Mark I. Darrah

This study was designed to investigate the quality of data in the pre-hospital and emergency departments when using a wearable vital signs monitor and examine the efficacy of a combined model of standard vital signs and respective data quality indices (DQIs) for predicting the need for life-saving interventions (LSIs) in trauma patients. It was hypothesised that prediction of needs for LSIs in trauma patients is associated with data quality. Also, a model utilizing vital signs and DQIs to predict the needs for LSIs would be able to outperform models using vital signs alone. Data from 104 pre-hospital trauma patients transported by helicopter were analysed, including means and standard deviations of continuous vital signs, related DQIs and Glasgow coma scale (GCS) scores for LSI and non-LSI patient groups. DQIs involved percentages of valid measurements and mean deviation ratios. Various multivariate logistic regression models for predicting LSI needs were also obtained and compared through receiver-operating characteristic (ROC) curves. Demographics of patients were not statistically different between LSI and non-LSI patient groups. In addition, ROC curves demonstrated better prediction of LSI needs in patients using heart rate and DQIs (area under the curve [AUC] of 0.86) than using heart rate alone (AUC of 0.73). Likewise, ROC curves demonstrated better prediction using heart rate, total GCS score and DQIs (AUC of 0.99) than using heart rate and total GCS score (AUC of 0.92). AUCs were statistically different (p < 0.05). This study showed that data quality could be used in addition to continuous vital signs for predicting the need for LSIs in trauma patients. Importantly, trauma systems should incorporate processes to regulate data quality of physiologic data in the pre-hospital and emergency departments. By doing so, data quality could be improved and lead to better prediction of needs for LSIs in trauma patients.

Accurate and effective diagnosis of actual injury severity can be problematic in trauma patients. Inherent physiologic compensatory mechanisms may prevent accurate diagnosis and mask true severity in many circumstances. The objective of this project was the development and validation of a multiparameter machine learning algorithm and system capable of predicting the need for life-saving interventions (LSIs) in trauma patients. Statistics based on means, slopes, and maxima of various vital sign measurements corresponding to 79 trauma patient records generated over 110,000 feature sets, which were used to develop, train, and implement the system. Comparisons among several machine learning models proved that a multilayer perceptron would best implement the algorithm in a hybrid system consisting of a machine learning component and basic detection rules. Additionally, 295,994 feature sets from 82 h of trauma patient data showed that the system can obtain 89.8 % accuracy within 5 min of recorded LSIs. Use of machine learning technologies combined with basic detection rules provides a potential approach for accurately assessing the need for LSIs in trauma patients. The performance of this system demonstrates that machine learning technology can be implemented in a real-time fashion and potentially used in a critical care environment.

Automation and decision support systems are vital for improving critical patient care in the battlefield environment. However, advances in data management, sensor fusion, and decision support algorithms must be developed and incorporated into existing patient monitoring systems for this technology to improve battlefield patient care. This paper examines issues related to research and development of advanced monitoring and decision support systems for use both on the battlefield and in the civilian trauma environment.