RESUMEN
This work leverages a custom implementation of a deep neural network-based object detection algorithm to detect people and a set of assistive devices relevant to clinical environments. The object detections form the basis for the quantification of different ambulatory activities and related behaviors. Using features extracted from detected people and objects as input to machine learning models, we quantify how a person ambulates and the mode of ambulation being used.Clinical relevance- This system provides the data required for clinicians and hospitalized patients to work together in the creation, monitoring, and adjustment of ambulatory goals.
Asunto(s)
Aprendizaje Profundo , Humanos , Redes Neurales de la Computación , Algoritmos , Aprendizaje Automático , CaminataRESUMEN
Interictal epileptiform discharges (IEDs) are intermittent electrophysiological events that occur in patients with epilepsy between seizures. Automated detection of IEDs helps clinician to identify cortical irritations and relations to seizure recurrence. It also reduces the necessity of visual inspection by physicians interpreting the EEG. This paper presents a novel deep learning-based approach that combines one-dimensional local binary pattern symbolization method with a regularized multi-head one-dimensional convolutional neural network to learn unique morphological patterns from different EEG sub-bands for IED detection. Experimentation using the Temple University Events corpus scalp EEG data shows promising performance, e.g. F1-score of 87.18%.
Asunto(s)
Epilepsia , Humanos , Epilepsia/diagnóstico , Electroencefalografía/métodos , Redes Neurales de la Computación , Convulsiones/diagnóstico , CabezaRESUMEN
Stereo-electroencephalography is a minimally invasive technique for patients with refractory epilepsy pursuing surgery to reduce or control seizures. Electrodes are implanted based on pre-surgery evaluations and can collect deep brain activities for surgery decisions. This paper presents a methodology to analyze stereo-electroencephalography and assist clinicians by recommending the optimal surgical option and target areas for focal epilepsy patients. A seizure network (graph) model is proposed to characterize the spatial distribution and temporal changes of ictal events. The network nodes and edges correspond to specific epileptogenic regions and propagation/impact pathways (weighted by directed transfer function), respectively. We then employ a K-means clustering strategy to group nodes into a few clusters, from which the target surgical areas can be identified. Ten patients with different types of focal seizures were thoroughly analyzed. Promising consistency between results of our method's recommendations, clinical decisions and surgery outcomes were observed.
Asunto(s)
Epilepsias Parciales , Epilepsia , Humanos , Convulsiones/cirugía , Epilepsias Parciales/cirugía , Electroencefalografía/métodos , Electrodos ImplantadosRESUMEN
Approximately, one third of patients with epilepsy are refractory to medical therapy and thus can be at high risk of injuries and sudden unexpected death. A low-complexity electroencephalography (EEG)-based seizure monitoring algorithm is critically important for daily use, especially for wearable monitoring platforms. This paper presents a personalized EEG feature selection approach, which is the key to achieve a reliable seizure monitoring with a low computational cost. We advocate a two-step, personalized feature selection strategy to enhance monitoring performances for each patient. In the first step, linear discriminant analysis (LDA) is applied to find a few seizure-indicative channels. Then in the second step, least absolute shrinkage and selection operator (LASSO) method is employed to select a discriminative subset of both frequency and time domain features (spectral powers and entropy). A personalization strategy is further customized to find the best settings (number of channels and features) that yield the highest classification scores for each subject. Experimental results of analyzing 23 subjects in CHB-MIT database are quite promising. We have achieved an average F-1 score of 88% with excellent sensitivity and specificity using not more than 7 features extracted from at most 3 channels.
Asunto(s)
Electroencefalografía , Epilepsia , Algoritmos , Humanos , Convulsiones/diagnóstico , Sensibilidad y Especificidad , Procesamiento de Señales Asistido por ComputadorRESUMEN
Our work identifies subjects based on their height and the distance between their joints. Using a depth sensing camera, we obtained the position of a person's joints in 3D space relative to each other. The distances between adjacent joints and height of a subject's head are used to create a vector of eight features for an individual to use for identification. Using modified KNN, full and partial feature sets were used to identify subjects. Additionally, our classifier can be utilized to assess ambulation (such as walking's velocity and distance) of subject, when identified.
Asunto(s)
Cabeza , Caminata , HumanosRESUMEN
Electroencephalography (EEG) is a highly complex and non-stationary signal that reflects the cortical electric activity. Feature selection and analysis of EEG for various purposes, such as epileptic seizure detection, are highly in demand. This paper presents an approach to enhance classification performance by selecting discriminative features from a combined feature set consisting of frequency domain and entropy based features. For each EEG channel, nine different features are extracted, including six sub-band spectral powers and three entropy values (sample, permutation and spectral entropy). Features are then ranked across all channels using F-statistic values and selected for SVM classification. Experimentation using CHB-MIT dataset shows that our method achieves average sensitivity, specificity and F-1 score of 92.63%, 99.72% and 91.21%, respectively.
Asunto(s)
Electroencefalografía , Epilepsia , Entropía , Epilepsia/diagnóstico , Humanos , Convulsiones , Sensibilidad y EspecificidadRESUMEN
BACKGROUND: Identifying drug-target interaction is a key element in drug discovery. In silico prediction of drug-target interaction can speed up the process of identifying unknown interactions between drugs and target proteins. In recent studies, handcrafted features, similarity metrics and machine learning methods have been proposed for predicting drug-target interactions. However, these methods cannot fully learn the underlying relations between drugs and targets. In this paper, we propose anew framework for drug-target interaction prediction that learns latent features from drug-target interaction network. RESULTS: We present a framework to utilize the network topology and identify interacting and non-interacting drug-target pairs. We model the problem as a semi-bipartite graph in which we are able to use drug-drug and protein-protein similarity in a drug-protein network. We have then used a graph labeling method for vertex ordering in our graph embedding process. Finally, we employed deep neural network to learn the complex pattern of interacting pairs from embedded graphs. We show our approach is able to learn sophisticated drug-target topological features and outperforms other state-of-the-art approaches. CONCLUSIONS: The proposed learning model on semi-bipartite graph model, can integrate drug-drug and protein-protein similarities which are semantically different than drug-protein information in a drug-target interaction network. We show our model can determine interaction likelihood for each drug-target pair and outperform other heuristics.
Asunto(s)
Aprendizaje Profundo/normas , Desarrollo de Medicamentos/métodos , Algoritmos , HumanosRESUMEN
Patients suffering from neuro-degenerative diseases have difficulties with normal locomotion. This problem progresses with the course of disease. Gait assessment is an effective way of diagnosing the disease and quantifying its progress which can effectively prevent falls. In this paper, an automatic assessment method for analyzing gait data obtained by force sensor insoles is introduced. The gait analysis method is based on measuring the complexity of gait data after extracting independent sources. The results are promising an average accuracy of 94% for three different diseases.
Asunto(s)
Marcha , Accidentes por Caídas , Trastornos Neurológicos de la Marcha , Humanos , ZapatosRESUMEN
Electroencephalography (EEG) is an essential component in evaluation of epilepsy. However, full-channel EEG signals recorded from 18 to 23 electrodes on the scalp is neither wearable nor computationally effective. This paper presents advantages of both channel selection and nonlinear dimension reduction for accurate automatic seizure detection. We first extract the frequency domain features from the full-channel EEG signals. Then, we use a random forest algorithm to determine which channels contribute the most in discriminating seizure from non-seizure events. Next, we apply a non-linear dimension reduction technique to capture the relationship among data elements and map them in low dimension. Finally, we apply a KNN classifier technique to discriminate between seizure and non-seizure events. The experimental results for 23 patients show that our proposed approach outperforms other techniques in terms of accuracy. It also visualizes long-term data in 2D to enhance physician cognition of occurrence and disease progression.
Asunto(s)
Algoritmos , Diagnóstico por Computador/métodos , Electroencefalografía/métodos , Aprendizaje Automático , Reconocimiento de Normas Patrones Automatizadas/métodos , Convulsiones/diagnóstico , Interpretación Estadística de Datos , Humanos , Dinámicas no Lineales , Reproducibilidad de los Resultados , Tamaño de la Muestra , Sensibilidad y EspecificidadRESUMEN
Complex tissues such as brain and bone marrow are made up of multiple cell types. As the study of biological tissue structure progresses, the role of cell-type-specific research becomes increasingly important. Novel sequencing technology such as single-cell cytometry provides researchers access to valuable biological data. Applying machine-learning techniques to these high-throughput datasets provides deep insights into the cellular landscape of the tissue where those cells are a part of. In this paper, we propose the use of random-forest-based single-cell profiling, a new machine-learning-based technique, to profile different cell types of intricate tissues using single-cell cytometry data. Our technique utilizes random forests to capture cell marker dependences and model the cellular populations using the cell network concept. This cellular network helps us discover what cell types are in the tissue. Our experimental results on public-domain datasets indicate promising performance and accuracy of our technique in extracting cell populations of complex tissues.
Asunto(s)
Algoritmos , Biología Computacional/métodos , Perfilación de la Expresión Génica/métodos , Análisis de la Célula Individual/métodos , Animales , Células de la Médula Ósea/citología , Análisis por Conglomerados , Bases de Datos Factuales , Árboles de Decisión , Humanos , Aprendizaje Automático , RatonesRESUMEN
Persons who suffer from intractable seizures are safer if attended when seizures strike. Consequently, there is a need for wearable devices capable of detecting both convulsive and nonconvulsive seizures in everyday life. We have developed a three-stage seizure detection methodology based on 339 h of data (26 seizures) collected from 10 patients in an epilepsy monitoring unit. Our intent is to develop a wearable system that will detect seizures, alert a caregiver and record the time of seizure in an electronic diary for the patient's physician. Stage I looks for concurrent activity in heart rate, arterial oxygenation and electrodermal activity, all of which can be monitored by a wrist-worn device and which in combination produce a very low false positive rate. Stage II looks for a specific pattern created by these three biosignals. For the patients whose seizures cannot be detected by Stage II, Stage III detects seizures using limited-channel electroencephalogram (EEG) monitoring with at most three electrodes. Out of 10 patients, Stage I recognized all 11 seizures from seven patients, Stage II detected all 10 seizures from six patients and Stage III detected all of the seizures of two out of the three patients it analyzed.
Asunto(s)
Análisis de los Gases de la Sangre/métodos , Electroencefalografía/métodos , Determinación de la Frecuencia Cardíaca/métodos , Monitorización Neurofisiológica/métodos , Convulsiones/diagnóstico , Procesamiento de Señales Asistido por Computador , Adulto , Algoritmos , Análisis de los Gases de la Sangre/instrumentación , Encéfalo/fisiopatología , Electroencefalografía/instrumentación , Registros Electrónicos de Salud , Femenino , Respuesta Galvánica de la Piel/fisiología , Frecuencia Cardíaca/fisiología , Determinación de la Frecuencia Cardíaca/instrumentación , Humanos , Masculino , Persona de Mediana Edad , Monitoreo Ambulatorio/instrumentación , Monitoreo Ambulatorio/métodos , Monitorización Neurofisiológica/instrumentación , Oxígeno/sangre , Reconocimiento de Normas Patrones Automatizadas/métodos , Convulsiones/fisiopatología , Sensibilidad y Especificidad , Muñeca , Adulto JovenRESUMEN
Single-cell flow cytometry is a technology that measures the expression of several cellular markers simultaneously for a large number of cells. Identification of homogeneous cell populations, currently done by manual biaxial gating, is highly subjective and time consuming. To overcome the shortcomings of manual gating, automatic algorithms have been proposed. However, the performance of these methods highly depends on the shape of populations and the dimension of the data. In this paper, we have developed a time-efficient method that accurately identifies cellular populations. This is done based on a novel technique that estimates the initial number of clusters in high dimension and identifies the final clusters by merging clusters using their phenotypic signatures in low dimension. The proposed method is called SigClust. We have applied SigClust to four public datasets and compared it with five well known methods in the field. The results are promising and indicate higher performance and accuracy compared to similar approaches reported in literature.
Asunto(s)
Biomarcadores/análisis , Células , Biología Computacional/métodos , Citometría de Flujo/métodos , Fenotipo , Algoritmos , Animales , Células/clasificación , Células/citología , Análisis por Conglomerados , Bases de Datos Factuales , Humanos , Ratones , Programas InformáticosRESUMEN
Single-cell technologies like flow cytometry (FCM) provide valuable biological data for knowledge discovery in complex cellular systems like tissues and organs. FCM data contains multi-dimensional information about the cellular heterogeneity of intricate cellular systems. It is possible to correlate single-cell markers with phenotypic properties of those systems. Cell population identification and clinical outcome prediction from single-cell measurements are challenging problems in the field of single cell analysis. In this paper, we propose a hybrid learning approach to predict clinical outcome using samples' single-cell FCM data. The proposed method is efficient in both i) identification of cellular clusters in each sample's FCM data and ii) predict clinical outcome (healthy versus unhealthy) for each subject. Our method is robust and the experimental results indicate promising performance.
Asunto(s)
Biomarcadores/metabolismo , Células Cultivadas/metabolismo , Células Cultivadas/patología , Sistemas de Apoyo a Decisiones Clínicas , Diagnóstico por Computador/métodos , Citometría de Flujo/métodos , Análisis de Matrices Tisulares/métodos , Humanos , Evaluación de Resultado en la Atención de Salud/métodos , Reproducibilidad de los Resultados , Sensibilidad y EspecificidadRESUMEN
BACKGROUND: Measurement of various markers of single cells using flow cytometry has several biological applications. These applications include improving our understanding of behavior of cellular systems, identifying rare cell populations and personalized medication. A common critical issue in the existing methods is identification of the number of cellular populations which heavily affects the accuracy of results. Furthermore, anomaly detection is crucial in flow cytometry experiments. In this work, we propose a two-stage clustering technique for cell type identification in single subject flow cytometry data and extend it for anomaly detection among multiple subjects. RESULTS: Our experimentation on 42 flow cytometry datasets indicates high performance and accurate clustering (F-measure > 91 %) in identifying main cellular populations. Furthermore, our anomaly detection technique evaluated on Acute Myeloid Leukemia dataset results in only <2 % false positives.
Asunto(s)
Células/clasificación , Citometría de Flujo/métodos , Biomarcadores/análisis , Células/citología , Análisis por Conglomerados , Lógica Difusa , Humanos , Leucemia Mieloide Aguda/patología , Cadenas de MarkovRESUMEN
Pressure ulcers (PUs) are common among vulnerable patients such as elderly, bedridden and diabetic. PUs are very painful for patients and costly for hospitals and nursing homes. Assessment of sleeping parameters on at-risk limbs is critical for ulcer prevention. An effective assessment depends on automatic identification and tracking of at-risk limbs. An accurate limb identification can be used to analyze the pressure distribution and assess risk for each limb. In this paper, we propose a graph-based clustering approach to extract the body limbs from the pressure data collected by a commercial pressure map system. A robust signature-based technique is employed to automatically label each limb. Finally, an assessment technique is applied to evaluate the experienced stress by each limb over time. The experimental results indicate high performance and more than 94% average accuracy of the proposed approach.
Asunto(s)
Procesamiento Automatizado de Datos/métodos , Extremidades/fisiopatología , Úlcera por Presión/prevención & control , Sueño , Extremidades/irrigación sanguínea , Femenino , Humanos , MasculinoRESUMEN
In this work, EEG spectral features of different subjects are uniquely mapped into a 2D feature space. Such distinctive 2D features pave the way to identify subjects from their EEG spectral characteristics in an unsupervised manner without any prior knowledge. First, we extract power spectral density of EEG signals in different frequency bands. Next, we use t-distributed stochastic neighbor embedding to map data points from high dimensional space in a visible 2D space. Such non-linear data embedding method visualizes different subjects' data points as well-separated islands in two dimensions. We use a fuzzy c-means clustering technique to identify different subjects without any prior knowledge. The experimental results show that our proposed method efficiently (precision greater than 90%) discriminates 10 subjects using only the spectral information within their EEG signals.
Asunto(s)
Electroencefalografía , Aprendizaje Automático no Supervisado , Análisis por Conglomerados , HumanosRESUMEN
Pressure ulcers are high prevalence complications among bed-bound patients which are not only extremely painful and difficult to treat, but also impose a great burden in our health-care system. We target automatic posture detection which is a key module in all pressure ulcer monitoring platforms. Using data collected from a commercially-available pressure mapping system, we applied deep neural networks to automatically classify in-bed posture using features extracted from the histogram of gradient technique. High accuracy of up to 98% was achieved in classifying five different in-bed postures for more than 60,000 pressure images.
Asunto(s)
Lechos , Procesamiento de Imagen Asistido por Computador , Monitoreo Fisiológico/métodos , Postura , Úlcera por Presión/diagnóstico , Humanos , Monitoreo Fisiológico/instrumentación , Redes Neurales de la ComputaciónRESUMEN
3D visualization of breast tumors are shown to be effective by previous studies. In this paper, we introduce a new augmented reality application that can help doctors and surgeons to have a more accurate visualization of breast tumors; this system uses a marker-based image-processing technique to render a 3D model of the tumors on the body. The model can be created using a combination of breast 3D mammography by experts. We have tested the system using an Android smartphone and a head-mounted device. This proof of concept can be useful for oncologists to have a more effective screening, and surgeons to plan the surgery.
Asunto(s)
Neoplasias de la Mama/diagnóstico por imagen , Imagenología Tridimensional/métodos , Interfaz Usuario-Computador , Humanos , Imagenología Tridimensional/instrumentación , MamografíaRESUMEN
We propose an algorithm for separating arterial and venous-related signals using second-order statistics of red and infrared signals in a blind source separation technique. The separated arterial signal is used to compute accurate arterial oxygen saturation. We have also introduced an algorithm for extracting the respiratory pattern from the extracted venous-related signal. In addition to real-time monitoring, respiratory rate is also extracted. Our experimental results from multiple subjects show that the proposed separation technique is extremely useful for extracting accurate arterial oxygen saturation and respiratory rate. Specifically, the breathing rate is extracted with average root mean square deviation of 1.89 and average mean difference of -0.69.