Predicting task performance for intelligent human-machine interactions.

Human-machine teams are deployed in a diverse range of task environments and paradigms that may have high failure costs (e.g., nuclear power plants). It is critical that the machine team member can interact with the human effectively without reducing task performance. These interactions may be used to manage the human's workload state intelligently, as the overall workload is related to task performance. Intelligent human-machine teaming systems rely on a facet of the human's state to determine how interaction occurs, but typically only consider the human's state at the current time step. Future task performance predictions may be leveraged to determine if adaptations need to occur in order to prevent future performance degradation. An individualized task performance prediction algorithm that relies on a multi-faceted human workload estimate is shown to predict a supervisor's task performance accurately. The analysis varies the prediction time frame (from 0 to 300 s) and compares results to a generalized algorithm.

Emergency Clinical Procedure Detection With Deep Learning.

Information about a patient's state is critical for hospitals to provide timely care and treatment. Prior work on improving the information flow from emergency medical services (EMS) to hospitals demonstrated the potential of using automated algorithms to detect clinical procedures. However, prior work has not made effective use of video sources that might be available during patient care. In this paper we explore the use convolutional neural networks (CNNs) on raw video data to determine how well video data alone can automatically identify clinical procedures. We apply multiple deep learning models to this problem, with significant variation in results. Our findings indicate performance improvements compared to prior work, but also indicate a need for more training data to reach clinically deployable levels of success.

Automatic Clinical Procedure Detection for Emergency Services.

Understanding a patient's state is critical to providing optimal care. However, information loss occurs during patient hand-offs (e.g., emergency services (EMS) transferring patient care to a receiving hospital), which hinders care quality. Augmenting the information flow from an EMS vehicle to a receiving hospital may reduce information loss and improve patient outcomes. Such augmentation requires a noninvasive system that can automatically recognize clinical procedures being performed and send near real-time information to a receiving hospital. An automatic clinical procedure detection system that uses wearable sensors, video, and machine-learning to recognize clinical procedures within a controlled environment is presented. The system demonstrated how contextual information and a majority vote method can substantially improve procedure recognition accuracy. Future work concerning computer vision techniques and deep learning are discussed.

Feasibility Assessment of a Pre-Hospital Automated Sensing Clinical Documentation System.

Clinical documentation in the pre-hospital setting is challenged by limited resources and fast-paced, high-acuity. Military and civilian medics are responsible for performing procedures and treatments to stabilize the patient, while transporting the injured to a trauma facility. Upon arrival, medics typically give a verbal report from memory or informal source of documentation such as a glove or piece of tape. The development of an automated documentation system would increase the accuracy and amount of information that is relayed to the receiving physicians. This paper discusses the 12-week deployment of an Automated Sensing Clinical Documentation (ASCD) system among the Nashville Fire Department EMS paramedics. The paper examines the data collection methods, operational challenges, and perceptions surrounding real-life deployment of the system. Our preliminary results suggest that the ASCD system is feasible for use in the pre-hospital setting, and it revealed several barriers and their solutions.