-
International Journal of Language &... 2024Dementia is a cognitive decline that leads to the progressive deterioration of an individual's ability to perform daily activities independently. As a result, a...
BACKGROUND
Dementia is a cognitive decline that leads to the progressive deterioration of an individual's ability to perform daily activities independently. As a result, a considerable amount of time and resources are spent on caretaking. Early detection of dementia can significantly reduce the effort and resources needed for caretaking.
AIMS
This research proposes an approach for assessing cognitive decline by analysing speech data, specifically focusing on speech relevance as a crucial indicator for memory recall.
METHODS & PROCEDURES
This is a cross-sectional, online, self-administered. The proposed method used deep learning architecture based on transformers, with BERT (Bidirectional Encoder Representations from Transformers) and Sentence-Transformer to derive encoded representations of speech transcripts. These representations provide contextually descriptive information that is used to analyse the relevance of sentences in their respective contexts. The encoded information is then compared using cosine similarity metrics to measure the relevance of uttered sequences of sentences. The study uses the Pitt Corpus Dementia dataset for experimentation, which consists of speech data from individuals with and without dementia. The accuracy of the proposed multi-QA-MPNet (Multi-Query Maximum Inner Product Search Pretraining) model is compared with other pretrained transformer models of Sentence-Transformer.
OUTCOMES & RESULTS
The results show that the proposed approach outperforms the other models in capturing context level information, particularly semantic memory. Additionally, the study explores the suitability of different similarity measures to evaluate the relevance of uttered sequences of sentences. The experimentation reveals that cosine similarity is the most appropriate measure for this task.
CONCLUSIONS & IMPLICATIONS
This finding has significant implications for the early warning signs of dementia, as it suggests that cosine similarity metrics can effectively capture the semantic relevance of spoken language. The persistent cognitive decline over time acts as one of the indicators for prevalence of dementia. Additionally early dementia could be recognised by analysis on other modalities like speech and brain images.
WHAT THIS PAPER ADDS
What is already known on this subject It is already known that speech- and language-based detection methods can be useful for dementia diagnosis, as language difficulties are often early signs of the disease. Additionally, deep learning algorithms have shown promise in detecting and diagnosing dementia through analysing large datasets, particularly in speech- and language-based detection methods. However, further research is needed to validate the performance of these algorithms on larger and more diverse datasets and to address potential biases and limitations. What this paper adds to existing knowledge This study presents a unique and effective approach for cognitive decline assessment through analysing speech data. The study provides valuable insights into the importance of context and semantic memory in accurately detecting the potential in dementia and demonstrates the applicability of deep learning models for this purpose. The findings of this study have important clinical implications and can inform future research and development in the field of dementia detection and care. What are the potential or actual clinical implications of this work? The proposed approach for cognitive decline assessment using speech data and deep learning models has significant clinical implications. It has the potential to improve the accuracy and efficiency of dementia diagnosis, leading to earlier detection and more effective treatments, which can improve patient outcomes and quality of life.
Topics: Humans; Deep Learning; Cognitive Dysfunction; Cross-Sectional Studies; Semantics; Aged; Female; Male; Aged, 80 and over; Dementia
PubMed: 37971395
DOI: 10.1111/1460-6984.12973 -
The Spine Journal : Official Journal of... Dec 2023A traumatic spinal cord injury (SCI) can cause temporary or permanent motor and sensory impairment, leading to serious short and long-term consequences that can result...
BACKGROUND CONTEXT
A traumatic spinal cord injury (SCI) can cause temporary or permanent motor and sensory impairment, leading to serious short and long-term consequences that can result in significant morbidity and mortality. The cervical spine is the most commonly affected area, accounting for about 60% of all traumatic SCI cases.
PURPOSE
This study aims to employ machine learning (ML) algorithms to predict various outcomes, such as in-hospital mortality, nonhome discharges, extended length of stay (LOS), extended length of intensive care unit stay (ICU-LOS), and major complications in patients diagnosed with cervical SCI (cSCI).
STUDY DESIGN
Our study was a retrospective machine learning classification study aiming to predict the outcomes of interest, which were binary categorical variables, in patients diagnosed with cSCI.
PATIENT SAMPLE
The data for this study were obtained from the American College of Surgeons (ACS) Trauma Quality Program (TQP) database, which was queried to identify patients who suffered from cSCI between 2019 and 2021.
OUTCOME MEASURES
The outcomes of interest of our study were in-hospital mortality, nonhome discharges, prolonged LOS, prolonged ICU-LOS, and major complications. The study evaluated the models' performance using both graphical and numerical methods. The receiver operating characteristic (ROC) and precision-recall curves (PRC) were used to assess model performance graphically. Numerical evaluation metrics included AUROC, balanced accuracy, weighted area under PRC (AUPRC), weighted precision, and weighted recall.
METHODS
The study employed data from the American College of Surgeons (ACS) Trauma Quality Program (TQP) database to identify patients with cSCI. Four ML algorithms, namely XGBoost, LightGBM, CatBoost, and Random Forest, were utilized to develop predictive models. The most effective models were then incorporated into a publicly available web application designed to forecast the outcomes of interest.
RESULTS
There were 71,661 patients included in the analysis for the outcome mortality, 67,331 for the outcome nonhome discharges, 76,782 for the outcome prolonged LOS, 26,615 for the outcome prolonged ICU-LOS, and 72,132 for the outcome major complications. The algorithms exhibited an AUROC value range of 0.78 to 0.839 for in-hospital mortality, 0.806 to 0.815 for nonhome discharges, 0.679 to 0.742 for prolonged LOS, 0.666 to 0.682 for prolonged ICU-LOS, and 0.637 to 0.704 for major complications. An open access web application was developed as part of the study, which can generate predictions for individual patients based on their characteristics.
CONCLUSIONS
Our study suggests that ML models can be valuable in assessing risk for patients with cervical cSCI and may have considerable potential for predicting outcomes during hospitalization. ML models demonstrated good predictive ability for in-hospital mortality and nonhome discharges, fair predictive ability for prolonged LOS, but poor predictive ability for prolonged ICU-LOS and major complications. Along with these promising results, the development of a user-friendly web application that facilitates the integration of these models into clinical practice is a significant contribution of this study. The product of this study may have significant implications in clinical settings to personalize care, anticipate outcomes, facilitate shared decision making and informed consent processes for cSCI patients.
Topics: Humans; Retrospective Studies; Cervical Cord; Precision Medicine; Spinal Cord Injuries; Machine Learning; Hospitals
PubMed: 37619871
DOI: 10.1016/j.spinee.2023.08.009 -
JMIR Formative Research Feb 2024The prevalence of childhood obesity and comorbidities is rising alarmingly, and diet is an important modifiable determinant. Numerous dietary interventions in children...
BACKGROUND
The prevalence of childhood obesity and comorbidities is rising alarmingly, and diet is an important modifiable determinant. Numerous dietary interventions in children have been developed to reduce childhood obesity and overweight rates, but their long-term effects are unsatisfactory. Stakeholders call for more personalized approaches, which require detailed dietary intake data. In the case of primary school children, caregivers are key to providing such dietary information. However, as school-aged children are not under the full supervision of one specific caregiver anymore, data are likely to be biased. Recent technological advancements provide opportunities for the role of children themselves, which would serve the overall quality of the obtained dietary data.
OBJECTIVE
This study aims to conduct a child-centered exploratory sequential mixed methods study to identify user requirements for a dietary assessment tool for children aged 5 to 6 years.
METHODS
Formative, nonsystematic narrative literature research was undertaken to delineate initial user requirements and inform prototype ideation in an expert panel workshop (n=11). This yielded 3 prototype dietary assessment tools: FoodBear (tangible piggy bank), myBear (smartphone or tablet app), and FoodCam (physical camera). All 3 prototypes were tested for usability by means of a usability task (video analyses) and user experience (This or That method) among 14 Dutch children aged 5 to 6 years (n=8, 57% boys and n=6, 43% girls).
RESULTS
Most children were able to complete FoodBear's (11/14, 79%), myBear's (10/14, 71%), and FoodCam's (9/14, 64%) usability tasks, but all children required assistance (14/14, 100%) and most of the children encountered usability problems (13/14, 93%). Usability issues were related to food group categorization and recognition, frustrations owing to unsatisfactory functioning of (parts) of the prototypes, recall of food products, and the distinction between eating moments. No short-term differences in product preference between the 3 prototypes were observed, but autonomy, challenge, gaming elements, being tablet based, appearance, social elements, and time frame were identified as determinants of liking the product.
CONCLUSIONS
Our results suggest that children can play a complementary role in dietary data collection to enhance the data collected by their parents. Incorporation of a training program, auditory or visual prompts, reminders and feedback, a user-friendly and intuitive interaction design, child-friendly food groups or icons, and room for children's autonomy were identified as requirements for the future development of a novel and usable dietary assessment tool for children aged 5 to 6 years. Our findings can serve as valuable guidance for ongoing innovations in the field of children's dietary assessment and the provision of personalized dietary support.
PubMed: 38300689
DOI: 10.2196/47850 -
Swiss Medical Weekly May 2024Listeriosis is a notifiable disease in Switzerland. In summer 2022, the Swiss Federal Office of Public Health noticed an increase in reports of listeriosis cases,...
AIMS OF THE STUDY
Listeriosis is a notifiable disease in Switzerland. In summer 2022, the Swiss Federal Office of Public Health noticed an increase in reports of listeriosis cases, indicating a possible ongoing outbreak. Here we present the approaches applied for rapidly confirming the outbreak, detecting the underlying source of infection and the measures put in place to eliminate it and contain the outbreak.
METHODS
For close surveillance and early detection of outbreak situations with their possible sources, listeriosis patients in Switzerland are systematically interviewed about risk behaviours and foods consumed prior to the infection. Listeria monocytogenes isolates derived from patients in medical laboratories are sent to the National Reference Laboratory for Enteropathogenic Bacteria and Listeria, where they routinely undergo whole-genome sequencing. Interview and whole-genome sequencing data are continuously linked for comparison and analysis.
RESULTS
In summer 2022, 20 patient-derived L. monocytogenes serotype 4b sequence type 388 strains were found to belong to an outbreak cluster (≤10 different alleles between neighbouring isolates) based on core genome multilocus sequence typing analysis. Geographically, 18 of 20 outbreak cases occurred in northeastern Switzerland. The median age of patients was 77.4 years (range: 58.1-89.7), with both sexes equally affected. Rolling analysis of the interview data revealed smoked trout from a local producer as a suspected infection source, triggering an on-site investigation of the production facility and sampling of the suspected products by the responsible cantonal food inspection team on 15 July 2022. Seven of ten samples tested positive for L. monocytogenes and the respective cantonal authority ordered a ban on production and distribution as well as a product recall. The Federal Food Safety and Veterinary Office released a nationwide public alert covering the smoked fish products concerned. Whole-genome sequencing analysis confirmed the interrelatedness of the L. monocytogenes smoked trout product isolates and the patient-derived isolates. Following the ban on production and distribution and the product recall, reporting of new outbreak-related cases rapidly dropped to zero.
CONCLUSIONS
This listeriosis outbreak could be contained within a relatively short time thanks to identification of the source of contamination through the established combined approach of timely interviewing of every listeriosis patient or a representative and continuous molecular analysis of the patient- and food-derived L. monocytogenes isolates. These findings highlight the effectiveness of this well-established, joint approach involving the federal and cantonal authorities and the research institutions mandated to contain listeriosis outbreaks in Switzerland.
Topics: Humans; Switzerland; Disease Outbreaks; Listeria monocytogenes; Listeriosis; Whole Genome Sequencing; Male; Aged; Female; Aged, 80 and over; Multilocus Sequence Typing; Middle Aged; Food Microbiology; Foodborne Diseases; Interviews as Topic
PubMed: 38701492
DOI: 10.57187/s.3745 -
Scientific Reports Jul 2023E-commerce is a field that changed how consumers purchase and interact with products. Although, inherent limitations such as the difficulty of testing the products...
E-commerce is a field that changed how consumers purchase and interact with products. Although, inherent limitations such as the difficulty of testing the products "first-hand" before a purchase can compromise consumers' trust in online purchases. Virtual Reality (VR) has been investigated as a tool to solve limitations in several fields and how we can harness its potential to improve the overall user experience. This study analysed how immersive VR (IVR) could solve these limitations by allowing consumers to test products beforehand. We have studied how the Novelty Factor (evaluated by the users' past VR experience) and Immersive Tendencies correlate with the users' Purchase Intention and Memory (how well they remember the product's characteristics). We have analysed a sample of 38 participants (21 males) from 18 to 28 years old. Participants experienced a refrigerator with an interactive touchscreen in an IVR setup and were guided through its functionalities. Results indicated that memory of the product's characteristics was positively correlated with how recently they experienced VR. No correlations were found in the female sample. A negative correlation between Purchase Intention and Memory of the product's characteristics was found in the male sample. We concluded that IVR applications could become helpful for both consumers and online shops in an e-commerce context regardless of the Novelty Factor and Immersive Tendencies of consumers. However, differences between genders should be further investigated.
Topics: Humans; Male; Female; Adolescent; Young Adult; Adult; Intention; Virtual Reality; Commerce; Consumer Behavior; Mental Recall
PubMed: 37452064
DOI: 10.1038/s41598-023-36557-8 -
Nicotine & Tobacco Research : Official... Feb 2024Prior research on the effects of social media promotion of tobacco products has predominantly relied on survey-based self-report measures of marketing exposure, which...
INTRODUCTION
Prior research on the effects of social media promotion of tobacco products has predominantly relied on survey-based self-report measures of marketing exposure, which potentially introduce endogeneity, recall, and selection biases. New approaches can enhance measurement and help better understand the effects of exposure to tobacco-related messages in a dynamic social media marketing environment. We used geolocation-specific tweet rate as an exogenous indicator of exposure to smokeless tobacco (ST)-related content and employed this measure to examine the influence of social media marketing on ST sales.
AIMS AND METHODS
Autoregressive error models were used to analyze the association between the ST-relevant tweet rate (aggregated by 4-week period from February 12, 2017 to June 26, 2021 and scaled by population density) and logarithmic ST unit sales across time by product type (newer, snus, conventional) in the United States, accounting for autocorrelated errors. Interrupted time series approach was used to control for policy change effects.
RESULTS
ST product category-related tweet rates were associated with ST unit sales of newer and conventional products, controlling for price, relevant policy events, and the coronavirus disease 2019 (COVID-19) pandemic. On average, 100-unit increase in the number of newer ST-related tweets was associated with 14% increase in unit sales (RR = 1.14; p = .01); 100-unit increase in conventional ST tweets was associated with ~1% increase in unit sales (p = .04). Average price was negatively associated with the unit sales.
CONCLUSIONS
Study findings reveal that ST social media tweet rate was related to increased ST consumption and illustrate the utility of exogenous measures in conceptualizing and assessing effects in the complex media environment.
IMPLICATIONS
Tobacco control initiatives should include efforts to monitor the role of social media in promoting tobacco use. Surveillance of social media platforms is critical to monitor emerging tobacco product-related marketing strategies and promotional content reach. Exogenous measures of potential exposure to social media messages can supplement survey data to study media effects on tobacco consumption.
Topics: Humans; United States; Tobacco, Smokeless; Social Media; Media Exposure; Commerce; Marketing; Tobacco Use; Tobacco Products
PubMed: 38366341
DOI: 10.1093/ntr/ntad169 -
Journal of Ethnopharmacology Oct 2023Traditional Chinese Medicine (TCM) prescriptions are a product of the Chinese medical theory's distinct thinking and clinical experience. TCM practitioners treat...
ETHNOPHARMACOLOGICAL RELEVANCE
Traditional Chinese Medicine (TCM) prescriptions are a product of the Chinese medical theory's distinct thinking and clinical experience. TCM practitioners treat diseases by enhancing the efficacy of TCM prescriptions and reducing their poisonous effects. Some TCM herb recommendation methods have been provided for curing the given symptoms to generate a group of herbs according to the TCM principles. However, they ignored the symptoms' semantic characteristics and herbs' different effects on symptoms.
AIM OF THE STUDY
We aim to recommend TCM herbs by considering symptoms' semantic information and the strength of different herbs in curing symptoms.
MATERIALS AND METHODS
We propose a herb recommendation model named Multi-Graph Residual Attention Network and Semantic Knowledge Fusion (SMRGAT) to address these problems. Concretely, it uses a multi-head attention mechanism to focus on herbs' different effects on symptoms. Meanwhile, it augments entities' features with a residual network structure while incorporating symptoms' semantic information and external knowledge of herbs. We will verify the effect of SMRGAT on the existing public datasets and the datasets that we have collected and cleaned.
RESULTS
Compared with the current best TCM herb recommendation model, on the public dataset, SMRGAT were increased by 15.11%, 20.60%, and 18.25% in Precision@5, Recall@5, and F1 - score@5, respectively; on ours, respectively increased by 9.72%, 9.03%, 9.24%.
CONCLUSIONS
Our experimental results on two datasets indicate that SMRGAT is capable of recommending herbs with greater precision and outperforms several comparison methods. It can provide a basis for assisting TCM clinical prescriptions.
Topics: Humans; Semantics; Medicine, Chinese Traditional; Language; Traditional Medicine Practitioners; Drugs, Chinese Herbal
PubMed: 37257707
DOI: 10.1016/j.jep.2023.116693 -
Pharmaceuticals (Basel, Switzerland) Dec 2023Levothyroxine tablets, although highly prescribed in the United States, have been one of the most frequently recalled products. Because of the importance of the...
Levothyroxine tablets, although highly prescribed in the United States, have been one of the most frequently recalled products. Because of the importance of the medication, several efforts have been put in place by the United States Food and Drug Administration (US FDA) to control the quality of levothyroxine tablets available to patients using the drug. The choice of excipients used in the formulation has been shown to impact the hygroscopicity and microenvironment, and ultimately the stability of the levothyroxine tablets formulations. Based on information generated from the US FDA Enforcement Report database, one of the main reasons for recalls is the low potency of different batches of the product. The yearly product recall trends for levothyroxine formulations were determined using the FDA Enforcement Report database. Three brands of levothyroxine tablets were selected with excipient lists similar to those products that have been historically recalled. The samples were placed at ambient (~23 °C), accelerated stability (40 °C/75% RH), and stress (50 °C/75% RH) conditions for up to 6 months. Sample potencies were determined at 0, 1.5, 3, and 6 months using the methods for assay and impurities in the United States Pharmacopeia (USP) monograph for levothyroxine tablets. Additional sample monitoring was conducted by overlaying the initial powder X-ray diffractograms (PXRD) of the samples from 0 months with the patterns generated thereafter. There has been a decline in the number of levothyroxine tablets recalled over the years. The highest numbers of recalls were recorded in the years 2013 [33] and 2020 [23]; no recalls occurred in the years 2019 and 2022. All of the brands evaluated met the USP 95.0-105.0% assay requirements at 1.5 months under accelerated conditions; only one of the brands complied at 3 months. Under ambient conditions, two brands were stable at 6 months, with borderline assay results. For stability, levothyroxine was found in microgram quantities in the formulations and PXRD could not detect changes at these low levels. However, we found some distinguishing data for samples under stress conditions.
PubMed: 38256876
DOI: 10.3390/ph17010042 -
Journal of Pharmaceutical Sciences Jun 2024This study addresses the identification of undesirable microorganisms (MOs) recovered during the environmental monitoring in manufacture of sterile medicinal products....
This study addresses the identification of undesirable microorganisms (MOs) recovered during the environmental monitoring in manufacture of sterile medicinal products. We developed a methodology evaluation based on a decision tree; then, such approach was applied to hypothetical scenarios of uncommon MOs isolation in sterile drugs production settings. The scenarios were formulated on the basis of our field experience, in terms of both MOs selection and types of sampling site. The MOs were chosen in order to include emerging pathogens and MOs responsible for drug recall, and several sampling sites were considered for their detection (air, surfaces, and personnel). The classification of the unusual MOs revealed that most of them were undesirable, because they represented the loss of environmental control or a potential impact on the quality of the product. In some cases, the uncommon MOs were not considered as undesirable. Therefore, our results demonstrated the importance of a methodology, also in terms of recovery rate of unusual MOs and of the threshold probability for the unacceptability (e.g., 1% or 5%). The proposed methodology allowed an easy and documented evaluation for the undesirable MOs isolated from the environment of the analyzed settings for sterile drugs production.
Topics: Drug Contamination; Environmental Monitoring; Sterilization; Drug Industry; Bacteria; Decision Trees; Environmental Microbiology
PubMed: 38325736
DOI: 10.1016/j.xphs.2024.01.019 -
ArXiv Apr 2024Tandem mass spectrometry (MS/MS) stands as the predominant high-throughput technique for comprehensively analyzing protein content within biological samples. This...
Tandem mass spectrometry (MS/MS) stands as the predominant high-throughput technique for comprehensively analyzing protein content within biological samples. This methodology is a cornerstone driving the advancement of proteomics. In recent years, substantial strides have been made in Data-Independent Acquisition (DIA) strategies, facilitating impartial and non-targeted fragmentation of precursor ions. The DIA-generated MS/MS spectra present a formidable obstacle due to their inherent high multiplexing nature. Each spectrum encapsulates fragmented product ions originating from multiple precursor peptides. This intricacy poses a particularly acute challenge in de novo peptide/protein sequencing, where current methods are ill-equipped to address the multiplexing conundrum. In this paper, we introduce DiaTrans, a deep-learning model based on transformer architecture. It deciphers peptide sequences from DIA mass spectrometry data. Our results show significant improvements over existing STOA methods, including DeepNovo-DIA and PepNet. DiaTrans enhances precision by 15.14% to 34.8%, recall by 11.62% to 31.94% at the amino acid level, and boosts precision by 59% to 81.36% at the peptide level. Integrating DIA data and our DiaTrans model holds considerable promise to uncover novel peptides and more comprehensive profiling of biological samples. DiaTrans is freely available under the GNU GPL license at https://github.com/Biocomputing-Research-Group/DiaTrans.
PubMed: 38659639
DOI: No ID Found