Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 719
Filtrar
1.
PLoS One ; 16(4): e0249450, 2021.
Artigo em Inglês | MEDLINE | ID: mdl-33793650

RESUMO

Coronavirus disease 2019 (COVID-19) has been spread out all over the world. Although a real-time reverse-transcription polymerase chain reaction (RT-PCR) test has been used as a primary diagnostic tool for COVID-19, the utility of CT based diagnostic tools have been suggested to improve the diagnostic accuracy and reliability. Herein we propose a semi-supervised deep neural network for an improved detection of COVID-19. The proposed method utilizes CT images in a supervised and unsupervised manner to improve the accuracy and robustness of COVID-19 diagnosis. Both labeled and unlabeled CT images are employed. Labeled CT images are used for supervised leaning. Unlabeled CT images are utilized for unsupervised learning in a way that the feature representations are invariant to perturbations in CT images. To systematically evaluate the proposed method, two COVID-19 CT datasets and three public CT datasets with no COVID-19 CT images are employed. In distinguishing COVID-19 from non-COVID-19 CT images, the proposed method achieves an overall accuracy of 99.83%, sensitivity of 0.9286, specificity of 0.9832, and positive predictive value (PPV) of 0.9192. The results are consistent between the COVID-19 challenge dataset and the public CT datasets. For discriminating between COVID-19 and common pneumonia CT images, the proposed method obtains 97.32% accuracy, 0.9971 sensitivity, 0.9598 specificity, and 0.9326 PPV. Moreover, the comparative experiments with respect to supervised learning and training strategies demonstrate that the proposed method is able to improve the diagnostic accuracy and robustness without exhaustive labeling. The proposed semi-supervised method, exploiting both supervised and unsupervised learning, facilitates an accurate and reliable diagnosis for COVID-19, leading to an improved patient care and management.


Assuntos
/diagnóstico por imagem , Redes Neurais de Computação , Aprendizado de Máquina Supervisionado , Tórax , Tomografia Computadorizada por Raios X , Algoritmos , Conjuntos de Dados como Assunto , Humanos , Tórax/diagnóstico por imagem , Tórax/patologia
2.
BMJ Open ; 11(2): e044500, 2021 02 26.
Artigo em Inglês | MEDLINE | ID: mdl-33637550

RESUMO

BACKGROUND: Despite the necessity, there is no reliable biomarker to predict disease severity and prognosis of patients with COVID-19. The currently published prediction models are not fully applicable to clinical use. OBJECTIVES: To identify predictive biomarkers of COVID-19 severity and to justify their threshold values for the stratification of the risk of deterioration that would require transferring to the intensive care unit (ICU). METHODS: The study cohort (560 subjects) included all consecutive patients admitted to Dubai Mediclinic Parkview Hospital from February to May 2020 with COVID-19 confirmed by the PCR. The challenge of finding the cut-off thresholds was the unbalanced dataset (eg, the disproportion in the number of 72 patients admitted to ICU vs 488 non-severe cases). Therefore, we customised supervised machine learning (ML) algorithm in terms of threshold value used to predict worsening. RESULTS: With the default thresholds returned by the ML estimator, the performance of the models was low. It was improved by setting the cut-off level to the 25th percentile for lymphocyte count and the 75th percentile for other features. The study justified the following threshold values of the laboratory tests done on admission: lymphocyte count <2.59×109/L, and the upper levels for total bilirubin 11.9 µmol/L, alanine aminotransferase 43 U/L, aspartate aminotransferase 32 U/L, D-dimer 0.7 mg/L, activated partial thromboplastin time (aPTT) 39.9 s, creatine kinase 247 U/L, C reactive protein (CRP) 14.3 mg/L, lactate dehydrogenase 246 U/L, troponin 0.037 ng/mL, ferritin 498 ng/mL and fibrinogen 446 mg/dL. CONCLUSION: The performance of the neural network trained with top valuable tests (aPTT, CRP and fibrinogen) is admissible (area under the curve (AUC) 0.86; 95% CI 0.486 to 0.884; p<0.001) and comparable with the model trained with all the tests (AUC 0.90; 95% CI 0.812 to 0.902; p<0.001). Free online tool at https://med-predict.com illustrates the study results.


Assuntos
Biomarcadores/análise , /diagnóstico , Algoritmos , Hospitalização , Humanos , Funções Verossimilhança , Prognóstico , Estudos Retrospectivos , Aprendizado de Máquina Supervisionado , Emirados Árabes Unidos
3.
Med Image Anal ; 69: 101978, 2021 04.
Artigo em Inglês | MEDLINE | ID: mdl-33588121

RESUMO

How to fast and accurately assess the severity level of COVID-19 is an essential problem, when millions of people are suffering from the pandemic around the world. Currently, the chest CT is regarded as a popular and informative imaging tool for COVID-19 diagnosis. However, we observe that there are two issues - weak annotation and insufficient data that may obstruct automatic COVID-19 severity assessment with CT images. To address these challenges, we propose a novel three-component method, i.e., 1) a deep multiple instance learning component with instance-level attention to jointly classify the bag and also weigh the instances, 2) a bag-level data augmentation component to generate virtual bags by reorganizing high confidential instances, and 3) a self-supervised pretext component to aid the learning process. We have systematically evaluated our method on the CT images of 229 COVID-19 cases, including 50 severe and 179 non-severe cases. Our method could obtain an average accuracy of 95.8%, with 93.6% sensitivity and 96.4% specificity, which outperformed previous works.


Assuntos
/diagnóstico por imagem , Adolescente , Adulto , Idoso , Idoso de 80 Anos ou mais , Criança , Pré-Escolar , Aprendizado Profundo , Feminino , Humanos , Lactente , Recém-Nascido , Masculino , Pessoa de Meia-Idade , Índice de Gravidade de Doença , Aprendizado de Máquina Supervisionado , Tomografia Computadorizada por Raios X , Adulto Jovem
4.
PLoS One ; 16(2): e0245909, 2021.
Artigo em Inglês | MEDLINE | ID: mdl-33630869

RESUMO

The spread of Covid-19 has resulted in worldwide health concerns. Social media is increasingly used to share news and opinions about it. A realistic assessment of the situation is necessary to utilize resources optimally and appropriately. In this research, we perform Covid-19 tweets sentiment analysis using a supervised machine learning approach. Identification of Covid-19 sentiments from tweets would allow informed decisions for better handling the current pandemic situation. The used dataset is extracted from Twitter using IDs as provided by the IEEE data port. Tweets are extracted by an in-house built crawler that uses the Tweepy library. The dataset is cleaned using the preprocessing techniques and sentiments are extracted using the TextBlob library. The contribution of this work is the performance evaluation of various machine learning classifiers using our proposed feature set. This set is formed by concatenating the bag-of-words and the term frequency-inverse document frequency. Tweets are classified as positive, neutral, or negative. Performance of classifiers is evaluated on the accuracy, precision, recall, and F1 score. For completeness, further investigation is made on the dataset using the Long Short-Term Memory (LSTM) architecture of the deep learning model. The results show that Extra Trees Classifiers outperform all other models by achieving a 0.93 accuracy score using our proposed concatenated features set. The LSTM achieves low accuracy as compared to machine learning classifiers. To demonstrate the effectiveness of our proposed feature set, the results are compared with the Vader sentiment analysis technique based on the GloVe feature extraction approach.


Assuntos
Mídias Sociais , Aprendizado de Máquina Supervisionado , Aprendizado Profundo , Humanos , Processamento de Linguagem Natural , Pandemias , Opinião Pública
5.
Sensors (Basel) ; 21(3)2021 Feb 02.
Artigo em Inglês | MEDLINE | ID: mdl-33540786

RESUMO

Hand gesture recognition and hand pose estimation are two closely correlated tasks. In this paper, we propose a deep-learning based approach which jointly learns an intermediate level shared feature for these two tasks, so that the hand gesture recognition task can be benefited from the hand pose estimation task. In the training process, a semi-supervised training scheme is designed to solve the problem of lacking proper annotation. Our approach detects the foreground hand, recognizes the hand gesture, and estimates the corresponding 3D hand pose simultaneously. To evaluate the hand gesture recognition performance of the state-of-the-arts, we propose a challenging hand gesture recognition dataset collected in unconstrained environments. Experimental results show that, the gesture recognition accuracy of ours is significantly boosted by leveraging the knowledge learned from the hand pose estimation task.


Assuntos
Gestos , Mãos , Reconhecimento Automatizado de Padrão , Cor , Humanos , Aprendizagem , Aprendizado de Máquina Supervisionado
6.
Nature ; 589(7843): 572-576, 2021 01.
Artigo em Inglês | MEDLINE | ID: mdl-33473211

RESUMO

Women (compared to men) and individuals from minority ethnic groups (compared to the majority group) face unfavourable labour market outcomes in many economies1,2, but the extent to which discrimination is responsible for these effects, and the channels through which they occur, remain unclear3,4. Although correspondence tests5-in which researchers send fictitious CVs that are identical except for the randomized minority trait to be tested (for example, names that are deemed to sound 'Black' versus those deemed to sound 'white')-are an increasingly popular method to quantify discrimination in hiring practices6,7, they can usually consider only a few applicant characteristics in select occupations at a particular point in time. To overcome these limitations, here we develop an approach to investigate hiring discrimination that combines tracking of the search behaviour of recruiters on employment websites and supervised machine learning to control for all relevant jobseeker characteristics that are visible to recruiters. We apply this methodology to the online recruitment platform of the Swiss public employment service and find that rates of contact by recruiters are 4-19% lower for individuals from immigrant and minority ethnic groups, depending on their country of origin, than for citizens from the majority group. Women experience a penalty of 7% in professions that are dominated by men, and the opposite pattern emerges for men in professions that are dominated by women. We find no evidence that recruiters spend less time evaluating the profiles of individuals from minority ethnic groups. Our methodology provides a widely applicable, non-intrusive and cost-efficient tool that researchers and policy-makers can use to continuously monitor hiring discrimination, to identify some of the drivers of discrimination and to inform approaches to counter it.


Assuntos
Emprego/estatística & dados numéricos , Internet , Seleção de Pessoal/métodos , Seleção de Pessoal/estatística & dados numéricos , Preconceito/estatística & dados numéricos , Emigrantes e Imigrantes/estatística & dados numéricos , Grupos Étnicos/estatística & dados numéricos , Feminino , Humanos , Internacionalidade , Masculino , Grupos Minoritários/estatística & dados numéricos , Ocupações/estatística & dados numéricos , Preconceito/prevenção & controle , Salários e Benefícios/estatística & dados numéricos , Sexismo/estatística & dados numéricos , Estereotipagem , Aprendizado de Máquina Supervisionado , Suíça , Fatores de Tempo
7.
Med Care ; 59: S58-S64, 2021 02 01.
Artigo em Inglês | MEDLINE | ID: mdl-33438884

RESUMO

BACKGROUND: Suicide prevention is a public health priority, but risk factors for suicide after medical hospitalization remain understudied. This problem is critical for women, for whom suicide rates in the United States are disproportionately increasing. OBJECTIVE: To differentiate the risk of suicide attempt and self-harm following general medical hospitalization among women with depression, bipolar disorder, and chronic psychosis. METHODS: We developed a machine learning algorithm that identified risk factors of suicide attempt and self-harm after general hospitalization using electronic health record data from 1628 women in the University of California Los Angeles Integrated Clinical and Research Data Repository. To assess replicability, we applied the algorithm to a larger sample of 140,848 women in the New York City Clinical Data Research Network. RESULTS: The classification tree algorithm identified risk groups in University of California Los Angeles Integrated Clinical and Research Data Repository (area under the curve 0.73, sensitivity 73.4, specificity 84.1, accuracy 0.84), and predictor combinations characterizing key risk groups were replicated in New York City Clinical Data Research Network (area under the curve 0.71, sensitivity 83.3, specificity 82.2, and accuracy 0.84). Predictors included medical comorbidity, history of pregnancy-related mental illness, age, and history of suicide-related behavior. Women with antecedent medical illness and history of pregnancy-related mental illness were at high risk (6.9%-17.2% readmitted for suicide-related behavior), as were women below 55 years old without antecedent medical illness (4.0%-7.5% readmitted). CONCLUSIONS: Prevention of suicide attempt and self-harm among women following acute medical illness may be improved by screening for sex-specific predictors including perinatal mental health history.


Assuntos
Hospitalização , Transtornos Mentais/psicologia , Comportamento Autodestrutivo/psicologia , Tentativa de Suicídio/psicologia , Aprendizado de Máquina Supervisionado , Mulheres/psicologia , Adulto , Idoso , Algoritmos , Estudos de Coortes , Registros Eletrônicos de Saúde , Feminino , Humanos , Pessoa de Meia-Idade , Readmissão do Paciente , Reprodutibilidade dos Testes , Estudos Retrospectivos , Fatores de Risco , Sensibilidade e Especificidade , Adulto Jovem
8.
Neural Netw ; 133: 166-176, 2021 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-33217685

RESUMO

Mixed sample augmentation (MSA) has witnessed great success in the research area of semi-supervised learning (SSL) and is performed by mixing two training samples as an augmentation strategy to effectively smooth the training space. Following the insights on the efficacy of cut-mix in particular, we propose FMixCut, an MSA that combines Fourier space-based data mixing (FMix) and the proposed Fourier space-based data cutting (FCut) for labeled and unlabeled data augmentation. Specifically, for the SSL task, our approach first generates soft pseudo-labels using the model's previous predictions. The model is then trained to penalize the outputs of the FMix-generated samples so that they are consistent with their mixed soft pseudo-labels. In addition, we propose to use FCut, a new Cutout-based data augmentation strategy that adopts the two masked sample pairs from FMix for weighted cross-entropy minimization. Furthermore, by implementing two regularization techniques, namely, batch label distribution entropy maximization and sample confidence entropy minimization, we further boost the training efficiency. Finally, we introduce a dynamic labeled-unlabeled data mixing (DDM) strategy to further accelerate the convergence of the model. Combining the above process, we finally call our SSL approach as "FMixCutMatch", in short FMCmatch. As a result, the proposed FMCmatch achieves state-of-the-art performance on CIFAR-10/100, SVHN and Mini-Imagenet across a variety of SSL conditions with the CNN-13, WRN-28-2 and ResNet-18 networks. In particular, our method achieves a 4.54% test error on CIFAR-10 with 4K labels under the CNN-13 and a 41.25% Top-1 test error on Mini-Imagenet with 10K labels under the ResNet-18. Our codes for reproducing these results are publicly available at https://github.com/biuyq/FMixCutMatch.


Assuntos
Bases de Dados Factuais , Aprendizado Profundo , Aprendizado de Máquina Supervisionado , Processamento Eletrônico de Dados/métodos , Entropia
9.
Neural Netw ; 135: 127-138, 2021 Mar.
Artigo em Inglês | MEDLINE | ID: mdl-33383527

RESUMO

Named entity recognition (NER) for identifying proper nouns in unstructured text is one of the most important and fundamental tasks in natural language processing. However, despite the widespread use of NER models, they still require a large-scale labeled data set, which incurs a heavy burden due to manual annotation. Domain adaptation is one of the most promising solutions to this problem, where rich labeled data from the relevant source domain are utilized to strengthen the generalizability of a model based on the target domain. However, the mainstream cross-domain NER models are still affected by the following two challenges (1) Extracting domain-invariant information such as syntactic information for cross-domain transfer. (2) Integrating domain-specific information such as semantic information into the model to improve the performance of NER. In this study, we present a semi-supervised framework for transferable NER, which disentangles the domain-invariant latent variables and domain-specific latent variables. In the proposed framework, the domain-specific information is integrated with the domain-specific latent variables by using a domain predictor. The domain-specific and domain-invariant latent variables are disentangled using three mutual information regularization terms, i.e., maximizing the mutual information between the domain-specific latent variables and the original embedding, maximizing the mutual information between the domain-invariant latent variables and the original embedding, and minimizing the mutual information between the domain-specific and domain-invariant latent variables. Extensive experiments demonstrated that our model can obtain state-of-the-art performance with cross-domain and cross-lingual NER benchmark data sets.


Assuntos
Armazenamento e Recuperação da Informação/métodos , Processamento de Linguagem Natural , Semântica , Aprendizado de Máquina Supervisionado , Humanos , Idioma
10.
BMC Bioinformatics ; 21(Suppl 18): 498, 2020 Dec 30.
Artigo em Inglês | MEDLINE | ID: mdl-33375939

RESUMO

BACKGROUND: Personalized cancer vaccines are emerging as one of the most promising approaches to immunotherapy of advanced cancers. However, only a small proportion of the neoepitopes generated by somatic DNA mutations in cancer cells lead to tumor rejection. Since it is impractical to experimentally assess all candidate neoepitopes prior to vaccination, developing accurate methods for predicting tumor-rejection mediating neoepitopes (TRMNs) is critical for enabling routine clinical use of cancer vaccines. RESULTS: In this paper we introduce Positive-unlabeled Learning using AuTOml (PLATO), a general semi-supervised approach to improving accuracy of model-based classifiers. PLATO generates a set of high confidence positive calls by applying a stringent filter to model-based predictions, then rescores remaining candidates by using positive-unlabeled learning. To achieve robust performance on clinical samples with large patient-to-patient variation, PLATO further integrates AutoML hyper-parameter tuning, classification threshold selection based on spies, and support for bootstrapping. CONCLUSIONS: Experimental results on real datasets demonstrate that PLATO has improved performance compared to model-based approaches for two key steps in TRMN prediction, namely somatic variant calling from exome sequencing data and peptide identification from MS/MS data.


Assuntos
Imunoterapia , Neoplasias/terapia , Peptídeos/análise , Medicina de Precisão , Aprendizado de Máquina Supervisionado , Epitopos/imunologia , Epitopos/metabolismo , Humanos , Polimorfismo de Nucleotídeo Único , Espectrometria de Massas em Tandem , Sequenciamento Completo do Exoma
11.
PLoS One ; 15(12): e0241696, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-33326445

RESUMO

Automated quantification of behavior is increasingly prevalent in neuroscience research. Human judgments can influence machine-learning-based behavior classification at multiple steps in the process, for both supervised and unsupervised approaches. Such steps include the design of the algorithm for machine learning, the methods used for animal tracking, the choice of training images, and the benchmarking of classification outcomes. However, how these design choices contribute to the interpretation of automated behavioral classifications has not been extensively characterized. Here, we quantify the effects of experimenter choices on the outputs of automated classifiers of Drosophila social behaviors. Drosophila behaviors contain a considerable degree of variability, which was reflected in the confidence levels associated with both human and computer classifications. We found that a diversity of sex combinations and tracking features was important for robust performance of the automated classifiers. In particular, features concerning the relative position of flies contained useful information for training a machine-learning algorithm. These observations shed light on the importance of human influence on tracking algorithms, the selection of training images, and the quality of annotated sample images used to benchmark the performance of a classifier (the 'ground truth'). Evaluation of these factors is necessary for researchers to accurately interpret behavioral data quantified by a machine-learning algorithm and to further improve automated classifications.


Assuntos
Técnicas de Observação do Comportamento/métodos , Comportamento de Escolha , Drosophila/fisiologia , Projetos de Pesquisa/normas , Pesquisadores/psicologia , Aprendizado de Máquina Supervisionado , Animais , Técnicas de Observação do Comportamento/normas , Técnicas de Observação do Comportamento/estatística & dados numéricos , Interpretação Estatística de Dados , Feminino , Humanos , Masculino , Variações Dependentes do Observador , Pesquisadores/normas , Fatores Sexuais , Comportamento Social , Gravação em Vídeo/métodos , Gravação em Vídeo/normas , Gravação em Vídeo/estatística & dados numéricos
12.
Bioinformatics ; 36(Suppl_2): i895-i902, 2020 12 30.
Artigo em Inglês | MEDLINE | ID: mdl-33381838

RESUMO

MOTIVATION: The ability to develop robust machine-learning (ML) models is considered imperative to the adoption of ML techniques in biology and medicine fields. This challenge is particularly acute when data available for training is not independent and identically distributed (iid), in which case trained models are vulnerable to out-of-distribution generalization problems. Of particular interest are problems where data correspond to observations made on phylogenetically related samples (e.g. antibiotic resistance data). RESULTS: We introduce DendroNet, a new approach to train neural networks in the context of evolutionary data. DendroNet explicitly accounts for the relatedness of the training/testing data, while allowing the model to evolve along the branches of the phylogenetic tree, hence accommodating potential changes in the rules that relate genotypes to phenotypes. Using simulated data, we demonstrate that DendroNet produces models that can be significantly better than non-phylogenetically aware approaches. DendroNet also outperforms other approaches at two biological tasks of significant practical importance: antiobiotic resistance prediction in bacteria and trophic level prediction in fungi. AVAILABILITY AND IMPLEMENTATION: https://github.com/BlanchetteLab/DendroNet.


Assuntos
Aprendizado de Máquina , Redes Neurais de Computação , Filogenia , Aprendizado de Máquina Supervisionado
13.
Bioinformatics ; 36(Suppl_2): i831-i839, 2020 12 30.
Artigo em Inglês | MEDLINE | ID: mdl-33381851

RESUMO

MOTIVATION: Recently, various approaches for diagnosing and treating dementia have received significant attention, especially in identifying key genes that are crucial for dementia. If the mutations of such key genes could be tracked, it would be possible to predict the time of onset of dementia and significantly aid in developing drugs to treat dementia. However, gene finding involves tremendous cost, time and effort. To alleviate these problems, research on utilizing computational biology to decrease the search space of candidate genes is actively conducted.In this study, we propose a framework in which diseases, genes and single-nucleotide polymorphisms are represented by a layered network, and key genes are predicted by a machine learning algorithm. The algorithm utilizes a network-based semi-supervised learning model that can be applied to layered data structures. RESULTS: The proposed method was applied to a dataset extracted from public databases related to diseases and genes with data collected from 186 patients. A portion of key genes obtained using the proposed method was verified in silico through PubMed literature, and the remaining genes were left as possible candidate genes. AVAILABILITY AND IMPLEMENTATION: The code for the framework will be available at http://www.alphaminers.net/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.


Assuntos
Demência , Redes Reguladoras de Genes , Algoritmos , Biologia Computacional , Humanos , Aprendizado de Máquina Supervisionado
14.
IEEE Trans Med Imaging ; 39(8): 2615-2625, 2020 08.
Artigo em Inglês | MEDLINE | ID: mdl-33156775

RESUMO

Accurate and rapid diagnosis of COVID-19 suspected cases plays a crucial role in timely quarantine and medical treatment. Developing a deep learning-based model for automatic COVID-19 diagnosis on chest CT is helpful to counter the outbreak of SARS-CoV-2. A weakly-supervised deep learning framework was developed using 3D CT volumes for COVID-19 classification and lesion localization. For each patient, the lung region was segmented using a pre-trained UNet; then the segmented 3D lung region was fed into a 3D deep neural network to predict the probability of COVID-19 infectious; the COVID-19 lesions are localized by combining the activation regions in the classification network and the unsupervised connected components. 499 CT volumes were used for training and 131 CT volumes were used for testing. Our algorithm obtained 0.959 ROC AUC and 0.976 PR AUC. When using a probability threshold of 0.5 to classify COVID-positive and COVID-negative, the algorithm obtained an accuracy of 0.901, a positive predictive value of 0.840 and a very high negative predictive value of 0.982. The algorithm took only 1.93 seconds to process a single patient's CT volume using a dedicated GPU. Our weakly-supervised deep learning model can accurately predict the COVID-19 infectious probability and discover lesion regions in chest CT without the need for annotating the lesions for training. The easily-trained and high-performance deep learning algorithm provides a fast way to identify COVID-19 patients, which is beneficial to control the outbreak of SARS-CoV-2. The developed deep learning software is available at https://github.com/sydney0zq/covid-19-detection.


Assuntos
Infecções por Coronavirus/diagnóstico por imagem , Interpretação de Imagem Assistida por Computador/métodos , Pulmão/diagnóstico por imagem , Pneumonia Viral/diagnóstico por imagem , Aprendizado de Máquina Supervisionado , Tomografia Computadorizada por Raios X/métodos , Adolescente , Adulto , Idoso , Idoso de 80 Anos ou mais , Betacoronavirus , Criança , Infecções por Coronavirus/patologia , Feminino , Humanos , Pulmão/patologia , Masculino , Pessoa de Meia-Idade , Pandemias , Pneumonia Viral/patologia , Estudos Retrospectivos , Tórax/diagnóstico por imagem , Adulto Jovem
15.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 776-779, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018101

RESUMO

Drug Induced Parkinsonism (DIP) is the most common, debilitating movement disorder induced by antipsychotics. There is no tool available in clinical practice to effectively diagnose the symptoms at the onset of the disease. In this study, the variations in gait accelerometer data due to the intermittency of tremor at the initial stages is examined. These variations are used to train a logistic regression model to predict subjects with early-stage DIP. The logistic classifier predicts if a subject is a DIP or control with approximately 89% sensitivity and 96% specificity. This paper discusses the algorithm used to extract the features in gait data for training the classifier to predict DIP at the earliest.Clinical Relevance- Diagnosing the disease and the causative drug is vital as the physical health of a patient who is mentally unstable can deteriorate with prolonged usage of the drug. The proposed model helps clinicians to diagnose the disease at the onset of tremors with an accuracy of 93.58%.


Assuntos
Doença de Parkinson Secundária , Aprendizado de Máquina Supervisionado , Algoritmos , Humanos , Modelos Logísticos , Tremor
16.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1408-1411, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018253

RESUMO

Interstitial Cells of Cajal (ICC) are specialized pacemaker cells that generate and actively propagate electrophysiological events called slow waves. Slow waves regulate the motility of the gastrointestinal tract necessary for digesting food. Degradation in the ICC network structure has been qualitatively associated to several gastrointestinal motility disorders. ICC network structure can be obtained using confocal microscopy, but the current limitations in imaging and segmentation techniques have hindered an accurate representation of the networks. In this study, supervised machine learning techniques were applied to extract the ICC networks from 3D confocal microscopy images. The results showed that the Fast Random Forest classification method using Trainable WEKA Segmentation outperformed the Decision Table and Naïve Bayes classification methods in sensitivity, accuracy, and F-measure. Using the Fast Random Forest classifier, 12 gastric antrum tissue blocks were segmented and variations in ICC network thickness, density and process width were quantified for the myenteric plexus ICC network (the primary pacemakers). Our findings demonstrated regional variation in ICC network density and thickness along the circumferential and longitudinal axis of the mouse antrum. An inverse relationship was observed in the distal and proximal antrum for density (proximal: 9.8±4.0% vs distal: 7.6±4.6%) and thickness (proximal: 15±3 µm vs distal: 24±10 µm). Limited variation in ICC process width was observed throughout the antrum (5±1 µm).Clinical Relevance- Detailed quantification of regional ICC structural properties will provide insights into the relationship between ICC structure, slow waves and resultant gut motility. This will improve techniques for the diagnosis and treatment of functional GI motility disorders.


Assuntos
Células Intersticiais de Cajal , Marca-Passo Artificial , Animais , Teorema de Bayes , Camundongos , Antro Pilórico , Aprendizado de Máquina Supervisionado
17.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 2047-2050, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018407

RESUMO

Ultrasound images are potentially invaluable for imaging internal organs and diseases. However, due to noise, they are still difficult to interpret. We apply and compare supervised machine learning approaches to train a model of lesions using features with unsupervised machine learning approaches to segment and detect tumours in breasts. Two synthetic and one real datasets are used in our experiments. The best system performance is achieved by Frost Filter with Quick Shift.


Assuntos
Neoplasias da Mama , Mama , Mama/diagnóstico por imagem , Neoplasias da Mama/diagnóstico por imagem , Humanos , Aprendizado de Máquina Supervisionado , Ultrassonografia , Aprendizado de Máquina não Supervisionado
18.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 2683-2686, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018559

RESUMO

In this paper, photoplethysmogram (PPG) features are combined with supervised machine learning algorithms to estimate arterial blood pressure (ABP). Three algorithms for the estimation of cuffless ABP using PPG signals are compared. Since PPG signals are measured non-invasively, this method guarantees an individuals comfort while not omitting important ABP information. The proposed framework predicts the ABP values by processing PPG signals with semi-classical signal analysis (SCSA) method, extracting several categories of features, which reflect the PPG signal morphology variations. Then, regression algorithms are selected for the ABP estimation. The proposed method is evaluated based on a virtual dataset with more than four thousand subjects and MIMIC II database with over eight thousand subjects for model training and testing. Mean average error (MAE) and standard deviation (STD) are evaluated for different machine learning algorithms during the prediction and estimation process. Multiple linear regression (MLR) meets the AAMI standard in terms of estimation accuracy, which proves that the ABP can be accurately estimated in a nonintrusive fashion. Given the easy implementation of the ABP estimation method, we regard that the proposed features and machine learning algorithms for the cuffless estimation of the ABP can potentially provide the means for mobile healthcare equipment to monitor the ABP continuously.


Assuntos
Pressão Arterial , Aprendizado de Máquina , Algoritmos , Bases de Dados Factuais , Humanos , Aprendizado de Máquina Supervisionado
19.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 3297-3301, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018709

RESUMO

Intuitive control of prostheses relies on training algorithms to correlate biological recordings to motor intent. The quality of the training dataset is critical to run-time performance, but it is difficult to label hand kinematics accurately after the hand has been amputated. We quantified the accuracy and precision of labeling hand kinematics for two different training approaches: 1) assuming a participant is perfectly mimicking predetermined motions of a prosthesis (mimicked training), and 2) assuming a participant is perfectly mirroring their contralateral hand during identical bilateral movements (mirrored training). We compared these approaches in non-amputee individuals, using an infrared camera to track eight different joint angles of the hands in real-time. Aggregate data revealed that mimicked training does not account for biomechanical coupling or temporal changes in hand posture. Mirrored training was significantly more accurate and precise at labeling hand kinematics. However, when training a modified Kalman filter to estimate motor intent, the mimicked and mirrored training approaches were not significantly different. The results suggest that the mirrored training approach creates a more faithful but more complex dataset. Advanced algorithms, more capable of learning the complex mirrored training dataset, may yield better run-time prosthetic control.


Assuntos
Amputados , Membros Artificiais , Eletromiografia , Mãos , Humanos , Aprendizado de Máquina Supervisionado
20.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 5468-5471, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33019217

RESUMO

Hypotension is common in critically ill patients. Early prediction of hypotensive events in the Intensive Care Units (ICUs) allows clinicians to pre-emptively treat the patient and avoid possible organ damage. In this study, we investigate the performance of various supervised machine-learning classification algorithms along with a real-time labeling technique to predict acute hypotensive events in the ICU. It is shown that logistic regression and SVM yield a better combination of specificity, sensitivity and positive predictive value (PPV). Logistic regression is able to predict 85% of events within 30 minutes of their onset with 81% PPV and 96% specificity, while SVM results in 96% specificity, 83% sensitivity and 82% PPV. To further reduce the false alarm rate, we propose a high-level decision-making algorithm that filters isolated false positives identified by the machine-learning algorithms. By implementing this technique, 24% of the false alarms are filtered. This saves 21 hours of medical staff time through 2,560 hours of monitoring and significantly reduces the disturbance caused by alarming monitors.


Assuntos
Hipotensão , Aprendizado de Máquina Supervisionado , Algoritmos , Humanos , Hipotensão/diagnóstico , Modelos Logísticos , Aprendizado de Máquina
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...