RESUMEN
BACKGROUND AND OBJECTIVES: Ambiguity in diagnosing acute heart failure (AHF) leads to inappropriate treatment and potential side effects of rescue medications. To address this issue, this study aimed to use multimodality deep learning models combining chest X-ray (CXR) and electronic health record (EHR) data to screen patients with abnormal N-terminal pro-B-type natriuretic peptide (NT-proBNP) levels in emergency departments. METHODS: Using the open-source dataset MIMIC-IV and MIMICCXR, the study population consisted of 1,432 patients and 1,833 pairs of CXRs and EHRs. We processed the CXRs, extracted relevant features through lung-heart masks, and combined these with the vital signs at triage to predict corresponding NT-proBNP levels. RESULTS: The proposed method achieved a 0.89 area under the receiver operating characteristic curve by fusing predictions from single-modality models of heart size ratio, radiomic features, CXR, and the region of interest in the CXR. The model can accurately predict dyspneic patients with abnormal NT-proBNP concentrations, allowing physicians to reduce the risks associated with inappropriate treatment. CONCLUSION: The study provided new image features related to AHF and offered insights into future research directions. Overall, these models have great potential to improve patient outcomes and reduce risks in emergency departments.
RESUMEN
We investigate the dynamic characteristics of Covid-19 daily infection rates in Taiwan during its initial surge period, focusing on 79 districts within the seven largest cities. By employing computational techniques, we extract 18 features from each district-specific curve, transforming unstructured data into structured data. Our analysis reveals distinct patterns of asymmetric growth and decline among the curves. Utilizing theoretical information measurements such as conditional entropy and mutual information, we identify major factors of order-1 and order-2 that influence the peak value and curvature at the peak of the curves, crucial features characterizing the infection rates. Additionally, we examine the impact of geographic and socioeconomic factors on the curves by encoding each of the 79 districts with two binary characteristics: North-vs-South and Urban-vs-Suburban. Furthermore, leveraging this data-driven understanding at the district level, we explore the fine-scale behavioral effects on disease spread by examining the similarity among 96 age-group-specific curves within urban districts of Taipei and suburban districts of New Taipei City, which collectively represent a substantial portion of the nation's population. Our findings highlight the implicit influence of human behaviors related to living, traveling, and working on the dynamics of Covid-19 transmission in Taiwan.
Asunto(s)
COVID-19 , Humanos , Taiwán/epidemiología , COVID-19/epidemiología , Factores Socioeconómicos , Ciudades/epidemiología , EmpleoRESUMEN
The proliferation of wearable devices has allowed the collection of electrocardiogram (ECG) recordings daily to monitor heart rhythm and rate. For example, 24-hour Holter monitors, cardiac patches, and smartwatches are widely used for ECG gathering and application. An automatic atrial fibrillation (AF) detector is required for timely ECG interpretation. Deep learning models can accurately identify AFs if large amounts of annotated data are available for model training. However, it is impractical to request sufficient labels for ECG recordings for an individual patient to train a personalized model. We propose a Siamese-network-based approach for transfer learning to address this issue. A pre-trained Siamese convolutional neural network is created by comparing two labeled ECG segments from the same patient. We sampled 30-second ECG segments with a 50% overlapping window from the ECG recordings of patients in the MIT-BIH Atrial Fibrillation Database. Subsequently, we independently detected the occurrence of AF in each patient in the Long-Term AF Database. By fine-tuning the model with the 1, 3, 5, 7, 9, or 11 ECG segments ranging from 30 to 180 s, our method achieved macro-F1 scores of 96.84%, 96.91%, 96.97%, 97.02%, 97.05%, and 97.07%, respectively.
Asunto(s)
Fibrilación Atrial , Humanos , Fibrilación Atrial/diagnóstico , Redes Neurales de la Computación , Electrocardiografía/métodos , Aprendizaje Automático , AlgoritmosRESUMEN
For a large ensemble of complex systems, a Many-System Problem (MSP) studies how heterogeneity constrains and hides structural mechanisms, and how to uncover and reveal hidden major factors from homogeneous parts. All member systems in an MSP share common governing principles of dynamics, but differ in idiosyncratic characteristics. A typical dynamic is found underlying response features with respect to covariate features of quantitative or qualitative data types. Neither all-system-as-one-whole nor individual system-specific functional structures are assumed in such response-vs-covariate (Re-Co) dynamics. We developed a computational protocol for identifying various collections of major factors of various orders underlying Re-Co dynamics. We first demonstrate the immanent effects of heterogeneity among member systems, which constrain compositions of major factors and even hide essential ones. Secondly, we show that fuller collections of major factors are discovered by breaking heterogeneity into many homogeneous parts. This process further realizes Anderson's "More is Different" phenomenon. We employ the categorical nature of all features and develop a Categorical Exploratory Data Analysis (CEDA)-based major factor selection protocol. Information theoretical measurements-conditional mutual information and entropy-are heavily used in two selection criteria: C1-confirmable and C2-irreplaceable. All conditional entropies are evaluated through contingency tables with algorithmically computed reliability against the finite sample phenomenon. We study one artificially designed MSP and then two real collectives of Major League Baseball (MLB) pitching dynamics with 62 slider pitchers and 199 fastball pitchers, respectively. Finally, our MSP data analyzing techniques are applied to resolve a scientific issue related to the Rosenberg Self-Esteem Scale.
RESUMEN
BACKGROUND: The incidence of toxic diffuse goiter (Graves' disease) is higher in adolescents and preschool-aged children, with an upward trend. The incidence at 6-13 years of age is approximately 11.0%, and the incidences in men and women are 7.8% and 14.3%, respectively. AIM: To explore the clinical effect of methimazole combined with selenium in the treatment of toxic diffuse goiter (Graves' disease) in children and its effect on serum anti-thyroglobulin antibody (TRAb) and anti-thyroid peroxidase antibody (TPOAb). METHODS: A total of 103 children with Graves' disease treated in our hospital from January 2018 to June 2021 were divided into a traditional group and a combined group (15-20 mg methimazole orally given to children) and a combined group (50 µg selenium added on the basis of traditional treatment) according to different treatment methods to explore the therapeutic effects of the two methods and to observe the changes in thyroid volume and serum TRAb, TPOAb, free thyroxine (FT4) and inflammatory factor levels before and after treatment. The time taken for FT4 to return to normal was compared between the two groups. RESULTS: Treatment was significantly more effective in the combined group than in the traditional group (P < 0.05). The thyroid volumes of the children in the two groups was measured before and after treatment. Thyroid volume decreased significantly after treatment in both groups, and the thyroid volume was significantly lower in the combined group than in the traditional group (P < 0.05). The serum levels of interleukin-6 (IL-6), IL-8, TRAb, TPOAb and FT4 in the two groups were detected before and after treatment. The levels of IL-6, IL-8, TRAb, TPOAb and FT4 were significantly lower in the combined group than in the traditional group (P < 0.05). Follow-up of the children in the two groups showed that compared with the traditional group, it took less time for children in the combined group to return to the normal level (P < 0.05). CONCLUSION: Methimazole combined with selenium can effectively treat Graves' disease in children, reduce the expression of TRAb, TPOAb, FT4 and inflammatory factors, and improve the curative effect. Thus, the combined treatment warrants further clinical research.
RESUMEN
BACKGROUND: Hashimoto's thyroiditis (HT) is recognized as the most common autoimmune thyroid disease, often accompanied by the diffuse enlargement of thyroid with abundant blood flow and elevated level of thyroid autoantibodies. As obesity had a positive association with the risk of HT. Thus, this retrospective study was established to further explore the gender relationship between metabolic obesity phenotypes and the risk of Hashimoto's thyroiditis (HT). MATERIALS AND METHODS: Data for 3697 subjects aged ≥18 years were randomly collected from a Health check-up database from April to December 2019. Obesity was defined by general obesity (GO; body mass index [BMI] ≥28 kg/m2) and abdominal obesity (AO; waist circumstance, male ≥90 cm, female ≥85 cm). Metabolic unhealthy was defined as having at least one metabolic syndrome component and a homeostasis model assessment of insulin resistance ≥2.5. Obesity phenotypes were divided into three groups: GO, AO, compound obesity (GO+AO). After adjustment for potential confounding factors, multivariate logistic regression was used to assess the association between metabolic obesity phenotypes and risk of HT by sex and explore the correlation between different obesity patterns and HT risk by metabolic health status. RESULTS: The incidence of HT was 23.5% and significantly higher among females than males with different metabolic phenotypes (26.2% vs 20.5%, p<0.05), except metabolically healthy AO. Compared with non-obese subjects, different metabolic obesity phenotypes were independent risk factors among males (p<0.05). Among females, unhealthy metabolic status with GO (adjusted odds ratio [OR]=2.62) or AO (adjusted OR=2.87) and metabolically healthy non-GO (adjusted OR=2.05) were risk factors of HT (p<0.05). Increasing BMI categories and waist circumstance quartiles were positively correlated with HT risk (p for trend <0.05). Subgroup analyses indicated that GO+AO (adjusted OR=2.52) or only AO (adjusted OR=2.41) were risk factors for HT for those with unhealthy metabolic status. Moreover, GO+AO (adjusted OR=2.37) was an independent risk factor for HT under healthy metabolic status. CONCLUSION: GO+AO was associated with an increased risk of HT, identifying higher BMI/WC as a significant risk factor for HT. Males with unhealthy metabolic state or obesity and metabolically unhealthy females with obesity are high-risk group for HT. Additionally, only AO and GO+AO conferred increased risk of HT for individuals with metabolic abnormalities.
RESUMEN
We reformulate and reframe a series of increasingly complex parametric statistical topics into a framework of response-vs.-covariate (Re-Co) dynamics that is described without any explicit functional structures. Then we resolve these topics' data analysis tasks by discovering major factors underlying such Re-Co dynamics by only making use of data's categorical nature. The major factor selection protocol at the heart of Categorical Exploratory Data Analysis (CEDA) paradigm is illustrated and carried out by employing Shannon's conditional entropy (CE) and mutual information (I[Re;Co]) as the two key Information Theoretical measurements. Through the process of evaluating these two entropy-based measurements and resolving statistical tasks, we acquire several computational guidelines for carrying out the major factor selection protocol in a do-and-learn fashion. Specifically, practical guidelines are established for evaluating CE and I[Re;Co] in accordance with the criterion called [C1:confirmable]. Following the [C1:confirmable] criterion, we make no attempts on acquiring consistent estimations of these theoretical information measurements. All evaluations are carried out on a contingency table platform, upon which the practical guidelines also provide ways of lessening the effects of the curse of dimensionality. We explicitly carry out six examples of Re-Co dynamics, within each of which, several widely extended scenarios are also explored and discussed.
RESUMEN
Without assuming any functional or distributional structure, we select collections of major factors embedded within response-versus-covariate (Re-Co) dynamics via selection criteria [C1: confirmable] and [C2: irrepaceable], which are based on information theoretic measurements. The two criteria are constructed based on the computing paradigm called Categorical Exploratory Data Analysis (CEDA) and linked to Wiener-Granger causality. All the information theoretical measurements, including conditional mutual information and entropy, are evaluated through the contingency table platform, which primarily rests on the categorical nature within all involved features of any data types: quantitative or qualitative. Our selection task identifies one chief collection, together with several secondary collections of major factors of various orders underlying the targeted Re-Co dynamics. Each selected collection is checked with algorithmically computed reliability against the finite sample phenomenon, and so is each member's major factor individually. The developments of our selection protocol are illustrated in detail through two experimental examples: a simple one and a complex one. We then apply this protocol on two data sets pertaining to two somewhat related but distinct pitching dynamics of two pitch types: slider and fastball. In particular, we refer to a specific Major League Baseball (MLB) pitcher and we consider data of multiple seasons.
RESUMEN
We develop Categorical Exploratory Data Analysis (CEDA) with mimicking to explore and exhibit the complexity of information content that is contained within any data matrix: categorical, discrete, or continuous. Such complexity is shown through visible and explainable serial multiscale structural dependency with heterogeneity. CEDA is developed upon all features' categorical nature via histogram and it is guided by all features' associative patterns (order-2 dependence) in a mutual conditional entropy matrix. Higher-order structural dependency of k(≥3) features is exhibited through block patterns within heatmaps that are constructed by permuting contingency-kD-lattices of counts. By growing k, the resultant heatmap series contains global and large scales of structural dependency that constitute the data matrix's information content. When involving continuous features, the principal component analysis (PCA) extracts fine-scale information content from each block in the final heatmap. Our mimicking protocol coherently simulates this heatmap series by preserving global-to-fine scales structural dependency. Upon every step of mimicking process, each accepted simulated heatmap is subject to constraints with respect to all of the reliable observed categorical patterns. For reliability and robustness in sciences, CEDA with mimicking enhances data visualization by revealing deterministic and stochastic structures within each scale-specific structural dependency. For inferences in Machine Learning (ML) and Statistics, it clarifies, upon which scales, which covariate feature-groups have major-vs.-minor predictive powers on response features. For the social justice of Artificial Intelligence (AI) products, it checks whether a data matrix incompletely prescribes the targeted system.
RESUMEN
BACKGROUND: Brain metastasis velocity (BMV) predicts outcomes after initial distant brain failure (DBF) following upfront stereotactic radiosurgery (SRS). We developed an integrated model of clinical predictors and pre-SRS MRI-derived radiomic scores (R-scores) to identify high-BMV (BMV-H) patients upon initial identification of brain metastases (BMs). METHODS: In total, 256 patients with BMs treated with upfront SRS alone were retrospectively included. R-scores were built from 1246 radiomic features in 2 target volumes by using the Extreme Gradient Boosting algorithm to predict BMV-H groups, as defined by BMV at least 4 or leptomeningeal disease at first DBF. Two R-scores and 3 clinical predictors were integrated into a predictive clinico-radiomic (CR) model. RESULTS: The related R-scores showed signiï¬cant differences between BMV-H and low BMV (BMV-L), as defined by BMV less than 4 or no DBF (P < .001). Regression analysis identiï¬ed BMs number, perilesional edema, and extracranial progression as significant predictors. The CR model using these 5 predictors achieved a bootstrapping corrected C-index of 0.842 and 0.832 in the discovery and test sets, respectively. Overall survival (OS) after first DBF was signiï¬cantly different between the CR-predicted BMV-L and BMV-H groups (median OS: 26.7 vs 13.0 months, P = .016). Among patients with a diagnosis-specific graded prognostic assessment of 1.5-2 or 2.5-4, the median OS after initial SRS was 33.8 and 67.8 months for CR-predicted BMV-L, compared to 13.5 and 31.0 months for CR-predicted BMV-H (P < .001 and <.001), respectively. CONCLUSION: Our CR model provides a novel approach showing good performance to predict BMV and clinical outcomes.
RESUMEN
The objective was to apply a novel modification of a genome-wide, comparative cytogenetic technique (comparative genomic hybridization, comparative genomic hybridization (CGH)), to study species belonging to the myrmecophagous (ant/termite eating) mammalian orders/superorders (Pholidota, Tubulidentata, Carnivora, and Xenarthra), as a model for other applications in mammalian systematics and conservation biology. In this study, CGH was applied to high-quality metaphase spreads of pangolin (Pholidota), using probes of sloth and canine (Xenarthra and Carnivora, respectively) genomic DNA labeled with different fluorophores, thereby facilitating analysis of the visible color spectrum on pangolin karyotypes. Our results posited that pholidotes are closer to carnivores than to xenarthrans, which confirmed the current consensus that myrmecophagy in these mammalian lineages was more likely because of homoplasy (convergent evolution) than being an ancestral character. Since the modified CGH technique used is genome-wide, has chromosome-level resolution, and does not need full genome sequencing, it has considerable potential in systematics and other fields.
Asunto(s)
Hibridación Genómica Comparativa/veterinaria , Genoma , Mamíferos/clasificación , Filogenia , Animales , Clasificación/métodos , Hibridación Genómica Comparativa/métodos , Conservación de los Recursos Naturales , ADN/química , Tamaño del GenomaRESUMEN
The variability of cortical activity in response to repeated presentations of a stimulus has been an area of controversy in the ongoing debate regarding the evidence for fine temporal structure in nervous system activity. We present a new statistical technique for assessing the significance of observed variability in the neural spike counts with respect to a minimal Poisson hypothesis, which avoids the conventional but troubling assumption that the spiking process is identically distributed across trials. We apply the method to recordings of inferotemporal cortical neurons of primates presented with complex visual stimuli. On this data, the minimal Poisson hypothesis is rejected: the neuronal responses are too reliable to be fit by a typical firing-rate model, even allowing for sudden, time-varying, and trial-dependent rate changes after stimulus onset. The statistical evidence favors a tightly regulated stimulus response in these neurons, close to stimulus onset, although not further away.