Identifying Sepsis Subphenotypes via Time-Aware Multi-Modal Auto-Encoder

Yin, Changchang; Liu, Ruoqi; Zhang, Dongdong; Zhang, Ping

doi:10.1145/3394486.3403129

Cited by 37 publications

(18 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DACMI challenge has generated considerable interests both across and beyond the challenge participating teams. Although the challenge has an extended embargo period for its full data release due to the pandemic, the released training part of the challenge data has been enabling development of advanced algorithms for clinical longitudinal data imputation, including Time-Aware Multi-Modal Auto-Encoder [ 33 ]. For latest progress on imputation for time series in the general domain, we refer the reader to the surveys [ 34 , 35 ] that complement this article.…”

Section: Discussionmentioning

confidence: 99%

Evaluating the state of the art in missing data imputation for clinical data

Luo

2021

Briefings in Bioinformatics

View full text Add to dashboard Cite

Clinical data are increasingly being mined to derive new medical knowledge with a goal of enabling greater diagnostic precision, better-personalized therapeutic regimens, improved clinical outcomes and more efficient utilization of health-care resources. However, clinical data are often only available at irregular intervals that vary between patients and type of data, with entries often being unmeasured or unknown. As a result, missing data often represent one of the major impediments to optimal knowledge derivation from clinical data. The Data Analytics Challenge on Missing data Imputation (DACMI) presented a shared clinical dataset with ground truth for evaluating and advancing the state of the art in imputing missing data for clinical time series. We extracted 13 commonly measured blood laboratory tests. To evaluate the imputation performance, we randomly removed one recorded result per laboratory test per patient admission and used them as the ground truth. DACMI is the first shared-task challenge on clinical time series imputation to our best knowledge. The challenge attracted 12 international teams spanning three continents across multiple industries and academia. The evaluation outcome suggests that competitive machine learning and statistical models (e.g. LightGBM, MICE and XGBoost) coupled with carefully engineered temporal and cross-sectional features can achieve strong imputation performance. However, care needs to be taken to prevent overblown model complexity. The challenge participating systems collectively experimented with a wide range of machine learning and probabilistic algorithms to combine temporal imputation and cross-sectional imputation, and their design principles will inform future efforts to better model clinical missing data.

show abstract

Section: Discussionmentioning

confidence: 99%

Evaluating the state of the art in missing data imputation for clinical data

Luo

2021

Briefings in Bioinformatics

View full text Add to dashboard Cite

show abstract

“…al. [34] used a time-aware autoencoder to learn from the data distribution of training data and also for considering the irregularities in the time intervals between the EHR time-series data. We use the temporal decay factor to consider the effect of irregular time intervals between the EHR time-series data.…”

Section: Related Workmentioning

confidence: 99%

Concurrent imputation and prediction on EHR data using bi-directional GANs

Gupta

Phan

Bunnell

et al. 2021

Proceedings of the 12th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics

View full text Add to dashboard Cite

Working with electronic health records (EHRs) is known to be challenging due to several reasons. These reasons include not having: 1) similar lengths (per visit), 2) the same number of observations (per patient), and 3) complete entries in the available records. These issues hinder the performance of the predictive models created using EHRs. In this paper, we approach these issues by presenting a model for the combined task of imputing and predicting values for the irregularly observed and varying length EHR data with missing entries. Our proposed model (dubbed as Bi-GAN) uses a bidirectional recurrent network in a generative adversarial setting. In this architecture, the generator is a bidirectional recurrent network that receives the EHR data and imputes the existing missing values. The discriminator attempts to discriminate between the actual and the imputed values generated by the generator. Using the input data in its entirety, Bi-GAN learns how to impute missing elements in-between (imputation) or outside of the input time steps (prediction). Our method has three advantages to the state-of-the-art methods in the field: (a) one single model performs both the imputation and prediction tasks; (b) the model can perform predictions using time-series of varying length with missing data; (c) it does not require to know the observation and prediction time window during training and can be used for the predictions with different observation and prediction window lengths, for short-and long-term predictions. We evaluate our model on two large EHR datasets to impute and predict body mass index (BMI) values and show its superior performance in both settings.

show abstract

“…Inspired by the position embedding technique [25,26] and recent practices on variable encoding methods, we utilize an embedding map to convert the medical expenditure variable and service date variable into continuous embedding space. Specifically, given the observed expenditures in the dataset, we sort the values and discretize them into 100 sub-ranges with an equal number of observed expenditures in each sub-range.…”

Section: Encoder and Decodermentioning

confidence: 99%

Transformer-based unsupervised patient representation learning based on medical claims for risk stratification and analysis

Zeng

Lin

Liu

2021

Proceedings of the 12th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics

View full text Add to dashboard Cite

The claims data, containing medical codes, services information, and incurred expenditure, can be a good resource for estimating an individual's health condition and medical risk level. In this study, we developed Transformer-based Multimodal AutoEncoder (TMAE), an unsupervised learning framework that can learn efficient patient representation by encoding meaningful information from the claims data. TMAE is motivated by the practical needs in healthcare to stratify patients into different risk levels for improving care delivery and management. Compared to previous approaches, TMAE is able to 1) model inpatient, outpatient, and medication claims collectively, 2) handle irregular time intervals between medical events, 3) alleviate the sparsity issue of the rare medical codes, and 4) incorporate medical expenditure information. We trained TMAE using a real-world pediatric claims dataset containing more than 600,000 patients and compared its performance with various approaches in two clustering tasks. Experimental results demonstrate that TMAE has superior performance compared to all baselines. Multiple downstream applications are also conducted to illustrate the effectiveness of our framework. The promising results confirm that the TMAE framework is scalable to large claims data and is able to generate efficient patient embeddings for risk stratification and analysis.

show abstract

Identifying Sepsis Subphenotypes via Time-Aware Multi-Modal Auto-Encoder

Cited by 37 publications

References 16 publications

Evaluating the state of the art in missing data imputation for clinical data

Evaluating the state of the art in missing data imputation for clinical data

Concurrent imputation and prediction on EHR data using bi-directional GANs

Transformer-based unsupervised patient representation learning based on medical claims for risk stratification and analysis

Contact Info

Product

Resources

About