologists categorized the responses of the chatbots in terms of their appropriateness. Flesch Reading Ease (FRE), Flesch Kincaid Grade Level (FKGL), and Coleman-Liau Index (CLI) were used to evaluate the readability of the responses of the AAPOS website and chatbots. Furthermore, the understandability scores were evaluated using the Patient Education Materials Assessment Tool (PEMAT).

RESULTS

The appropriateness of the chatbots' responses was 84% for ChatGPT-3.5 and Bard and 80% for Bing Chat (P > .05). For understandability (mean PEMAT-U score AAPOS website: 81.5%, Bard: 77.6%, ChatGPT-3.5: 76.1%, and Bing Chat: 71.5%, P < .05) and actionability (mean PEMAT-A score AAPOS website: 74.6%, Bard: 69.2%, ChatGPT-3.5: 67.8%, and Bing Chat: 64.8%, P < .05), the AAPOs website scored better than the chat-bots. Three readability analyses showed that Bard had the highest mean score, followed by the AAPOS website, Bing Chat, and ChatGPT-3.5, and these scores were more challenging than the recommended level.

CONCLUSIONS

Chatbots have the potential to provide detailed and appropriate responses at acceptable levels. The AAPOS website has the advantage of providing information that is more understandable and actionable. The AAPOS website and chatbots, especially Chat-GPT, provided difficult-to-read data for patient education regarding amblyopia. [J Pediatr Ophthalmol Strabismus. 2024;61(5):325-331.].

Utilizing natural language processing and large language models in the diagnosis and prediction of infectious diseases: A systematic review

BACKGROUND

Natural Language Processing (NLP) and Large Language Models (LLMs) hold largely untapped potential in infectious disease management. This review explores their current use and uncovers areas needing more attention.

METHODS

This analysis followed systematic review procedures, registered with the Prospective Register of Systematic Reviews. We conducted a search across major databases including PubMed, Embase, Web of Science, and Scopus, up to December 2023, using keywords related to NLP, LLM, and infectious diseases. We also employed the Quality Assessment of Diagnostic Accuracy Studies-2 tool for evaluating the quality and robustness of the included studies.

RESULTS

Our review identified 15 studies with diverse applications of NLP in infectious disease management. Notable examples include GPT-4's application in detecting urinary tract infections and BERTweet's use in Lyme Disease surveillance through social media analysis. These models demonstrated effective disease monitoring and public health tracking capabilities. However, the effectiveness varied across studies. For instance, while some NLP tools showed high accuracy in pneumonia detection and high sensitivity in identifying invasive mold diseases from medical reports, others fell short in areas like bloodstream infection management.

CONCLUSIONS

This review highlights the yet-to-be-fully-realized promise of NLP and LLMs in infectious disease management. It calls for more exploration to fully harness AI's capabilities, particularly in the areas of diagnosis, surveillance, predicting disease courses, and tracking epidemiological trends.

Does machine learning have a high performance to predict obesity among adults and older adults? A systematic review and meta-analysis

AIM

Machine learning may be a tool with the potential for obesity prediction. This study aims to review the literature on the performance of machine learning models in predicting obesity and to quantify the pooled results through a meta-analysis.

DATA SYNTHESIS

A systematic review and meta-analysis were conducted, including studies that used machine learning to predict obesity. Searches were conducted in October 2023 across databases including LILACS, Web of Science, Scopus, Embase, and CINAHL. We included studies that utilized classification models and reported results in the Area Under the ROC Curve (AUC) (PROSPERO registration: CRD42022306940), without imposing restrictions on the year of publication. The risk of bias was assessed using an adapted version of the Transparent Reporting of a multivariable prediction model for individual Prognosis or Diagnosis (TRIPOD). Meta-analysis was conducted using MedCalc software. A total of 14 studies were included, with the majority demonstrating satisfactory performance for obesity prediction, with AUCs exceeding 0.70. The random forest algorithm emerged as the top performer in obesity prediction, achieving an AUC of 0.86 (95%CI: 0.76-0.96; I2: 99.8%), closely followed by logistic regression with an AUC of 0.85 (95%CI: 0.75-0.95; I2: 99.6%). The least effective model was gradient boosting, with an AUC of 0.77 (95%CI: 0.71-0.82; I2: 98.1%).

CONCLUSION

Machine learning models demonstrated satisfactory predictive performance for obesity. However, future research should utilize more comparable data, larger databases, and a broader range of machine learning models.

Disambiguation of acronyms in clinical narratives with large language models

OBJECTIVE

To assess the performance of large language models (LLMs) for zero-shot disambiguation of acronyms in clinical narratives.

MATERIALS AND METHODS

Clinical narratives in English, German, and Portuguese were applied for testing the performance of four LLMs: GPT-3.5, GPT-4, Llama-2-7b-chat, and Llama-2-70b-chat. For English, the anonymized Clinical Abbreviation Sense Inventory (CASI, University of Minnesota) was used. For German and Portuguese, at least 500 text spans were processed. The output of LLM models, prompted with contextual information, was analyzed to compare their acronym disambiguation capability, grouped by document-level metadata, the source language, and the LLM.

RESULTS

On CASI, GPT-3.5 achieved 0.91 in accuracy. GPT-4 outperformed GPT-3.5 across all datasets, reaching 0.98 in accuracy for CASI, 0.86 and 0.65 for two German datasets, and 0.88 for Portuguese. Llama models only reached 0.73 for CASI and failed severely for German and Portuguese. Across LLMs, performance decreased from English to German and Portuguese processing languages. There was no evidence that additional document-level metadata had a significant effect.

CONCLUSION

For English clinical narratives, acronym resolution by GPT-4 can be recommended to improve readability of clinical text by patients and professionals. For German and Portuguese, better models are needed. Llama models, which are particularly interesting for processing sensitive content on premise, cannot yet be recommended for acronym resolution.

Deciphering salt stress responses in Solanum pimpinellifolium through high-throughput phenotyping

Soil salinity is a major environmental stressor affecting agricultural productivity worldwide. Understanding plant responses to salt stress is crucial for developing resilient crop varieties. Wild relatives of cultivated crops, such as wild tomato, Solanum pimpinellifolium, can serve as a useful resource to further expand the resilience potential of the cultivated germplasm, S. lycopersicum. In this study, we employed high-throughput phenotyping in the greenhouse and field conditions to explore salt stress responses of a S. pimpinellifolium diversity panel. Our study revealed extensive phenotypic variations in response to salt stress, with traits such as transpiration rate, shoot mass, and ion accumulation showing significant correlations with plant performance. We found that while transpiration was a key determinant of plant performance in the greenhouse, shoot mass strongly correlated with yield under field conditions. Conversely, ion accumulation was the least influential factor under greenhouse conditions. Through a Genome Wide Association Study, we identified candidate genes not previously associated with salt stress, highlighting the power of high-throughput phenotyping in uncovering novel aspects of plant stress responses. This study contributes to our understanding of salt stress tolerance in S. pimpinellifolium and lays the groundwork for further investigations into the genetic basis of these traits, ultimately informing breeding efforts for salinity tolerance in tomato and other crops.

A deep learning approach for overall survival prediction in lung cancer with missing values

BACKGROUND AND OBJECTIVE

In the field of lung cancer research, particularly in the analysis of overall survival (OS), artificial intelligence (AI) serves crucial roles with specific aims. Given the prevalent issue of missing data in the medical domain, our primary objective is to develop an AI model capable of dynamically handling this missing data. Additionally, we aim to leverage all accessible data, effectively analyzing both uncensored patients who have experienced the event of interest and censored patients who have not, by embedding a specialized technique within our AI model, not commonly utilized in other AI tasks. Through the realization of these objectives, our model aims to provide precise OS predictions for non-small cell lung cancer (NSCLC) patients, thus overcoming these significant challenges.

METHODS

We present a novel approach to survival analysis with missing values in the context of NSCLC, which exploits the strengths of the transformer architecture to account only for available features without requiring any imputation strategy. More specifically, this model tailors the transformer architecture to tabular data by adapting its feature embedding and masked self-attention to mask missing data and fully exploit the available ones. By making use of ad-hoc designed losses for OS, it is able to account for both censored and uncensored patients, as well as changes in risks over time.

RESULTS

We compared our method with state-of-the-art models for survival analysis coupled with different imputation strategies. We evaluated the results obtained over a period of 6 years using different time granularities obtaining a Ct-index, a time-dependent variant of the C-index, of 71.97, 77.58 and 80.72 for time units of 1 month, 1 year and 2 years, respectively, outperforming all state-of-the-art methods regardless of the imputation method used.

CONCLUSIONS

The results show that our model not only outperforms the state-of-the-art's performance but also simplifies the analysis in the presence of missing data, by effectively eliminating the need to identify the most appropriate imputation strategy for predicting OS in NSCLC patients.

The Comparative Diagnostic Capability of Large Language Models in Otolaryngology

OBJECTIVES

Evaluate and compare the ability of large language models (LLMs) to diagnose various ailments in otolaryngology.

METHODS

We collected all 100 clinical vignettes from the second edition of Otolaryngology Cases-The University of Cincinnati Clinical Portfolio by Pensak et al. With the addition of the prompt "Provide a diagnosis given the following history," we prompted ChatGPT-3.5, Google Bard, and Bing-GPT4 to provide a diagnosis for each vignette. These diagnoses were compared to the portfolio for accuracy and recorded. All queries were run in June 2023.

RESULTS

ChatGPT-3.5 was the most accurate model (89% success rate), followed by Google Bard (82%) and Bing GPT (74%). A chi-squared test revealed a significant difference between the three LLMs in providing correct diagnoses (p = 0.023). Of the 100 vignettes, seven require additional testing results (i.e., biopsy, non-contrast CT) for accurate clinical diagnosis. When omitting these vignettes, the revised success rates were 95.7% for ChatGPT-3.5, 88.17% for Google Bard, and 78.72% for Bing-GPT4 (p = 0.002).

CONCLUSIONS

ChatGPT-3.5 offers the most accurate diagnoses when given established clinical vignettes as compared to Google Bard and Bing-GPT4. LLMs may accurately offer assessments for common otolaryngology conditions but currently require detailed prompt information and critical supervision from clinicians. There is vast potential in the clinical applicability of LLMs; however, practitioners should be wary of possible "hallucinations" and misinformation in responses.

LEVEL OF EVIDENCE

3 Laryngoscope, 134:3997-4002, 2024.

Neuroimage analysis using artificial intelligence approaches: a systematic review

In the contemporary era, artificial intelligence (AI) has undergone a transformative evolution, exerting a profound influence on neuroimaging data analysis. This development has significantly elevated our comprehension of intricate brain functions. This study investigates the ramifications of employing AI techniques on neuroimaging data, with a specific objective to improve diagnostic capabilities and contribute to the overall progress of the field. A systematic search was conducted in prominent scientific databases, including PubMed, IEEE Xplore, and Scopus, meticulously curating 456 relevant articles on AI-driven neuroimaging analysis spanning from 2013 to 2023. To maintain rigor and credibility, stringent inclusion criteria, quality assessments, and precise data extraction protocols were consistently enforced throughout this review. Following a rigorous selection process, 104 studies were selected for review, focusing on diverse neuroimaging modalities with an emphasis on mental and neurological disorders. Among these, 19.2% addressed mental illness, and 80.7% focused on neurological disorders. It is found that the prevailing clinical tasks are disease classification (58.7%) and lesion segmentation (28.9%), whereas image reconstruction constituted 7.3%, and image regression and prediction tasks represented 9.6%. AI-driven neuroimaging analysis holds tremendous potential, transforming both research and clinical applications. Machine learning and deep learning algorithms outperform traditional methods, reshaping the field significantly.

Characteristics of Immunogenicity against SARS-CoV-2 in a Community-Based Model of Care during the Fourth Wave of COVID-19 Outbreak in Ho Chi Minh City

PURPOSE

Although some immune protection from close contact with individuals who have coronavirus disease 2019 (COVID-19) has been documented, there is limited data on the seroprevalence of antibodies against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in individuals who were in lockdown with confirmed COVID-19 cases. This study investigated immunogenicity against SARS-CoV-2 in household members and people who lived near home-quarantined patients with COVID-19.

MATERIALS AND METHODS

This cross-sectional study was conducted during the community-based care that took place during lockdowns in District 10, Ho Chi Minh City, Vietnam from July to September 2021. SARS-CoV-2 antibody levels were determined in index cases of COVID-19, household contacts, and a no-contact group from the same area.

RESULTS

A total of 770 participants were included (355 index cases, 103 household contacts, and 312 no contacts). All index cases were unvaccinated, but >90% of individuals in the household and no-contact groups had received ≥1 vaccine dose. SARS-CoV-2 neutralizing antibodies (Nabs) were present in >77% of unvaccinated index cases versus 64%/65.4% in the household/no-contact groups (p=0.001). Antibody concentrations in unvaccinated index cases were significantly higher than those in household contacts and no contacts, with no difference between the latter groups. In all cases, antibody levels declined markedly ≥6 weeks after infection, and failed to persist beyond this time in the household and no-contact groups.

CONCLUSION

Community-based care may have helped to create community immunogenicity, but Nabs did not persist, highlighting a need for vaccination for all individuals before, or from 6 weeks after, infection with SARS-CoV-2.

Comparison of automated deep neural network against manual sleep stage scoring in clinical data

OBJECTIVE

To compare the accuracy and generalizability of an automated deep neural network and the Philip Sleepware G3™ Somnolyzer system (Somnolyzer) for sleep stage scoring using American Academy of Sleep Medicine (AASM) guidelines.

METHODS

Sleep recordings from 104 participants were analyzed by a convolutional neural network (CNN), the Somnolyzer and skillful technicians. Evaluation metrics were derived for different combinations of sleep stages. A further comparison between the Somnolyzer and the CNN model using a single-channel signal as input was also performed. Sleep recordings from 263 participants with a lower prevalence of OSA served as a cross-validation dataset to validate the generalizability of the CNN model.

RESULTS

The overall agreement between automated and manual scoring for sleep staging in 104 participants outperformed that of the Somnolyzer according to various metrics (accuracy: 81.81 % vs. 77.07 %; F1: 76.36 % vs. 73.80 %; Cohen's kappa: 0.7403 vs. 0.6848). The results showed that the left electrooculography (EOG) single-channel model had minor advantages over the Somnolyzer. In terms of consistency with manual sleep staging, the CNN model demonstrated superior performance in identifying more pronounced sleep transitions, particularly in the N2 stage and sleep latency metrics. Conversely, the Somnolyzer showed enhanced proficiency in the analysis of REM stages, notably in measuring REM latency. The accuracy in the cross-validation set of 263 participants was also above 80 %.

CONCLUSIONS

The CNN-based automated deep neural network outperformed the Somnolyzer and is sufficiently accurate for sleep study analyses using the AASM classification criteria.

Evaluating the accuracy of ChatGPT-4 in predicting ASA scores: A prospective multicentric study ChatGPT-4 in ASA score prediction

BACKGROUND

This study investigates the potential of ChatGPT-4, developed by OpenAI, in enhancing medical decision-making processes, particularly in preoperative assessments using the American Society of Anesthesiologists (ASA) scoring system. The ASA score, a critical tool in evaluating patients' health status and anesthesia risks before surgery, categorizes patients from I to VI based on their overall health and risk factors. Despite its widespread use, determining accurate ASA scores remains a subjective process that may benefit from AI-supported assessments. This research aims to evaluate ChatGPT-4's capability to predict ASA scores accurately compared to expert anesthesiologists' assessments.

METHODS

In this prospective multicentric study, ethical board approval was obtained, and the study was registered with clinicaltrials.gov (NCT06321445). We included 2851 patients from anesthesiology outpatient clinics, spanning neonates to all age groups and genders, with ASA scores between I-IV. Exclusion criteria were set for ASA V and VI scores, emergency operations, and insufficient information for ASA score determination. Data on patients' demographics, health conditions, and ASA scores by anesthesiologists were collected and anonymized. ChatGPT-4 was then tasked with assigning ASA scores based on the standardized patient data.

RESULTS

Our results indicate a high level of concordance between ChatGPT-4 predictions and anesthesiologists' evaluations, with Cohen's kappa analysis showing a kappa value of 0.858 (p = 0.000). While the model demonstrated over 90% accuracy in predicting ASA scores I to III, it showed a notable variance in ASA IV scores, suggesting a potential limitation in assessing patients with more complex health conditions.

DISCUSSION

The findings suggest that ChatGPT-4 can significantly contribute to the medical field by supporting anesthesiologists in preoperative assessments. This study not only demonstrates ChatGPT-4's efficacy in medical data analysis and decision-making but also opens new avenues for AI applications in healthcare, particularly in enhancing patient safety and optimizing surgical outcomes. Further research is needed to refine AI models for complex case assessments and integrate them seamlessly into clinical workflows.

Google Gemini and Bard artificial intelligence chatbot performance in ophthalmology knowledge assessment

PURPOSE

With the popularization of ChatGPT (Open AI, San Francisco, California, United States) in recent months, understanding the potential of artificial intelligence (AI) chatbots in a medical context is important. Our study aims to evaluate Google Gemini and Bard's (Google, Mountain View, California, United States) knowledge in ophthalmology.

METHODS

In this study, we evaluated Google Gemini and Bard's performance on EyeQuiz, a platform containing ophthalmology board certification examination practice questions, when used from the United States (US). Accuracy, response length, response time, and provision of explanations were evaluated. Subspecialty-specific performance was noted. A secondary analysis was conducted using Bard from Vietnam, and Gemini from Vietnam, Brazil, and the Netherlands.

RESULTS

Overall, Google Gemini and Bard both had accuracies of 71% across 150 text-based multiple-choice questions. The secondary analysis revealed an accuracy of 67% using Bard from Vietnam, with 32 questions (21%) answered differently than when using Bard from the US. Moreover, the Vietnam version of Gemini achieved an accuracy of 74%, with 23 (15%) answered differently than the US version of Gemini. While the Brazil (68%) and Netherlands (65%) versions of Gemini performed slightly worse than the US version, differences in performance across the various country-specific versions of Bard and Gemini were not statistically significant.

CONCLUSION

Google Gemini and Bard had an acceptable performance in responding to ophthalmology board examination practice questions. Subtle variability was noted in the performance of the chatbots across different countries. The chatbots also tended to provide a confident explanation even when providing an incorrect answer.

Leveraging artificial intelligence in vaccine development: A narrative review

Vaccine development stands as a cornerstone of public health efforts, pivotal in curbing infectious diseases and reducing global morbidity and mortality. However, traditional vaccine development methods are often time-consuming, costly, and inefficient. The advent of artificial intelligence (AI) has ushered in a new era in vaccine design, offering unprecedented opportunities to expedite the process. This narrative review explores the role of AI in vaccine development, focusing on antigen selection, epitope prediction, adjuvant identification, and optimization strategies. AI algorithms, including machine learning and deep learning, leverage genomic data, protein structures, and immune system interactions to predict antigenic epitopes, assess immunogenicity, and prioritize antigens for experimentation. Furthermore, AI-driven approaches facilitate the rational design of immunogens and the identification of novel adjuvant candidates with optimal safety and efficacy profiles. Challenges such as data heterogeneity, model interpretability, and regulatory considerations must be addressed to realize the full potential of AI in vaccine development. Integrating emerging technologies, such as single-cell omics and synthetic biology, promises to enhance vaccine design precision and scalability. This review underscores the transformative impact of AI on vaccine development and highlights the need for interdisciplinary collaborations and regulatory harmonization to accelerate the delivery of safe and effective vaccines against infectious diseases.

HarmonyTM: multi-center data harmonization applied to distributed learning for Parkinson's disease classification

Purpose

Distributed learning is widely used to comply with data-sharing regulations and access diverse datasets for training machine learning (ML) models. The traveling model (TM) is a distributed learning approach that sequentially trains with data from one center at a time, which is especially advantageous when dealing with limited local datasets. However, a critical concern emerges when centers utilize different scanners for data acquisition, which could potentially lead models to exploit these differences as shortcuts. Although data harmonization can mitigate this issue, current methods typically rely on large or paired datasets, which can be impractical to obtain in distributed setups.

Approach

We introduced HarmonyTM, a data harmonization method tailored for the TM. HarmonyTM effectively mitigates bias in the model's feature representation while retaining crucial disease-related information, all without requiring extensive datasets. Specifically, we employed adversarial training to "unlearn" bias from the features used in the model for classifying Parkinson's disease (PD). We evaluated HarmonyTM using multi-center three-dimensional (3D) neuroimaging datasets from 83 centers using 23 different scanners.

Results

Our results show that HarmonyTM improved PD classification accuracy from 72% to 76% and reduced (unwanted) scanner classification accuracy from 53% to 30% in the TM setup.

Conclusion

HarmonyTM is a method tailored for harmonizing 3D neuroimaging data within the TM approach, aiming to minimize shortcut learning in distributed setups. This prevents the disease classifier from leveraging scanner-specific details to classify patients with or without PD-a key aspect for deploying ML models for clinical applications.

Statistical and machine learning models for location-specific crop yield prediction using weather indices

Crop yield prediction gains growing importance for all stakeholders in agriculture. Since the growth and development of crops are fully connected with many weather factors, it is inevitable to incorporate meteorological information into yield prediction mechanism. The changes in climate-yield relationship are more pronounced at a local level than across relatively large regions. Hence, district or sub-region-level modeling may be an appropriate approach. To obtain a location- and crop-specific model, different models with different functional forms have to be explored. This systematic review aims to discuss research papers related to statistical and machine-learning models commonly used to predict crop yield using weather factors. It was found that Artificial Neural Network (ANN) and Multiple Linear Regression were the most applied models. Support Vector Regression (SVR) model has a high success ratio as it performed well in most of the cases. The optimization options in ANN and SVR models allow us to tune models to specific patterns of association between weather conditions of a location and crop yield. ANN model can be trained using different activation functions with optimized learning rate and number of hidden layer neurons. Similarly, the SVR model can be trained with different kernel functions and various combinations of hyperparameters. Penalized regression models namely, LASSO and Elastic Net are better alternatives to simple linear regression. The nonlinear machine learning models namely, SVR and ANN were found to perform better in most of the cases which indicates there exists a nonlinear complex association between crop yield and weather factors.

CA-ViT: Contour-Guided and Augmented Vision Transformers to Enhance Glaucoma Classification Using Fundus Images

Glaucoma, a predominant cause of visual impairment on a global scale, poses notable challenges in diagnosis owing to its initially asymptomatic presentation. Early identification is vital to prevent irreversible vision impairment. Cutting-edge deep learning techniques, such as vision transformers (ViTs), have been employed to tackle the challenge of early glaucoma detection. Nevertheless, limited approaches have been suggested to improve glaucoma classification due to issues like inadequate training data, variations in feature distribution, and the overall quality of samples. Furthermore, fundus images display significant similarities and slight discrepancies in lesion sizes, complicating glaucoma classification when utilizing ViTs. To address these obstacles, we introduce the contour-guided and augmented vision transformer (CA-ViT) for enhanced glaucoma classification using fundus images. We employ a Conditional Variational Generative Adversarial Network (CVGAN) to enhance and diversify the training dataset by incorporating conditional sample generation and reconstruction. Subsequently, a contour-guided approach is integrated to offer crucial insights into the disease, particularly concerning the optic disc and optic cup regions. Both the original images and extracted contours are given to the ViT backbone; then, feature alignment is performed with a weighted cross-entropy loss. Finally, in the inference phase, the ViT backbone, trained on the original fundus images and augmented data, is used for multi-class glaucoma categorization. By utilizing the Standardized Multi-Channel Dataset for Glaucoma (SMDG), which encompasses various datasets (e.g., EYEPACS, DRISHTI-GS, RIM-ONE, REFUGE), we conducted thorough testing. The results indicate that the proposed CA-ViT model significantly outperforms current methods, achieving a precision of 93.0%, a recall of 93.08%, an F1 score of 92.9%, and an accuracy of 93.0%. Therefore, the integration of augmentation with the CVGAN and contour guidance can effectively enhance glaucoma classification tasks.

SG-Fusion: A swin-transformer and graph convolution-based multi-modal deep neural network for glioma prognosis

The integration of morphological attributes extracted from histopathological images and genomic data holds significant importance in advancing tumor diagnosis, prognosis, and grading. Histopathological images are acquired through microscopic examination of tissue slices, providing valuable insights into cellular structures and pathological features. On the other hand, genomic data provides information about tumor gene expression and functionality. The fusion of these two distinct data types is crucial for gaining a more comprehensive understanding of tumor characteristics and progression. In the past, many studies relied on single-modal approaches for tumor diagnosis. However, these approaches had limitations as they were unable to fully harness the information from multiple data sources. To address these limitations, researchers have turned to multi-modal methods that concurrently leverage both histopathological images and genomic data. These methods better capture the multifaceted nature of tumors and enhance diagnostic accuracy. Nonetheless, existing multi-modal methods have, to some extent, oversimplified the extraction processes for both modalities and the fusion process. In this study, we presented a dual-branch neural network, namely SG-Fusion. Specifically, for the histopathological modality, we utilize the Swin-Transformer structure to capture both local and global features and incorporate contrastive learning to encourage the model to discern commonalities and differences in the representation space. For the genomic modality, we developed a graph convolutional network based on gene functional and expression level similarities. Additionally, our model integrates a cross-attention module to enhance information interaction and employs divergence-based regularization to enhance the model's generalization performance. Validation conducted on glioma datasets from the Cancer Genome Atlas unequivocally demonstrates that our SG-Fusion model outperforms both single-modal methods and existing multi-modal approaches in both survival analysis and tumor grading.

Evaluating customer perspectives on omnichannel shopping satisfaction in the fashion retail sector

The effective implementation of omnichannel commerce can fundamentally alter how consumers shop online. This study attempted to understand Thai consumers' omnichannel fashion retail purchasing activities. The objectives of the study were to investigate the determinants shaping omnichannel customer experiences within the fashion retail industry and to examine the impact of omnichannel customer experiences on customer satisfaction within the Thai retail industry. The research utilized the Unified Theory of Acceptance and Use of Technology (UTAUT) model to analyze the effects of omnichannels on purchasing behaviors and levels of satisfaction of consumers. The study employed a survey research design, applying simple random sampling to select 509 respondents with omnichannel shopping experience in the clothing and fashion. The respondent data was analyzed using structural equation modeling utilizing the Amos software version 24. Analyzing the results revealed a significant correlation between omnichannel shopping and customer satisfaction in fashion retail shopping. Perceived ease of use, perceived enjoyment, integrated promotions, integrated customer service, and integrated transactions were all found to influence omnichannel experiences favorably. The findings suggest that fashion retailers prioritize customer satisfaction by enhancing their omnichannel experiences through better coordination and synchronization of their different customer service channels.

Deep Learning-Based System Combining Chest X-Ray and Computerized Tomography Images for COVID-19 Diagnosis

Aims/Background: The coronavirus disease 2019 (COVID-19) pandemic has highlighted the need for accurate and efficient diagnostic methods. This study aims to improve COVID-19 detection by integrating chest X-ray (CXR) and computerized tomography (CT) images using deep learning techniques, further improving diagnostic accuracy by using a combined imaging approach. Methods: The study used two publicly accessible databases, COVID-19 Questionnaires for Understanding the Exposure (COVID-QU-Ex) and Integrated Clinical and Translational Cancer Foundation (iCTCF), containing CXR and CT images, respectively. The proposed system employed convolutional neural networks (CNNs) for classification, specifically EfficientNet and ResNet architectures. The data underwent preprocessing steps, including image resizing, Gaussian noise addition, and data augmentation. The dataset was divided into training, validation, and test sets. Gradient-weighted Class Activation Mapping (Grad-CAM) was used for model interpretability. Results: The EfficientNet-based models outperformed the ResNet-based models across all metrics. The highest accuracy achieved was 99.44% for CXR images and 99.81% for CT images with EfficientNetB5. The models also demonstrated high precision, recall, and F1 scores. For statistical significance, the p-values were less than 0.05, indicating that the results are significant. Conclusion: Integrating CXR and CT images using deep learning significantly improves the accuracy of COVID-19 diagnosis. The EfficientNet-based models, with their superior feature extraction capabilities, show better performance than ResNet models. Grad-CAM Visualizations provide insights into the model's decision-making process, potentially reducing diagnostic errors and accelerating diagnosis processes. This approach can improve patient care and support healthcare systems in managing the pandemic more effectively.

BioBricks.ai: A Versioned Data Registry for Life Sciences Data Assets

Researchers in biomedical research, public health and the life sciences often spend weeks or months discovering, accessing, curating, and integrating data from disparate sources, significantly delaying the onset of actual analysis and innovation. Instead of countless developers creating redundant and inconsistent data pipelines, BioBricks.ai offers a centralized data repository and a suite of developer-friendly tools to simplify access to scientific data. Currently, BioBricks.ai delivers over ninety biological and chemical datasets. It provides a package manager-like system for installing and managing dependencies on data sources. Each 'brick' is a Data Version Control git repository that supports an updateable pipeline for extraction, transformation, and loading data into the BioBricks.ai backend at https://biobricks.ai. Use cases include accelerating data science workflows and facilitating the creation of novel data assets by integrating multiple datasets into unified, harmonized resources. In conclusion, BioBricks.ai offers an opportunity to accelerate access and use of public data through a single open platform.

Gaps in the Global Regulatory Frameworks for the Use of Artificial Intelligence (AI) in the Healthcare Services Sector and Key Recommendations

Artificial Intelligence (AI) has shown remarkable potential to revolutionise healthcare by enhancing diagnostics, improving treatment outcomes, and streamlining administrative processes. In the global regulatory landscape, several countries are working on regulating AI in healthcare. There are five key regulatory issues that need to be addressed: (i) data security and protection-measures to cover the "digital health footprints" left unknowingly by patients when they access AI in health services; (ii) data quality-availability of safe and secure data and more open database sources for AI, algorithms, and datasets to ensure equity and prevent demographic bias; (iii) validation of algorithms-mapping of the explainability and causability of the AI system; (iv) accountability-whether this lies with the healthcare professional, healthcare organisation, or the personified AI algorithm; (v) ethics and equitable access-whether fundamental rights of people are met in an ethical manner. Policymakers may need to consider the entire life cycle of AI in healthcare services and the databases that were used for the training of the AI system, along with requirements for their risk assessments to be publicly accessible for effective regulatory oversight. AI services that enhance their functionality over time need to undergo repeated algorithmic impact assessment and must also demonstrate real-time performance. Harmonising regulatory frameworks at the international level would help to resolve cross-border issues of AI in healthcare services.

EEG correlates of static and dynamic face perception: the role of naturalistic motion

Much of our understanding of how the brain processes dynamic faces comes from research that compares static photographs to dynamic morphs, which exhibit simplified, computer-generated motion. By comparing static, video recorded, and dynamic morphed expressions, we aim to identify the neural correlates of naturalistic facial dynamism, using time-domain and time-frequency analysis. Dynamic morphs were made from the neutral and peak frames of video recorded transitions of happy and fearful expressions, which retained expression change and removed asynchronous and non-linear features of naturalistic facial motion. We found that dynamic morphs elicited increased N400 amplitudes and lower LPP amplitudes compared to other stimulus types. Video recordings elicited higher LPP amplitudes and greater frontal delta activity compared to other stimuli. Thematic analysis of participant interviews using a large language model revealed that participants found it difficult to assess the genuineness of morphed expressions, and easier to analyse the genuineness of happy compared to fearful expressions. Our findings suggest that animating real faces with artificial motion may violate expectations (N400) and reduce the social salience (LPP) of dynamic morphs. Results also suggest that delta oscillations in the frontal region may be involved with the perception of naturalistic facial motion in happy and fearful expressions. Overall, our findings highlight the sensitivity of neural mechanisms required for face perception to subtle changes in facial motion characteristics, which has important implications for neuroimaging research using faces with simplified motion.

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.

Investigation of Relationship between Hemodynamic and Morphometric Characteristics of Aortas in Pediatric Patients

Background: The utilization of hemodynamic parameters, whose estimation is often cumbersome, can fasten diagnostics and decision-making related to congenital heart diseases. The main goal of this study is to investigate the relationship between hemodynamic and morphometric features of the thoracic aorta and to construct corresponding predictive models. Methods: Multi-slice spiral computed tomography images of the aortas of patients with coarctation diagnoses and patients without cardiac or vascular diseases were evaluated to obtain numerical models of the aorta and branches of the aortic arch. Hemodynamic characteristics were estimated in key subdomains of the aorta and three branches using computational fluid dynamics methods. The key morphometric features (diameters) were calculated at locations in proximity to the domains, where hemodynamic characteristics are evaluated. Results: The functional dependencies for velocities and pressure on the corresponding diameters have been fitted, and a metamodel has been constructed employing the predicted values from these models. Conclusions: The metamodel demonstrated high accuracy in classifying aortas into their respective types, thereby confirming the adequacy of the predicted hemodynamic characteristics by morphometric characteristics. The proposed methodology is applicable to other heart diseases without fundamental changes.

Obtaining the Most Accurate, Explainable Model for Predicting Chronic Obstructive Pulmonary Disease: Triangulation of Multiple Linear Regression and Machine Learning Methods

BACKGROUND

Lung disease is a severe problem in the United States. Despite the decreasing rates of cigarette smoking, chronic obstructive pulmonary disease (COPD) continues to be a health burden in the United States. In this paper, we focus on COPD in the United States from 2016 to 2019.

OBJECTIVE

We gathered a diverse set of non-personally identifiable information from public data sources to better understand and predict COPD rates at the core-based statistical area (CBSA) level in the United States. Our objective was to compare linear models with machine learning models to obtain the most accurate and interpretable model of COPD.

METHODS

We integrated non-personally identifiable information from multiple Centers for Disease Control and Prevention sources and used them to analyze COPD with different types of methods. We included cigarette smoking, a well-known contributing factor, and race/ethnicity because health disparities among different races and ethnicities in the United States are also well known. The models also included the air quality index, education, employment, and economic variables. We fitted models with both multiple linear regression and machine learning methods.

RESULTS

The most accurate multiple linear regression model has variance explained of 81.1%, mean absolute error of 0.591, and symmetric mean absolute percentage error of 9.666. The most accurate machine learning model has variance explained of 85.7%, mean absolute error of 0.456, and symmetric mean absolute percentage error of 6.956. Overall, cigarette smoking and household income are the strongest predictor variables. Moderately strong predictors include education level and unemployment level, as well as American Indian or Alaska Native, Black, and Hispanic population percentages, all measured at the CBSA level.

CONCLUSIONS

This research highlights the importance of using diverse data sources as well as multiple methods to understand and predict COPD. The most accurate model was a gradient boosted tree, which captured nonlinearities in a model whose accuracy is superior to the best multiple linear regression. Our interpretable models suggest ways that individual predictor variables can be used in tailored interventions aimed at decreasing COPD rates in specific demographic and ethnographic communities. Gaps in understanding the health impacts of poor air quality, particularly in relation to climate change, suggest a need for further research to design interventions and improve public health.

Transforming Health Care Through Chatbots for Medical History-Taking and Future Directions: Comprehensive Systematic Review

BACKGROUND

The integration of artificial intelligence and chatbot technology in health care has attracted significant attention due to its potential to improve patient care and streamline history-taking. As artificial intelligence-driven conversational agents, chatbots offer the opportunity to revolutionize history-taking, necessitating a comprehensive examination of their impact on medical practice.

OBJECTIVE

This systematic review aims to assess the role, effectiveness, usability, and patient acceptance of chatbots in medical history-taking. It also examines potential challenges and future opportunities for integration into clinical practice.

METHODS

A systematic search included PubMed, Embase, MEDLINE (via Ovid), CENTRAL, Scopus, and Open Science and covered studies through July 2024. The inclusion and exclusion criteria for the studies reviewed were based on the PICOS (participants, interventions, comparators, outcomes, and study design) framework. The population included individuals using health care chatbots for medical history-taking. Interventions focused on chatbots designed to facilitate medical history-taking. The outcomes of interest were the feasibility, acceptance, and usability of chatbot-based medical history-taking. Studies not reporting on these outcomes were excluded. All study designs except conference papers were eligible for inclusion. Only English-language studies were considered. There were no specific restrictions on study duration. Key search terms included "chatbot*," "conversational agent*," "virtual assistant," "artificial intelligence chatbot," "medical history," and "history-taking." The quality of observational studies was classified using the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) criteria (eg, sample size, design, data collection, and follow-up). The RoB 2 (Risk of Bias) tool assessed areas and the levels of bias in randomized controlled trials (RCTs).

RESULTS

The review included 15 observational studies and 3 RCTs and synthesized evidence from different medical fields and populations. Chatbots systematically collect information through targeted queries and data retrieval, improving patient engagement and satisfaction. The results show that chatbots have great potential for history-taking and that the efficiency and accessibility of the health care system can be improved by 24/7 automated data collection. Bias assessments revealed that of the 15 observational studies, 5 (33%) studies were of high quality, 5 (33%) studies were of moderate quality, and 5 (33%) studies were of low quality. Of the RCTs, 2 had a low risk of bias, while 1 had a high risk.

CONCLUSIONS

This systematic review provides critical insights into the potential benefits and challenges of using chatbots for medical history-taking. The included studies showed that chatbots can increase patient engagement, streamline data collection, and improve health care decision-making. For effective integration into clinical practice, it is crucial to design user-friendly interfaces, ensure robust data security, and maintain empathetic patient-physician interactions. Future research should focus on refining chatbot algorithms, improving their emotional intelligence, and extending their application to different health care settings to realize their full potential in modern medicine.

TRIAL REGISTRATION

PROSPERO CRD42023410312; www.crd.york.ac.uk/prospero.

Effectiveness of ChatGPT 4.0 in Telemedicine-Based Management of Metastatic Prostate Carcinoma

The recent rise in telemedicine, notably during the COVID-19 pandemic, highlights the potential of integrating artificial intelligence tools in healthcare. This study assessed the effectiveness of ChatGPT versus medical oncologists in the telemedicine-based management of metastatic prostate cancer. In this retrospective study, 102 patients who met inclusion criteria were analyzed to compare the competencies of ChatGPT and oncologists in telemedicine consultations. ChatGPT's role in pre-charting and determining the need for in-person consultations was evaluated. The primary outcome was the concordance between ChatGPT and oncologists in treatment decisions. Results showed a moderate concordance (Cohen's Kappa = 0.43, p < 0.001). The number of diagnoses made by both parties was not significantly different (median number of diagnoses: 5 vs. 5, p = 0.12). In conclusion, ChatGPT exhibited moderate agreement with oncologists in management via telemedicine, indicating the need for further research to explore its healthcare applications.

From admission to discharge: a systematic review of clinical natural language processing along the patient journey

BACKGROUND

Medical text, as part of an electronic health record, is an essential information source in healthcare. Although natural language processing (NLP) techniques for medical text are developing fast, successful transfer into clinical practice has been rare. Especially the hospital domain offers great potential while facing several challenges including many documents per patient, multiple departments and complex interrelated processes.

METHODS

In this work, we survey relevant literature to identify and classify approaches which exploit NLP in the clinical context. Our contribution involves a systematic mapping of related research onto a prototypical patient journey in the hospital, along which medical documents are created, processed and consumed by hospital staff and patients themselves. Specifically, we reviewed which dataset types, dataset languages, model architectures and tasks are researched in current clinical NLP research. Additionally, we extract and analyze major obstacles during development and implementation. We discuss options to address them and argue for a focus on bias mitigation and model explainability.

RESULTS

While a patient's hospital journey produces a significant amount of structured and unstructured documents, certain steps and documents receive more research attention than others. Diagnosis, Admission and Discharge are clinical patient steps that are researched often across the surveyed paper. In contrast, our findings reveal significant under-researched areas such as Treatment, Billing, After Care, and Smart Home. Leveraging NLP in these stages can greatly enhance clinical decision-making and patient outcomes. Additionally, clinical NLP models are mostly based on radiology reports, discharge letters and admission notes, even though we have shown that many other documents are produced throughout the patient journey. There is a significant opportunity in analyzing a wider range of medical documents produced throughout the patient journey to improve the applicability and impact of NLP in healthcare.

CONCLUSIONS

Our findings suggest that there is a significant opportunity to leverage NLP approaches to advance clinical decision-making systems, as there remains a considerable understudied potential for the analysis of patient journey data.

Functional Characterization of Odorant Receptors for Sex Pheromone (Z)-11-Hexadecenol in Orthaga achatina

Pheromone receptor (PR)-mediated transduction of sex pheromones to electrophysiological signals is the basis for sex pheromone communication. Orthaga achatina, a serious pest of the camphor tree, uses a mixture of four components (Z11-16:OAc, Z11-16:OH, Z11-16:Ald, and Z3,Z6,Z9,Z12,Z15-23:H) as its sex pheromone. In this study, we identified five PR genes (OachPR1-5) by phylogenetic analysis. Further RT-PCR and qPCR experiments showed that PR1-3 were specifically expressed in male antennae, while PR4 was significantly female-biased in expression. Functional characterization using the XOE-TEVC assay demonstrated that PR1 and PR3 both responded strongly to Z11-16:OH, while PR1 and PR3 had a weak response to Z3,Z6,Z9,Z12,Z15-23:H and Z11-16:Ald, respectively. Finally, two key amino acid residues (N78 and R331) were confirmed to be essential for binding of PR3 with Z11-16:OH by molecular docking and site-directed mutagenesis. This study helps understand the sex pheromone recognition molecular mechanism of O. achatina.

A comparison of machine learning methods for recovering noisy and missing 4D flow MRI data

Experimental blood flow measurement techniques are invaluable for a better understanding of cardiovascular disease formation, progression, and treatment. One of the emerging methods is time-resolved three-dimensional phase-contrast magnetic resonance imaging (4D flow MRI), which enables noninvasive time-dependent velocity measurements within large vessels. However, several limitations hinder the usability of 4D flow MRI and other experimental methods for quantitative hemodynamics analysis. These mainly include measurement noise, corrupt or missing data, low spatiotemporal resolution, and other artifacts. Traditional filtering is routinely applied for denoising experimental blood flow data without any detailed discussion on why it is preferred over other methods. In this study, filtering is compared to different singular value decomposition (SVD)-based machine learning and autoencoder-type deep learning methods for denoising and filling in missing data (imputation). An artificially corrupted and voxelized computational fluid dynamics (CFD) simulation as well as in vitro 4D flow MRI data are used to test the methods. SVD-based algorithms achieve excellent results for the idealized case but severely struggle when applied to in vitro data. The autoencoders are shown to be versatile and applicable to all investigated cases. For denoising, the in vitro 4D flow MRI data, the denoising autoencoder (DAE), and the Noise2Noise (N2N) autoencoder produced better reconstructions than filtering both qualitatively and quantitatively. Deep learning methods such as N2N can result in noise-free velocity fields even though they did not use clean data during training. This work presents one of the first comprehensive assessments and comparisons of various classical and modern machine-learning methods for enhancing corrupt cardiovascular flow data in diseased arteries for both synthetic and experimental test cases.

Large Language Model Prompting Techniques for Advancement in Clinical Medicine

Large Language Models (LLMs have the potential to revolutionize clinical medicine by enhancing healthcare access, diagnosis, surgical planning, and education. However, their utilization requires careful, prompt engineering to mitigate challenges like hallucinations and biases. Proper utilization of LLMs involves understanding foundational concepts such as tokenization, embeddings, and attention mechanisms, alongside strategic prompting techniques to ensure accurate outputs. For innovative healthcare solutions, it is essential to maintain ongoing collaboration between AI technology and medical professionals. Ethical considerations, including data security and bias mitigation, are critical to their application. By leveraging LLMs as supplementary resources in research and education, we can enhance learning and support knowledge-based inquiries, ultimately advancing the quality and accessibility of medical care. Continued research and development are necessary to fully realize the potential of LLMs in transforming healthcare.

A trust based framework for the envelopment of medical AI

The importance of a trust-based relationship between patients and medical professionals has been recognized as one of the most important predictors of treatment success and patients' satisfaction. We have developed a novel legal, social and regulatory envelopment of medical AI that is explicitly based on the preservation of trust between patients and medical professionals. We require that the envelopment fosters reliance on the medical AI by both patients and medical professionals. Focusing on this triangle of desirable attitudes allows us to develop eight envelopment components that will support, strengthen and preserve these attitudes. We then demonstrate how each envelopment component can be enacted during different stages of the systems development life cycle and demonstrate that this requires the involvement of medical professionals and patients at the earliest stages of the life cycle. Therefore, this framework requires medical AI start-ups to cooperate with medical professionals and patients throughout.

Visual interpretability of image-based classification models by generative latent space disentanglement applied to in vitro fertilization

The success of deep learning in identifying complex patterns exceeding human intuition comes at the cost of interpretability. Non-linear entanglement of image features makes deep learning a "black box" lacking human meaningful explanations for the models' decision. We present DISCOVER, a generative model designed to discover the underlying visual properties driving image-based classification models. DISCOVER learns disentangled latent representations, where each latent feature encodes a unique classification-driving visual property. This design enables "human-in-the-loop" interpretation by generating disentangled exaggerated counterfactual explanations. We apply DISCOVER to interpret classification of in vitro fertilization embryo morphology quality. We quantitatively and systematically confirm the interpretation of known embryo properties, discover properties without previous explicit measurements, and quantitatively determine and empirically verify the classification decision of specific embryo instances. We show that DISCOVER provides human-interpretable understanding of "black box" classification models, proposes hypotheses to decipher underlying biomedical mechanisms, and provides transparency for the classification of individual predictions.

COVID-19 severity detection using chest X-ray segmentation and deep learning

COVID-19 has resulted in a significant global impact on health, the economy, education, and daily life. The disease can range from mild to severe, with individuals over 65 or those with underlying medical conditions being more susceptible to severe illness. Early testing and isolation are vital due to the virus's variable incubation period. Chest radiographs (CXR) have gained importance as a diagnostic tool due to their efficiency and reduced radiation exposure compared to CT scans. However, the sensitivity of CXR in detecting COVID-19 may be lower. This paper introduces a deep learning framework for accurate COVID-19 classification and severity prediction using CXR images. U-Net is used for lung segmentation, achieving a precision of 0.9924. Classification is performed using a Convulation-capsule network, with high true positive rates of 86% for COVID-19, 93% for pneumonia, and 85% for normal cases. Severity assessment employs ResNet50, VGG-16, and DenseNet201, with DenseNet201 showing superior accuracy. Empirical results, validated with 95% confidence intervals, confirm the framework's reliability and robustness. This integration of advanced deep learning techniques with radiological imaging enhances early detection and severity assessment, improving patient management and resource allocation in clinical settings.

Precognition of Known And Unknown Biothreats: A Risk-Based Approach

Data mining and artificial intelligence algorithms can estimate the probability of future occurrences with defined precision. Yet, the prediction of infectious disease outbreaks remains a complex and difficult task. This is demonstrated by the limited accuracy and sensitivity of current models in predicting the emergence of previously unknown pathogens such as Zika, Chikungunya, and SARS-CoV-2, and the resurgence of Mpox, along with their impacts on global health, trade, and security. Comprehensive analysis of infectious disease risk profiles, vulnerabilities, and mitigation capacities, along with their spatiotemporal dynamics at the international level, is essential for preventing their transnational propagation. However, annual indexes about the impact of infectious diseases provide a low level of granularity to allow stakeholders to craft better mitigation strategies. A quantitative risk assessment by analytical platforms requires billions of near real-time data points from heterogeneous sources, integrating and analyzing univariable or multivariable data with different levels of complexity and latency that, in most cases, overwhelm human cognitive capabilities. Autonomous biosurveillance can open the possibility for near real-time, risk- and evidence-based policymaking and operational decision support.

More, better feedback please: are learning analytics dashboards (LAD) the solution to a wicked problem?

There is a long-standing lack of learner satisfaction with quality and quantity of feedback in health professions education (HPE) and training. To address this, university and training programmes are increasingly using technological advancements and data analytic tools to provide feedback. One such educational technology is the Learning Analytic Dashboard (LAD), which holds the promise of a comprehensive view of student performance via partial or fully automated feedback delivered to learners in real time. The possibility of displaying performance data visually, on a single platform, so users can access and process feedback efficiently and constantly, and use this to improve their performance, is very attractive to users, educators and institutions. However, the mainstream literature tends to take an atheoretical and instrumentalist view of LADs, a view that uncritically celebrates the promise of LAD's capacity to provide a 'technical fix' to the 'wicked problem' of feedback in health professions education. This paper seeks to recast the discussion of LADs as something other than a benign material technology using the lenses of Miller and Rose's technologies of government and Barry's theory of Technological Societies, where such technical devices are also inherently agentic and political. An examination of the purpose, design and deployment of LADs from these theoretical perspectives can reveal how these educational devices shape and govern the HPE learner body in different ways, which in turn, may produce a myriad of unintended- and ironic- effects on the feedback process. In this Reflections article we wish to encourage health professions education scholars to examine the practices and consequences thereof of the ever-expanding use of LADs more deeply and with a sense of urgency.

Mapping cognitive biases in multidisciplinary team (MDT) decision-making for cancer care in Scotland: a cognitive ethnography study protocol

INTRODUCTION

The efficiency of multidisciplinary teams (MDTs) in cancer care hinges on facilitating clinicians' cognitive processes as they navigate complex and uncertain judgements during treatment planning. When systems and workflows are not designed to adequately support human judgement and decision-making, even experts are prone to fallible reasoning due to cognitive biases. Incomplete integration of information or biased interpretations of patient data can lead to clinical errors and delays in the implementation of treatment recommendations. Though their impact is intuitively recognised, there is currently a paucity of empirical work on cognitive biases in MDT decision-making. Our study aims to explicate the impact of such biases on treatment planning and establish a foundation for targeted investigations and interventions to mitigate their negative effects.

METHODS AND ANALYSIS

This is a qualitative, observational study. We employ cognitive ethnography, informed by the Distributed Cognition for Teamwork framework to assess and evaluate MDT decision-making processes. The study involves in-person and virtual field observations of hepatopancreaticobiliary and upper gastrointestinal MDTs and interviews with their members over several months. The data generated will be analysed in a hybrid inductive/deductive fashion to develop a comprehensive map of potential cognitive biases in MDT decision processes identifying antecedents and risk factors of suboptimal treatment planning processes. Further, we will identify components of the MDT environment that can be redesigned to support decision-making via development of an MDT workspace evaluation tool.

ETHICS AND DISSEMINATION

This project has received management and ethical approvals from NHS Lothian Research and Development (2023/0245) and the University of Edinburgh Medical School ethical review committee (23-EMREC-049). Findings will be shared with participating MDTs and disseminated via a PhD thesis, international conference presentations and relevant scientific journals.

Evaluating EHR-Integrated Digital Technologies for Medication-Related Outcomes and Health Equity in Hospitalised Adults: A Scoping Review

The purpose of this scoping review is to identify and evaluate studies that examine the effectiveness and implementation strategies of Electronic Health Record (EHR)-integrated digital technologies aimed at improving medication-related outcomes and promoting health equity among hospitalised adults. Using the Consolidated Framework for Implementation Research (CFIR), the implementation methods and outcomes of the studies were evaluated, as was the assessment of methodological quality and risk of bias. Searches through Medline, Embase, Web of Science, and CINAHL Plus yielded 23 relevant studies from 1,232 abstracts, spanning 11 countries and from 2008 to 2022, with varied research designs. Integrated digital tools such as alert systems, clinical decision support systems, predictive analytics, risk assessment, and real-time screening and surveillance within EHRs demonstrated potential in reducing medication errors, adverse events, and inappropriate medication use, particularly in older patients. Challenges include alert fatigue, clinician acceptance, workflow integration, cost, data integrity, interoperability, and the potential for algorithmic bias, with a call for long-term and ongoing monitoring of patient safety and health equity outcomes. This review, guided by the CFIR framework, highlights the importance of designing health technology based on evidence and user-centred practices. Quality assessments identified eligibility and representativeness issues that affected the reliability and generalisability of the findings. This review also highlights a critical research gap on whether EHR-integrated digital tools can address or worsen health inequities among hospitalised patients. Recognising the growing role of Artificial Intelligence (AI) and Machine Learning (ML), this review calls for further research on its influence on medication management and health equity through integration of EHR and digital technology.

A cross sectional investigation of ChatGPT-like large language models application among medical students in China

OBJECTIVE

To investigate the level of understanding and trust of medical students towards ChatGPT-like large language models, as well as their utilization and attitudes towards these models.

METHODS

Data collection was concentrated from December 2023 to mid-January 2024, utilizing a self-designed questionnaire to assess the use of large language models among undergraduate medical students at Anhui Medical University. The normality of the data was confirmed with Shapiro-Wilk tests. We used Chi-square tests for comparisons of categorical variables, Mann-Whitney U tests for comparisons of ordinal variables and non-normal continuous variables between two groups, Kruskall-Wallis H tests for comparisons of ordinal variables between multiple groups, and Bonferroni tests for post hoc comparisons.

RESULTS

A total of 1774 questionnaires were distributed and 1718 valid questionnaires were collected, with an effective rate of 96.84%. Among these students, 34.5% had heard and used large language models. There were statistically significant differences in the understanding of large language models between genders (p < 0.001), grade levels (junior-level students and senior-level students) (p = 0.03), and major (p < 0.001). Male, junior-level students, and public health management had a higher level of understanding of these models. Genders and majors had statistically significant effects on the degree of trust in large language models (p = 0.004; p = 0.02). Male and nursing students exhibited a higher degree of trust in large language models. As for usage, Male and junior-level students showed a significantly higher proportion of using these models for assisted learning (p < 0.001). Neutral sentiments were held by over two-thirds of the students (66.7%) regarding large language models, with only 51(3.0%) expressing pessimism. There were significant gender-based disparities in attitudes towards large language models, and male exhibited a more optimistic attitude towards these models (p < 0.001). Notably, among students with different levels of knowledge and trust in large language models, statistically significant differences were observed in their perceptions of the shortcomings and benefits of these models.

CONCLUSION

Our study identified gender, grade levels, and major as influential factors in students' understanding and utilization of large language models. This also suggested the feasibility of integrating large language models with traditional medical education to further enhance teaching effectiveness in the future.

Artificial intelligence applied to 'omics data in liver disease: towards a personalised approach for diagnosis, prognosis and treatment

Advancements in omics technologies and artificial intelligence (AI) methodologies are fuelling our progress towards personalised diagnosis, prognosis and treatment strategies in hepatology. This review provides a comprehensive overview of the current landscape of AI methods used for analysis of omics data in liver diseases. We present an overview of the prevalence of different omics levels across various liver diseases, as well as categorise the AI methodology used across the studies. Specifically, we highlight the predominance of transcriptomic and genomic profiling and the relatively sparse exploration of other levels such as the proteome and methylome, which represent untapped potential for novel insights. Publicly available database initiatives such as The Cancer Genome Atlas and The International Cancer Genome Consortium have paved the way for advancements in the diagnosis and treatment of hepatocellular carcinoma. However, the same availability of large omics datasets remains limited for other liver diseases. Furthermore, the application of sophisticated AI methods to handle the complexities of multiomics datasets requires substantial data to train and validate the models and faces challenges in achieving bias-free results with clinical utility. Strategies to address the paucity of data and capitalise on opportunities are discussed. Given the substantial global burden of chronic liver diseases, it is imperative that multicentre collaborations be established to generate large-scale omics data for early disease recognition and intervention. Exploring advanced AI methods is also necessary to maximise the potential of these datasets and improve early detection and personalised treatment strategies.

Research Trends and Visualization of Cerebrospinal Fluid Dynamics (2013-2023)

OBJECTIVE

This study aims to analyze cerebrospinal fluid (CSF) dynamics using VOSviewer, CiteSpace, and the Bibliometrix R-package software to identify research hotspots and future directions.

METHODS

Search by Web of Science Core Collection Database for related literature on CSF dynamics from 2013 to 2023. Bibliometric and visual analysis of data on number of citations, number of publications, most productive countries and institutions, important authors and journals, time of publication, popular topics, and keywords were performed by CiteSpace and VOSviewer.

RESULTS

In the field of CSF dynamics, there is a clear upward trend in annual publications. The United States, Japan, and China are among the top three countries in publishing output. The University of Copenhagen, the University of Idaho, and the University of Zurich are leading institutions in research publications. The most prolific writers in this field are Bryn A. Martin, and Olivier Baledent. Active authors and institutions in the field form multiple structurally stable research teams with each other, but the collaboration between different authors and institutional teams needs to be further strengthened. The literature with the highest citation rates in the past decade is "Blood-Brain Barrier Breakdown in the Aging Human Hippocampus," "Blood-Brain Barrier Breakdown Is an Early Biomarker of Human Cognitive Dysfunction," "Serum Neurofilament Dynamics Predicts Neurodegeneration and Clinical Progression in Presymptomatic Alzheimer's Disease," and Coupled Electrophysiological, Hemodynamic, and Cerebrospinal Fluid Oscillations in Human Sleep." Key research keywords such as CSF, hydrocephalus, dynamics, brain, blood flow, CSF, pressure, CSF flow, and MRI highlight focal areas for CSF dynamics studies. These keywords represent current research priorities and research frontiers in this field.

CONCLUSIONS

This bibliometric analysis reveals hot and future research issues in the field of CSF fluid dynamics, demonstrating the need for enhanced international collaboration and interdisciplinary research to deepen the field. Keyword analysis further clarified the research focus and provided useful guidance for subsequent studies.

Hybrid similarity based feature selection and cascade deep maxout fuzzy network for Autism Spectrum Disorder detection using EEG signal

Autism Spectrum Disorder (ASD) is a neurological disorder that influences a person's comprehension and way of behaving. It is a lifetime disability that cannot be completely treated using any therapy up to date. Nevertheless, in time identification and continuous therapies have a huge effect on autism patients. The existing models took a long time to confirm the diagnosis process and also, it is highly complex to differentiate autism from various developmental disorders. To facilitate early diagnosis by providing timely intervention, saving healthcare costs and reducing stress for the family in the long run, this research introduces an affordable and straightforward diagnostic model to detect ASD using EEG and deep learning models. Here, a hybrid deep learning model called Cascade deep maxout fuzzy network (Cascade DMFN) is proposed to identify ASD and it is achieved by the integration of Deep Maxout Network (DMN) and hybrid cascade neuro-fuzzy. Moreover, hybrid similarity measures like Canberra distance and Kumar-hassebrook is employed to conduct the feature selection technique. Also, the EEG dataset and BCIAUT_P300 dataset are used for analyzing the designed Cascade DMFN for detecting Autism Spectrum Disorder. The designed Cascade DMFN has outperformed other classical models by yielding a high accuracy of 0.930, Negative Predictive Value (NPV) of 0.919, Positive Predictive Value (PPV) of 0.923, True Negative Rate (TNR) of 0.926, and True Positive Rate (TPR) of 0.934.

Investigating the role of artificial intelligence in predicting perceived dysphonia level

PURPOSE

This study aims to investigate the role of one of these models in the field of voice pathology and compare its performance in distinguishing the perceived dysphonia level.

METHODS

Demographic information, voice self-assessments, and acoustic measurements related to a sample of 50 adult dysphonic outpatients were presented to ChatGPT and Perplexity AI chatbots, which were interrogated for the perceived dysphonia level.

RESULTS

The agreement between the auditory-perceptual assessment by experts and ChatGPT and Perplexity AI chatbots, as determined by Cohen's Kappa, was not statistically significant (p = 0.429). There was also a low positive correlation (rs = 0.30, p = 0.03) between the diagnosis made by ChatGPT and Perplexity AI chatbots (rs = 0.30, p = 0.03).

CONCLUSION

It seems that AI could not play a vital role in helping the voice care teams determine the perceptual level of dysphonia.

A Review of Advancements and Challenges in Liver Segmentation

Liver segmentation technologies play vital roles in clinical diagnosis, disease monitoring, and surgical planning due to the complex anatomical structure and physiological functions of the liver. This paper provides a comprehensive review of the developments, challenges, and future directions in liver segmentation technology. We systematically analyzed high-quality research published between 2014 and 2024, focusing on liver segmentation methods, public datasets, and evaluation metrics. This review highlights the transition from manual to semi-automatic and fully automatic segmentation methods, describes the capabilities and limitations of available technologies, and provides future outlooks.

Strong and weak alignment of large language models with human values

Minimizing negative impacts of Artificial Intelligent (AI) systems on human societies without human supervision requires them to be able to align with human values. However, most current work only addresses this issue from a technical point of view, e.g., improving current methods relying on reinforcement learning from human feedback, neglecting what it means and is required for alignment to occur. Here, we propose to distinguish strong and weak value alignment. Strong alignment requires cognitive abilities (either human-like or different from humans) such as understanding and reasoning about agents' intentions and their ability to causally produce desired effects. We argue that this is required for AI systems like large language models (LLMs) to be able to recognize situations presenting a risk that human values may be flouted. To illustrate this distinction, we present a series of prompts showing ChatGPT's, Gemini's and Copilot's failures to recognize some of these situations. We moreover analyze word embeddings to show that the nearest neighbors of some human values in LLMs differ from humans' semantic representations. We then propose a new thought experiment that we call "the Chinese room with a word transition dictionary", in extension of John Searle's famous proposal. We finally mention current promising research directions towards a weak alignment, which could produce statistically satisfying answers in a number of common situations, however so far without ensuring any truth value.

Assessing the Readability, Reliability, and Quality of AI-Modified and Generated Patient Education Materials for Endoscopic Skull Base Surgery

BACKGROUND

Despite National Institutes of Health and American Medical Association recommendations to publish online patient education materials at or below sixth-grade literacy, those pertaining to endoscopic skull base surgery (ESBS) have lacked readability and quality. ChatGPT is an artificial intelligence (AI) system capable of synthesizing vast internet data to generate responses to user queries but its utility in improving patient education materials has not been explored.

OBJECTIVE

To examine the current state of readability and quality of online patient education materials and determined the utility of ChatGPT for improving articles and generating patient education materials.

METHODS

An article search was performed utilizing 10 different search terms related to ESBS. The ten least readable existing patient-facing articles were modified with ChatGPT and iterative queries were used to generate an article de novo. The Flesch Reading Ease (FRE) and related metrics measured overall readability and content literacy level, while DISCERN assessed article reliability and quality.

RESULTS

Sixty-six articles were located. ChatGPT improved FRE readability of the 10 least readable online articles (19.7 ± 4.4 vs. 56.9 ± 5.9, p < 0.001), from university to 10th grade level. The generated article was more readable than 48.5% of articles (38.9 vs. 39.4 ± 12.4) and higher quality than 94% (51.0 vs. 37.6 ± 6.1). 56.7% of the online articles had "poor" quality.

CONCLUSIONS

ChatGPT improves the readability of articles, though most still remain above the recommended literacy level for patient education materials. With iterative queries, ChatGPT can generate more reliable and higher quality patient education materials compared to most existing online articles and can be tailored to match readability of average online articles.

Mitigating Sociodemographic Bias in Opioid Use Disorder Prediction: Fairness-Aware Machine Learning Framework

BACKGROUND

Opioid use disorder (OUD) is a critical public health crisis in the United States, affecting >5.5 million Americans in 2021. Machine learning has been used to predict patient risk of incident OUD. However, little is known about the fairness and bias of these predictive models.

OBJECTIVE

The aims of this study are two-fold: (1) to develop a machine learning bias mitigation algorithm for sociodemographic features and (2) to develop a fairness-aware weighted majority voting (WMV) classifier for OUD prediction.

METHODS

We used the 2020 National Survey on Drug and Health data to develop a neural network (NN) model using stochastic gradient descent (SGD; NN-SGD) and an NN model using Adam (NN-Adam) optimizers and evaluated sociodemographic bias by comparing the area under the curve values. A bias mitigation algorithm, based on equality of odds, was implemented to minimize disparities in specificity and recall. Finally, a WMV classifier was developed for fairness-aware prediction of OUD. To further analyze bias detection and mitigation, we did a 1-N matching of OUD to non-OUD cases, controlling for socioeconomic variables, and evaluated the performance of the proposed bias mitigation algorithm and WMV classifier.

RESULTS

Our bias mitigation algorithm substantially reduced bias with NN-SGD, by 21.66% for sex, 1.48% for race, and 21.04% for income, and with NN-Adam by 16.96% for sex, 8.87% for marital status, 8.45% for working condition, and 41.62% for race. The fairness-aware WMV classifier achieved a recall of 85.37% and 92.68% and an accuracy of 58.85% and 90.21% using NN-SGD and NN-Adam, respectively. The results after matching also indicated remarkable bias reduction with NN-SGD and NN-Adam, respectively, as follows: sex (0.14% vs 0.97%), marital status (12.95% vs 10.33%), working condition (14.79% vs 15.33%), race (60.13% vs 41.71%), and income (0.35% vs 2.21%). Moreover, the fairness-aware WMV classifier achieved high performance with a recall of 100% and 85.37% and an accuracy of 73.20% and 89.38% using NN-SGD and NN-Adam, respectively.

CONCLUSIONS

The application of the proposed bias mitigation algorithm shows promise in reducing sociodemographic bias, with the WMV classifier confirming bias reduction and high performance in OUD prediction.

Prosody matters: Preserved prominence marking strategies in people with Parkinson's disease independent of motor status

While many studies focus on segmental variation in Parkinsonian speech, little is known about prosodic modulations reflecting the ability to adapt to communicative demands in people with Parkinson's disease (PwPD). This type of prosodic modulation is important for social interaction, and it involves modifications in speech melody (intonational level) and articulation of consonants and vowels (segmental level). The present study investigates phonetic cues of prosodic modulations with respect to different focus structures in mild dysarthric PwPD as a function of levodopa. Acoustic and kinematic speech parameters of 25 PwPD were assessed in two motor conditions. Speech production data from PwPD were collected before (medication-OFF) and after levodopa intake (medication-ON) by means of 3-D electromagnetic articulography. On the acoustic level, intensity, pitch, and syllable durations were analyzed. On the kinematic level, movement duration and amplitude were investigated. Spatio-temporal modulations of speech parameters were examined and compared across three different prosodic focus structures (out-of-focus, broad focus, contrastive focus) to display varying speech demands. Overall, levodopa had beneficial effects on motor performance, speech loudness, and pitch modulation. Acoustic syllable durations and kinematic movement durations did not change, revealing no systematic effects of motor status on the temporal domain. In contrast, there were spatial modulations of the oral articulators: tongue tip movements were smaller and lower lip movements were larger in amplitude under levodopa, reflecting a more agile and efficient articulatory movement under levodopa. Thus, respiratory-phonatory functions and consonant production improved, while syllable duration and tongue body kinematics did not change. Interestingly, prominence marking strategies were comparable between the medication conditions under investigation, and in fact, appear to be preserved in mild dysarthric PwPD.

Fast and robust analog in-memory deep neural network training

Analog in-memory computing is a promising future technology for efficiently accelerating deep learning networks. While using in-memory computing to accelerate the inference phase has been studied extensively, accelerating the training phase has received less attention, despite its arguably much larger compute demand to accelerate. While some analog in-memory training algorithms have been suggested, they either invoke significant amount of auxiliary digital compute-accumulating the gradient in digital floating point precision, limiting the potential speed-up-or suffer from the need for near perfectly programming reference conductance values to establish an algorithmic zero point. Here, we propose two improved algorithms for in-memory training, that retain the same fast runtime complexity while resolving the requirement of a precise zero point. We further investigate the limits of the algorithms in terms of conductance noise, symmetry, retention, and endurance which narrow down possible device material choices adequate for fast and robust in-memory deep neural network training.