Machine learning models for abstract screening task - A systematic literature review application for health economics and outcome research.

OBJECTIVE: Systematic literature reviews (SLRs) are critical for life-science research. However, the manual selection and retrieval of relevant publications can be a time-consuming process. This study aims to (1) develop two disease-specific annotated corpora, one for human papillomavirus (HPV) associated diseases and the other for pneumococcal-associated pediatric diseases (PAPD), and (2) optimize machine- and deep-learning models to facilitate automation of the SLR abstract screening. METHODS: This study constructed two disease-specific SLR screening corpora for HPV and PAPD, which contained citation metadata and corresponding abstracts. Performance was evaluated using precision, recall, accuracy, and F1-score of multiple combinations of machine- and deep-learning algorithms and features such as keywords and MeSH terms. RESULTS AND CONCLUSIONS: The HPV corpus contained 1697 entries, with 538 relevant and 1159 irrelevant articles. The PAPD corpus included 2865 entries, with 711 relevant and 2154 irrelevant articles. Adding additional features beyond title and abstract improved the performance (measured in Accuracy) of machine learning models by 3% for HPV corpus and 2% for PAPD corpus. Transformer-based deep learning models that consistently outperformed conventional machine learning algorithms, highlighting the strength of domain-specific pre-trained language models for SLR abstract screening. This study provides a foundation for the development of more intelligent SLR systems.

Enhancing Early Detection of Cognitive Decline in the Elderly: A Comparative Study Utilizing Large Language Models in Clinical Notes.

Background: Large language models (LLMs) have shown promising performance in various healthcare domains, but their effectiveness in identifying specific clinical conditions in real medical records is less explored. This study evaluates LLMs for detecting signs of cognitive decline in real electronic health record (EHR) clinical notes, comparing their error profiles with traditional models. The insights gained will inform strategies for performance enhancement. Methods: This study, conducted at Mass General Brigham in Boston, MA, analyzed clinical notes from the four years prior to a 2019 diagnosis of mild cognitive impairment in patients aged 50 and older. We used a randomly annotated sample of 4,949 note sections, filtered with keywords related to cognitive functions, for model development. For testing, a random annotated sample of 1,996 note sections without keyword filtering was utilized. We developed prompts for two LLMs, Llama 2 and GPT-4, on HIPAA-compliant cloud-computing platforms using multiple approaches (e.g., both hard and soft prompting and error analysis-based instructions) to select the optimal LLM-based method. Baseline models included a hierarchical attention-based neural network and XGBoost. Subsequently, we constructed an ensemble of the three models using a majority vote approach. Results: GPT-4 demonstrated superior accuracy and efficiency compared to Llama 2, but did not outperform traditional models. The ensemble model outperformed the individual models, achieving a precision of 90.3%, a recall of 94.2%, and an F1-score of 92.2%. Notably, the ensemble model showed a significant improvement in precision, increasing from a range of 70%-79% to above 90%, compared to the best-performing single model. Error analysis revealed that 63 samples were incorrectly predicted by at least one model; however, only 2 cases (3.2%) were mutual errors across all models, indicating diverse error profiles among them. Conclusions: LLMs and traditional machine learning models trained using local EHR data exhibited diverse error profiles. The ensemble of these models was found to be complementary, enhancing diagnostic performance. Future research should investigate integrating LLMs with smaller, localized models and incorporating medical data and domain knowledge to enhance performance on specific tasks.

Improving large language models for clinical named entity recognition via prompt engineering.

IMPORTANCE: The study highlights the potential of large language models, specifically GPT-3.5 and GPT-4, in processing complex clinical data and extracting meaningful information with minimal training data. By developing and refining prompt-based strategies, we can significantly enhance the models' performance, making them viable tools for clinical NER tasks and possibly reducing the reliance on extensive annotated datasets. OBJECTIVES: This study quantifies the capabilities of GPT-3.5 and GPT-4 for clinical named entity recognition (NER) tasks and proposes task-specific prompts to improve their performance. MATERIALS AND METHODS: We evaluated these models on 2 clinical NER tasks: (1) to extract medical problems, treatments, and tests from clinical notes in the MTSamples corpus, following the 2010 i2b2 concept extraction shared task, and (2) to identify nervous system disorder-related adverse events from safety reports in the vaccine adverse event reporting system (VAERS). To improve the GPT models' performance, we developed a clinical task-specific prompt framework that includes (1) baseline prompts with task description and format specification, (2) annotation guideline-based prompts, (3) error analysis-based instructions, and (4) annotated samples for few-shot learning. We assessed each prompt's effectiveness and compared the models to BioClinicalBERT. RESULTS: Using baseline prompts, GPT-3.5 and GPT-4 achieved relaxed F1 scores of 0.634, 0.804 for MTSamples and 0.301, 0.593 for VAERS. Additional prompt components consistently improved model performance. When all 4 components were used, GPT-3.5 and GPT-4 achieved relaxed F1 socres of 0.794, 0.861 for MTSamples and 0.676, 0.736 for VAERS, demonstrating the effectiveness of our prompt framework. Although these results trail BioClinicalBERT (F1 of 0.901 for the MTSamples dataset and 0.802 for the VAERS), it is very promising considering few training samples are needed. DISCUSSION: The study's findings suggest a promising direction in leveraging LLMs for clinical NER tasks. However, while the performance of GPT models improved with task-specific prompts, there's a need for further development and refinement. LLMs like GPT-4 show potential in achieving close performance to state-of-the-art models like BioClinicalBERT, but they still require careful prompt engineering and understanding of task-specific knowledge. The study also underscores the importance of evaluation schemas that accurately reflect the capabilities and performance of LLMs in clinical settings. CONCLUSION: While direct application of GPT models to clinical NER tasks falls short of optimal performance, our task-specific prompt framework, incorporating medical knowledge and training samples, significantly enhances GPT models' feasibility for potential clinical applications.

Dynamic Prognosis Prediction for Patients on DAPT After Drug-Eluting Stent Implantation: Model Development and Validation.

BACKGROUND: The rapid evolution of artificial intelligence (AI) in conjunction with recent updates in dual antiplatelet therapy (DAPT) management guidelines emphasizes the necessity for innovative models to predict ischemic or bleeding events after drug-eluting stent implantation. Leveraging AI for dynamic prediction has the potential to revolutionize risk stratification and provide personalized decision support for DAPT management. METHODS AND RESULTS: We developed and validated a new AI-based pipeline using retrospective data of drug-eluting stent-treated patients, sourced from the Cerner Health Facts data set (n=98 236) and Optum's de-identified Clinformatics Data Mart Database (n=9978). The 36 months following drug-eluting stent implantation were designated as our primary forecasting interval, further segmented into 6 sequential prediction windows. We evaluated 5 distinct AI algorithms for their precision in predicting ischemic and bleeding risks. Model discriminative accuracy was assessed using the area under the receiver operating characteristic curve, among other metrics. The weighted light gradient boosting machine stood out as the preeminent model, thus earning its place as our AI-DAPT model. The AI-DAPT demonstrated peak accuracy in the 30 to 36 months window, charting an area under the receiver operating characteristic curve of 90% [95% CI, 88%-92%] for ischemia and 84% [95% CI, 82%-87%] for bleeding predictions. CONCLUSIONS: Our AI-DAPT excels in formulating iterative, refined dynamic predictions by assimilating ongoing updates from patients' clinical profiles, holding value as a novel smart clinical tool to facilitate optimal DAPT duration management with high accuracy and adaptability.

Covalent Organic Network Membranes with Tunable Nanoarchitectonics from Macrocycle Building Blocks for Graded Molecular Sieving.

Traditional piperazine-based polyamide membranes usually suffer from the intrinsic trade-off relationship between selectivity and permeance. The development of macrocycle membranes with customized nanoscale pores is expected to address this challenge. Herein, we introduce 1,4-diazacyclohexane (2N), 1,4,7-triazacyclononane (3N), and 1,4,8,11-tetraazacyclotetradecane (4N) as molecular building blocks to construct the nanoarchitectonics of polyamide membranes prepared from interfacial polymerization (IP). The permeance of covalent organic network membranes follows the trend of 4N-TMC > 3N-TMC > 2N-TMC, while the molecular weight cutoff (MWCO) also follows the same trend of 4N-TMC > 3N-TMC > 2N-TMC, according to their nanopore size of the membranes. The microporosity, orientation, and surface chemistry of covalent organic network membranes can be rationally designed by macrocycle building units. The ordered nanoarchitectonics allows the membranes to attain an excellent performance in graded molecular sieving. Importantly, the novel covalent organic network membranes with tunable nanoarchitectonics prepared from macrocycle building units exhibited high water permeance (32.5 LMH/bar) and retained long-term stability after 100 h of test and bovine serum albumin fouling. These results reveal the enormous potential of 3N-TMC and 4N-TMC membranes in saline textile wastewater treatments and precise molecular sieving.

AutoCriteria: a generalizable clinical trial eligibility criteria extraction system powered by large language models.

OBJECTIVES: We aim to build a generalizable information extraction system leveraging large language models to extract granular eligibility criteria information for diverse diseases from free text clinical trial protocol documents. We investigate the model's capability to extract criteria entities along with contextual attributes including values, temporality, and modifiers and present the strengths and limitations of this system. MATERIALS AND METHODS: The clinical trial data were acquired from https://ClinicalTrials.gov/. We developed a system, AutoCriteria, which comprises the following modules: preprocessing, knowledge ingestion, prompt modeling based on GPT, postprocessing, and interim evaluation. The final system evaluation was performed, both quantitatively and qualitatively, on 180 manually annotated trials encompassing 9 diseases. RESULTS: AutoCriteria achieves an overall F1 score of 89.42 across all 9 diseases in extracting the criteria entities, with the highest being 95.44 for nonalcoholic steatohepatitis and the lowest of 84.10 for breast cancer. Its overall accuracy is 78.95% in identifying all contextual information across all diseases. Our thematic analysis indicated accurate logic interpretation of criteria as one of the strengths and overlooking/neglecting the main criteria as one of the weaknesses of AutoCriteria. DISCUSSION: AutoCriteria demonstrates strong potential to extract granular eligibility criteria information from trial documents without requiring manual annotations. The prompts developed for AutoCriteria generalize well across different disease areas. Our evaluation suggests that the system handles complex scenarios including multiple arm conditions and logics. CONCLUSION: AutoCriteria currently encompasses a diverse range of diseases and holds potential to extend to more in the future. This signifies a generalizable and scalable solution, poised to address the complexities of clinical trial application in real-world settings.

Machine learning-based donor permission extraction from informed consent documents.

BACKGROUND: With more clinical trials are offering optional participation in the collection of bio-specimens for biobanking comes the increasing complexity of requirements of informed consent forms. The aim of this study is to develop an automatic natural language processing (NLP) tool to annotate informed consent documents to promote biorepository data regulation, sharing, and decision support. We collected informed consent documents from several publicly available sources, then manually annotated them, covering sentences containing permission information about the sharing of either bio-specimens or donor data, or conducting genetic research or future research using bio-specimens or donor data. RESULTS: We evaluated a variety of machine learning algorithms including random forest (RF) and support vector machine (SVM) for the automatic identification of these sentences. 120 informed consent documents containing 29,204 sentences were annotated, of which 1250 sentences (4.28%) provide answers to a permission question. A support vector machine (SVM) model achieved a F-1 score of 0.95 on classifying the sentences when using a gold standard, which is a prefiltered corpus containing all relevant sentences. CONCLUSIONS: This study provides the feasibility of using machine learning tools to classify permission-related sentences in informed consent documents.

Flexible Covalent Organic Network with Ordered Honeycomb Nanoarchitecture for Molecular Separations.

Membranes with precisely defined nanostructure are desirable for energy-efficient molecular separations. The emergence of membranes with honeycomb lattice or topological nanopores is of fundamental importance. The tailor-made nanostructure and morphology may have huge potential to resolve the longstanding bottlenecks in membrane science and technology. Herein, inspired by honeycomb architecture, we demonstrate an effective and scalable route based on interfacial polymerization (IP) to generate flexible and ordered covalent organic network (CON) membranes for liquid-phase molecular separations. The aperture size of a CON membrane can be reasonably designed through the strong covalent bond between molecular building blocks. The fabricated CON membrane formed by IP showed an obviously size-dependent sieving of molecules, yielding a stepwise conversion from low rejection to the expected high rejection. Moreover, the CON membrane was also found to have the sieving capability for tetracycline and ciprofloxacin, ascribed to the effect of size exclusion by an ordered single-nanoscale channel (<1 nm). This approach provides a viable strategy for creating target-sized channels from molecular-level design and demonstrates their potential for accurate molecular separations.

SHAPE: A Sample-Adaptive Hierarchical Prediction Network for Medication Recommendation.

Effectively medication recommendation with complex multimorbidity conditions is a critical yet challenging task in healthcare. Most existing works predicted medications based on longitudinal records, which assumed the encoding format of intra-visit medical events are serialized and information transmitted patterns of learning longitudinal sequence data are stable. However, the following conditions may have been ignored: 1) A more compact encoder for intra-relationship in the intra-visit medical event is urgent; 2) Strategies for learning accurate representations of the variable longitudinal sequences of patients are different. In this article, we proposed a novel Sample-adaptive Hierarchical medicAtion Prediction nEtwork, termed SHAPE, to tackle the above challenges in the medication recommendation task. Specifically, we design a compact intra-visit set encoder to encode the relationship in the medical event for obtaining visit-level representation and then develop an inter-visit longitudinal encoder to learn the patient-level longitudinal representation efficiently. To endow the model with the capability of modeling the variable visit length, we introduce a soft curriculum learning method to assign the difficulty of each sample automatically by the visit length. Extensive experiments on a benchmark dataset verify the superiority of our model compared with several state-of-the-art baselines.

Systematic design and data-driven evaluation of social determinants of health ontology (SDoHO).

OBJECTIVE: Social determinants of health (SDoH) play critical roles in health outcomes and well-being. Understanding the interplay of SDoH and health outcomes is critical to reducing healthcare inequalities and transforming a "sick care" system into a "health-promoting" system. To address the SDOH terminology gap and better embed relevant elements in advanced biomedical informatics, we propose an SDoH ontology (SDoHO), which represents fundamental SDoH factors and their relationships in a standardized and measurable way. MATERIAL AND METHODS: Drawing on the content of existing ontologies relevant to certain aspects of SDoH, we used a top-down approach to formally model classes, relationships, and constraints based on multiple SDoH-related resources. Expert review and coverage evaluation, using a bottom-up approach employing clinical notes data and a national survey, were performed. RESULTS: We constructed the SDoHO with 708 classes, 106 object properties, and 20 data properties, with 1,561 logical axioms and 976 declaration axioms in the current version. Three experts achieved 0.967 agreement in the semantic evaluation of the ontology. A comparison between the coverage of the ontology and SDOH concepts in 2 sets of clinical notes and a national survey instrument also showed satisfactory results. DISCUSSION: SDoHO could potentially play an essential role in providing a foundation for a comprehensive understanding of the associations between SDoH and health outcomes and paving the way for health equity across populations. CONCLUSION: SDoHO has well-designed hierarchies, practical objective properties, and versatile functionalities, and the comprehensive semantic and coverage evaluation achieved promising performance compared to the existing ontologies relevant to SDoH.

Nanoarchitectonics of carbon molecular sieve membranes with graphene oxide and polyimide for hydrogen purification.

Hydrogen is an important energy carrier for the transition to a carbon-neutral society, the efficient separation and purification of hydrogen from gaseous mixtures is a critical step for the implementation of a hydrogen economy. In this work, graphene oxide (GO) tuned polyimide carbon molecular sieve (CMS) membranes were prepared by carbonization, which show an attractive combination of high permeability, selectivity and stability. The gas sorption isotherms indicate that the gas sorption capability increases with the carbonization temperature and follows the order of PI-GO-1.0%-600 °C > PI-GO-1.0%-550 °C > PI-GO-1.0%-500 °C, more micropores would be created under higher temperatures under GO guidance. The synergistic GO guidance and subsequent carbonization of PI-GO-1.0% at 550 °C increased H2 permeability from 958 to 7462 Barrer and H2/N2 selectivity from 14 to 117, superior to state-of-the-art polymeric materials and surpassing Robeson's upper bound line. As the carbonization temperature increased, the CMS membranes gradually changed from the turbostratic polymeric structure to a denser and more ordered graphite structure. Therefore, ultrahigh selectivities for H2/CO2 (17), H2/N2 (157), and H2/CH4 (243) gas pairs were achieved while maintaining moderate H2 gas permeabilities. This research opens up new avenues for GO tuned CMS membranes with desirable molecular sieving ability for hydrogen purification.

A 2D Soft Covalent Organic Framework Membrane Prepared via a Molecular Bridge.

Highly flexible and robust self-standing covalent organic framework (COF) membranes with rapid preparation are important but technically challenging for achieving precise separation. Herein , a novel imine-based 2D soft covalent organic framework (SCOF) membrane with a large area of 226.9 cm2 , via ingeniously selecting an aldehyde flexible linker and a trigonal building block, is reported. The soft 2D covalent organic framework membrane is rapidly formed (≈5 min) based on the sodium dodecyl sulfate (SDS) molecular channel constructed at the water/dichloromethane (DCM) interface, which is the record-fast SCOF membrane formation and 72 times faster than that in the reported literature. MD simulation and DFT calculation elucidate that the dynamic, self-assembled SDS molecular channel facilitates faster and more homogeneous transfer of amine monomers in the bulk, thereby forming a soft 2D self-standing COF membrane with more uniform pores. The formed SCOF membrane exhibits superb sieving capability for small molecules, robustness in strong alkaline (5 mol L-1 NaOH), acid (0.1 mol L-1 HCl), and various organic solutions, and sufficient flexibility with a large curvature of 2000 m-1 for membrane-based separation science and technology.

Mining on Alzheimer's diseases related knowledge graph to identity potential AD-related semantic triples for drug repurposing.

BACKGROUND: To date, there are no effective treatments for most neurodegenerative diseases. Knowledge graphs can provide comprehensive and semantic representation for heterogeneous data, and have been successfully leveraged in many biomedical applications including drug repurposing. Our objective is to construct a knowledge graph from literature to study the relations between Alzheimer's disease (AD) and chemicals, drugs and dietary supplements in order to identify opportunities to prevent or delay neurodegenerative progression. We collected biomedical annotations and extracted their relations using SemRep via SemMedDB. We used both a BERT-based classifier and rule-based methods during data preprocessing to exclude noise while preserving most AD-related semantic triples. The 1,672,110 filtered triples were used to train with knowledge graph completion algorithms (i.e., TransE, DistMult, and ComplEx) to predict candidates that might be helpful for AD treatment or prevention. RESULTS: Among three knowledge graph completion models, TransE outperformed the other two (MR = 10.53, Hits@1 = 0.28). We leveraged the time-slicing technique to further evaluate the prediction results. We found supporting evidence for most highly ranked candidates predicted by our model which indicates that our approach can inform reliable new knowledge. CONCLUSION: This paper shows that our graph mining model can predict reliable new relationships between AD and other entities (i.e., dietary supplements, chemicals, and drugs). The knowledge graph constructed can facilitate data-driven knowledge discoveries and the generation of novel hypotheses.

Multi-label classification for biomedical literature: an overview of the BioCreative VII LitCovid Track for COVID-19 literature topic annotations.

The coronavirus disease 2019 (COVID-19) pandemic has been severely impacting global society since December 2019. The related findings such as vaccine and drug development have been reported in biomedical literature-at a rate of about 10 000 articles on COVID-19 per month. Such rapid growth significantly challenges manual curation and interpretation. For instance, LitCovid is a literature database of COVID-19-related articles in PubMed, which has accumulated more than 200 000 articles with millions of accesses each month by users worldwide. One primary curation task is to assign up to eight topics (e.g. Diagnosis and Treatment) to the articles in LitCovid. The annotated topics have been widely used for navigating the COVID literature, rapidly locating articles of interest and other downstream studies. However, annotating the topics has been the bottleneck of manual curation. Despite the continuing advances in biomedical text-mining methods, few have been dedicated to topic annotations in COVID-19 literature. To close the gap, we organized the BioCreative LitCovid track to call for a community effort to tackle automated topic annotation for COVID-19 literature. The BioCreative LitCovid dataset-consisting of over 30 000 articles with manually reviewed topics-was created for training and testing. It is one of the largest multi-label classification datasets in biomedical scientific literature. Nineteen teams worldwide participated and made 80 submissions in total. Most teams used hybrid systems based on transformers. The highest performing submissions achieved 0.8875, 0.9181 and 0.9394 for macro-F1-score, micro-F1-score and instance-based F1-score, respectively. Notably, these scores are substantially higher (e.g. 12%, higher for macro F1-score) than the corresponding scores of the state-of-art multi-label classification method. The level of participation and results demonstrate a successful track and help close the gap between dataset curation and method development. The dataset is publicly available via https://ftp.ncbi.nlm.nih.gov/pub/lu/LitCovid/biocreative/ for benchmarking and further development. Database URL https://ftp.ncbi.nlm.nih.gov/pub/lu/LitCovid/biocreative/.

Comparability of clinical trials and spontaneous reporting data regarding COVID-19 vaccine safety.

Severe adverse events (AEs) after COVID-19 vaccination are not well studied in randomized controlled trials (RCTs) due to rarity and short follow-up. To monitor the safety of COVID-19 vaccines ("Pfizer" vaccine dose 1 and 2, "Moderna" vaccine dose 1 and 2, and "Janssen" vaccine single dose) in the U.S., especially regarding severe AEs, we compare the relative rankings of these vaccines using both RCT and the Vaccine Adverse Event Reporting System (VAERS) data. The risks of local and systemic AEs were assessed from the three pivotal COVID-19 vaccine trials and also calculated in the VAERS cohort consisting of 559,717 reports between December 14, 2020 and September 17, 2021. AE rankings of the five vaccine groups calculated separately by RCT and VAERS were consistent, especially for systemic AEs. For severe AEs reported in VAERS, the reported risks of thrombosis and GBS after Janssen vaccine were highest. The reported risk of shingles after the first dose of Moderna vaccine was highest, followed by the second dose of the Moderna vaccine. The reported risk of myocarditis was higher after the second dose of Pfizer and Moderna vaccines. The reported risk of anaphylaxis was higher after the first dose of Pfizer vaccine. Limitations of this study are the inherent biases of the spontaneous reporting system data, and only including three pivotal RCTs and no comparison with other active vaccine safety surveillance systems.

Understanding Public Perceptions of Measles from Twitter Using Multi-Task Convolutional Neural Networks.

Measles is a highly contagious cause of febrile illness typically seen in young children. Recent years have witnessed the resurgence of measles cases in the United States. Prompt understanding of public perceptions of measles will allow public health agencies to respond appropriately promptly. We proposed a multi-task Convolutional Neural Network (MT-CNN) model to classify measles-related tweets in terms of three characteristics: Type of Message (6 subclasses), Emotion Expressed (6 subclasses), and Attitude towards Vaccination (3 subclasses). A gold standard corpus that contains 2,997 tweets with annotation in these dimensions was manually curated. A variety of conventional machine learning and deep learning models were evaluated as baseline models. The MT-CNN model performed better than other baseline conventional machine learning and the signal-task CNN models, and was then applied to predict unlabeled measles-related Twitter discussions that were crawled from 2007 to 2019, and the trends of public perceptions were analyzed along three dimensions.

LitMC-BERT: Transformer-Based Multi-Label Classification of Biomedical Literature With An Application on COVID-19 Literature Curation.

The rapid growth of biomedical literature poses a significant challenge for curation and interpretation. This has become more evident during the COVID-19 pandemic. LitCovid, a literature database of COVID-19 related papers in PubMed, has accumulated over 200,000 articles with millions of accesses. Approximately 10,000 new articles are added to LitCovid every month. A main curation task in LitCovid is topic annotation where an article is assigned with up to eight topics, e.g., Treatment and Diagnosis. The annotated topics have been widely used both in LitCovid (e.g., accounting for ∼18% of total uses) and downstream studies such as network generation. However, it has been a primary curation bottleneck due to the nature of the task and the rapid literature growth. This study proposes LITMC-BERT, a transformer-based multi-label classification method in biomedical literature. It uses a shared transformer backbone for all the labels while also captures label-specific features and the correlations between label pairs. We compare LITMC-BERT with three baseline models on two datasets. Its micro-F1 and instance-based F1 are 5% and 4% higher than the current best results, respectively, and only requires ∼18% of the inference time than the Binary BERT baseline. The related datasets and models are available via https://github.com/ncbi/ml-transformer.

A Bayesian Network to Predict the Risk of Post Influenza Vaccination Guillain-Barré Syndrome: Development and Validation Study.

BACKGROUND: Identifying the key factors of Guillain-Barré syndrome (GBS) and predicting its occurrence are vital for improving the prognosis of patients with GBS. However, there are scarcely any publications on a forewarning model of GBS. A Bayesian network (BN) model, which is known to be an accurate, interpretable, and interaction-sensitive graph model in many similar domains, is worth trying in GBS risk prediction. OBJECTIVE: The aim of this study is to determine the most significant factors of GBS and further develop and validate a BN model for predicting GBS risk. METHODS: Large-scale influenza vaccine postmarketing surveillance data, including 79,165 US (obtained from the Vaccine Adverse Event Reporting System between 1990 and 2017) and 12,495 European (obtained from the EudraVigilance system between 2003 and 2016) adverse events (AEs) reports, were extracted for model development and validation. GBS, age, gender, and the top 50 prevalent AEs were included for initial BN construction using the R package bnlearn. RESULTS: Age, gender, and 10 AEs were identified as the most significant factors of GBS. The posttest probability of GBS suggested that male vaccinees aged 50-64 years and without erythema should be on the alert or be warned by clinicians about an increased risk of GBS, especially when they also experience symptoms of asthenia, hypesthesia, muscular weakness, or paresthesia. The established BN model achieved an area under the receiver operating characteristic curve of 0.866 (95% CI 0.865-0.867), sensitivity of 0.752 (95% CI 0.749-0.756), specificity of 0.882 (95% CI 0.879-0.885), and accuracy of 0.882 (95% CI 0.879-0.884) for predicting GBS risk during the internal validation and obtained values of 0.829, 0.673, 0.854, and 0.843 for area under the receiver operating characteristic curve, sensitivity, specificity, and accuracy, respectively, during the external validation. CONCLUSIONS: The findings of this study illustrated that a BN model can effectively identify the most significant factors of GBS, improve understanding of the complex interactions among different postvaccination symptoms through its graphical representation, and accurately predict the risk of GBS. The established BN model could further assist clinical decision-making by providing an estimated risk of GBS for a specific vaccinee or be developed into an open-access platform for vaccinees' self-monitoring.

Using a Machine Learning Approach to Monitor COVID-19 Vaccine Adverse Events (VAE) from Twitter Data.

Social media can be used to monitor the adverse effects of vaccines. The goal of this project is to develop a machine learning and natural language processing approach to identify COVID-19 vaccine adverse events (VAE) from Twitter data. Based on COVID-19 vaccine-related tweets (1 December 2020-1 August 2021), we built a machine learning-based pipeline to identify tweets containing personal experiences with COVID-19 vaccinations and to extract and normalize VAE-related entities, including dose(s); vaccine types (Pfizer, Moderna, and Johnson & Johnson); and symptom(s) from tweets. We further analyzed the extracted VAE data based on the location, time, and frequency. We found that the four most populous states (California, Texas, Florida, and New York) in the US witnessed the most VAE discussions on Twitter. The frequency of Twitter discussions of VAE coincided with the progress of the COVID-19 vaccinations. Sore to touch, fatigue, and headache are the three most common adverse effects of all three COVID-19 vaccines in the US. Our findings demonstrate the feasibility of using social media data to monitor VAEs. To the best of our knowledge, this is the first study to identify COVID-19 vaccine adverse event signals from social media. It can be an excellent supplement to the existing vaccine pharmacovigilance systems.

Application of artificial intelligence and machine learning for HIV prevention interventions.

In 2019, the US Government announced its goal to end the HIV epidemic within 10 years, mirroring the initiatives set forth by UNAIDS. Public health prevention interventions are a crucial part of this ambitious goal. However, numerous challenges to this goal exist, including improving HIV awareness, increasing early HIV infection detection, ensuring rapid treatment, optimising resource distribution, and providing efficient prevention services for vulnerable populations. Artificial intelligence has had a pivotal role in revolutionising health care and has shown great potential in developing effective HIV prevention intervention strategies. Although artificial intelligence has been used in a few HIV prevention intervention areas, there are challenges to address and opportunities to explore.