How Deep is your Guess? A Fresh Perspective on Deep Learning for Medical Time-Series Imputation

• URL: http://arxiv.org/abs/2407.08442v1
• Date: Thu, 11 Jul 2024 12:33:28 GMT
• Title: How Deep is your Guess? A Fresh Perspective on Deep Learning for Medical Time-Series Imputation
• Authors: Linglong Qian, Tao Wang, Jun Wang, Hugh Logan Ellis, Robin Mitra, Richard Dobson, Zina Ibrahim,
• Abstract summary: We introduce a novel classification framework for time-series imputation using deep learning. By identifying conceptual gaps in the literature and existing reviews, we devise a taxonomy grounded on the inductive bias of neural imputation frameworks.
• Score: 6.547981908229007
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce a novel classification framework for time-series imputation using deep learning, with a particular focus on clinical data. By identifying conceptual gaps in the literature and existing reviews, we devise a taxonomy grounded on the inductive bias of neural imputation frameworks, resulting in a classification of existing deep imputation strategies based on their suitability for specific imputation scenarios and data-specific properties. Our review further examines the existing methodologies employed to benchmark deep imputation models, evaluating their effectiveness in capturing the missingness scenarios found in clinical data and emphasising the importance of reconciling mathematical abstraction with clinical insights. Our classification aims to serve as a guide for researchers to facilitate the selection of appropriate deep learning imputation techniques tailored to their specific clinical data. Our novel perspective also highlights the significance of bridging the gap between computational methodologies and medical insights to achieve clinically sound imputation models.

Related papers

• Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling [53.7117640028211]
  We present a geometry-constrained probabilistic modeling treatment to resolve the identified issues. We incorporate a suite of critical geometric properties to impose proper constraints on the layout of constructed embedding space. A spectral graph-theoretic method is devised to estimate the number of potential novel classes.
  arXiv  Detail & Related papers  (2024-03-02T00:56:05Z)
• On the Importance of Step-wise Embeddings for Heterogeneous Clinical Time-Series [1.3285222309805063]
  Recent advances in deep learning for sequence modeling have not fully transferred to tasks handling time-series from electronic health records. In particular, in problems related to the Intensive Care Unit (ICU), the state-of-the-art remains to tackle sequence classification in a tabular manner with tree-based methods.
  arXiv  Detail & Related papers  (2023-11-15T12:18:15Z)
• Language Model Training Paradigms for Clinical Feature Embeddings [1.4513150969598638]
  We use self-supervised training paradigms for language models to learn high-quality clinical feature embeddings. We visualize the learnt embeddings via unsupervised dimension reduction techniques and observe a high degree of consistency with prior clinical knowledge.
  arXiv  Detail & Related papers  (2023-11-01T18:23:12Z)
• Multi-task Explainable Skin Lesion Classification [54.76511683427566]
  We propose a few-shot-based approach for skin lesions that generalizes well with few labelled data. The proposed approach comprises a fusion of a segmentation network that acts as an attention module and classification network.
  arXiv  Detail & Related papers  (2023-10-11T05:49:47Z)
• Investigating Poor Performance Regions of Black Boxes: LIME-based Exploration in Sepsis Detection [0.5872014229110214]
  This paper proposes leveraging Local Interpretable Model-Agnostic Explanations (LIME) to provide interpretable descriptions of black box classification models in sepsis detection. By analyzing misclassified instances, significant features contributing to suboptimal performance are identified.
  arXiv  Detail & Related papers  (2023-06-21T18:36:15Z)
• Overview of Deep Learning Methods for Retinal Vessel Segmentation [0.0]
  Methods for automated retinal vessel segmentation play an important role in the treatment and diagnosis of many eye and systemic diseases. With the fast development of deep learning methods, more and more retinal vessel segmentation methods are implemented as deep neural networks.
  arXiv  Detail & Related papers  (2023-06-01T17:05:18Z)
• Tissue Classification During Needle Insertion Using Self-Supervised Contrastive Learning and Optical Coherence Tomography [53.38589633687604]
  We propose a deep neural network that classifies the tissues from the phase and intensity data of complex OCT signals acquired at the needle tip. We show that with 10% of the training set, our proposed pretraining strategy helps the model achieve an F1 score of 0.84 whereas the model achieves an F1 score of 0.60 without it.
  arXiv  Detail & Related papers  (2023-04-26T14:11:04Z)
• LifeLonger: A Benchmark for Continual Disease Classification [59.13735398630546]
  We introduce LifeLonger, a benchmark for continual disease classification on the MedMNIST collection. Task and class incremental learning of diseases address the issue of classifying new samples without re-training the models from scratch. Cross-domain incremental learning addresses the issue of dealing with datasets originating from different institutions while retaining the previously obtained knowledge.
  arXiv  Detail & Related papers  (2022-04-12T12:25:05Z)
• Explaining Clinical Decision Support Systems in Medical Imaging using Cycle-Consistent Activation Maximization [112.2628296775395]
  Clinical decision support using deep neural networks has become a topic of steadily growing interest. clinicians are often hesitant to adopt the technology because its underlying decision-making process is considered to be intransparent and difficult to comprehend. We propose a novel decision explanation scheme based on CycleGAN activation which generates high-quality visualizations of classifier decisions even in smaller data sets.
  arXiv  Detail & Related papers  (2020-10-09T14:39:27Z)
• Trajectories, bifurcations and pseudotime in large clinical datasets: applications to myocardial infarction and diabetes data [94.37521840642141]
  We suggest a semi-supervised methodology for the analysis of large clinical datasets, characterized by mixed data types and missing values. The methodology is based on application of elastic principal graphs which can address simultaneously the tasks of dimensionality reduction, data visualization, clustering, feature selection and quantifying the geodesic distances (pseudotime) in partially ordered sequences of observations.
  arXiv  Detail & Related papers  (2020-07-07T21:04:55Z)
• Explainable deep learning models in medical image analysis [0.0]
  Methods have been very effective for a variety of medical diagnostic tasks and has even beaten human experts on some of those. Recent explainability studies aim to show the features that influence the decision of a model the most. A review of the current applications of explainable deep learning for different medical imaging tasks is presented here.
  arXiv  Detail & Related papers  (2020-05-28T06:31:05Z)

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.