Deep learning for temporal data representation in electronic health records: A systematic review of challenges and methodologies

Xie, Feng; Yuan, Han; Ning, Yilin; Ong, Marcus Eng Hock; Feng, Mengling; Hsu, William H.; Chakraborty, Bibhas; Liu, Nan

doi:10.1016/j.jbi.2021.103980

Cited by 62 publications

(26 citation statements)

References 141 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 1 provides a brief description of the main methods discussed in this paper, and the reader is referred to other more detailed literature for detailed merits and demerits of each method. [ 42 , 43 , 44 , 45 ]…”

Section: The Way Machine Learning Workmentioning

confidence: 99%

SERS‐Based Biosensors Combined with Machine Learning for Medical Application**

et al. 2023

View full text Add to dashboard Cite

Surface‐enhanced Raman spectroscopy (SERS) has shown strength in non‐invasive, rapid, trace analysis and has been used in many fields in medicine. Machine learning (ML) is an algorithm that can imitate human learning styles and structure existing content with the knowledge to effectively improve learning efficiency. Integrating SERS and ML can have a promising future in the medical field. In this review, we summarize the applications of SERS combined with ML in recent years, such as the recognition of biological molecules, rapid diagnosis of diseases, developing of new immunoassay techniques, and enhancing SERS capabilities in semi‐quantitative measurements. Ultimately, the possible opportunities and challenges of combining SERS with ML are addressed.

show abstract

Section: The Way Machine Learning Workmentioning

confidence: 99%

SERS‐Based Biosensors Combined with Machine Learning for Medical Application**

et al. 2023

View full text Add to dashboard Cite

show abstract

“…LSTM models, a gated variant of RNN, can keep long-term memory by remembering long sequences of data since. Existing works were focused on the use of DL for the temporal data representation in EHR, facing various challenges, such as the data irregularity and data heterogeneity [11]. Mainly, RNN, LSTM and Gated Recurrent Units (GRUs) have been proposed for their suitability in representing temporal sequences.…”

Section: Background and Related Workmentioning

confidence: 99%

An Explainable Multimodal Fusion Approach for Mass Casualty Incidents

Vasileiou

Meditskos

Vrochidis

et al. 2022

Communications in Computer and Information Science

View full text Add to dashboard Cite

During a Mass Casualty Incident, it is essential to make effective decisions to save lives and nursing the injured. This paper presents a work in progress on the design and development of an explainable decision support system, intended for the medical personnel and care givers, that capitalises on multiple modalities to achieve situational awareness and pre-hospital life support. Our novelty is two-fold: first, we use stateof-the-art techniques for combining static and time-series data in deep recurrent neural networks, and second we increase the trustworthiness of the system by enriching it with neurosymbolic explainable capabilities.

show abstract

“…[4][5][6][7] Recently, a lightweight DL framework was developed by using a large-scale dataset of 28 581 cases.Superior accuracy with an average Dice of 0.95 was achieved on 67 delineation tasks and real-time delineation in whole-body organs at risk (OARs) and tumors was less than 2 s. 8 Despite the great promise of this technique, it is still necessary to evaluate its geometric accuracy before implementing it in clinical applications. [9][10][11] Generally, two main categories of evaluation metrics (region-based and boundary-based) were used for assessment of the goodness and usefulness of automatic delineation. 12 The commonly used region-based metrics compare the region overlap between autosegmentation contours and their corresponding ground truth, such as the Dice similarity coefficient (DSC) 13 and Jaccard index (JI).…”

Section: Introductionmentioning

confidence: 99%

Geometric and dosimetric evaluation of deep learning based auto‐segmentation for clinical target volume on breast cancer

Yang

Guo

Fang

et al. 2023

J Applied Clin Med Phys

View full text Add to dashboard Cite

Background: Recently, target auto-segmentation techniques based on deep learning (DL) have shown promising results. However, inaccurate target delineation will directly affect the treatment planning dose distribution and the effect of subsequent radiotherapy work. Evaluation based on geometric metrics alone may not be sufficient for target delineation accuracy assessment. The purpose of this paper is to validate the performance of automatic segmentation with dosimetric metrics and try to construct new evaluation geometric metrics to comprehensively understand the dose-response relationship from the perspective of clinical application. Materials and Methods: A DL-based target segmentation model was developed by using 186 manual delineation modified radical mastectomy breast cancer cases. The resulting DL model were used to generate alternative target contours in a new set of 48 patients. The Auto-plan was reoptimized to ensure the same optimized parameters as the reference Manual-plan. To assess the dosimetric impact of target auto-segmentation,not only common geometric metrics but also new spatial parameters with distance and relative volume (R V ) to target were used. Correlations were performed using Spearman's correlation between segmentation evaluation metrics and dosimetric changes. Results: Only strong (|R 2 | > 0.6, p < 0.01) or moderate (|R 2 | > 0.4, p < 0.01) Pearson correlation was established between the traditional geometric metric and three dosimetric evaluation indices to target (conformity index,homogeneity index, and mean dose). For organs at risk (OARs), inferior or no significant relationship was found between geometric parameters and dosimetric differences. Furthermore, we found that OARs dose distribution was affected by boundary error of target segmentation instead of distance and R V to target. Conclusions: Current geometric metrics could reflect a certain degree of dose effect of target variation. To find target contour variations that do lead to OARs dosimetry changes, clinically oriented metrics that more accurately reflect how segmentation quality affects dosimetry should be constructed.

show abstract

Deep learning for temporal data representation in electronic health records: A systematic review of challenges and methodologies

Cited by 62 publications

References 141 publications

SERS‐Based Biosensors Combined with Machine Learning for Medical Application**

SERS‐Based Biosensors Combined with Machine Learning for Medical Application**

An Explainable Multimodal Fusion Approach for Mass Casualty Incidents

Geometric and dosimetric evaluation of deep learning based auto‐segmentation for clinical target volume on breast cancer

Contact Info

Product

Resources

About