Matrix Profile-Based Interpretable Time Series Classifier
Ontology highlight
ABSTRACT:
SUBMITTER: Guidotti R
PROVIDER: S-EPMC8564499 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Disseminated intravascular coagulation (DIC) is a complex, life-threatening syndrome associated with the end-stage of different coagulation disorders. Early prediction of the risk of DIC development is an urgent clinical need to reduce adverse outcomes. However, effective approaches and models to identify early DIC are still lacking. In this study, a novel interpretable deep learning based time series is used to predict the risk of DIC. The study cohort included ICU patients from a 4300-bed academic hospital between January 1, 2019, and January 1, 2022. Experimental results show that our model achieves excellent performance (AUC: 0.986, Accuracy: 95.7%, and F1:0.935). Gradient-weighted Class Activation Mapping (Grad-CAM) was used to explain how predictive models identified patients with DIC. The decision basis of the model was displayed in the form of a heat map. The model can be used to identify high-risk patients with DIC early, which will help in the early intervention of DIC patients and improve the treatment effect.
| S-EPMC9644626 | biostudies-literature
Project description:Explainable artificial intelligence holds a great promise for neuroscience and plays an important role in the hypothesis generation process. We follow-up a recent machine learning-oriented study that constructed a deep convolutional neural network to automatically identify biological sex from EEG recordings in healthy individuals and highlighted the discriminative role of beta-band power. If generalizing, this finding would be relevant not only theoretically by pointing to some specific neurobiological sexual dimorphisms, but potentially also as a relevant confound in quantitative EEG diagnostic practice. To put this finding to test, we assess whether the automatic identification of biological sex generalizes to another dataset, particularly in the presence of a psychiatric disease, by testing the hypothesis of higher beta power in women compared to men on 134 patients suffering from Major Depressive Disorder. Moreover, we construct ROC curves and compare the performance of the classifiers in determining sex both before and after the antidepressant treatment. We replicate the observation of a significant difference in beta-band power between men and women, providing classification accuracy of nearly 77%. The difference was consistent across the majority of electrodes, however multivariate classification models did not generally improve the performance. Similar results were observed also after the antidepressant treatment (classification accuracy above 70%), further supporting the robustness of the initial finding.
| S-EPMC7652844 | biostudies-literature
Project description:The linear dynamical system (LDS) model is arguably the most commonly used time series model for real-world engineering and financial applications due to its relative simplicity, mathematically predictable behavior, and the fact that exact inference and predictions for the model can be done efficiently. In this work, we propose a new generalized LDS framework, gLDS, for learning LDS models from a collection of multivariate time series (MTS) data based on matrix factorization, which is different from traditional EM learning and spectral learning algorithms. In gLDS, each MTS sequence is factorized as a product of a shared emission matrix and a sequence-specific (hidden) state dynamics, where an individual hidden state sequence is represented with the help of a shared transition matrix. One advantage of our generalized formulation is that various types of constraints can be easily incorporated into the learning process. Furthermore, we propose a novel temporal smoothing regularization approach for learning the LDS model, which stabilizes the model, its learning algorithm and predictions it makes. Experiments on several real-world MTS data show that (1) regular LDS models learned from gLDS are able to achieve better time series predictive performance than other LDS learning algorithms; (2) constraints can be directly integrated into the learning process to achieve special properties such as stability, low-rankness; and (3) the proposed temporal smoothing regularization encourages more stable and accurate predictions.
| S-EPMC5098501 | biostudies-literature
Project description:Current machine learning classifiers have successfully been applied to whole-genome sequencing data to identify genetic determinants of antimicrobial resistance (AMR), but they lack causal interpretation. Here we present a metabolic model-based machine learning classifier, named Metabolic Allele Classifier (MAC), that uses flux balance analysis to estimate the biochemical effects of alleles. We apply the MAC to a dataset of 1595 drug-tested Mycobacterium tuberculosis strains and show that MACs predict AMR phenotypes with accuracy on par with mechanism-agnostic machine learning models (isoniazid AUC = 0.93) while enabling a biochemical interpretation of the genotype-phenotype map. Interpretation of MACs for three antibiotics (pyrazinamide, para-aminosalicylic acid, and isoniazid) recapitulates known AMR mechanisms and suggest a biochemical basis for how the identified alleles cause AMR. Extending flux balance analysis to identify accurate sequence classifiers thus contributes mechanistic insights to GWAS, a field thus far dominated by mechanism-agnostic results.
| S-EPMC7244534 | biostudies-literature
Project description:Accumulated evidence indicates that various types of miRNA are aberrantly expressed in lung cancer and secreted into the bloodstream. For this study, we constructed a serum diagnostic classifier based on detailed bioinformatics analysis of miRNA profiles from a training cohort of 143 lung adenocarcinoma patients and 49 healthy subjects, resulting in a 20 miRNA-based classifier. Validation performed with an independent cohort of samples from lung adenocarcinoma patients (n?=?110), healthy subjects (n?=?52), and benign pulmonary disease patients (n?=?47) showed a sensitivity of 89.1% and specificity of 94.9%, with an area under the curve value of 0.958. Notably, 90.8% of Stage I lung adenocarcinoma cases were correctly diagnosed. Interestingly, this classifier also detected squamous and large cell lung carcinoma cases at relatively high rates (70.4% and 70.0%, respectively), which appears to be consistent with organ site-dependent miRNA expression in cancer tissues. In contrast, we observed significantly lower rates (0-35%) using samples from 96 cases of cancer in other major organs, with breast cancer the lowest. These findings warrant a future study to realize its clinical application as a part of diagnostic procedures for lung cancers, for which early detection and surgical removal is presently the only hope for eventual cure.
| S-EPMC4979017 | biostudies-literature
Project description:Temporal and technical variability of human gut metagenomes
| PRJEB8347 | ENA
Project description:Fungal control of early-stage bacterial community development in wood
| PRJEB87091 | ENA
Project description:PurposeTo investigate the efficacy of radiomics in diagnosing patients with coronavirus disease (COVID-19) and other types of viral pneumonia with clinical symptoms and CT signs similar to those of COVID-19.MethodsBetween 18 January 2020 and 20 May 2020, 110 SARS-CoV-2 positive and 108 SARS-CoV-2 negative patients were retrospectively recruited from three hospitals based on the inclusion criteria. Manual segmentation of pneumonia lesions on CT scans was performed by four radiologists. The latest version of Pyradiomics was used for feature extraction. Four classifiers (linear classifier, k-nearest neighbour, least absolute shrinkage and selection operator [LASSO], and random forest) were used to differentiate SARS-CoV-2 positive and SARS-CoV-2 negative patients. Comparison of the performance of the classifiers and radiologists was evaluated by ROC curve and Kappa score.ResultsWe manually segmented 16,053 CT slices, comprising 32,625 pneumonia lesions, from the CT scans of all patients. Using Pyradiomics, 120 radiomic features were extracted from each image. The key radiomic features screened by different classifiers varied and lead to significant differences in classification accuracy. The LASSO achieved the best performance (sensitivity: 72.2%, specificity: 75.1%, and AUC: 0.81) on the external validation dataset and attained excellent agreement (Kappa score: 0.89) with radiologists (average sensitivity: 75.6%, specificity: 78.2%, and AUC: 0.81). All classifiers indicated that "Original_Firstorder_RootMeanSquared" and "Original_Firstorder_Uniformity" were significant features for this task.ConclusionsWe identified radiomic features that were significantly associated with the classification of COVID-19 pneumonia using multiple classifiers. The quantifiable interpretation of the differences in features between the two groups extends our understanding of CT imaging characteristics of COVID-19 pneumonia.
| S-EPMC7810032 | biostudies-literature
Project description:BackgroundGene expression is mediated by specialized cis-regulatory modules (CRMs), the most prominent of which are called enhancers. Early experiments indicated that enhancers located far from the gene promoters are often responsible for mediating gene transcription. Knowing their properties, regulatory activity, and genomic targets is crucial to the functional understanding of cellular events, ranging from cellular homeostasis to differentiation. Recent genome-wide investigation of epigenomic marks has indicated that enhancer elements could be enriched for certain epigenomic marks, such as, combinatorial patterns of histone modifications.MethodsOur efforts in this paper are motivated by these recent advances in epigenomic profiling methods, which have uncovered enhancer-associated chromatin features in different cell types and organisms. Specifically, in this paper, we use recent state-of-the-art Deep Learning methods and develop a deep neural network (DNN)-based architecture, called EP-DNN, to predict the presence and types of enhancers in the human genome. It uses as features, the expression levels of the histone modifications at the peaks of the functional sites as well as in its adjacent regions. We apply EP-DNN to four different cell types: H1, IMR90, HepG2, and HeLa S3. We train EP-DNN using p300 binding sites as enhancers, and TSS and random non-DHS sites as non-enhancers. We perform EP-DNN predictions to quantify the validation rate for different levels of confidence in the predictions and also perform comparisons against two state-of-the-art computational models for enhancer predictions, DEEP-ENCODE and RFECS.ResultsWe find that EP-DNN has superior accuracy and takes less time to make predictions. Next, we develop methods to make EP-DNN interpretable by computing the importance of each input feature in the classification task. This analysis indicates that the important histone modifications were distinct for different cell types, with some overlaps, e.g., H3K27ac was important in cell type H1 but less so in HeLa S3, while H3K4me1 was relatively important in all four cell types. We finally use the feature importance analysis to reduce the number of input features needed to train the DNN, thus reducing training time, which is often the computational bottleneck in the use of a DNN.ConclusionsIn this paper, we developed EP-DNN, which has high accuracy of prediction, with validation rates above 90 % for the operational region of enhancer prediction for all four cell lines that we studied, outperforming DEEP-ENCODE and RFECS. Then, we developed a method to analyze a trained DNN and determine which histone modifications are important, and within that, which features proximal or distal to the enhancer site, are important.
| S-EPMC4977478 | biostudies-literature
Project description:During the COVID-19 pandemic, wastewater surveillance of the SARS CoV-2 virus has been demonstrated to be effective for population surveillance at the county level down to the building level. At the University of California, San Diego, daily high-resolution wastewater surveillance conducted at the building level is being used to identify potential undiagnosed infections and trigger notification of residents and responsive testing, but the optimal determinants for notifications are unknown. To fill this gap, we propose a pipeline for data processing and identifying features of a series of wastewater test results that can predict the presence of COVID-19 in residences associated with the test sites. Using time series of wastewater results and individual testing results during periods of routine asymptomatic testing among UCSD students from 11/2020 to 11/2021, we develop hierarchical classification/decision tree models to select the most informative wastewater features (patterns of results) which predict individual infections. We find that the best predictor of positive individual level tests in residence buildings is whether or not the wastewater samples were positive in at least 3 of the past 7 days. We also demonstrate that the tree models outperform a wide range of other statistical and machine models in predicting the individual COVID-19 infections while preserving interpretability. Results of this study have been used to refine campus-wide guidelines and email notification systems to alert residents of potential infections.
| S-EPMC10673837 | biostudies-literature