RESUMEN
Monitoring heart electrical activity is an effective way of detecting existing and developing conditions. This is usually performed as a non-invasive test using a network of up to 12 sensors (electrodes) on the chest and limbs to create an electrocardiogram (ECG). By visually observing these readings, experienced professionals can make accurate diagnoses and, if needed, request further testing. However, the training and experience needed to make accurate diagnoses are significant. This work explores the potential of recurrent neural networks for anomaly detection in ECG readings. Furthermore, to attain the best possible performance for these networks, training parameters, and network architectures are optimized using a modified version of the well-established particle swarm optimization algorithm. The performance of the optimized models is compared to models created by other contemporary optimizers, and the results show significant potential for real-world applications. Further analyses are carried out on the best-performing models to determine feature importance.
Asunto(s)
Algoritmos , Redes Neurales de la Computación , Electrocardiografía/métodosRESUMEN
BACKGROUND: Congenital Heart Disease represents the most frequent fetal malformation. The lack of prenatal identification of congenital heart defects can have adverse consequences for the neonate, while a correct prenatal diagnosis of specific cardiac anomalies improves neonatal care neurologic and surgery outcomes. Sonographers perform prenatal diagnosis manually during the first or second-trimester scan, but the reported detection rates are low. This project's primary objective is to develop an Intelligent Decision Support System that uses two-dimensional video files of cardiac sweeps obtained during the standard first-trimester fetal echocardiography (FE) to signal the presence/absence of previously learned key features. METHODS: The cross-sectional study will be divided into a training part of the machine learning approaches and the testing phase on previously unseen frames and eventually on actual video scans. Pregnant women in their 12-13 + 6 weeks of gestation admitted for routine first-trimester anomaly scan will be consecutively included in a two-year study, depending on the availability of the experienced sonographers in early fetal cardiac imaging involved in this research. The Data Science / IT department (DSIT) will process the key planes identified by the sonographers in the two- dimensional heart cine loop sweeps: four-chamber view, left and right ventricular outflow tracts, three vessels, and trachea view. The frames will be grouped into the classes representing the plane views, and then different state-of-the- art deep-learning (DL) pre-trained algorithms will be tested on the data set. The sonographers will validate all the intermediary findings at the frame level and the meaningfulness of the video labeling. DISCUSSION: FE is feasible and efficient during the first trimester. Still, the continuous training process is impaired by the lack of specialists or their limited availability. Therefore, in our study design, the sonographer benefits from a second opinion provided by the developed software, which may be very helpful, especially if a more experienced colleague is unavailable. In addition, the software may be implemented on the ultrasound device so that the process could take place during the live examination. TRIAL REGISTRATION: The study is registered under the name "Learning deep architectures for the Interpretation of Fetal Echocardiography (LIFE)", project number 408PED/2020, project code PN-III-P2-2.1-PED-2019. TRIAL REGISTRATION: ClinicalTrials.gov , unique identifying number NCT05090306, date of registration 30.10.2020.
Asunto(s)
Cardiopatías Congénitas , Ultrasonografía Prenatal , Recién Nacido , Embarazo , Femenino , Humanos , Primer Trimestre del Embarazo , Estudios Transversales , Ultrasonografía Prenatal/métodos , Cardiopatías Congénitas/diagnóstico por imagen , Ecocardiografía , Corazón Fetal/diagnóstico por imagenRESUMEN
The study presented here considers the analysis of a medical dataset for the identification of the stage of onset of COVID-19 coronavirus. These data, presented in previous work by the authors, have been subjected to extensive analysis and additional calculations. The data were obtained by analyzing blood samples of infected individuals at 1, 3, and 6 months after COVID-19 infection. Results were obtained from FTIR spectrometry experiments. The results indicate a very effective ability to identify the different states of infection, and between 1 and 6 months even perfect. Specific spectrometry wavelength ranges can also be distinguished as medical markers.
RESUMEN
There are many machine learning approaches available and commonly used today, however, the extreme learning machine is appraised as one of the fastest and, additionally, relatively efficient models. Its main benefit is that it is very fast, which makes it suitable for integration within products that require models taking rapid decisions. Nevertheless, despite their large potential, they have not yet been exploited enough, according to the recent literature. Extreme learning machines still face several challenges that need to be addressed. The most significant downside is that the performance of the model heavily depends on the allocated weights and biases within the hidden layer. Finding its appropriate values for practical tasks represents an NP-hard continuous optimization challenge. Research proposed in this study focuses on determining optimal or near optimal weights and biases in the hidden layer for specific tasks. To address this task, a multi-swarm hybrid optimization approach has been proposed, based on three swarm intelligence meta-heuristics, namely the artificial bee colony, the firefly algorithm and the sine-cosine algorithm. The proposed method has been thoroughly validated on seven well-known classification benchmark datasets, and obtained results are compared to other already existing similar cutting-edge approaches from the recent literature. The simulation results point out that the suggested multi-swarm technique is capable to obtain better generalization performance than the rest of the approaches included in the comparative analysis in terms of accuracy, precision, recall, and f1-score indicators. Moreover, to prove that combining two algorithms is not as effective as joining three approaches, additional hybrids generated by pairing, each, two methods employed in the proposed multi-swarm approach, were also implemented and validated against four challenging datasets. The findings from these experiments also prove superior performance of the proposed multi-swarm algorithm. Sample code from devised ELM tuning framework is available on the GitHub.
Asunto(s)
Algoritmos , Aprendizaje Automático , Simulación por Computador , HeurísticaRESUMEN
We live in a period when smart devices gather a large amount of data from a variety of sensors and it is often the case that decisions are taken based on them in a more or less autonomous manner. Still, many of the inputs do not prove to be essential in the decision-making process; hence, it is of utmost importance to find the means of eliminating the noise and concentrating on the most influential attributes. In this sense, we put forward a method based on the swarm intelligence paradigm for extracting the most important features from several datasets. The thematic of this paper is a novel implementation of an algorithm from the swarm intelligence branch of the machine learning domain for improving feature selection. The combination of machine learning with the metaheuristic approaches has recently created a new branch of artificial intelligence called learnheuristics. This approach benefits both from the capability of feature selection to find the solutions that most impact on accuracy and performance, as well as the well known characteristic of swarm intelligence algorithms to efficiently comb through a large search space of solutions. The latter is used as a wrapper method in feature selection and the improvements are significant. In this paper, a modified version of the salp swarm algorithm for feature selection is proposed. This solution is verified by 21 datasets with the classification model of K-nearest neighborhoods. Furthermore, the performance of the algorithm is compared to the best algorithms with the same test setup resulting in better number of features and classification accuracy for the proposed solution. Therefore, the proposed method tackles feature selection and demonstrates its success with many benchmark datasets.
Asunto(s)
Algoritmos , Inteligencia Artificial , Aprendizaje AutomáticoRESUMEN
Medical data are often tricky to get mined for patterns even by the generally demonstrated successful modern methodologies of deep learning. This paper puts forward such a medical classification task, where patient registers of two of the categories are sometimes hard to be distinguished because of samples showing characteristics of both labels in turn in several repetitions of the screening procedure. To this end, the current research appoints a pre-processing clustering step (through self-organizing maps) to group the data based on shape similarity and relabel it accordingly. Subsequently, a deep learning approach (a tandem of convolutional and long short-term memory networks) performs the training classification phase on the 'cleaned' samples. The dual methodology was applied for the computational diagnosis of electrooculography tests within spino-cerebral ataxia of type 2. The accuracy obtained for the discrimination into three classes was of 78.24%. The improvement that this duo brings over the deep learner alone does not stem from significantly higher accuracy results when the performance is considered for all classes. The major finding of this combination is that half of the presymptomatic cases were correctly found, in opposition to the single deep model, where this category was sacrificed by the learner in favor of a good accuracy overall. A high accuracy in general is desirable for any medical task, however the correct identification of cases before the symptoms become evident is more important.
Asunto(s)
Aprendizaje Profundo , Electrooculografía , Aprendizaje Automático no Supervisado , Algoritmos , Análisis por Conglomerados , Bases de Datos como Asunto , Humanos , Redes Neurales de la Computación , Estimulación Luminosa , Movimientos Sacádicos/fisiología , Factores de TiempoRESUMEN
Application of deep learning (DL) to the field of healthcare is aiding clinicians to make an accurate diagnosis. DL provides reliable results for image processing and sensor interpretation problems most of the time. However, model uncertainty should also be thoroughly quantified. This paper therefore addresses the employment of Monte Carlo dropout within the DL structure to automatically discriminate presymptomatic signs of spinocerebellar ataxia type 2 in saccadic samples obtained from electrooculograms. The current work goes beyond the common incorporation of this special type of dropout into deep neural networks and uses the uncertainty derived from the validation samples to construct a decision tree at the register level of the patients. The decision tree built from the uncertainty estimates obtained a classification accuracy of 81.18% in automatically discriminating control, presymptomatic and sick classes. This paper proposes a novel method to address both uncertainty quantification and explainability to develop reliable healthcare support systems.
Asunto(s)
Electrooculografía , Método de Montecarlo , Redes Neurales de la Computación , Ataxias Espinocerebelosas , Árboles de Decisión , Humanos , Procesamiento de Imagen Asistido por Computador , Ataxias Espinocerebelosas/diagnósticoRESUMEN
Current histopathological diagnosis involves human expert interpretation of stained images for diagnosis. This process is prone to inter-observer variability, often leading to low concordance rates amongst pathologists across many types of tissues. Further, since structural features are mostly just defined for epithelial alterations during tumor progression, the use of associated stromal changes is limited. Here we sought to examine whether digital analysis of commonly used hematoxylin and eosin-stained images could provide precise and quantitative metrics of disease from both epithelial and stromal cells. We developed a convolutional neural network approach to identify epithelial breast cells from their microenvironment. Second, we analyzed the microenvironment to further observe different constituent cells using unsupervised clustering. Finally, we categorized breast cancer by the combined effects of stromal and epithelial inertia. Together, the work provides insight and evidence of cancer association for interpretable features from deep learning methods that provide new opportunities for comprehensive analysis of standard pathology images.
RESUMEN
Stock price prediction is a popular yet challenging task and deep learning provides the means to conduct the mining for the different patterns that trigger its dynamic movement. In this paper, the task is to predict the close price for 25 companies enlisted at the Bucharest Stock Exchange, from a novel data set introduced herein. Towards this scope, two traditional deep learning architectures are designed in comparison: a long short-memory network and a temporal convolutional neural model. Based on their predictions, a trading strategy, whose decision to buy or sell depends on two different thresholds, is proposed. A hill climbing approach selects the optimal values for these parameters. The prediction of the two deep learning representatives used in the subsequent trading strategy leads to distinct facets of gain.
Asunto(s)
Comercio , Simulación por Computador , Aprendizaje Profundo , Heurística , Inversiones en Salud/economía , Algoritmos , Redes Neurales de la Computación , Reproducibilidad de los Resultados , Rumanía , Factores de TiempoRESUMEN
The current research study is concerned with the automated differentiation between histopathological slides from colon tissues with respect to four classes (healthy tissue and cancerous of grades 1, 2 or 3) through an optimized ensemble of predictors. Six distinct classifiers with prediction accuracies ranging from 87% to 95% are considered for the task. The proposed method of combining them takes into account the probabilities of the individual classifiers for each sample to be assigned to any of the four classes, optimizes weights for each technique by differential evolution and attains an accuracy that is significantly better than the individual results. Moreover, a degree of confidence is defined that would allow the pathologists to separate the data into two distinct sets, one that is correctly classified with a high level of confidence and the rest that would need their further attention. The tandem is also validated on other benchmark data sets. The proposed methodology proves to be efficient in improving the classification accuracy of each algorithm taken separately and performs reasonably well on other data sets, even with default weights. In addition, by establishing a degree of confidence the method becomes more viable for use by actual practitioners.
Asunto(s)
Neoplasias del Colon/diagnóstico por imagen , Neoplasias del Colon/diagnóstico , Diagnóstico por Computador/métodos , Algoritmos , Colon/diagnóstico por imagen , Colon/patología , Neoplasias del Colon/clasificación , Diagnóstico por Computador/estadística & datos numéricos , Diagnóstico Precoz , Técnicas Histológicas , Humanos , Interpretación de Imagen Asistida por Computador/métodos , Interpretación de Imagen Asistida por Computador/estadística & datos numéricos , Aprendizaje Automático , Clasificación del Tumor/métodos , Clasificación del Tumor/estadística & datos numéricosRESUMEN
We analyzed 82 patients with colorectal cancer (CRC) [75 patients with mucinous adenocarcinoma (ADK) and seven patients with "signet ring cell" ADK] using multi-cytokeratin (CK) AE1∕AE3 immunohistochemical assay. In order to determine the mucinous nature of some of the lymph node metastases of the mucinous colorectal ADKs studied, Periodic Acid Schiff-Alcian Blue (PAS-AB) histochemical staining was used. The counting results were systematized in the following ranges: 0 budding areas; between 1-4 budding areas; between 5-9 budding areas; and =10 tumor budding (TB) areas. The statistical analysis was performed using the Student's t-test. More than half of the cases of mucinous ADK revealed an increased intensity of TB, whereas in the case of "signet ring cell" ADK, an average intensity of this phenomenon. Mucinous ADKs, which were pT3 staged, showed an increased intensity of TB, and those in pT2 stage demonstrated, in the vast majority of cases, the absence of TB. There was a predominance of TB intensity in the absence of vascular-lymphatic invasion. Our study shows the existence of a concordance between tumor progression, the histological type of CRC, vascular-lymphatic invasion and the phenomenon of TB.
Asunto(s)
Neoplasias Colorrectales/inmunología , Inmunohistoquímica/métodos , Neoplasias Colorrectales/patología , Femenino , Humanos , Masculino , PronósticoRESUMEN
This paper presents an automatic tool capable to learn from a patients data set with 24 medical indicators characterizing each sample and to subsequently use the acquired knowledge to differentiate between five degrees of liver fibrosis. The indicators represent clinical observations and the liver stiffness provided by the new, non-invasive procedure of Fibroscan. The proposed technique combines a hill climbing algorithm that selects subsets of important attributes for an accurate classification and a core represented by a cooperative coevolutionary classifier that builds rules for establishing the diagnosis for every new patient. The results of the novel method proved to be superior as compared to the ones obtained by other important classification techniques from the literature. Additionally, the proposed methodology extracts a set of the most meaningful attributes from the available ones.
Asunto(s)
Algoritmos , Diagnóstico por Computador/métodos , Cirrosis Hepática/diagnóstico , Diseño de Software , HumanosRESUMEN
OBJECTIVE: Hepatic fibrosis, the principal pointer to the development of a liver disease within chronic hepatitis C, can be measured through several stages. The correct evaluation of its degree, based on recent different non-invasive procedures, is of current major concern. The latest methodology for assessing it is the Fibroscan and the effect of its employment is impressive. However, the complex interaction between its stiffness indicator and the other biochemical and clinical examinations towards a respective degree of liver fibrosis is hard to be manually discovered. In this respect, the novel, well-performing evolutionary-powered support vector machines are proposed towards an automated learning of the relationship between medical attributes and fibrosis levels. The traditional support vector machines have been an often choice for addressing hepatic fibrosis, while the evolutionary option has been validated on many real-world tasks and proven flexibility and good performance. METHODS AND MATERIALS: The evolutionary approach is simple and direct, resulting from the hybridization of the learning component within support vector machines and the optimization engine of evolutionary algorithms. It discovers the optimal coefficients of surfaces that separate instances of distinct classes. Apart from a detached manner of establishing the fibrosis degree for new cases, a resulting formula also offers insight upon the correspondence between the medical factors and the respective outcome. What is more, a feature selection genetic algorithm can be further embedded into the method structure, in order to dynamically concentrate search only on the most relevant attributes. The data set refers 722 patients with chronic hepatitis C infection and 24 indicators. The five possible degrees of fibrosis range from F0 (no fibrosis) to F4 (cirrhosis). RESULTS: Since the standard support vector machines are among the most frequently used methods in recent artificial intelligence studies for hepatic fibrosis staging, the evolutionary method is viewed in comparison to the traditional one. The multifaceted discrimination into all five degrees of fibrosis and the slightly less difficult common separation into solely three related stages are both investigated. The resulting performance proves the superiority over the standard support vector classification and the attained formula is helpful in providing an immediate calculation of the liver stage for new cases, while establishing the presence/absence and comprehending the weight of each medical factor with respect to a certain fibrosis level. CONCLUSION: The use of the evolutionary technique for fibrosis degree prediction triggers simplicity and offers a direct expression of the influence of dynamically selected indicators on the corresponding stage. Perhaps most importantly, it significantly surpasses the classical support vector machines, which are both widely used and technically sound. All these therefore confirm the promise of the new methodology towards a dependable support within the medical decision-making.