Browse
Submit Data
Databases
API
Help

Dataset Information

24 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Contrastive learning improves critical event prediction in COVID-19 patients.

ABSTRACT: Deep learning (DL) models typically require large-scale, balanced training data to be robust, generalizable, and effective in the context of healthcare. This has been a major issue for developing DL models for the coronavirus disease 2019 (COVID-19) pandemic, where data are highly class imbalanced. Conventional approaches in DL use cross-entropy loss (CEL), which often suffers from poor margin classification. We show that contrastive loss (CL) improves the performance of CEL, especially in imbalanced electronic health records (EHR) data for COVID-19 analyses. We use a diverse EHR dataset to predict three outcomes: mortality, intubation, and intensive care unit (ICU) transfer in hospitalized COVID-19 patients over multiple time windows. To compare the performance of CEL and CL, models are tested on the full dataset and a restricted dataset. CL models consistently outperform CEL models, with differences ranging from 0.04 to 0.15 for area under the precision and recall curve (AUPRC) and 0.05 to 0.1 for area under the receiver-operating characteristic curve (AUROC).

SUBMITTER: Wanyan T

PROVIDER: S-EPMC8542449 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Proteomic blood profiling in mild, severe and critical COVID-19 patients

Project description: Not available

| S-BSST416 | biostudies-other

Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19.

Project description:Machine learning (ML) models require large datasets which may be siloed across different healthcare institutions. Using federated learning, a ML technique that avoids locally aggregating raw clinical data across multiple institutions, we predict mortality within seven days in hospitalized COVID-19 patients. Patient data was collected from Electronic Health Records (EHRs) from five hospitals within the Mount Sinai Health System (MSHS). Logistic Regression with L1 regularization (LASSO) and Multilayer Perceptron (MLP) models were trained using local data at each site, a pooled model with combined data from all five sites, and a federated model that only shared parameters with a central aggregator. Both the federated LASSO and federated MLP models performed better than their local model counterparts at four hospitals. The federated MLP model also outperformed the federated LASSO model at all hospitals. Federated learning shows promise in COVID-19 EHR data to develop robust predictive models without compromising patient privacy.

| S-EPMC7430624 | biostudies-literature

Contrastive learning and subtyping of post-COVID-19 lung computed tomography images.

Project description:Patients who recovered from the novel coronavirus disease 2019 (COVID-19) may experience a range of long-term symptoms. Since the lung is the most common site of the infection, pulmonary sequelae may present persistently in COVID-19 survivors. To better understand the symptoms associated with impaired lung function in patients with post-COVID-19, we aimed to build a deep learning model which conducts two tasks: to differentiate post-COVID-19 from healthy subjects and to identify post-COVID-19 subtypes, based on the latent representations of lung computed tomography (CT) scans. CT scans of 140 post-COVID-19 subjects and 105 healthy controls were analyzed. A novel contrastive learning model was developed by introducing a lung volume transform to learn latent features of disease phenotypes from CT scans at inspiration and expiration of the same subjects. The model achieved 90% accuracy for the differentiation of the post-COVID-19 subjects from the healthy controls. Two clusters (C1 and C2) with distinct characteristics were identified among the post-COVID-19 subjects. C1 exhibited increased air-trapping caused by small airways disease (4.10%, p = 0.008) and diffusing capacity for carbon monoxide %predicted (DLCO %predicted, 101.95%, p < 0.001), while C2 had decreased lung volume (4.40L, p < 0.001) and increased ground glass opacity (GGO%, 15.85%, p < 0.001). The contrastive learning model is able to capture the latent features of two post-COVID-19 subtypes characterized by air-trapping due to small airways disease and airway-associated interstitial fibrotic-like patterns, respectively. The discovery of post-COVID-19 subtypes suggests the need for different managements and treatments of long-term sequelae of patients with post-COVID-19.

| S-EPMC9593072 | biostudies-literature

Virtual Learning Improves Attendance for Critical Care Education During the COVID-19 Pandemic.

Project description:The COVID-19 pandemic has pushed medical educators and learners to adapt to virtual learning (VL) in an expedited manner. The effect of VL for critical care education has not yet been evaluated. In a quantitative analysis of survey data and attendance records, we sought to determine the association of VL with conference attendance and work-life balance. Attending physicians, fellows, and advanced practice providers (APP) at a pediatric critical care department at a quaternary children's hospital participated in the study. Attendance records were obtained before and after the adaption of a VL platform. In addition, an electronic, anonymous survey to evaluate current satisfaction and the strengths and weaknesses of VL as well as its impact on work-life balance was administered. In total, 31 learners (17 attending physicians, 13 fellows, and 1 APP) completed the survey. A total of 83.9% (26/31) of participants were satisfied, and 77.4% (24/31) found VL to be similar or more engaging than non-VL. However, 6.5% (2/31) of learners reported difficulty in using the new platform, 87% (27/31) of participants supported VL as an effective learning tool, and 83.3% (25/30) reported a positive impact on work-life balance. Additionally, median monthly conference attendance increased significantly from 85 to 114 attendees per month ( p < 0.05). Our results suggest that a virtual model has advantages for overall attendance and work-life balance. We anticipate VL will continue to be an integral part of medical education. Future work evaluating the impact of VL on interdepartmental and interinstitutional collaborations is needed.

| S-EPMC10631843 | biostudies-literature

Molecular property prediction by semantic-invariant contrastive learning.

Project description:MotivationContrastive learning has been widely used as pretext tasks for self-supervised pre-trained molecular representation learning models in AI-aided drug design and discovery. However, existing methods that generate molecular views by noise-adding operations for contrastive learning may face the semantic inconsistency problem, which leads to false positive pairs and consequently poor prediction performance.ResultsTo address this problem, in this article, we first propose a semantic-invariant view generation method by properly breaking molecular graphs into fragment pairs. Then, we develop a Fragment-based Semantic-Invariant Contrastive Learning (FraSICL) model based on this view generation method for molecular property prediction. The FraSICL model consists of two branches to generate representations of views for contrastive learning, meanwhile a multi-view fusion and an auxiliary similarity loss are introduced to make better use of the information contained in different fragment-pair views. Extensive experiments on various benchmark datasets show that with the least number of pre-training samples, FraSICL can achieve state-of-the-art performance, compared with major existing counterpart models.Availability and implementationThe code is publicly available at https://github.com/ZiqiaoZhang/FraSICL.

| S-EPMC10397537 | biostudies-literature

Machine learning-based mortality prediction models for smoker COVID-19 patients.

Project description:BackgroundThe large number of SARS-Cov-2 cases during the COVID-19 global pandemic has burdened healthcare systems and created a shortage of resources and services. In recent years, mortality prediction models have shown a potential in alleviating this issue; however, these models are susceptible to biases in specific subpopulations with different risks of mortality, such as patients with prior history of smoking. The current study aims to develop a machine learning-based mortality prediction model for COVID-19 patients that have a history of smoking in the Iranian population.MethodsA retrospective study was conducted across six medical centers between 18 and 2020 and 15 March 2022, comprised of 678 CT scans and laboratory-confirmed COVID-19 patients that had a history of smoking. Multiple machine learning models were developed using 10-fold cross-validation. The target variable was in-hospital mortality and input features included patient demographics, levels of care, vital signs, medications, and comorbidities. Two sets of models were developed for at-admission and post-admission predictions. Subsequently, the top five prediction models were selected from at-admission models and post-admission models and their probabilities were calibrated.ResultsThe in-hospital mortality rate for smoker COVID-19 patients was 20.1%. For "at admission" models, the best-calibrated model was XGBoost which yielded an accuracy of 87.5% and F1 score of 86.2%. For the "post-admission" models, XGBoost also outperformed the rest with an accuracy of 90.5% and F1 score of 89.9%. Active smoking was among the most important features in patients' mortality prediction.ConclusionOur machine learning-based mortality prediction models have the potential to be adapted for improving the management of smoker COVID-19 patients and predicting patients' chance of survival.

| S-EPMC10360290 | biostudies-literature

Electrocardiogram-based mortality prediction in patients with COVID-19 using machine learning.

Project description:Background and purposeThe electrocardiogram (ECG) is frequently obtained in the work-up of COVID-19 patients. So far, no study has evaluated whether ECG-based machine learning models have added value to predict in-hospital mortality specifically in COVID-19 patients.MethodsUsing data from the CAPACITY-COVID registry, we studied 882 patients admitted with COVID-19 across seven hospitals in the Netherlands. Raw format 12-lead ECGs recorded within 72 h of admission were studied. With data from five hospitals (n = 634), three models were developed: (a) a logistic regression baseline model using age and sex, (b) a least absolute shrinkage and selection operator (LASSO) model using age, sex and human annotated ECG features, and (c) a pre-trained deep neural network (DNN) using age, sex and the raw ECG waveforms. Data from two hospitals (n = 248) was used for external validation.ResultsPerformances for models a, b and c were comparable with an area under the receiver operating curve of 0.73 (95% confidence interval [CI] 0.65-0.79), 0.76 (95% CI 0.68-0.82) and 0.77 (95% CI 0.70-0.83) respectively. Predictors of mortality in the LASSO model were age, low QRS voltage, ST depression, premature atrial complexes, sex, increased ventricular rate, and right bundle branch block.ConclusionThis study shows that the ECG-based prediction models could be helpful for the initial risk stratification of patients diagnosed with COVID-19, and that several ECG abnormalities are associated with in-hospital all-cause mortality of COVID-19 patients. Moreover, this proof-of-principle study shows that the use of pre-trained DNNs for ECG analysis does not underperform compared with time-consuming manual annotation of ECG features.

| S-EPMC8929464 | biostudies-literature

Molecular property prediction by contrastive learning with attention-guided positive sample selection.

Project description:MotivationPredicting molecular properties is one of the fundamental problems in drug design and discovery. In recent years, self-supervised learning (SSL) has shown its promising performance in image recognition, natural language processing, and single-cell data analysis. Contrastive learning (CL) is a typical SSL method used to learn the features of data so that the trained model can more effectively distinguish the data. One important issue of CL is how to select positive samples for each training example, which will significantly impact the performance of CL.ResultsIn this article, we propose a new method for molecular property prediction (MPP) by Contrastive Learning with Attention-guided Positive-sample Selection (CLAPS). First, we generate positive samples for each training example based on an attention-guided selection scheme. Second, we employ a Transformer encoder to extract latent feature vectors and compute the contrastive loss aiming to distinguish positive and negative sample pairs. Finally, we use the trained encoder for predicting molecular properties. Experiments on various benchmark datasets show that our approach outperforms the state-of-the-art (SOTA) methods in most cases.Availability and implementationThe code is publicly available at https://github.com/wangjx22/CLAPS.

| S-EPMC10188298 | biostudies-literature

Large-scale single-cell analysis reveals critical immune characteristics of COVID-19 patients

Project description:We profiled scRNA-seq of 284 samples collected from 196 individuals, including 22 patients with mild/moderate symptoms, 54 hospitalized patients with severe symptoms, and 95 recovered convalescent persons, as well as 25 healthy controls. The samples were obtained from various tissue types, including human peripheral blood mononuclear cells (249), bronchoalveolar lavage fluid (12) and pleural pleural effusion (1)/sputum (22).

2021-02-04 | GSE158055 | GEO

Deep Representation Learning Improves Prediction of LacI-mediated Transcriptional Repression

Project description:We analyze LacI mutations with the goal to understand and better predict basal transcriptional repression function after mutation. This study utilized lac repressor variants from the Taylor, et al. 2015 Nature Methods study including ten tiles of synthesized single mutations (NCBI GEO Series GSE75009), and an additional six tiles corresponding to higher-order mutations (this study).

2021-06-22 | GSE175456 | GEO

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data