A Survey of Deep Learning for Electronic Health Records

Xu, Jiabao; Xi, Xuefeng; Chen, Jie; Sheng, Victor S.; Ma, Jieming; Cui, Zhiming

doi:10.3390/app122211709

Cited by 13 publications

(8 citation statements)

References 93 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning methods: In recent years, deep learning techniques have achieved significant success in various domains by constructing deep hierarchical features and effectively capturing long-range dependencies in the data [19]. Therefore, we have employed two neural network architectures-deep neural network (DNN) and long short-term memory (LSTM).…”

Section: Comparative Modelsmentioning

confidence: 99%

“…Currently, the integration of temporal information with textual data are becoming a popular choice to enhance the performance of prediction tasks. Common approaches include using RNN and its variants or architectures based on transformers [19]. However, for time series medical data, the uneven distribution of data and the longer length of clinical texts pose challenges in employing conventional models like transformers.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Research on Multimodal Fusion of Temporal Electronic Medical Records

Ma,

Wang,

Gao

et al. 2024

Bioengineering

View full text Add to dashboard Cite

The surge in deep learning-driven EMR research has centered on harnessing diverse data forms. Yet, the amalgamation of diverse modalities within time series data remains an underexplored realm. This study probes a multimodal fusion approach, merging temporal and non-temporal clinical notes along with tabular data. We leveraged data from 1271 myocardial infarction and 6450 stroke inpatients at a Beijing tertiary hospital. Our dataset encompassed static, and time series note data, coupled with static and time series table data. The temporal data underwent a preprocessing phase, padding to a 30-day interval, and segmenting into 3-day sub-sequences. These were fed into a long short-term memory (LSTM) network for sub-sequence representation. Multimodal attention gates were implemented for both static and temporal subsequence representations, culminating in fused representations. An attention-backtracking module was introduced for the latter, adept at capturing enduring dependencies in temporal fused representations. The concatenated results were channeled into an LSTM to yield the ultimate fused representation. Initially, two note modalities were designated as primary modes, and subsequently, the proposed fusion model was compared with comparative models including recent models such as Crossformer. The proposed model consistently exhibited superior predictive prowess in both tasks. Removing the attention-backtracking module led to performance decline. The proposed model consistently shows excellent predictive capabilities in both tasks. The proposed method not only effectively integrates data from the four modalities, but also has a good understanding of how to handle irregular time series data and lengthy clinical texts. An effective method is provided, which is expected to be more widely used in multimodal medical data representation.

show abstract

Section: Comparative Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Research on Multimodal Fusion of Temporal Electronic Medical Records

Ma,

Wang,

Gao

et al. 2024

Bioengineering

View full text Add to dashboard Cite

show abstract

“…EHRs have become the cornerstone in modeling the classification of patients and the progression and sub-typing of diseases through advanced technologies (e.g. machine and deep learning [DL]), enabling healthcare providers to analyze vast volumes of data, extract valuable insights, and make more precise and data-driven clinical decisions ( Xu et al 2022 , Yang et al 2022 ). Structured EHRs are longitudinal in nature, providing a dynamic and chronological representation of a patient’s medical history.…”

Section: Introductionmentioning

confidence: 99%

“…To preserve the temporal nature of EHR and address varying number of visits per patient, recurrent neural networks (RNN) models such as Long Short-Term Memory (LSTM) ( Hochreiter and Schmidhuber 1997 ) and Gated Recurrent Unit (GRU) ( Cho et al 2014 ), along with Transformer ( Vaswani et al 2017 ) have been employed ( Yadav et al 2018 , Xu et al 2022 , Yang et al 2022 , 2023 , Herp et al 2023 , Hossain et al 2023 ).…”

Section: Introductionmentioning

confidence: 99%

TA-RNN: an attention-based time-aware recurrent neural network architecture for electronic health records

Al Olaimat,

Bozdag

2024

Bioinformatics

View full text Add to dashboard Cite

Motivation Electronic health records (EHRs) represent a comprehensive resource of a patient’s medical history. EHRs are essential for utilizing advanced technologies such as deep learning (DL), enabling healthcare providers to analyze extensive data, extract valuable insights, and make precise and data-driven clinical decisions. DL methods such as recurrent neural networks (RNN) have been utilized to analyze EHR to model disease progression and predict diagnosis. However, these methods do not address some inherent irregularities in EHR data such as irregular time intervals between clinical visits. Furthermore, most DL models are not interpretable. In this study, we propose two interpretable DL architectures based on RNN, namely time-aware RNN (TA-RNN) and TA-RNN-autoencoder (TA-RNN-AE) to predict patient’s clinical outcome in EHR at the next visit and multiple visits ahead, respectively. To mitigate the impact of irregular time intervals, we propose incorporating time embedding of the elapsed times between visits. For interpretability, we propose employing a dual-level attention mechanism that operates between visits and features within each visit. Results The results of the experiments conducted on Alzheimer’s Disease Neuroimaging Initiative (ADNI) and National Alzheimer’s Coordinating Center (NACC) datasets indicated the superior performance of proposed models for predicting Alzheimer’s Disease (AD) compared to state-of-the-art and baseline approaches based on F2 and sensitivity. Additionally, TA-RNN showed superior performance on the Medical Information Mart for Intensive Care (MIMIC-III) dataset for mortality prediction. In our ablation study, we observed enhanced predictive performance by incorporating time embedding and attention mechanisms. Finally, investigating attention weights helped identify influential visits and features in predictions. Availability and implementation https://github.com/bozdaglab/TA-RNN.

show abstract

“…In recent years, deep learning has demonstrated powerful visual feature learning abilities [10][11][12][13][14]. A large number of deep learning methods are applied in object detection [15], semantic segmentation [16], image classification [17], recommender systems [18] and medical image analysis [19].…”

Section: Introductionmentioning

confidence: 99%

From Segmentation to Classification: A Deep Learning Scheme for Sintered Surface Images Processing

Yang,

Chen,

Zhao

2023

Processes

View full text Add to dashboard Cite

Effectively managing the quality of iron ore is critical to iron and steel metallurgy. Although quality inspection is crucial, the perspective of sintered surface identification remains largely unexplored. To bridge this gap, we propose a deep learning scheme for mining the necessary information in sintered images processing to replace manual labor and realize intelligent inspection, consisting of segmentation and classification. Specifically, we first employ a DeepLabv3+ semantic segmentation algorithm to extract the effective material surface features. Unlike the original model, which includes a high number of computational parameters, we use SqueezeNet as the backbone to improve model efficiency. Based on the initial annotation of the processed images, the sintered surface dataset is constructed. Then, considering the scarcity of labeled data, a semi-supervised deep learning scheme for sintered surface classification is developed, which is based on pseudo-labels. Experiments show that the improved semantic segmentation model can effectively segment the sintered surface, achieving 98.01% segmentation accuracy with only a 5.71 MB size. In addition, the effectiveness of the adopted semi-supervised learning classification method based on pseudo-labels is validated in six state-of-the-art models. Among them, the ResNet-101 model has the best classification performance, with 94.73% accuracy for the semi-supervised strategy while only using 30% labeled data, which is an improvement of 1.66% compared with the fully supervised strategy.

show abstract

A Survey of Deep Learning for Electronic Health Records

Cited by 13 publications

References 93 publications

Research on Multimodal Fusion of Temporal Electronic Medical Records

Research on Multimodal Fusion of Temporal Electronic Medical Records

TA-RNN: an attention-based time-aware recurrent neural network architecture for electronic health records

From Segmentation to Classification: A Deep Learning Scheme for Sintered Surface Images Processing

Contact Info

Product

Resources

About