Missing data imputation techniques for wireless continuous vital signs monitoring

Wireless vital signs sensors are increasingly used for remote patient monitoring, but data analysis is often challenged by missing data periods. This study explored the performance of various imputation techniques for continuous vital signs measurements. Wireless vital signs measurements (heart rate, respiratory rate, blood oxygen saturation, axillary temperature) from surgical ward patients were used for repeated random simulation of missing data periods (gaps) of 5-60 min in two-hour windows. Gaps were imputed using linear interpolation, spline interpolation, last observation- and mean carried forwards technique, and cluster-based prognosis. Imputation performance was evaluated using the mean absolute error (MAE) between original and imputed gap samples. Besides, effects on signal features (window's slope, mean) and early warning scores (EWS) were explored. Gaps were simulated in 1743 data windows, obtained from 52 patients. Although MAE ranges overlapped, median MAE was structurally lowest for linear interpolation (heart rate: 0.9-2.6 beats/min, respiratory rate: 0.8-1.8 breaths/min, temperature: 0.04-0.17 °C, oxygen saturation: 0.3-0.7% for 5-60 min gaps) but up to twice as high for other techniques. Three techniques resulted in larger ranges of signal feature bias compared to no imputation. Imputation led to EWS misclassification in 1-8% of all simulations. Imputation error ranges vary between imputation techniques and increase with gap length. Imputation may result in larger signal feature bias compared to performing no imputation, and can affect patient risk assessment as illustrated by the EWS. Accordingly, careful implementation and selection of imputation techniques is warranted.

Scalable tensor factorization for recovering multiday missing intramuscular electromyography data

To design a prosthetic hand which can classify movements based on the electromyography (EMG) signals, complete and good quality signals are essential. However, due to different reasons such as disconnection of electrodes or muscles fatigue the recorded EMG data can be incomplete, which degrades the classification of test movements. In this paper, we first acquire multiday intramuscular EMG (iEMG) signals (which are invasive) with higher Signal-to-Noise Ratio (SNR) compared to surface EMG (sEMG) signals; followed by application of matrix (non-negative matrix factorization – NMF) and tensor factorization methods (Canonical Polyadic Decomposition (CPD), Tucker decomposition (TD) & Canonical Polyadic-Weighted Optimization (CP-WOPT)) for recovering structured missing data i.e., chunks of missing samples in channels. Furthermore, we tested the scalability of NMF, CPD, TD and CP-WOPT by employing them on the large multiday (seven days) iEMG data where the size of missing data is increased from day 1 to day 7, and for each day a fixed percentage of missing data is introduced from 10% to worst case of 50%. Results show that CP-WOPT outperformed NMF, CPD and TD to recover large percentage of missing data in terms of Relative Mean Error (RME) even when 7 days of data is considered. CP-WOPT showed robustness even for the worse case even when 50% iEMG data is removed from day 1 to day 7 where it’s RME degraded slightly from 0.08 to 0.1.

Machine Learning and Decision Support in Critical Care

Clinical data management systems typically provide caregiver teams with useful information, derived from large, sometimes highly heterogeneous, data sources that are often changing dynamically. Over the last decade there has been a significant surge in interest in using these data sources, from simply re-using the standard clinical databases for event prediction or decision support, to including dynamic and patient-specific information into clinical monitoring and prediction problems. However, in most cases, commercial clinical databases have been designed to document clinical activity for reporting, liability and billing reasons, rather than for developing new algorithms. With increasing excitement surrounding "secondary use of medical records" and "Big Data" analytics, it is important to understand the limitations of current databases and what needs to change in order to enter an era of "precision medicine." This review article covers many of the issues involved in the collection and preprocessing of critical care data. The three challenges in critical care are considered: compartmentalization, corruption, and complexity. A range of applications addressing these issues are covered, including the modernization of static acuity scoring; on-line patient tracking; personalized prediction and risk assessment; artifact detection; state estimation; and incorporation of multimodal data sources such as genomic and free text data.