Objective The purpose of this study was to identify objective measures that predict surgeon nontechnical skills (NTS) during surgery. Background NTS are cognitive and social skills that impact operative performance and patient outcomes. Current methods for NTS assessment in surgery rely on observation-based tools to rate intraoperative behavior. These tools are resource intensive (e.g., time for observation or manual labeling) to perform; therefore, more efficient approaches are needed. Method Thirty-four robotic-assisted surgeries were observed. Proximity sensors were placed on the surgical team and voice recorders were placed on the surgeon. Surgeon NTS was assessed by trained observers using the NonTechnical Skills for Surgeons (NOTSS) tool. NTS behavior metrics from the sensors included communication, speech, and proximity features. The metrics were used to develop mixed effect models to predict NOTSS score and in machine learning classifiers to distinguish between exemplar NTS scores (highest NOTSS score) and non-exemplar scores. Results NTS metrics were collected from 16 nurses, 12 assistants, 11 anesthesiologists, and four surgeons. Nineteen behavior features and overall NOTSS score were significantly correlated (12 communication features, two speech features, five proximity features). The random forest classifier achieved the highest accuracy of 70% (80% F1 score) to predict exemplar NTS score. Conclusion Sensor-based measures of communication, speech, and proximity can potentially predict NOTSS scores of surgeons during robotic-assisted surgery. These sensing-based approaches can be utilized for further reducing resource costs of NTS and team performance assessment in surgical environments. Application Sensor-based assessment of operative teams’ behaviors can lead to objective, real-time NTS measurement.

No abstract

No abstract

Effective communication in healthcare is critical for effective patient care. This study explored communication in an acute care team simulation where medical students were asked to perform as the physician in charge to manage pre-and post-operative patients. Students' speech was analyzed to determine differences according to communication receiver (i.e., student to nurse, student to patient). Statistical analyses revealed that speech ratio, speech intensity, and number of questions students asked to the nurse or patient were significantly different between communication receivers (p<0.05). Furthermore, communications initiated by student to nurse contributed 34% of the total time, and 31% from student to patient. Lastly, students spoke 3% higher volume to patient than to nurse, 20% more questions were asked to nurse than to patient. Findings indicated an overall positive relationship between measured audio variables and performance.To analyze communication in a team-based setting, Fairbanks, Bisantz and Sunm (2007) conducted an observational study on emergency physician and nursing staff communication patterns in an academic emergency department (ED). Using link analysis, a technique that evaluates connections between providers, Fairbanks et al investigated links between provider roles, mode (i.e., verbal or non-verbal), and frequency and duration of interactions. Findings from this study suggest that nurses tend to be at the center of communication based on the frequency of speech interactions. By understanding communication roles and patterns among teams, areas for performance improvement and workload distribution can also be identified .There are numerous ways of evaluating healthcare providers' communication. For example, the Communication Assessment Tool (CAT) is a patient satisfaction-type evaluation to measure physicians' communication from a patient's perspective (Makoul et al, 2007). However, this assessment is subjective, which can potentially introduce bias that negatively impacts the instrument's validity. Other studies have suggested sensing-based wearable devices for measuring communication to understand teamwork; however, raters were still needed to process the audio data (Yu et al, 2015). Although these tools can provide valuable insight into communication, audio patterns collected from voice data may provide objective metrics to evaluate communication behaviors with greater effectiveness. The purpose of this study was to: 1) Identify objective metrics that can be derived from voice audio recordings, and 2) Determine their relationship to clinical performance in a simulated patient care setting. METHODS Study DesignThis study was approved by Indiana University School of Medicine's institutional review board. Participants were third year medical students (MS3) on 588 being a manikin and the Student desired to speak clearly for the manikin's microphone to pick up.According to the indication of Students' performance, all measured variables had a positive relationship with their scores. The frequency...

No abstract