Open Res Eur. 2024 Oct 18;4:133. doi: 10.12688/openreseurope.17992.2. eCollection 2024.

ABSTRACT

BACKGROUND: Earth Observation (EO) datasets have become vital for decision support applications, particularly from open satellite portals that provide extensive historical datasets. These datasets can be integrated with in-situ data to power artificial intelligence mechanisms for accurate forecasting and trend analysis. However, researchers and data scientists face challenges in finding appropriate EO datasets due to inconsistent metadata structures and varied keyword descriptions. This misalignment hinders the discoverability and usability of EO data.

METHODS: To address this challenge, the EIFFEL ontology (EIFF-O) is proposed. EIFF-O introduces taxonomies and ontologies to provide (i) global classification of EO data and (ii) linkage between different datasets through common concepts. The taxonomies specified by the European Association of Remote Sensing Companies (EARSC) have been formalized and implemented in EIFF-O. Additionally, EIFF-O incorporates:1.An Essential Climate Variable (ECV) ontology, defined by the Global Climate Observing System (GCOS), is embedded and tailored for Climate Change (CC) applications.2.The Sustainable Development Goals (SDG) ontology is included to facilitate linking datasets to specific targets.3.The ontology extends schema.org vocabularies and promotes the use of JavaScript Object Notation for Linked Data (JSON-LD) formats for semantic web integration.

RESULTS: EIFF-O provides a unified framework that enhances the discoverability, usability, and application of EO datasets. The implementation of EIFF-O allows data providers and users to bridge the gap between varied metadata descriptions and structured classification, thereby facilitating better linkage and integration of EO datasets.

CONCLUSIONS: The EIFFEL ontology represents a significant advancement in the organization and application of EO datasets. By embedding ECV and SDG ontologies and leveraging semantic web technologies, EIFF-O not only streamlines the data discovery process but also supports diverse applications, particularly in Climate Change monitoring and Sustainable Development Goals achievement. The open-source nature of the ontology and its associated tools promotes rapid adoption among developers.

PMID:39534879 | PMC:PMC11555329 | DOI:10.12688/openreseurope.17992.2

Int J Med Inform. 2024 Nov 7;193:105663. doi: 10.1016/j.ijmedinf.2024.105663. Online ahead of print.

ABSTRACT

BACKGROUND: As artificial intelligence AI-supported applications become integral to web-based information-seeking, assessing their impact on healthy nutrition and weight management during the antenatal period is crucial.

OBJECTIVE: This study was conducted to evaluate both the quality and semantic similarity of responses created by AI models to the most frequently asked questions about healthy nutrition and weight management during the antenatal period, based on existing clinical knowledge.

METHODS: In this study, a cross-sectional assessment design was used to explore data from 3 AI models (GPT-4, MedicalGPT, Med-PaLM). We directed the most frequently asked questions about nutrition during pregnancy, obtained from the American College of Obstetricians and Gynecologists (ACOG) to each model in a new and single session on October 21, 2023, without any prior conversation. Immediately after, instructions were given to the AI models to generate responses to these questions. The responses created by AI models were evaluated using the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) scale. Additionally, to assess the semantic similarity between answers to 31 pregnancy nutrition-related frequently asked questions sourced from the ACOG and responses from AI models we evaluated cosine similarity using both WORD2VEC and BioLORD-2023.

RESULTS: Med-PaLM outperformed GPT-4 and MedicalGPT in response quality (mean = 3.93), demonstrating superior clinical accuracy over both GPT-4 (p = 0.016) and MedicalGPT (p = 0.001). GPT-4 had higher quality than MedicalGPT (p = 0.027). The semantic similarity between ACOG and Med-PaLM is higher with WORD2VEC (0.92) compared to BioLORD-2023 (0.81), showing a difference of +0.11. The similarity scores for ACOG-MedicalGPT and ACOG-GPT-4 are similar across both models, with minimal differences of -0.01. Overall, WORD2VEC has a slightly higher average similarity (0.82) than BioLORD-2023 (0.79), with a difference of +0.03.

CONCLUSIONS: Despite the superior performance of Med-PaLM, there is a need for further evidence-based research and improvement in the integration of AI in healthcare due to varying AI model performances.

PMID:39531902 | DOI:10.1016/j.ijmedinf.2024.105663

Front Neuroinform. 2024 Oct 16;18:1378281. doi: 10.3389/fninf.2024.1378281. eCollection 2024.

ABSTRACT

Machine learning (ML) methodologies for detecting Mild Cognitive Impairment (MCI) are progressively gaining prevalence to manage the vast volume of processed information. Nevertheless, the black-box nature of ML algorithms and the heterogeneity within the data may result in varied interpretations across distinct studies. To avoid this, in this proposal, we present the design of a decision support system that integrates a machine learning model represented using the Semantic Web Rule Language (SWRL) in an ontology with specialized knowledge in neuropsychological tests, the NIO ontology. The system's ability to detect MCI subjects was evaluated on a database of 520 neuropsychological assessments conducted in Spanish and compared with other well-established ML methods. Using the F2 coefficient to minimize false negatives, results indicate that the system performs similarly to other well-established ML methods (F2TE2 = 0.830, only below bagging, F2BAG = 0.832) while exhibiting other significant attributes such as explanation capability and data standardization to a common framework thanks to the ontological part. On the other hand, the system's versatility and ease of use were demonstrated with three additional use cases: evaluation of new cases even if the acquisition stage is incomplete (the case records have missing values), incorporation of a new database into the integrated system, and use of the ontology capabilities to relate different domains. This makes it a useful tool to support physicians and neuropsychologists in population-based screenings for early detection of MCI.

PMID:39478874 | PMC:PMC11522961 | DOI:10.3389/fninf.2024.1378281

Proc (IEEE Int Conf Healthc Inform). 2024 Jun;2024:31-39. doi: 10.1109/ichi61247.2024.00012. Epub 2024 Aug 22.

ABSTRACT

Many studies have examined the impact of exercise and other physical activities in influencing the health outcomes of individuals. These physical activities entail an intricate sequence and series of physical anatomy, physiological movement, movement of the anatomy, etc. To better understand how these components interact with one another and their downstream impact on health outcomes, there needs to be an information model that conceptualizes all entities involved. In this study, we introduced our early development of an ontology model to computationally describe human physical activities and the various entities that compose each activity. We developed an open-sourced biomedical ontology called the Kinetic Human Movement Ontology that reused OBO Foundry terminologies and encoded in OWL2. We applied this ontology in modeling and linking a specific Tai Chi movement. The contribution of this work could enable modeling of information relating to human physical activity, like exercise, and lead towards information standardization of human movement for analysis. Future work will include expanding our ontology to include more expressive information and completely modeling entire sets of movement from human physical activity.

PMID:39464170 | PMC:PMC11503552 | DOI:10.1109/ichi61247.2024.00012

Cureus. 2024 Sep 23;16(9):e70029. doi: 10.7759/cureus.70029. eCollection 2024 Sep.

ABSTRACT

Dementia encompasses symptoms resulting from brain damage that impairs cognitive functions, surpassing natural aging effects. This condition affects emotional regulation, behavior, and motivation while preserving consciousness. Dr. Manfred Spitzer coined the term 'digital dementia,' highlighting the cognitive decline associated with excessive reliance on digital devices such as smartphones and Google, potentially exacerbating attention deficit hyperactivity disorder (ADHD) and memory loss. This condition mirrors terms like 'digital amnesia' and 'the Google Effect,' highlighting the brain's tendency to offload peripheral information, leading to panic and forgetfulness. Spitzer's book, Digital Dementia, focuses on gaming effects on children and has thus popularized the term. Teenagers are known to use electronic devices regularly, correlating with rising cognitive impairments. The advent of the internet's fifth generation (5G) has transformed technology use, impacting mental health treatments and clinical practices globally. Digital media's influence on the developing brain encompasses motor skills, language, and cognition. Excessive digital media use in young adults correlates with lower cognitive empathy, affecting interpersonal understanding and facial recognition. Studies link heavy reliance on web-based media to decreased white matter integrity, crucial for language skills. Adolescents may be more vulnerable to anxiety and unrealistic expectations due to digital media overuse. Digital media overuse impacts brain development, especially cognitive and inhibitory control, attention, memory, and reasoning, essential for adapting to dynamic environments. Early exposure to fast-paced media can impair motor skills, spatial awareness, problem-solving, and language learning. Neuroimaging studies reveal that environmental factors like screen usage affect brain networks controlling social-emotional behavior and executive functions. Overreliance on smartphones diminishes gray matter in key brain regions, affecting cognitive and emotional regulation. The internet generation, characterized by advancements such as Web 3.0, introduces artificial intelligence and semantic web technologies, reshaping digital content processing. The neurobiological basis of digital dementia involves changes in the brain structure and function, with excessive screen exposure linked to cognitive impairments. Neuroplasticity, or the brain's adaptability, plays a role in cognitive decline from digital media overuse. Early childhood and adolescent brain development stages exhibit significant plasticity, influencing cognitive trajectories. Addressing digital dementia requires strategies to reduce screen time, promote cognitive exercises, and enhance awareness. Parents should regulate children's screen usage, encourage digital detox periods, and substitute screen time with other activities. Cognitive training programs such as Cogmed (Neural Assembly Int AB, Stockholm, SWE) and CogniFit (San Francisco, CA, USA) can improve memory and attention in older adults. Promoting balanced technology use and educating on the risks of excessive digital media consumption is crucial for maintaining cognitive health in the digital age.

PMID:39449887 | PMC:PMC11499077 | DOI:10.7759/cureus.70029

IEEE/ACM Trans Comput Biol Bioinform. 2024 Oct 24;PP. doi: 10.1109/TCBB.2024.3486216. Online ahead of print.

ABSTRACT

Protein-protein interactions (PPIs) are essential to understanding cellular mechanisms, signaling networks, disease processes, and drug development, as they represent the physical contacts and functional associations between proteins. Recent advances have witnessed the achievements of artificial intelligence (AI) methods aimed at predicting PPIs. However, these approaches often handle the intricate web of relationships and mechanisms among proteins, drugs, diseases, ribonucleic acid (RNA), and protein structures in a fragmented or superficial manner. This is typically due to the limitations of non-end-to-end learning frameworks, which can lead to sub-optimal feature extraction and fusion, thereby compromising the prediction accuracy. To address these deficiencies, this paper introduces a novel end-to-end learning model, the Knowledge Graph Fused Graph Neural Network (KGF-GNN). This model comprises three integral components: (1) Protein Associated Network (PAN) Construction: We begin by constructing a PAN that extensively captures the diverse relationships and mechanisms linking proteins with drugs, diseases, RNA, and protein structures. (2) Graph Neural Network for Feature Extraction: A Graph Neural Network (GNN) is then employed to distill both topological and semantic features from the PAN, alongside another GNN designed to extract topological features directly from observed PPI networks. (3) Multi-layer Perceptron for Feature Fusion: Finally, a multi-layer perceptron integrates these varied features through end-to-end learning, ensuring that the feature extraction and fusion processes are both comprehensive and optimized for PPI prediction. Extensive experiments conducted on real-world PPI datasets validate the effectiveness of our proposed KGF-GNN approach, which not only achieves high accuracy in predicting PPIs but also significantly surpasses existing state-of-the-art models. This work not only enhances our ability to predict PPIs with a higher precision but also contributes to the broader application of AI in Bioinformatics, offering profound implications for biological research and therapeutic development.

PMID:39446541 | DOI:10.1109/TCBB.2024.3486216

Arch Public Health. 2024 Oct 23;82(1):188. doi: 10.1186/s13690-024-01414-1.

ABSTRACT

BACKGROUND: The global health system remains determined to leverage on every workable opportunity, including artificial intelligence (AI) to provide care that is consistent with patients' needs. Unfortunately, while AI models generally return high accuracy within the trials in which they are trained, their ability to predict and recommend the best course of care for prospective patients is left to chance.

PURPOSE: This review maps evidence between January 1, 2010 to December 31, 2023, on the perceived threats posed by the usage of AI tools in healthcare on patients' rights and safety.

METHODS: We deployed the guidelines of Tricco et al. to conduct a comprehensive search of current literature from Nature, PubMed, Scopus, ScienceDirect, Dimensions AI, Web of Science, Ebsco Host, ProQuest, JStore, Semantic Scholar, Taylor & Francis, Emeralds, World Health Organisation, and Google Scholar. In all, 80 peer reviewed articles qualified and were included in this study.

RESULTS: We report that there is a real chance of unpredictable errors, inadequate policy and regulatory regime in the use of AI technologies in healthcare. Moreover, medical paternalism, increased healthcare cost and disparities in insurance coverage, data security and privacy concerns, and bias and discriminatory services are imminent in the use of AI tools in healthcare.

CONCLUSIONS: Our findings have some critical implications for achieving the Sustainable Development Goals (SDGs) 3.8, 11.7, and 16. We recommend that national governments should lead in the roll-out of AI tools in their healthcare systems. Also, other key actors in the healthcare industry should contribute to developing policies on the use of AI in healthcare systems.

PMID:39444019 | DOI:10.1186/s13690-024-01414-1

Int J Pediatr. 2024 Oct 5;2024:4213025. doi: 10.1155/2024/4213025. eCollection 2024.

ABSTRACT

Background: Various initiatives are underway to improve maternal satisfaction with the vaccination of children in developing nations. Governments, international organizations, and nongovernmental organizations are actively working to improve healthcare infrastructure, expand service accessibility, improve communication, and foster community engagement. However, despite these efforts, maternal satisfaction with child vaccination services continues to be a significant issue. Objective: This systematic review and meta-analysis is aimed at assessing the pooled prevalence of maternal satisfaction with the child's vaccination service and its predictors in Ethiopia. Methods: Scopus, Embase, Web of Science, Google Scholar, PubMed, African Journals Online, and Semantic Scholar were searched to access the included articles. A weighted inverse-variance random effect model was used to estimate the prevalence of maternal satisfaction with vaccination of children. Variations in pooled prevalence estimates were adjusted by subgroup analysis according to the specific region where the study was conducted. Funnel plot and Egger's regression test were used to check publication bias. STATA version 14 statistical software was used for meta-analysis. Results: The combined prevalence of maternal satisfaction with vaccination of children was found to be 73% (95% CI: 72-75; I 2 = 0.00%, p value < 0.001). Based on the subgroup analysis, the result revealed that the prevalence of maternal satisfaction with vaccination of children was 63% in SNNPR, 79% in Oromia, and 74% in Amhara. Conclusions: A meta-analysis of mothers' satisfaction with vaccination services for their children in Ethiopia found a low level of satisfaction. Therefore, provide regular training and capacity-building programs for healthcare workers involved in the delivery of vaccination services.

PMID:39411518 | PMC:PMC11479785 | DOI:10.1155/2024/4213025

Sci Rep. 2024 Oct 15;14(1):24190. doi: 10.1038/s41598-024-74539-6.

ABSTRACT

Lifestyle diseases significantly contribute to the global health burden, with lifestyle factors playing a crucial role in the development of depression. The COVID-19 pandemic has intensified many determinants of depression. This study aimed to identify lifestyle and demographic factors associated with depression symptoms among Indians during the pandemic, focusing on a sample from Kolkata, India. An online public survey was conducted, gathering data from 1,834 participants (with 1,767 retained post-cleaning) over three months via social media and email. The survey consisted of 44 questions and was distributed anonymously to ensure privacy. Data were analyzed using statistical methods and machine learning, with principal component analysis (PCA) and analysis of variance (ANOVA) employed for feature selection. K-means clustering divided the pre-processed dataset into five clusters, and a support vector machine (SVM) with a linear kernel achieved 96% accuracy in a multi-class classification problem. The Local Interpretable Model-agnostic Explanations (LIME) algorithm provided local explanations for the SVM model predictions. Additionally, an OWL (web ontology language) ontology facilitated the semantic representation and reasoning of the survey data. The study highlighted a pipeline for collecting, analyzing, and representing data from online public surveys during the pandemic. The identified factors were correlated with depressive symptoms, illustrating the significant influence of lifestyle and demographic variables on mental health. The online survey method proved advantageous for data collection, visualization, and cost-effectiveness while maintaining anonymity and reducing bias. Challenges included reaching the target population, addressing language barriers, ensuring digital literacy, and mitigating dishonest responses and sampling errors. In conclusion, lifestyle and demographic factors significantly impact depression during the COVID-19 pandemic. The study's methodology offers valuable insights into addressing mental health challenges through scalable online surveys, aiding in the understanding and mitigation of depression risk factors.

PMID:39406791 | DOI:10.1038/s41598-024-74539-6

J Int Med Res. 2024 Oct;52(10):3000605241282116. doi: 10.1177/03000605241282116.

ABSTRACT

OBJECTIVES: This review aimed to summarize the existing data on the contribution of four single nucleotide polymorphisms (SNPs) in the cytotoxic T lymphocyte-associated antigen-4 (CTLA-4) genes to pemphigus susceptibility.

METHODS: An electronic literature search for eligible studies among those published prior to 30 April 2024 was conducted through the PubMed, EMBASE, Web of Science, and Scopus databases. To minimize publication bias, an additional search was performed via the Google Scholar and Semantic Scholar search engines. Meta-analyses, together with subgroup analyses and meta-regressions, were performed for the following four CTLA-4 SNPs: rs231775, rs5742909, rs3087243, and rs733618.

RESULTS: Combined analyses revealed a significant increase in pemphigus risk conferred by the CTLA-4 rs5742909*C and rs733618*C alleles. Conversely, there was no evidence of any significant association between the rs231775*G and rs3087243*G alleles and susceptibility to pemphigus. Subgroup analyses by ethnicity and pemphigus type (vulgaris or foliaceus) and meta-regressions did not reveal any significant difference.

CONCLUSION: This meta-analysis suggested that two of the four investigated CTLA-4 SNPs were significantly associated with increased pemphigus risk.Registration: This review has been registered on PROSPERO: CRD42024550668; available from: https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42024550668.

PMID:39397428 | DOI:10.1177/03000605241282116

Genomics Inform. 2024 Oct 10;22(1):17. doi: 10.1186/s44342-024-00021-4.

ABSTRACT

This report presents the findings of a project from the 8th Biomedical Linked Annotation Hackathon (BLAH) to explore lightweight technology stacks to enhance assistive linked annotations. Using modern JavaScript frameworks and edge functions, in-browser Named Entity Recognition (NER), serverless embedding and vector search within web interfaces, and efficient serverless full-text search were implemented. Through this experimental approach, a proof of concept to demonstrate the feasibility and performance of these technologies was demonstrated. The results show that lightweight stacks can significantly improve the efficiency and cost-effectiveness of annotation tools and provide a local-first, privacy-oriented, and secure alternative to traditional server-based solutions in various use cases. This work emphasizes the potential of developing annotation interfaces that are more responsive, scalable, and user-friendly, which would benefit bioinformatics researchers, practitioners, and software developers.

PMID:39390526 | PMC:PMC11468380 | DOI:10.1186/s44342-024-00021-4

Inquiry. 2024 Jan-Dec;61:469580241288346. doi: 10.1177/00469580241288346.

ABSTRACT

The "Leave No One Behind" (LNOB) principle, a fundamental commitment of the United Nations' Sustainable Development Goals, emphasizes the urgent need to address and reduce global health inequalities. As global health initiatives strive to uphold this principle, they face significant ethical challenges in balancing equity, resource allocation, and diverse health priorities. This narrative review critically examines these ethical dilemmas and their implications for translating LNOB into actionable global health strategies. A comprehensive literature search was conducted using PubMed, Scopus, Web of Science, and Semantic Scholar, covering publications from January 1990 to April 2024. The review included peer-reviewed articles, gray literature, and official reports that addressed the ethical dimensions of LNOB in global health contexts. A thematic analysis was employed to identify and synthesize recurring ethical issues, dilemmas, and proposed solutions. The thematic analysis identified 4 primary ethical tensions that complicate the operationalization of LNOB: (1) Universalism versus Targeting, where the challenge lies in balancing broad health improvements with targeted interventions for the most disadvantaged; (2) Resource Scarcity versus Equity; highlighting the ethical conflicts between maximizing efficiency and ensuring fairness; (3) Top-down versus Bottom-up Approaches, reflecting the tension between externally driven initiatives and local community needs; and (4) Short-term versus Long-term Sustainability, addressing the balance between immediate health interventions and sustainable systemic changes. To navigate these ethical challenges effectively, global health strategies must adopt a nuanced, context-sensitive approach incorporating structured decision-making processes and authentic community participation. The review advocates for systemic reforms that address the root causes of health disparities, promote equitable collaboration between health practitioners and marginalized communities, and align global health interventions with ethical imperatives. Such an approach is essential to truly operationalize the LNOB principle and foster sustainable health equity.

PMID:39385394 | PMC:PMC11465308 | DOI:10.1177/00469580241288346

Data Brief. 2024 Sep 10;57:110910. doi: 10.1016/j.dib.2024.110910. eCollection 2024 Dec.

ABSTRACT

Papaya is a popular vegetable and fruit in both developing and developed countries. Nonetheless, Bangladesh's agricultural landscape is significantly influenced by papaya cultivation. However, disease is a common impediment to papaya productivity, adversely affecting papaya quality and yield and leading to substantial economic losses for farmers. Research suggests that computer-aided disease diagnosis and machine learning (ML) models can improve papaya production by detecting and classifying diseases. In this line, a dataset of papaya is required to diagnose the disease. Moreover, like many other fruits, papaya disease may vary from country to country. Therefore, the country-based papaya disease dataset is required. In this study, a papaya dataset is collected from Dhaka, Bangladesh. This dataset contains 2159 original images from five classes, including the healthy control class and four papaya leaf diseases: Anthracnose, Bacterial Spot, Curl, and Ring spot. Besides the original images, the dataset contains 210 annotated data for each of the five classes. The dataset contains two types of data: the whole image and the annotated image. The image will interest data scientists who apply disease detection through a convolutional neural network (CNN) and its variants. Furthermore, the annotated images, such as You Only Look Once (YOLO), U-Net, Mask R-CNN, and Single Shot Detection (SSD), will be helpful for semantic segmentation. Since firm-applicable AI devices and mobile and web applications are in demand, the dataset collected in this study will offer multiple options for integrating ML models into AI devices. In countries with weather and climate similar to Bangladesh, data scientists may use their dataset in that context.

PMID:39381009 | PMC:PMC11460515 | DOI:10.1016/j.dib.2024.110910

Brain Topogr. 2024 Oct 2;38(1):1. doi: 10.1007/s10548-024-01083-x.

ABSTRACT

Microstates represent brief periods of quasi-stable electroencephalography (EEG) scalp topography, offering insights into dynamic fluctuations in event-related potential (ERP) topographies. Despite this, there is a lack of a comprehensive systematic overview of microstate findings concerning cognitive face processing. This review aims to summarize ERP findings on face processing using microstate analyses and assess their effectiveness in characterizing face-related neural representations. A literature search was conducted for microstate ERP studies involving healthy individuals and psychiatric populations, utilizing PubMed, Google Scholar, Web of Science, PsychInfo, and Scopus databases. Twenty-two studies were identified, primarily focusing on healthy individuals (n = 16), with a smaller subset examining psychiatric populations (n = 6). The evidence reviewed in this study suggests that various microstates are consistently associated with distinct ERP stages involved in face processing, encompassing the processing of basic visual facial features to more complex functions such as analytical processing, facial recognition, and semantic representations. Furthermore, these studies shed light on atypical attentional neural mechanisms in Autism Spectrum Disorder (ASD), facial recognition deficits among emotional dysregulation disorders, and encoding and semantic dysfunctions in Post-Traumatic Stress Disorder (PTSD). In conclusion, this review underscores the practical utility of ERP microstate analyses in investigating face processing. Methodologies have evolved towards greater automation and data-driven approaches over time. Future research should aim to forecast clinical outcomes and conduct validation studies to directly demonstrate the efficacy of such analyses in inverse space.

PMID:39358648 | DOI:10.1007/s10548-024-01083-x

Acta Otolaryngol. 2024 Oct 2:1-8. doi: 10.1080/00016489.2024.2404614. Online ahead of print.

ABSTRACT

BACKGROUND: It has been shown that there is a link between thyroid-related diseases and hearing loss.

OBJECTIVES: The purpose of this study is to investigate the relationship between thyroid-related diseases and hearing loss by conducting a meta-analysis.

MATERIAL AND METHODS: A thorough search was carried out in the following electronic databases: PubMed, Cochrane Library, Embase, Web of Science, Google Scholar, Semantic Scholar, and ResearchRabbit. The chi-square test and the I2 index examined the research's heterogeneity. A funnel plot and the Eger test were used to examine publication-biased effects.

RESULTS: A total of 48,507 individuals (6482 hypothyroid patients, 4162 hearing loss patients, and 37863 controls) were included in this meta-analysis of 18 research. Individuals with hypothyroidism had a 1.69-fold increased risk of hearing loss compared to those without the condition (OR: 1.69; 95% CI: 1.11-2.57, p < 0.001). among hypothyroidism, the prevalence of hearing loss was 24% (EC: 0.24; 95% CI: 0.11-0.39, p = 0.00), while among hearing-impaired individuals, the prevalence of hypothyroidism was 7% (EC: 0.21; 95% CI: 0.07-0.40).

CONCLUSION: This study demonstrated how thyroid dysfunction can raise the chance of hearing loss. To completely comprehend the underlying mechanisms and create efficient treatments for this illness, more study is required.

PMID:39356749 | DOI:10.1080/00016489.2024.2404614

J Biomed Semantics. 2024 Oct 2;15(1):18. doi: 10.1186/s13326-024-00319-w.

ABSTRACT

Biomedical relation classification has been significantly improved by the application of advanced machine learning techniques on the raw texts of scholarly publications. Despite this improvement, the reliance on large chunks of raw text makes these algorithms suffer in terms of generalization, precision, and reliability. The use of the distinctive characteristics of bibliographic metadata can prove effective in achieving better performance for this challenging task. In this research paper, we introduce an approach for biomedical relation classification using the qualifiers of co-occurring Medical Subject Headings (MeSH). First of all, we introduce MeSH2Matrix, our dataset consisting of 46,469 biomedical relations curated from PubMed publications using our approach. Our dataset includes a matrix that maps associations between the qualifiers of subject MeSH keywords and those of object MeSH keywords. It also specifies the corresponding Wikidata relation type and the superclass of semantic relations for each relation. Using MeSH2Matrix, we build and train three machine learning models (Support Vector Machine [SVM], a dense model [D-Model], and a convolutional neural network [C-Net]) to evaluate the efficiency of our approach for biomedical relation classification. Our best model achieves an accuracy of 70.78% for 195 classes and 83.09% for five superclasses. Finally, we provide confusion matrix and extensive feature analyses to better examine the relationship between the MeSH qualifiers and the biomedical relations being classified. Our results will hopefully shed light on developing better algorithms for biomedical ontology classification based on the MeSH keywords of PubMed publications. For reproducibility purposes, MeSH2Matrix, as well as all our source codes, are made publicly accessible at https://github.com/SisonkeBiotik-Africa/MeSH2Matrix .

PMID:39354632 | PMC:PMC11445994 | DOI:10.1186/s13326-024-00319-w

Dement Geriatr Cogn Disord. 2024 Sep 30:1-28. doi: 10.1159/000541581. Online ahead of print.

ABSTRACT

INTRODUCTION: The Toolkit to Examine Lifelike Language (TELL) is a web-based application providing speech biomarkers of neurodegeneration. After deployment of TELL v.1.0 in over 20 sites, we now introduce TELL v.2.0.

METHODS: First, we describe the app's usability features, including functions for collecting and processing data onsite, offline, and via videoconference. Second, we summarize its clinical survey, tapping on relevant habits (e.g., smoking, sleep) alongside linguistic predictors of performance (language history, use, proficiency, and difficulties). Third, we detail TELL's speech-based assessments, each combining strategic tasks and features capturing diagnostically relevant domains (motor function, semantic memory, episodic memory, and emotional processing). Fourth, we specify the app's new data analysis, visualization, and download options. Finally, we list core challenges and opportunities for development.

RESULTS: Overall, through its technical and scientific breakthroughs, TELL v.2.0 offers scalable, objective, and multidimensional insights for the field.

CONCLUSION: This tool can enhance disease detection, phenotyping, and monitoring.

PMID:39348797 | DOI:10.1159/000541581

Patient Prefer Adherence. 2024 Sep 24;18:1965-1977. doi: 10.2147/PPA.S478576. eCollection 2024.

ABSTRACT

BACKGROUND: Rapid recovery after lung cancer surgery is challenging. Exercise is a low-cost, effective method to expedite recovery. Despite numerous exercise interventions, many fail to consider patient perspectives, leading to low adherence and short-term effects. Understanding lung cancer patients' perspectives on postoperative exercise and exploring their exercise-related concerns and needs are crucial for enhancing the effectiveness of exercise-based rehabilitation programs.

OBJECTIVE: This study aims to analyze lung cancer patients' perspectives on postoperative exercise in their daily lives, exploring their concerns and needs related to postoperative exercise to help healthcare professionals develop personalized exercise plans.

METHODS: An internet crawling technique collected online inquiries from Baidu webpages about postoperative physical activity in lung cancer patients, using "lung cancer", "surgery", and "exercise" as keywords. The data was encoded, categorized, and analyzed using a large-scale semantic analysis platform in natural language processing and information retrieval to examine term frequency, sentiment tendencies, and attributes in the inquiry texts.

RESULTS: Initially, 2727 queries were retrieved; after screening, deduplication, and cleansing, 201 unique queries were identified. Queries related to "modes of exercise" constituted the largest proportion. The most frequently occurring words in the word frequency analysis were "lung", " cancer", "should", "can", "long", "early", and "surgery", "exercise", "respiratory". Postoperative lung cancer patients demonstrate significant interest in whether they should engage in exercise, as well as in the appropriate types and duration of such activities, indicating a strong need for detailed guidance and knowledge related to exercise. The sentiment analysis showed a positive score of 87.5% and a negative score of 12.5%, indicating that postoperative lung cancer patients view exercise positively and have an enthusiastic attitude towards it. Among the positive sentiment attributes, "good" was the most frequently mentioned term, whereas "bad" and "surprising" were the most prevalent terms within the negative sentiment attributes.

CONCLUSION: Postoperative physical activity receives limited attention from lung cancer patients, who emphasize their preferences for exercise modalities. Their inquiries often reflect psychological concerns, such as fear and helplessness caused by symptoms. Understanding patients' perspectives on postoperative physical activity within their real-life contexts can help integrate psychological support into exercise plans. This integration could guide healthcare professionals in developing more personalized postoperative exercise regimens for lung cancer patients.

PMID:39345759 | PMC:PMC11438453 | DOI:10.2147/PPA.S478576

Physiol Plant. 2024 Sep-Oct;176(5):e14537. doi: 10.1111/ppl.14537.

ABSTRACT

Long non-coding RNAs (lncRNAs) have emerged as important regulators of many biological processes, although their regulatory roles remain poorly characterized in woody plants, especially in gymnosperms. A major challenge of working with lncRNAs is to assign functional annotations, since they have a low coding potential and low cross-species conservation. We utilised an existing RNA-Sequencing resource and performed short RNA sequencing of somatic embryogenesis developmental stages in Norway spruce (Picea abies L. Karst). We implemented a pipeline to identify lncRNAs located within the intergenic space (lincRNAs) and generated a co-expression network including protein coding, lincRNA and miRNA genes. To assign putative functional annotation, we employed a guilt-by-association approach using the co-expression network and integrated these results with annotation assigned using semantic similarity and co-expression. Moreover, we evaluated the relationship between lincRNAs and miRNAs, and identified which lincRNAs are conserved in other species. We identified lincRNAs with clear evidence of differential expression during somatic embryogenesis and used network connectivity to identify those with the greatest regulatory potential. This work provides the most comprehensive view of lincRNAs in Norway spruce and is the first study to perform global identification of lincRNAs during somatic embryogenesis in conifers. The data have been integrated into the expression visualisation tools at the PlantGenIE.org web resource to enable easy access to the community. This will facilitate the use of the data to address novel questions about the role of lincRNAs in the regulation of embryogenesis and facilitate future comparative genomics studies.

PMID:39319989 | DOI:10.1111/ppl.14537

Front Bioinform. 2024 Sep 10;4:1395981. doi: 10.3389/fbinf.2024.1395981. eCollection 2024.

ABSTRACT

We present a tool for multi-omics data analysis that enables simultaneous visualization of up to four types of omics data on organism-scale metabolic network diagrams. The tool's interactive web-based metabolic charts depict the metabolic reactions, pathways, and metabolites of a single organism as described in a metabolic pathway database for that organism; the charts are constructed using automated graphical layout algorithms. The multi-omics visualization facility paints each individual omics dataset onto a different "visual channel" of the metabolic-network diagram. For example, a transcriptomics dataset might be displayed by coloring the reaction arrows within the metabolic chart, while a companion proteomics dataset is displayed as reaction arrow thicknesses, and a complementary metabolomics dataset is displayed as metabolite node colors. Once the network diagrams are painted with omics data, semantic zooming provides more details within the diagram as the user zooms in. Datasets containing multiple time points can be displayed in an animated fashion. The tool will also graph data values for individual reactions or metabolites designated by the user. The user can interactively adjust the mapping from data value ranges to the displayed colors and thicknesses to provide more informative diagrams.

PMID:39318761 | PMC:PMC11420163 | DOI:10.3389/fbinf.2024.1395981