Liangyou Chen

Recent reports suggest that photoplethysmo-graphy (PPG), which is a component of routine pulse oximetry, may be useful for detecting hypovolemia. An essential step in extracting and analyzing common PPG features is the robust identification of onset and peak locations of the vascular beats, despite varying beat morphologies and major oscillations in the baseline. Some prior reports used manual analysis of the PPG waveform; however, for systematic widespread use, an automated method is required. In this paper, we report an algorithm that automatically detects beat onsets and peaks from noisy field-collected PPG waveforms. We validated the algorithm by clinician evaluation of 100 randomly selected PPG waveform samples. For 99% of the beats, the algorithm was able to credibly identify the onsets and peaks of vascular beats, although the precise locations were ambiguous, given the very noisy data from actual clinical operations. The algorithm appears promising, and future consideration of its diagnostic capabilities and limitations is warranted.

Unattended hemorrhage is a major source of mortality in trauma casualties. In this study, we explore a set of prehospital heart rate (HR) time-series data collected from 358 civilian casualties to examine whether temporal HR patterns can be used for automated hemorrhage identification. Continuous and reliable HR time series are fragmented into overlapping segments of 128 s, with a 118-s overlap between each two neighboring segments, which are projected into a wavelet coefficient space using the Haar wavelet function. A supervised nearest-neighbor clustering algorithm is developed to explore the existence of temporal HR patterns represented by the wavelet coefficients to discriminate casualties with and without (control) major hemorrhage. The clustering algorithm identifies 162 HR patterns. The most frequent pattern is observed in 11 (23%) hemorrhage and 16 (5%) control patients, which is a significant association (p<0.05, chi-square test). When the top 10 patterns are combined for hemorrhage detection, their sensitivity and specificity are 0.68 and 0.79, respectively, and when the top 20 patterns are used sensitivity increases to 0.77 and specificity decreases to 0.71.

In this study, we analyzed a dataset of time-series vital-signs data collected by standard Propaq travel monitor during helicopter transport of 898 civilian trauma casualties from the scene of injury to a receiving trauma center. The goals of the analysis are two fold. First, to determine which combination of the automatically-collected and -qualified vital signs provides the best discrimination between casualties with and without major hemorrhage. Second, to determine whether nonlinear classifiers provide improved discrimination over simpler, linear classifiers. Major hemorrhage is defined by the presence of injuries consistent with hemorrhage in casualties who received one or more units of blood. We randomly selected a subset of the casualties to train and test the classifiers with multiple combinations of the vital-signs variables, and used the area under the receiver operating characteristic curve (ROC AUC) as a decision metric. Based on the results of 100 simulations, we observe that: (i) the best two features obtained are systolic blood pressure and heart rate (mean AUC = 0.75 from a linear classifier), and (ii) the use of nonlinear classifiers does not improve discrimination. These results support earlier findings that the interaction of systolic blood pressure and heart rate is useful for the identification of trauma hemorrhage and that linear classifiers are adequate for many real-world applications.

We developed a quality indexing system to numerically qualify respiratory data collected by vital-sign monitors in order to support reliable post-hoc mining of respiratory data. Each monitor-provided (reference) respiratory rate (RR(R)) is evaluated, second-by-second, to quantify the reliability of the rate with a quality index (QI(R)). The quality index is calculated from: (1) a breath identification algorithm that identifies breaths of 'typical' sizes and recalculates the respiratory rate (RR(C)); (2) an evaluation of the respiratory waveform quality (QI(W)) by assessing waveform ambiguities as they impact the calculation of respiratory rates and (3) decision rules that assign a QI(R) based on RR(R), RR(C) and QI(W). RR(C), QI(W) and QI(R) were compared to rates and quality indices independently determined by human experts, with the human measures used as the 'gold standard', for 163 randomly chosen 15 s respiratory waveform samples from our database. The RR(C) more closely matches the rates determined by human evaluation of the waveforms than does the RR(R) (difference of 3.2 +/- 4.6 breaths min(-1) versus 14.3 +/- 19.3 breaths min(-1), mean +/- STD, p < 0.05). Higher QI(W) is found to be associated with smaller differences between calculated and human-evaluated rates (average differences of 1.7 and 8.1 breaths min(-1) for the best and worst QI(W), respectively). Establishment of QI(W) and QI(R), which ranges from 0 for the worst-quality data to 3 for the best, provides a succinct quantitative measure that allows for automatic and systematic selection of respiratory waveforms and rates based on their data quality.