Query-based-learning mortality-related decoders for the developed island economy.
Ontology highlight
ABSTRACT:
SUBMITTER: Yeh CH
PROVIDER: S-EPMC8770507 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:IntroductionIn brain-computer interfaces (BCI) research, recording data is time-consuming and expensive, which limits access to big datasets. This may influence the BCI system performance as machine learning methods depend strongly on the training dataset size. Important questions arise: taking into account neuronal signal characteristics (e.g., non-stationarity), can we achieve higher decoding performance with more data to train decoders? What is the perspective for further improvement with time in the case of long-term BCI studies? In this study, we investigated the impact of long-term recordings on motor imagery decoding from two main perspectives: model requirements regarding dataset size and potential for patient adaptation.MethodsWe evaluated the multilinear model and two deep learning (DL) models on a long-term BCI & Tetraplegia (ClinicalTrials.gov identifier: NCT02550522) clinical trial dataset containing 43 sessions of ECoG recordings performed with a tetraplegic patient. In the experiment, a participant executed 3D virtual hand translation using motor imagery patterns. We designed multiple computational experiments in which training datasets were increased or translated to investigate the relationship between models' performance and different factors influencing recordings.ResultsOur results showed that DL decoders showed similar requirements regarding the dataset size compared to the multilinear model while demonstrating higher decoding performance. Moreover, high decoding performance was obtained with relatively small datasets recorded later in the experiment, suggesting motor imagery patterns improvement and patient adaptation during the long-term experiment. Finally, we proposed UMAP embeddings and local intrinsic dimensionality as a way to visualize the data and potentially evaluate data quality.DiscussionDL-based decoding is a prospective approach in BCI which may be efficiently applied with real-life dataset size. Patient-decoder co-adaptation is an important factor to consider in long-term clinical BCI.
| S-EPMC10061076 | biostudies-literature
Project description:In this study, we aimed to develop and validate a machine learning-based mortality prediction model for hospitalized heat-related illness patients. After 2393 hospitalized patients were extracted from a multicentered heat-related illness registry in Japan, subjects were divided into the training set for development (n = 1516, data from 2014, 2017-2019) and the test set (n = 877, data from 2020) for validation. Twenty-four variables including characteristics of patients, vital signs, and laboratory test data at hospital arrival were trained as predictor features for machine learning. The outcome was death during hospital stay. In validation, the developed machine learning models (logistic regression, support vector machine, random forest, XGBoost) demonstrated favorable performance for outcome prediction with significantly increased values of the area under the precision-recall curve (AUPR) of 0.415 [95% confidence interval (CI) 0.336-0.494], 0.395 [CI 0.318-0.472], 0.426 [CI 0.346-0.506], and 0.528 [CI 0.442-0.614], respectively, compared to that of the conventional acute physiology and chronic health evaluation (APACHE)-II score of 0.287 [CI 0.222-0.351] as a reference standard. The area under the receiver operating characteristic curve (AUROC) values were also high over 0.92 in all models, although there were no statistical differences compared to APACHE-II. This is the first demonstration of the potential of machine learning-based mortality prediction models for heat-related illnesses.
| S-EPMC8096946 | biostudies-literature
Project description:Methods of weakening and attenuating pathogens' abilities to infect and propagate in a host, thus allowing the natural immune system to more easily decimate invaders, have gained attention as alternatives to broad-spectrum targeting approaches. The following work describes a technique to identifying proteins involved in virulence by relying on latent information computationally gathered across biological repositories, applicable to both generic and specific virulence categories.A lightweight method for data integration is used, which links information regarding a protein via a path-based query graph. A method of weighting is then applied to query graphs that can serve as input to various statistical classification methods for discrimination, and the combined usage of both data integration and learning methods are tested against the problem of both generalized and specific virulence function prediction.This approach improves coverage of functional data over a protein. Moreover, while depending largely on noisy and potentially non-curated data from public sources, we find it outperforms other techniques to identification of general virulence factors and baseline remote homology detection methods for specific virulence categories.
| S-EPMC3560104 | biostudies-literature
Project description:A query optimizer attempts to predict a performance metric based on the amount of time elapsed. Theoretically, this would necessitate the creation of a significant overhead on the core engine to provide the necessary query optimizing statistics. Machine learning is increasingly being used to improve query performance by incorporating regression models. To predict the response time for a query, most query performance approaches rely on DBMS optimizing statistics and the cost estimation of each operator in the query execution plan, which also focuses on resource utilization (CPU, I/O). Modeling query features is thus a critical step in developing a robust query performance prediction model. In this paper, we propose a new framework based on query feature modeling and ensemble learning to predict query performance and use this framework as a query performance predictor simulator to optimize the query features that influence query performance. In query feature modeling, we propose five dimensions used to model query features. The query features dimensions are syntax, hardware, software, data architecture, and historical performance logs. These features will be based on developing training datasets for the performance prediction model that employs the ensemble learning model. As a result, ensemble learning leverages the query performance prediction problem to deal with missing values. Handling overfitting via regularization. The section on experimental work will go over how to use the proposed framework in experimental work. The training dataset in this paper is made up of performance data logs from various real-world environments. The outcomes were compared to show the difference between the actual and expected performance of the proposed prediction model. Empirical work shows the effectiveness of the proposed approach compared to related work.
| S-EPMC8523072 | biostudies-literature
Project description:BackgroundClimate change is expected to cause increases in heat-related mortality, especially among the elderly and very young. However, additional studies are needed to clarify the effects of heat on morbidity across all age groups and across a wider range of temperatures.ObjectivesWe aimed to estimate the impact of current and projected future temperatures on morbidity and mortality in Rhode Island.MethodsWe used Poisson regression models to estimate the association between daily maximum temperature and rates of all-cause and heat-related emergency department (ED) admissions and all-cause mortality. We then used downscaled Coupled Model Intercomparison Project Phase 5 (CMIP5; a standardized set of climate change model simulations) projections to estimate the excess morbidity and mortality that would be observed if this population were exposed to the temperatures projected for 2046-2053 and 2092-2099 under two representative concentration pathways (RCP): RCP 8.5 and 4.5.ResultsBetween 2005 and 2012, an increase in maximum daily temperature from 75 to 85°F was associated with 1.3% and 23.9% higher rates of all-cause and heat-related ED visits, respectively. The corresponding effect estimate for all-cause mortality from 1999 through 2011 was 4.0%. The association with all-cause ED admissions was strongest for those < 18 or ≥ 65 years of age, whereas the association with heat-related ED admissions was most pronounced among 18- to 64-year-olds. If this Rhode Island population were exposed to temperatures projected under RCP 8.5 for 2092-2099, we estimate that there would be 1.2% (range, 0.6-1.6%) and 24.4% (range, 6.9-41.8%) more all-cause and heat-related ED admissions, respectively, and 1.6% (range, 0.8-2.1%) more deaths annually between April and October.ConclusionsWith all other factors held constant, our findings suggest that the current population of Rhode Island would experience substantially higher morbidity and mortality if maximum daily temperatures increase further as projected.CitationKingsley SL, Eliot MN, Gold J, Vanderslice RR, Wellenius GA. 2016. Current and projected heat-related morbidity and mortality in Rhode Island. Environ Health Perspect 124:460-467; http://dx.doi.org/10.1289/ehp.1408826.
| S-EPMC4829994 | biostudies-literature
Project description:Encoding- and retrieval-related neural activity jointly determine mnemonic success. We ask whether electroencephalographic activity can reliably predict encoding and retrieval success on individual trials. Each of 98 participants performed a delayed recall task on 576 lists across 24 experimental sessions. Logistic regression classifiers trained on spectral features measured immediately preceding spoken recall of individual words successfully predict whether or not those words belonged to the target list. Classifiers trained on features measured during word encoding also reliably predict whether those words will be subsequently recalled and further predict the temporal and semantic organization of the recalled items. These findings link neural variability predictive of successful memory with item-to-context binding, a key cognitive process thought to underlie episodic memory function.
| S-EPMC10998865 | biostudies-literature
Project description:BackgroundWeb queries are now widely used for modeling, nowcasting and forecasting influenza-like illness (ILI). However, given that ILI attack rates vary significantly across ages, in terms of both magnitude and timing, little is known about whether the association between ILI morbidity and ILI-related queries is comparable across different age-groups. The present study aimed to investigate features of the association between ILI morbidity and ILI-related query volume from the perspective of age.MethodsSince Google Flu Trends is unavailable in Italy, Google Trends was used to identify entry terms that correlated highly with official ILI surveillance data. All-age and age-class-specific modeling was performed by means of linear models with generalized least-square estimation. Hold-out validation was used to quantify prediction accuracy. For purposes of comparison, predictions generated by exponential smoothing were computed.ResultsFive search terms showed high correlation coefficients of > .6. In comparison with exponential smoothing, the all-age query-based model correctly predicted the peak time and yielded a higher correlation coefficient with observed ILI morbidity (.978 vs. .929). However, query-based prediction of ILI morbidity was associated with a greater error. Age-class-specific query-based models varied significantly in terms of prediction accuracy. In the 0-4 and 25-44-year age-groups, these did well and outperformed exponential smoothing predictions; in the 15-24 and ≥ 65-year age-classes, however, the query-based models were inaccurate and highly overestimated peak height. In all but one age-class, peak timing predicted by the query-based models coincided with observed timing.ConclusionsThe accuracy of web query-based models in predicting ILI morbidity rates could differ among ages. Greater age-specific detail may be useful in flu query-based studies in order to account for age-specific features of the epidemiology of ILI.
| S-EPMC4444192 | biostudies-literature
Project description:For large-scale vision tasks in biomedical images, the labeled data is often limited to train effective deep models. Active learning is a common solution, where a query suggestion method selects representative unlabeled samples for annotation, and the new labels are used to improve the base model. However, most query suggestion models optimize their learnable parameters only on the limited labeled data and consequently become less effective for the more challenging unlabeled data. To tackle this, we propose a two-stream active query suggestion approach. In addition to the supervised feature extractor, we introduce an unsupervised one optimized on all raw images to capture diverse image features, which can later be improved by fine-tuning on new labels. As a use case, we build an end-to-end active learning framework with our query suggestion method for 3D synapse detection and mitochondria segmentation in connectomics. With the framework, we curate, to our best knowledge, the largest connectomics dataset with dense synapses and mitochondria annotation. On this new dataset, our method outperforms previous state-of-the-art methods by 3.1% for synapse and 3.8% for mitochondria in terms of region-of-interest proposal accuracy. We also apply our method to image classification, where it outperforms previous approaches on CIFAR-10 under the same limited annotation budget. The project page is https://zudi-lin.github.io/projects/#two_stream_active.
| S-EPMC7746018 | biostudies-literature
Project description:Investigators have examined whether heat mortality risk is increased in neighborhoods subject to the urban heat island (UHI) effect but have not identified degrees of difference in susceptibility to heat and cold between cool and hot areas, which we call acclimatization to the UHI.We developed methods to examine and quantify the degree of acclimatization to heat- and cold-related mortality in relation to UHI anomalies and applied these methods to London, UK.Case-crossover analyses were undertaken on 1993-2006 mortality data from London UHI decile groups defined by anomalies from the London average of modeled air temperature at a 1-km grid resolution. We estimated how UHI anomalies modified excess mortality on cold and hot days for London overall and displaced a fixed-shape temperature-mortality function ("shifted spline" model). We also compared the observed associations with those expected under no or full acclimatization to the UHI.The relative risk of death on hot versus normal days differed very little across UHI decile groups. A 1°C UHI anomaly multiplied the risk of heat death by 1.004 (95% CI: 0.950, 1.061) (interaction rate ratio) compared with the expected value of 1.070 (1.057, 1.082) if there were no acclimatization. The corresponding UHI interaction for cold was 1.020 (0.979, 1.063) versus 1.030 (1.026, 1.034) (actual versus expected under no acclimatization, respectively). Fitted splines for heat shifted little across UHI decile groups, again suggesting acclimatization. For cold, the splines shifted somewhat in the direction of no acclimatization, but did not exclude acclimatization.We have proposed two analytical methods for estimating the degree of acclimatization to the heat- and cold-related mortality burdens associated with UHIs. The results for London suggest relatively complete acclimatization to the UHI effect on summer heat-related mortality, but less clear evidence for cold-related mortality.Milojevic A, Armstrong BG, Gasparrini A, Bohnenstengel SI, Barratt B, Wilkinson P. 2016. Methods to estimate acclimatization to urban heat island effects on heat- and cold-related mortality. Environ Health Perspect 124:1016-1022;?http://dx.doi.org/10.1289/ehp.1510109.
| S-EPMC4937865 | biostudies-other
Project description:Researchers often seek to decode mental states from brain activity measured with functional MRI. Rigorous decoding requires the use of formal neural prediction models, which are likely to be the most accurate if they use the whole brain. However, the computational burden and lack of interpretability of off-the-shelf statistical methods can make whole-brain decoding challenging. Here, we propose a method to build whole-brain neural decoders that are both interpretable and computationally efficient. We extend the partial least squares algorithm to build a regularized model with variable selection that offers a unique "fit once, tune later" approach: users need to fit the model only once and can choose the best tuning parameters post hoc. We show in real data that our method scales well with increasing data size and yields interpretable predictors. The algorithm is publicly available in multiple languages in the hope that interpretable whole-brain predictors can be implemented more widely in neuroimaging research.
| S-EPMC9243546 | biostudies-literature