RESUMO
BACKGROUND: Caregiver workload in the ICU setting is difficult to numerically quantify. Ambient Intelligence utilises computer vision-guided neural networks to continuously monitor multiple datapoints in video feeds, has become increasingly efficient at automatically tracking various aspects of human movement. OBJECTIVES: To assess the feasibility of using Ambient Intelligence to track and quantify allpatient and caregiver activity within a bedspace over the course of an ICU admission and also to establish patient specific factors, and environmental factors such as time ofday, that might contribute to an increased workload in ICU workers. METHODS: 5000 images were manually annotated and then used to train You Only LookOnce (YOLOv4), an open-source computer vision algorithm. Comparison of patientmotion and caregiver activity was then performed between these patients. RESULTS: The algorithm was deployed on 14 patients comprising 1762800 framesof new, untrained data. There was a strong correlation between the number ofcaregivers in the room and the standardized movement of the patient (p < 0.0001) withmore caregivers associated with more movement. There was a significant difference incaregiver activity throughout the day (p < 0.05), HDU vs. ICU status (p < 0.05), delirious vs. non delirious patients (p < 0.05), and intubated vs. not intubated patients(p < 0.05). Caregiver activity was lowest between 0400 and 0800 (average .71 ± .026caregivers per hour) with statistically significant differences in activity compared to 0800-2400 (p < 0.05). Caregiver activity was highest between 1200 and 1600 (1.02 ± .031 caregivers per hour) with a statistically significant difference in activity comparedto activity from 1600 to 0800 (p < 0.05). The three most dominant predictors of workeractivity were patient motion (Standardized Dominance 78.6%), Mechanical Ventilation(Standardized Dominance 7.9%) and Delirium (Standardized Dominance 6.2%). CONCLUSION: Ambient Intelligence could potentially be used to derive a single standardized metricthat could be applied to patients to illustrate their overall workload. This could be usedto predict workflow demands for better staff deployment, monitoring of caregiver workload, and potentially as a tool to predict burnout.
Assuntos
Inteligência Ambiental , Cuidados Críticos , Humanos , Unidades de Terapia Intensiva , Hospitalização , Carga de TrabalhoRESUMO
OBJECTIVE: To assess the magnitude of active and recovering COVID-19 patients among at-risk communities and to identify the factors associated with positive serology. METHODS: Four hundred and eighty-three close contacts of COVID-19 patients residing in Ho Chi Minh City, Vietnam, during the fourth wave of the COVID-19 epidemic (September and October 2021) were included. Five weeks after exposure to a COVID-19 patient, they underwent a serology test using the BIOSYNEX COVID-19 BSS kit. RESULTS: The median age of participants was 37 years. A total of 34.6% individuals presented at least one clinical symptom between the time of contact with the COVID-19 patient and inclusion in study. A total of 1.7% unvaccinated individuals tested positive for SARS-CoV-2 using real-time PCR, and 9.5% had evidence of recent infection (positive PCR and/or IgM). A further 26.7% unvaccinated individuals presented evidence of a past infection (positive IgG only). Socio-demographic characteristics, vaccination status and clinical symptoms were not associated with a positive IgM test. CONCLUSION: This is the first serosurvey conducted during the fourth wave of the epidemic in Vietnam. It revealed a seropositivity rate higher than in previous studies and confirmed the hyperendemicity of SARS-CoV-2. Testing using rapid serological tests proved to be a reliable, easy-to-use method and enabled a rapid estimation of the burden of COVID-19.
Assuntos
COVID-19 , SARS-CoV-2 , Adulto , Anticorpos Antivirais , COVID-19/diagnóstico , COVID-19/epidemiologia , Humanos , Imunoglobulina M , Estudos Soroepidemiológicos , Vietnã/epidemiologiaRESUMO
Public health measurement is important for government administration as it provides indicators and implications to public healthcare strategies. The measurement of health status has been traditionally conducted via surveys in the forms of pre-designed questionnaires to collect responses from targeted participants. Apart from benefits, traditional approach is costly, time-consuming, and not scalable. These limitations make a major obstacle to policy makers to develop up-to-date healthcare programs. This paper studies the use of health-related information conveyed in user-generated content from social media for prediction of health outcomes at population level. Specifically, we investigate linguistic features for analysing textual data. We propose the use of visual features learnt from deep neural networks for understanding visual data. We introduce collective social capital information from location-based social media data. We conducted extensive experiments on large-scale datasets collected from two online social networks: Foursquare and Flickr, against the task of prediction of the U.S. county health indices. Experimental results showed that visual and collective social capital data achieved comparable prediction performance and outperformed textual information. These promising results also suggest the potential of social media for health analysis at population scales.
Assuntos
Nível de Saúde , Saúde da População/estatística & dados numéricos , Mídias Sociais , Visualização de Dados , Pesquisa Empírica , Humanos , Redes Neurais de Computação , Psicolinguística , Saúde Pública , Inquéritos e QuestionáriosRESUMO
Ground parrot vocalisation can be considered as an audio event. Test-based diverse density multiple instance learning (TB-DD-MIL) is proposed for detecting this event in audio files recorded in the field. The proposed method is motivated by the advantages of multiple instance learning from incomplete training data. Spectral features suitable for encoding the vocal source information of the ground parrot vocalization are also investigated. The proposed method was benchmarked against a dataset collected in various environmental conditions and an audio detection evaluation scheme is proposed. The evaluation includes a study on performance of the various vocal source features and comparison with other classification techniques. Experimental results indicated that the most appropriate feature to encode ground parrot calls is the spectral bandwidth and the proposed TB-DD-MIL method outperformed other existing classification methods.
Assuntos
Aprendizado de Máquina , Papagaios , Espectrografia do Som , Vocalização Animal , Algoritmos , Animais , Austrália , Comportamento Animal , Conjuntos de Dados como Assunto , Reconhecimento Automatizado de PadrãoRESUMO
Aspergillus niger is a well-known workhorse for the industrial production of enzymes and organic acids. This fungus can also cause postharvest diseases in fruits. Although Agrobacterium tumefaciens-mediated transformation (ATMT) based on antibiotic resistance markers has been effectively exploited for inspecting functions of target genes in wild-type fungi, it still needs to be further improved in A. niger. In the present study, we re-examined the ATMT in the wild-type A. niger strains using the hygromycin resistance marker and introduced the nourseothricin resistance gene as a new selection marker for this fungus. Unexpectedly, our results revealed that the ATMT method using the resistance markers in A. niger led to numerous small colonies as false-positive transformants on transformation plates. Using the top agar overlay technique to restrict false positive colonies, a transformation efficiency of 87 ± 18 true transformants could be achieved for 106 conidia. With two different selection markers, we could perform both the deletion and complementation of a target gene in a single wild-type A. niger strain. Our results also indicated that two key regulatory genes (laeA and veA) of the velvet complex are required for A. niger to infect apple fruits. Notably, we demonstrated for the first time that a laeA homologous gene from the citrus postharvest pathogen Penicillium digitatum was able to restore the acidification ability and pathogenicity of the A. niger ΔlaeA mutant. The dual resistance marker ATMT system from our work represents an improved genetic tool for gene function characterization in A. niger.
RESUMO
BACKGROUND: The COVID-19 pandemic has made devastating impacts on public health and global economy. While most people experience mild symptoms, it is highly transmissible and deadly in at-risk populations. Telemedicine has the potential to prevent hospitalization and provide remote care. METHODS: This retrospective study included 336 people with COVID-19, among which 141 (42%) and 195 (58%) were in Delta and Omicron dominant groups, respectively. Patients were confirmed to have COVID-19 by PCR or rapid test and were cared for via telemedicine. Severe cases were hospitalized for more intensive treatment. RESULTS: The majority of individuals recovered at home (97.02%), while 2.98% required hospitalization. All hospital admissions were in Delta dominant group. No deaths were reported. Delta dominant group was more likely to develop loss of taste and smell, decreased appetite and need longer treatment time than those in Omicron dominant group. CONCLUSIONS: Telemedicine is a safe measure to provide at-home care for people with COVID-19 infections caused by both Delta and Omicron variants. TRIAL REGISTRATION: This study was approved by the Institutional Review Board Committee of University of Medicine and Pharmacy at Ho Chi Minh City (IRB No: 22115-DHYD).
Assuntos
COVID-19 , Serviços de Assistência Domiciliar , Humanos , COVID-19/epidemiologia , Pandemias , Estudos Retrospectivos , SARS-CoV-2RESUMO
The wallago catfish (Wallago attu) is a new potential fish for aquaculture in Vietnam. Data related to the reproductive cycle of W. attu in captivity are, however, not available. To provide reliable indicators for oocyte maturation (OM) and the spawning season of the captive W. attu, this study investigated the temporal variation in hepatosomatic and gonadosomatic indices, oocyte diameter and color (greenish vs yellowish), germinal vesicle migration, and plasma concentrations of estradiol-17ß (E2) and vitellogenin (Vtg) in female broodstock in association with changes in light density, temperature and amount of rainfall during the reproductive cycle. The results of this study displayed a clear seasonality in all the investigated parameters. The highest concentration of E2 (2.6 ± 3.5 ng/mL) was found in April, followed by a peak of Vtg (543 ± 43 ng/mL) in June. Meanwhile, the largest mean oocyte diameter (1.70 ± 0.02 mm) was observed in June. The shortest distance between the germinal vesicle and the edge of the oocyte (0.20 ± 0.01 mm) was recorded in July. Correspondingly, the amount of rainfall increased remarkably in July from 43.9 mm to over 200 mm in August. Taken together, we conclude that OM and the onset of the spawning season of captive W. attu occur in July and August, respectively. The percentage of greenish oocytes increased significantly over sampling time points. The changes in the color of oocytes combined with oocyte diameter could, therefore, be considered as promising indicators to predict the OM and spawning season of captive W. attu.
Assuntos
Peixes-Gato , Animais , Estradiol , Feminino , Oócitos , Oogênese , Reprodução , VitelogeninasRESUMO
Origin of the COVID-19 virus (SARS-CoV-2) has been intensely debated in the scientific community since the first infected cases were detected in December 2019. The disease has caused a global pandemic, leading to deaths of thousands of people across the world and thus finding origin of this novel coronavirus is important in responding and controlling the pandemic. Recent research results suggest that bats or pangolins might be the hosts for SARS-CoV-2 based on comparative studies using its genomic sequences. This paper investigates the SARS-CoV-2 origin by using artificial intelligence (AI)-based unsupervised learning algorithms and raw genomic sequences of the virus. More than 300 genome sequences of COVID-19 infected cases collected from different countries are explored and analysed using unsupervised clustering methods. The results obtained from various AI-enabled experiments using clustering algorithms demonstrate that all examined SARS-CoV-2 genomes belong to a cluster that also contains bat and pangolin coronavirus genomes. This provides evidence strongly supporting scientific hypotheses that bats and pangolins are probable hosts for SARS-CoV-2. At the whole genome analysis level, our findings also indicate that bats are more likely the hosts for the COVID-19 virus than pangolins.
RESUMO
We propose in this work a graph-based approach for automatic public health analysis using social media. In our approach, graphs are created to model the interactions between features and between tweets in social media. We investigated different graph properties and methods in constructing graph-based representations for population health analysis. The proposed approach is applied in two case studies: (1) estimating health indices, and (2) classifying health situation of counties in the US. We evaluate our approach on a dataset including more than one billion tweets collected in three years 2014, 2015, and 2016, and the health surveys from the Behavioral Risk Factor Surveillance System. We conducted realistic and large-scale experiments on various textual features and graph-based representations. Experimental results verified the robustness of the proposed approach and its superiority over existing ones in both case studies, confirming the potential of graph-based approach for modeling interactions in social networks for population health analysis.
RESUMO
The wide adoption of Electronic Health Records (EHR) has resulted in large amounts of clinical data becoming available, which promises to support service delivery and advance clinical and informatics research. Deep learning techniques have demonstrated performance in predictive analytic tasks using EHRs yet they typically lack model result transparency or explainability functionalities and require cumbersome pre-processing tasks. Moreover, EHRs contain heterogeneous and multi-modal data points such as text, numbers and time series which further hinder visualisation and interpretability. This paper proposes a deep learning framework to: 1) encode patient pathways from EHRs into images, 2) highlight important events within pathway images, and 3) enable more complex predictions with additional intelligibility. The proposed method relies on a deep attention mechanism for visualisation of the predictions and allows predicting multiple sequential outcomes.
Assuntos
Aprendizado Profundo , Registros Eletrônicos de Saúde , HumanosRESUMO
The objective of this study was to describe the overall pattern of morbidity and mortality of children seen at the Thai Binh Paediatric Hospital in Vietnam, with a focus on infectious diseases. A retrospective review of hospitalisation records was conducted from 1 January 2015 to 31 December 2019. Data were obtained from a total of 113,999 records. The median age of patients was 18 months, with 84.0% of patients aged <5 years. Infectious diseases accounted for 61.0% of all cases. The most prevalent diseases were lower respiratory tract infections (32.8%), followed by gastrointestinal infections (13.3%) and confirmed influenza (5.4%). Most infections were not microbiologically documented. A total of 81.4% patients received at least one antibiotic. Most patients (97.0%) were hospitalised for less than 15 days. Regarding outcomes, 87.8% patients were discharged home with a favourable outcome. Twelve percent were transferred to the Vietnam National Children's Hospital because their condition had worsened and 0.1% died. In total, infectious diseases accounted for 40.4% of deaths, followed by neonatal disorders (34.6%). Our data serves a basis for the identification of needs for diagnostic tools and for future evaluation of the effect of the targeted implementation of such facilities. Point-of-care tests, including real-time polymerase chain reaction assays to identify common pathogens should be implemented for more accurate diagnosis and more appropriate antibiotic use.
Assuntos
Mortalidade da Criança , Doenças Transmissíveis , Hospitalização , Morbidade , Criança , Mortalidade da Criança/tendências , Pré-Escolar , Doenças Transmissíveis/epidemiologia , Doenças Transmissíveis/mortalidade , Doenças Transmissíveis/terapia , Hospitalização/estatística & dados numéricos , Hospitais Pediátricos , Humanos , Lactente , Recém-Nascido , Morbidade/tendências , Estudos Retrospectivos , Vietnã/epidemiologiaRESUMO
BACKGROUND: Overweight and obesity is a severe global health issue in both developed and developing nations. This study aims to estimate the national prevalence of overweight and obesity among school-aged children in Vietnam. METHOD: We conducted a national cross-sectional study on 2788 children aged from 11-14 years old from September to November 2018. We applied the WHO 2007 and IOTF criteria to estimate the prevalence of overweight and obesity among participants. Poison regression analysis with cluster sampling adjustment was employed to assess associated factors with obesity and overweight. Metadata on sociodemographic characteristics, physical measurements, and lifestyle behaviors were also extracted to investigate these factors in association with overweight and obesity prevalence. RESULTS: The prevalences of overweight and obesity in Vietnamese children were 17.4% and 8.6%, respectively by WHO Z-score criteria, and 17.1% and 5.4%, according to the IOTF reference. Using WHO Z-score yielded a higher prevalence of obesity than the IOTF and CDC criteria of all ages and both sexes. The proportions of overweight and obesity were substantially higher among boys than girls across ages. Parental BMI was shown to be a significant factor associated with overweight/obesity status in both girls and boys. Only for boys, age (PR = 0.83, 95% CI 0.76-0.90) and belonging to ethnic minorities (PR = 0.43, 95% CI 0.24-0.76) were significant risk factors for overweight/obesity. CONCLUSION: Our findings indicate a high prevalence of childhood overweight and obesity in Vietnam, especially in boys.
Assuntos
Índice de Massa Corporal , Estilo de Vida , Sobrepeso/epidemiologia , Obesidade Infantil/epidemiologia , Fatores Socioeconômicos , Adolescente , Fatores Etários , Criança , Estudos Transversais , Feminino , Humanos , Masculino , Sobrepeso/diagnóstico , Obesidade Infantil/diagnóstico , Prevalência , Fatores Sexuais , Vietnã/epidemiologia , Organização Mundial da SaúdeRESUMO
BACKGROUND: Early diagnosis of Alzheimer's disease (AD) and Mild Cognitive Impairment (MCI) is essential for timely treatment. Machine learning and multivariate pattern analysis (MVPA) for the diagnosis of brain disorders are explicitly attracting attention in the neuroimaging community. In this paper, we propose a voxel-wise discriminative framework applied to multi-measure resting-state fMRI (rs-fMRI) that integrates hybrid MVPA and extreme learning machine (ELM) for the automated discrimination of AD and MCI from the cognitive normal (CN) state. MATERIALS AND METHODS: We used two rs-fMRI cohorts: the public Alzheimer's disease Neuroimaging Initiative database (ADNI2) and an in-house Alzheimer's disease cohort from South Korea, both including individuals with AD, MCI, and normal controls. After extracting three-dimensional (3-D) patterns measuring regional coherence and functional connectivity during the resting state, we performed univariate statistical t-tests to generate a 3-D mask that retained only voxels showing significant changes. Given the initial univariate features, to enhance discriminative patterns, we implemented MVPA feature reduction using support vector machine-recursive feature elimination (SVM-RFE), and least absolute shrinkage and selection operator (LASSO), in combination with the univariate t-test. Classifications were performed by an ELM, and its efficiency was compared to linear and nonlinear (radial basis function) SVMs. RESULTS: The maximal accuracies achieved by the method in the ADNI2 cohort were 98.86% (p<0.001) and 98.57% (p<0.001) for AD and MCI vs. CN, respectively. In the in-house cohort, the same accuracies were 98.70% (p<0.001) and 94.16% (p<0.001). CONCLUSION: From a clinical perspective, combining extreme learning machine and hybrid MVPA applied on concatenations of multiple rs-fMRI biomarkers can potentially assist the clinicians in AD and MCI diagnosis.
Assuntos
Doença de Alzheimer/diagnóstico por imagem , Disfunção Cognitiva/diagnóstico por imagem , Imageamento por Ressonância Magnética , Máquina de Vetores de Suporte , Idoso , Idoso de 80 Anos ou mais , Mapeamento Encefálico , Feminino , Humanos , Masculino , República da CoreiaRESUMO
In this paper, we propose a novel image reconstruction algorithm using multi-scale 3D convolutional sparse coding and a spectral decomposition technique for highly undersampled dynamic Magnetic Resonance Imaging (MRI) data. The proposed method recovers high-frequency information using a shared 3D convolution-based dictionary built progressively during the reconstruction process in an unsupervised manner, while low-frequency information is recovered using a total variation-based energy minimization method that leverages temporal coherence in dynamic MRI. Additionally, the proposed 3D dictionary is built across three different scales to more efficiently adapt to various feature sizes, and elastic net regularization is employed to promote a better approximation to the sparse input data. We also propose an automatic parameter selection technique based on a genetic algorithm to find optimal parameters for our numerical solver which is a variant of the alternating direction method of multipliers (ADMM). We demonstrate the performance of our method by comparing it with state-of-the-art methods on 15 single-coil cardiac, 7 single-coil DCE, and a multi-coil brain MRI datasets at different sampling rates (12.5%, 25% and 50%). The results show that our method significantly outperforms the other state-of-the-art methods in reconstruction quality with a comparable running time and is resilient to noise.
Assuntos
Processamento de Imagem Assistida por Computador/métodos , Imageamento Tridimensional/métodos , Imageamento por Ressonância Magnética/métodos , Algoritmos , Encéfalo/diagnóstico por imagem , Conjuntos de Dados como Assunto , Coração/diagnóstico por imagem , HumanosRESUMO
Compressed sensing magnetic resonance imaging (CS-MRI) has provided theoretical foundations upon which the time-consuming MRI acquisition process can be accelerated. However, it primarily relies on iterative numerical solvers, which still hinders their adaptation in time-critical applications. In addition, recent advances in deep neural networks have shown their potential in computer vision and image processing, but their adaptation to MRI reconstruction is still in an early stage. In this paper, we propose a novel deep learning-based generative adversarial model, RefineGAN, for fast and accurate CS-MRI reconstruction. The proposed model is a variant of fully-residual convolutional autoencoder and generative adversarial networks (GANs), specifically designed for CS-MRI formulation; it employs deeper generator and discriminator networks with cyclic data consistency loss for faithful interpolation in the given under-sampled -space data. In addition, our solution leverages a chained network to further enhance the reconstruction quality. RefineGAN is fast and accurate-the reconstruction process is extremely rapid, as low as tens of milliseconds for reconstruction of a image, because it is one-way deployment on a feed-forward network, and the image quality is superior even for extremely low sampling rate (as low as 10%) due to the data-driven nature of the method. We demonstrate that RefineGAN outperforms the state-of-the-art CS-MRI methods by a large margin in terms of both running time and image quality via evaluation using several open-source MRI databases.
Assuntos
Processamento de Imagem Assistida por Computador/métodos , Imageamento por Ressonância Magnética/métodos , Redes Neurais de Computação , Algoritmos , Encéfalo/diagnóstico por imagem , HumanosRESUMO
Nutritional quality of most maize varieties is very low due to the lack of lysine and tryptophan and extremely low provitamin A carotenoids including ß-carotene, α-carotene, and ß-cryptoxanthin. In this study, we report the successful overexpression of the IbOr gene in H145 and H95 inbred maize lines under the control of maize seed-specific promoter globulin 1 (Glo1) for the purpose of improving ß-carotene in maize. The results showed that the total carotenoid and ß-carotene content of all analyzed transgenic maize plants were significantly higher than those of wild-type lines. For H145-IbOr transgenic maize, in the best line (H145-IbOr.10), the total carotenoid and ß-carotene contents were increased up to 10.36- and 15.11-fold, respectively, compared to the wild type (H145-WT). In the case of H95-IbOr transgenic plants, 5.58-fold increase in total carotenoid and 7.63-fold increase in ß-carotene were achieved in the H95-IbOr.6 line compared to nontransgenic plants (H95-WT). In all the transgenic plants derived from the wild-type maize line with less carotenoid content (H145-WT), the content of both total carotenoid and ß-carotene was higher than in transgenic plants derived from the wild-type maize line having more carotenoid content (H95-WT). Our research is the first in successful overexpression of IbOr gene in maize.
RESUMO
Dietary assessment, while traditionally based on pen-and-paper, is rapidly moving towards automatic approaches. This study describes an Australian automatic food record method and its prototype for dietary assessment via the use of a mobile phone and techniques of image processing and pattern recognition. Common visual features including scale invariant feature transformation (SIFT), local binary patterns (LBP), and colour are used for describing food images. The popular bag-of-words (BoW) model is employed for recognizing the images taken by a mobile phone for dietary assessment. Technical details are provided together with discussions on the issues and future work.