Contrast Everything: A Hierarchical Contrastive Framework for Medical
Time-Series
- URL: http://arxiv.org/abs/2310.14017v4
- Date: Mon, 6 Nov 2023 17:49:44 GMT
- Title: Contrast Everything: A Hierarchical Contrastive Framework for Medical
Time-Series
- Authors: Yihe Wang, Yu Han, Haishuai Wang, Xiang Zhang
- Abstract summary: We present COMET, an innovative hierarchical framework that leverages data consistencies at all inherent levels in medical time series.
Our meticulously designed model systematically captures data consistency from four potential levels: observation, sample, trial, and patient levels.
We compare COMET against six baselines using three diverse datasets, which include ECG signals for myocardial infarction and EEG signals for Alzheimer's and Parkinson's diseases.
- Score: 12.469204999759965
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Contrastive representation learning is crucial in medical time series
analysis as it alleviates dependency on labor-intensive, domain-specific, and
scarce expert annotations. However, existing contrastive learning methods
primarily focus on one single data level, which fails to fully exploit the
intricate nature of medical time series. To address this issue, we present
COMET, an innovative hierarchical framework that leverages data consistencies
at all inherent levels in medical time series. Our meticulously designed model
systematically captures data consistency from four potential levels:
observation, sample, trial, and patient levels. By developing contrastive loss
at multiple levels, we can learn effective representations that preserve
comprehensive data consistency, maximizing information utilization in a
self-supervised manner. We conduct experiments in the challenging
patient-independent setting. We compare COMET against six baselines using three
diverse datasets, which include ECG signals for myocardial infarction and EEG
signals for Alzheimer's and Parkinson's diseases. The results demonstrate that
COMET consistently outperforms all baselines, particularly in setup with 10%
and 1% labeled data fractions across all datasets. These results underscore the
significant impact of our framework in advancing contrastive representation
learning techniques for medical time series. The source code is available at
https://github.com/DL4mHealth/COMET.
Related papers
- Global Contrastive Training for Multimodal Electronic Health Records with Language Supervision [1.6245786035158123]
This paper introduces a novel multimodal contrastive learning framework, specifically focusing on medical time series and clinical notes.
The framework integrates temporal cross-attention transformers with a dynamic embedding and tokenization scheme for learning multimodal feature representations.
Experiments with a real-world EHR dataset demonstrated that our framework outperformed state-of-the-art approaches on the exemplar task of predicting the occurrence of nine postoperative complications.
arXiv Detail & Related papers (2024-04-10T04:19:59Z) - Multi-Modal Federated Learning for Cancer Staging over Non-IID Datasets with Unbalanced Modalities [9.476402318365446]
In this work, we introduce a novel FL architecture designed to accommodate not only the heterogeneity of data samples, but also the inherent heterogeneity/non-uniformity of data modalities across institutions.
We propose a solution by devising a distributed gradient blending and proximity-aware client weighting strategy tailored for multi-modal FL.
arXiv Detail & Related papers (2024-01-07T23:45:01Z) - The effect of data augmentation and 3D-CNN depth on Alzheimer's Disease
detection [51.697248252191265]
This work summarizes and strictly observes best practices regarding data handling, experimental design, and model evaluation.
We focus on Alzheimer's Disease (AD) detection, which serves as a paradigmatic example of challenging problem in healthcare.
Within this framework, we train predictive 15 models, considering three different data augmentation strategies and five distinct 3D CNN architectures.
arXiv Detail & Related papers (2023-09-13T10:40:41Z) - Extraction of volumetric indices from echocardiography: which deep
learning solution for clinical use? [6.144041824426555]
We show that the proposed 3D nnU-Net outperforms alternative 2D and recurrent segmentation methods.
Overall, the experimental results suggest that with sufficient training data, 3D nnU-Net could become the first automated tool to meet the standards of an everyday clinical device.
arXiv Detail & Related papers (2023-05-03T09:38:52Z) - Best of Both Worlds: Multimodal Contrastive Learning with Tabular and
Imaging Data [7.49320945341034]
We propose the first self-supervised contrastive learning framework to train unimodal encoders.
Our solution combines SimCLR and SCARF, two leading contrastive learning strategies.
We show the generalizability of our approach to natural images using the DVM car advertisement dataset.
arXiv Detail & Related papers (2023-03-24T15:44:42Z) - Contrastive learning for unsupervised medical image clustering and
reconstruction [0.23624125155742057]
We propose an unsupervised autoencoder framework which is augmented with a contrastive loss to encourage high separability in the latent space.
Our method achieves similar performance to the supervised architecture, indicating that separation in the latent space reproduces expert medical observer-assigned labels.
arXiv Detail & Related papers (2022-09-24T13:17:02Z) - Bootstrapping Your Own Positive Sample: Contrastive Learning With
Electronic Health Record Data [62.29031007761901]
This paper proposes a novel contrastive regularized clinical classification model.
We introduce two unique positive sampling strategies specifically tailored for EHR data.
Our framework yields highly competitive experimental results in predicting the mortality risk on real-world COVID-19 EHR data.
arXiv Detail & Related papers (2021-04-07T06:02:04Z) - HINT: Hierarchical Interaction Network for Trial Outcome Prediction
Leveraging Web Data [56.53715632642495]
Clinical trials face uncertain outcomes due to issues with efficacy, safety, or problems with patient recruitment.
In this paper, we propose Hierarchical INteraction Network (HINT) for more general, clinical trial outcome predictions.
arXiv Detail & Related papers (2021-02-08T15:09:07Z) - Uncovering the structure of clinical EEG signals with self-supervised
learning [64.4754948595556]
Supervised learning paradigms are often limited by the amount of labeled data that is available.
This phenomenon is particularly problematic in clinically-relevant data, such as electroencephalography (EEG)
By extracting information from unlabeled data, it might be possible to reach competitive performance with deep neural networks.
arXiv Detail & Related papers (2020-07-31T14:34:47Z) - Semi-supervised Medical Image Classification with Relation-driven
Self-ensembling Model [71.80319052891817]
We present a relation-driven semi-supervised framework for medical image classification.
It exploits the unlabeled data by encouraging the prediction consistency of given input under perturbations.
Our method outperforms many state-of-the-art semi-supervised learning methods on both single-label and multi-label image classification scenarios.
arXiv Detail & Related papers (2020-05-15T06:57:54Z) - Dynamic Graph Correlation Learning for Disease Diagnosis with Incomplete
Labels [66.57101219176275]
Disease diagnosis on chest X-ray images is a challenging multi-label classification task.
We propose a Disease Diagnosis Graph Convolutional Network (DD-GCN) that presents a novel view of investigating the inter-dependency among different diseases.
Our method is the first to build a graph over the feature maps with a dynamic adjacency matrix for correlation learning.
arXiv Detail & Related papers (2020-02-26T17:10:48Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.