VISUALIZING MISSING SURFACES IN COLONOSCOPY VIDEOS USING SHARED LATENT SPACE REPRESENTATIONS.
Ontology highlight
ABSTRACT:
SUBMITTER: Mathew S
PROVIDER: S-EPMC8504422 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundNowadays, patients with chronic diseases such as diabetes and hypertension have reached alarming numbers worldwide. These diseases increase the risk of developing acute complications and involve a substantial economic burden and demand for health resources. The widespread adoption of Electronic Health Records (EHRs) is opening great opportunities for supporting decision-making. Nevertheless, data extracted from EHRs are complex (heterogeneous, high-dimensional and usually noisy), hampering the knowledge extraction with conventional approaches.MethodsWe propose the use of the Denoising Autoencoder (DAE), a Machine Learning (ML) technique allowing to transform high-dimensional data into latent representations (LRs), thus addressing the main challenges with clinical data. We explore in this work how the combination of LRs with a visualization method can be used to map the patient data in a two-dimensional space, gaining knowledge about the distribution of patients with different chronic conditions. Furthermore, this representation can be also used to characterize the patient's health status evolution, which is of paramount importance in the clinical setting.ResultsTo obtain clinical LRs, we considered real-world data extracted from EHRs linked to the University Hospital of Fuenlabrada in Spain. Experimental results showed the great potential of DAEs to identify patients with clinical patterns linked to hypertension, diabetes and multimorbidity. The procedure allowed us to find patients with the same main chronic disease but different clinical characteristics. Thus, we identified two kinds of diabetic patients with differences in their drug therapy (insulin and non-insulin dependant), and also a group of women affected by hypertension and gestational diabetes. We also present a proof of concept for mapping the health status evolution of synthetic patients when considering the most significant diagnoses and drugs associated with chronic patients.ConclusionOur results highlighted the value of ML techniques to extract clinical knowledge, supporting the identification of patients with certain chronic conditions. Furthermore, the patient's health status progression on the two-dimensional space might be used as a tool for clinicians aiming to characterize health conditions and identify their more relevant clinical codes.
| S-EPMC9446539 | biostudies-literature
Project description:BackgroundUnsupervised compression algorithms applied to gene expression data extract latent or hidden signals representing technical and biological sources of variation. However, these algorithms require a user to select a biologically appropriate latent space dimensionality. In practice, most researchers fit a single algorithm and latent dimensionality. We sought to determine the extent by which selecting only one fit limits the biological features captured in the latent representations and, consequently, limits what can be discovered with subsequent analyses.ResultsWe compress gene expression data from three large datasets consisting of adult normal tissue, adult cancer tissue, and pediatric cancer tissue. We train many different models across a large range of latent space dimensionalities and observe various performance differences. We identify more curated pathway gene sets significantly associated with individual dimensions in denoising autoencoder and variational autoencoder models trained using an intermediate number of latent dimensionalities. Combining compressed features across algorithms and dimensionalities captures the most pathway-associated representations. When trained with different latent dimensionalities, models learn strongly associated and generalizable biological representations including sex, neuroblastoma MYCN amplification, and cell types. Stronger signals, such as tumor type, are best captured in models trained at lower dimensionalities, while more subtle signals such as pathway activity are best identified in models trained with more latent dimensionalities.ConclusionsThere is no single best latent dimensionality or compression algorithm for analyzing gene expression data. Instead, using features derived from different compression models across multiple latent space dimensionalities enhances biological representations.
| S-EPMC7212571 | biostudies-literature
Project description:In silico prediction of chemical ecotoxicity (HC50) represents an important complement to improve in vivo and in vitro toxicological assessment of manufactured chemicals. Recent application of machine learning models to predict chemical HC50 yields variable prediction performance that depends on effectively learning chemical representations from high-dimension data. To improve HC50 prediction performance, we developed an autoencoder model by learning latent space chemical embeddings. This novel approach achieved state-of-the-art prediction performance of HC50 with R2 of 0.668 ± 0.003 and mean absolute error (MAE) of 0.572 ± 0.001, and outperformed other dimension reduction methods including principal component analysis (PCA) (R2 = 0.601 ± 0.031 and MAE = 0.629 ± 0.005), kernel PCA (R2 = 0.631 ± 0.008 and MAE = 0.625 ± 0.006), and uniform manifold approximation and projection dimensionality reduction (R2 = 0.400 ± 0.008 and MAE = 0.801 ± 0.002). A simple linear layer with chemical embeddings learned from the autoencoder model performed better than random forest (R2 = 0.663 ± 0.007 and MAE = 0.591 ± 0.008), fully connected neural network (R2 = 0.614 ± 0.016 and MAE = 0.610 ± 0.008), least absolute shrinkage and selection operator (R2 = 0.617 ± 0.037 and MAE = 0.619 ± 0.007), and ridge regression (R2 = 0.638 ± 0.007 and MAE = 0.613 ± 0.005) using unlearned raw input features. Our results highlighted the usefulness of learning latent chemical representations, and our autoencoder model provides an alternative approach for robust HC50 prediction.
| S-EPMC9044254 | biostudies-literature
Project description:BACKGROUND:Scalable and accurate health outcome prediction using electronic health record (EHR) data has gained much attention in research recently. Previous machine learning models mostly ignore relations between different types of clinical data (ie, laboratory components, International Classification of Diseases codes, and medications). OBJECTIVE:This study aimed to model such relations and build predictive models using the EHR data from intensive care units. We developed innovative neural network models and compared them with the widely used logistic regression model and other state-of-the-art neural network models to predict the patient's mortality using their longitudinal EHR data. METHODS:We built a set of neural network models that we collectively called as long short-term memory (LSTM) outcome prediction using comprehensive feature relations or in short, CLOUT. Our CLOUT models use a correlational neural network model to identify a latent space representation between different types of discrete clinical features during a patient's encounter and integrate the latent representation into an LSTM-based predictive model framework. In addition, we designed an ablation experiment to identify risk factors from our CLOUT models. Using physicians' input as the gold standard, we compared the risk factors identified by both CLOUT and logistic regression models. RESULTS:Experiments on the Medical Information Mart for Intensive Care-III dataset (selected patient population: 7537) show that CLOUT (area under the receiver operating characteristic curve=0.89) has surpassed logistic regression (0.82) and other baseline NN models (<0.86). In addition, physicians' agreement with the CLOUT-derived risk factor rankings was statistically significantly higher than the agreement with the logistic regression model. CONCLUSIONS:Our results support the applicability of CLOUT for real-world clinical use in identifying patients at high risk of mortality.
| S-EPMC7136840 | biostudies-literature
Project description:Artificial neural networks have recently achieved many successes in solving sequential processing and planning tasks. Their success is often ascribed to the emergence of the task's low-dimensional latent structure in the network activity - i.e., in the learned neural representations. Here, we investigate the hypothesis that a means for generating representations with easily accessed low-dimensional latent structure, possibly reflecting an underlying semantic organization, is through learning to predict observations about the world. Specifically, we ask whether and when network mechanisms for sensory prediction coincide with those for extracting the underlying latent variables. Using a recurrent neural network model trained to predict a sequence of observations we show that network dynamics exhibit low-dimensional but nonlinearly transformed representations of sensory inputs that map the latent structure of the sensory environment. We quantify these results using nonlinear measures of intrinsic dimensionality and linear decodability of latent variables, and provide mathematical arguments for why such useful predictive representations emerge. We focus throughout on how our results can aid the analysis and interpretation of experimental data.
| S-EPMC7930246 | biostudies-literature
Project description:Perception of number and space are tightly intertwined. It has been proposed that this is due to 'cortical recycling', where numerosity processing takes over circuits originally processing space. Do such 'recycled' circuits retain their original functionality? Here, we investigate interactions between numerosity and motion direction, two functions that both localize to parietal cortex. We describe a new phenomenon in which visual motion direction adapts nonsymbolic numerosity perception, giving rise to a repulsive aftereffect: motion to the left adapts small numbers, leading to overestimation of numerosity, while motion to the right adapts large numbers, resulting in underestimation. The reference frame of this effect is spatiotopic. Together with the tuning properties of the effect this suggests that motion direction-numerosity cross-adaptation may occur in a homolog of area LIP. 'Cortical recycling' thus expands but does not obliterate the functions originally performed by the recycled circuit, allowing for shared computations across domains.
| S-EPMC4764558 | biostudies-literature
Project description:Spurious correlations allow flexible models to predict well during training but poorly on related test populations. Recent work has shown that models that satisfy particular independencies involving correlation-inducing nuisance variables have guarantees on their test performance. Enforcing such independencies requires nuisances to be observed during training. However, nuisances, such as demographics or image background labels, are often missing. Enforcing independence on just the observed data does not imply independence on the entire population. Here we derive MMD estimators used for invariance objectives under missing nuisances. On simulations and clinical data, optimizing through these estimates achieves test performance similar to using estimators that make use of the full data.
| S-EPMC10465015 | biostudies-literature
Project description:We developed a novel method based on the Fourier analysis of protein molecular surfaces to speed up the analysis of the vast structural data generated in the post-genomic era. This method computes the power spectrum of surfaces of the molecular electrostatic potential, whose three-dimensional coordinates have been either experimentally or theoretically determined. Thus we achieve a reduction of the initial three-dimensional information on the molecular surface to the one-dimensional information on pairs of points at a fixed scale apart. Consequently, the similarity search in our method is computationally less demanding and significantly faster than shape comparison methods. As proof of principle, we applied our method to a training set of viral proteins that are involved in major diseases such as Hepatitis C, Dengue fever, Yellow fever, Bovine viral diarrhea and West Nile fever. The training set contains proteins of four different protein families, as well as a mammalian representative enzyme. We found that the power spectrum successfully assigns a unique signature to each protein included in our training set, thus providing a direct probe of functional similarity among proteins. The results agree with established biological data from conventional structural biochemistry analyses.
| S-EPMC3807749 | biostudies-literature
Project description:Background and aimsUpper GI endoscopy is speculated to be an aerosol-generating procedure (AGP). Robust evidence exists for aerosol transmission of severe acute respiratory syndrome coronavirus 2. The quality of data available confirming aerosol generation during GI endoscopy is limited. We aimed to objectively demonstrate that GI endoscopy is an AGP and illustrate the mechanism by which the greatest risk for aerosolization of droplets during endoscopy may occur.MethodsAerosolized droplets generated during insertion and withdrawal of an endoscope and with passage of various tools through the endoscopic working channel using 2 experimental apparatuses modeling an upper GI tract (ie, a fluid-filled tube and a lamb esophagus) were qualitatively assessed by laser light scattering.ResultsInsertion and withdrawal of the upper endoscope into the upper GI tract models generated numerous aerosolized particles. A large number of brightly scattering particles were observed at the site of insertion and withdrawal of the endoscope. Passage of a cytology brush, biopsy forceps, and hemostatic clip through the working endoscope channel also generated aerosolized particles but in fewer numbers. There was no significant variation in quantity or brightness of droplets generated on testing different biopsy valve cap models or when suctioning fluid with an open versus closed biopsy valve cap. These results were reproducible over several trials.ConclusionsWe illustrate in an objective manner that upper GI endoscopy is an AGP. These findings may have implications for transmission of infectious airborne pathogens outside of severe acute respiratory syndrome coronavirus 2 and can help to inform guidance on appropriate personal protective equipment use and other measures for transmission risk mitigation during GI endoscopy.
| S-EPMC9596173 | biostudies-literature
Project description:We describe an inexpensive handheld fluorescence imager (low-magnification microscope), constructed from poly(vinyl chloride) pipe and other inexpensive components for use as a teaching tool to understand the principles of fluorescence detection. Optical filters are used to select the excitation and emission wavelengths and can be easily interchanged to accommodate different fluorescent samples. As a demonstration, we used the fluorescence imager to view lawsone-dyed fingerprints on paper, which fluoresce red when illuminated with green light. This emission can be seen by viewing the sample through the instrument by eye, or the fluorescence can be captured by a camera. The entire imager can be built for less than $300.
| S-EPMC2940251 | biostudies-literature