Recurrent Imputation for Multivariate Time Series with Missing Values

Suo, Qiuling; Yao, Liuyi; Xun, Guangxu; Sun, Jianhui; Zhang, Aidong

doi:10.1109/ichi.2019.8904638

Cited by 30 publications

(15 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Team Buffalo/Virginia [ 26 ] used a RNN to learn the global representations of all laboratory tests and a series of RNNs to learn laboratory test-specific patterns and to merge them through a fusion gate. They enabled both forward and backward directions of recurrence for imputation in order to improve its ability of long-term memory.…”

Section: Challenge Participating Systemsmentioning

confidence: 99%

See 1 more Smart Citation

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: Challenge Participating Systemsmentioning

confidence: 99%

“…Comparing the challenge participating systems, we note that several teams adopted the gradient boosting algorithms as primary tools for imputation [ 14 , 17 , 22 ]. A few teams used RNN (including LSTM and GRU) for imputation [ 20 , 26–28 ]. Several teams used KNN-based approaches [ 21 , 23 , 27 ].…”

Section: Challenge Participating Systemsmentioning

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

“…In recent years, deep learning models have become research hotspots and have been applied to time series data imputation. Suo et al [17] adopt a bidirectional RNN to predict the missing values based on the prefilled data. Yan et al propose DETROIT [21], which builds features based on the former and latter two collections for each collection.…”

Section: Related Workmentioning

confidence: 99%

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

Yin

Liu

Zhang

et al. 2020

Preprint

View full text Add to dashboard Cite

Sepsis is a heterogeneous clinical syndrome that is the leading cause of mortality in hospital intensive care units (ICUs). Identification of sepsis subphenotypes may allow for more precise treatments and lead to more targeted clinical interventions. Recently, sepsis subtyping on electronic health records (EHRs) has attracted interest from healthcare researchers. However, most sepsis subtyping studies ignore the temporality of EHR data and suffer from missing values. In this paper, we propose a new sepsis subtyping framework to address the two issues. Our subtyping framework consists of a novel Time-Aware Multi-modal auto-Encoder (TAME) model which introduces time-aware attention mechanism and incorporates multi-modal inputs (e.g., demographics, diagnoses, medications, lab tests and vital signs) to impute missing values, a dynamic time wrapping (DTW) method to measure patients' temporal similarity based on the imputed EHR data, and a weighted k-means algorithm to cluster patients. Comprehensive experiments on real-world datasets show TAME outperforms the baselines on imputation accuracy. After analyzing TAME-imputed EHR data, we identify four novel subphenotypes of sepsis patients, paving the way for improved personalization of sepsis management.

show abstract

“…Existing methods for analyzing irregular time series can be categorized into three main directions [9]: (i) the repair approach in which missing observations are recovered via smoothing or imputation [10][11][12][13][14]-also implemented, especially in recent years, by machine learning methods [15][16][17][18]; (ii) the generalization of spectral analysis tools [19,20], such as wavelets [21][22][23][24]; (iii) kernel methods [25,26]. In this paper, we deal with a repair approach which uses an input preparation step based on machine learning.…”

Section: Introductionmentioning

confidence: 99%

Ensemble Methods for Jump-Diffusion Models of Power Prices

Mari

Baldassari

2021

Energies

View full text Add to dashboard Cite

We propose a machine learning-based methodology which makes use of ensemble methods with the aims (i) of treating missing data in time series with irregular observation times and detecting anomalies in the observed time behavior; (ii) of defining suitable models of the system dynamics. We applied this methodology to US wholesale electricity price time series that are characterized by missing data, high and stochastic volatility, jumps and pronounced spikes. For missing data, we provide a repair approach based on the missForest algorithm, an imputation algorithm which is completely agnostic about the data distribution. To identify anomalies, i.e., turbulent movements of power prices in which jumps and spikes are observed, we took into account the no-gap reconstructed electricity price time series, and then we detected anomalous regions using the isolation forest algorithm, an anomaly detection method that isolates anomalies instead of profiling normal data points as in the most common techniques. After removing anomalies, the additional gaps will be newly filled by the missForest imputation algorithm. In this way, a complete and clean time series describing the stable dynamics of power prices can be obtained. The decoupling between the stable motion and the turbulent motion allows us to define suitable jump-diffusion models of power prices and to provide an estimation procedure that uses the full information contained in both the stable and the turbulent dynamics.

show abstract

Recurrent Imputation for Multivariate Time Series with Missing Values

Cited by 30 publications

References 3 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

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

Ensemble Methods for Jump-Diffusion Models of Power Prices

Contact Info

Product

Resources

About