Batch Integrated Gradients: Explanations for Temporal Electronic Health Records

Duell, Jamie; Fan, Xiangyu; Fu, Hsuan; Seisenberger, Monika

doi:10.1007/978-3-031-34344-5_15

Cited by 4 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous work mainly used transformers for generating representations, like learnable embeddings, that encode temporal dynamics in multivariable time series [40][41][42] . Other authors used more traditional techniques such as temporal association rules to learn temporal dynamics 60,61 . A systematic review by Xie et al investigated DL temporal representations identifying data missingness as an important impediment 43 .…”

Section: Transformer Model and Attentionmentioning

confidence: 99%

TRAPOD: A Transformer Architecture Exploits Intraoperative Temporal Dynamics Improving the Prediction of Postoperative Delirium

Giesa,

Sekutowicz,

Rubarth

et al. 2024

Preprint

View full text Add to dashboard Cite

Motivation. Patients who experienced postoperative delirium (POD) are at higher risk of poor outcomes like dementia or death. Previous machine learning (ML) models predicting POD mostly relied on time-aggregated features. Objective. We assessed the potential of temporal patterns in clinical parameters during surgeries to predict POD. Methods. Long short-term memory (LSTM) and transformer models, directly consuming time series, were compared to multi-layer perceptrons (MLPs) trained on time-aggregated features. We also fitted hybrid models, fusing either LSTM or transformer models with MLPs. Univariate Spearman’s rank correlations and linear mixed-effect models establish the importance of individual features that we compared to transformers’ attention weights. Results. Best performance was achieved by a transformer architecture ingesting 30 minutes of intraoperative parameter sequences. Systolic invasive blood pressure and given opioids marked the most important input variables, in line with univariate feature importances. Conclusion. Intraoperative temporal dynamics of clinical parameters, exploited by a tailored transformer architecture named TRAPOD, are critical for the accurate prediction of POD.

show abstract

Section: Transformer Model and Attentionmentioning

confidence: 99%

TRAPOD: A Transformer Architecture Exploits Intraoperative Temporal Dynamics Improving the Prediction of Postoperative Delirium

Giesa,

Sekutowicz,

Rubarth

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Applying a transformer architecture to intraoperative temporal dynamics improves the prediction of postoperative delirium

Giesa,

Sekutowicz,

Rubarth

et al. 2024

Commun Med

View full text Add to dashboard Cite

Background Patients who experienced postoperative delirium (POD) are at higher risk of poor outcomes like dementia or death. Previous machine learning models predicting POD mostly relied on time-aggregated features. We aimed to assess the potential of temporal patterns in clinical parameters during surgeries to predict POD. Methods Long short-term memory (LSTM) and transformer models, directly consuming time series, were compared to multi-layer perceptrons (MLPs) trained on time-aggregated features. We also fitted hybrid models, fusing either LSTM or transformer models with MLPs. Univariate Spearman’s rank correlations and linear mixed-effect models establish the importance of individual features that we compared to transformers’ attention weights. Results Best performance is achieved by a transformer architecture ingesting 30 min of intraoperative parameter sequences. Systolic invasive blood pressure and given opioids mark the most important input variables, in line with univariate feature importances. Conclusions Intraoperative temporal dynamics of clinical parameters, exploited by a transformer architecture named TRAPOD, are critical for the accurate prediction of POD.

show abstract

Counterfactual-Integrated Gradients: Counterfactual Feature Attribution for Medical Records

Duell,

Seisenberger,

Fan

2023

2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

View full text Add to dashboard Cite

Batch Integrated Gradients: Explanations for Temporal Electronic Health Records

Cited by 4 publications

References 7 publications

TRAPOD: A Transformer Architecture Exploits Intraoperative Temporal Dynamics Improving the Prediction of Postoperative Delirium

TRAPOD: A Transformer Architecture Exploits Intraoperative Temporal Dynamics Improving the Prediction of Postoperative Delirium

Applying a transformer architecture to intraoperative temporal dynamics improves the prediction of postoperative delirium

Counterfactual-Integrated Gradients: Counterfactual Feature Attribution for Medical Records

Contact Info

Product

Resources

About