Design and evaluation of RFID deployments in a trauma resuscitation bay

Measuring intraoperative surgical instrument use with radio-frequency identification

Objective

Surgical instrument oversupply drives cost, confusion, and workload in the operating room. With an estimated 78%–87% of instruments being unused, many health systems have recognized the need for supply refinement. By manually recording instrument use and tasking surgeons to review instrument trays, previous quality improvement initiatives have achieved an average 52% reduction in supply. While demonstrating the degree of instrument oversupply, previous methods for identifying required instruments are qualitative, expensive, lack scalability and sustainability, and are prone to human error. In this work, we aim to develop and evaluate an automated system for measuring surgical instrument use.

Materials and Methods

We present the first system to our knowledge that automates the collection of real-time instrument use data with radio-frequency identification (RFID). Over 15 breast surgeries, 10 carpometacarpal (CMC) arthroplasties, and 4 craniotomies, instrument use was tracked by both a trained observer manually recording instrument use and the RFID system.

Results

The average Cohen’s Kappa agreement between the system and the observer was 0.81 (near perfect agreement), and the system enabled a supply reduction of 50.8% in breast and orthopedic surgery. Over 10 monitored breast surgeries and 1 CMC arthroplasty with reduced trays, no eliminated instruments were requested, and both trays continue to be used as the supplied standard. Setup time in breast surgery decreased from 23 min to 17 min with the reduced supply.

Conclusion

The RFID system presented herein achieves a novel data stream that enables accurate instrument supply optimization.

Speech-Based Activity Recognition for Trauma Resuscitation

We present a speech-based approach to recognize team activities in the context of trauma resuscitation. We first analyzed the audio recordings of trauma resuscitations in terms of activity frequency, noise-level, and activity-related keyword frequency to determine the dataset characteristics. We next evaluated different audio-preprocessing parameters (spectral feature types and audio channels) to find the optimal configuration. We then introduced a novel neural network to recognize the trauma activities using a modified VGG network that extracts features from the audio input. The output of the modified VGG network is combined with the output of a network that takes keyword text as input, and the combination is used to generate activity labels. We compared our system with several baselines and performed a detailed analysis of the performance results for specific activities. Our results show that our proposed architecture that uses Mel-spectrum spectral coefficients features with a stereo channel and activity-specific frequent keywords achieve the highest accuracy and average F1-score.

Object motion detection based on passive UHF RFID tags using a hidden Markov model-based classifier

We present an object motion detection system using backscattered signal strength of passive UHF RFID tags as a sensor for providing information on the movement and identity of work objects-important cues for activity recognition. For using the signal strength for accurate detection of object movement we propose a novel Markov model with continuous observations, RSSI preprocessor, frame-based data segmentation, and motion-transition finder. We use the change of backscattered signal strength caused by tag's relocation to reliably detect movement of tagged objects. To maximize the accuracy of movement detection, an HMM-based classifier is designed and trained for dynamic settings, and the frequency of transitions between stationary/moving states that is characteristic for different object types. We deployed a RFID system in a hospital trauma bay and evaluated our approach with data recorded in the trauma room during 28 simulated resuscitations performed by trauma teams. Our motion detection system shows 89.5% accuracy in this domain.

Deep Neural Network for RFID-Based Activity Recognition

We propose a Deep Neural Network (DNN) structure for RFID-based activity recognition. RFID data collected from several reader antennas with overlapping coverage have potential spatiotemporal relationships that can be used for object tracking. We augmented the standard fully-connected DNN structure with additional pooling layers to extract the most representative features. For model training and testing, we used RFID data from 12 tagged objects collected during 25 actual trauma resuscitations. Our results showed 76% recognition micro-accuracy for 7 resuscitation activities and 85% average micro-accuracy for 5 resuscitation phases, which is similar to existing system that, however, require the user to wear an RFID antenna.