Poster W8 - Wearable Spirometry: Feasibility of Measuring Volume of Inspiration via Non-invasive Motion Sensors

Introduction: Postoperative pulmonary complications (PPCs) encompass a broad and heterogenous spectrum of conditions which serve as a leading cause of suboptimal surgical outcomes globally. Approximately 10-20% of the 310 million patients undergoing surgery each year will develop a PPC and up to 25% of all deaths occurring within one week post-operatively attributed to PPCs. Incentive spirometry (IS) has traditionally served as a cornerstone in the prophylaxis and management of PPCs. The incentive spirometer works by emulating a natural deep breath, serving simply as a visual tool for both patients and providers to gauge the quality and depth of lung expansion. Despite its widespread acceptance in clinical practice, recent literature has shed light on various limitations associated with conventional incentive spirometry. Some of these drawbacks include patient compliance, nursing burden, lack of data storage for longitudinal tracking, and ergonomic disincentives of a bulky device. Quantitatively evaluation of patient effort and progress are the foundation of post-operative assessment of the impact of incentive spirometry on patient outcomes.
The continual advancements of digital health technologies and artificial intelligence present a compelling opportunity to address these gaps. It is possible that we might identify unique patterns in chest wall motion via motion sensors adhered to the patient’s thorax to easily measure and track volume of inspiration and respiratory effort post-operatively. This technology could open a door to improved IS compliance or improved ergonomics and ease of use and may ultimately result in decreased nursing burden and improved post-operative outcomes.

Materials and

Methods: Using hypoallergenic surgical tape, a motion sensor was adhered to the right thorax of healthy volunteers at approximately the level of the 9th and 10th ribs at the mid-axillary line. While seated upright with the motion sensor in place, participants took three breaths through a traditional incentive spirometer at each of the following volumes: 250mL, 500mL, 750mL, 1000mL, 1250mL, 1500mL, 1750mL, 2000mL, 2250mL, and 2500mL. Throughout this period, the wearable device detected chest wall expansion and transmitted the data to a secure server for analysis and model creation.

Motion data was quality checked and corrupted waveforms were removed. Waveforms corresponding to activity (motion artifacts) were also be removed, per standard signal processing techniques. The waveforms were then parsed out by corresponding volume of inspiration and grouped into low-volume (250, 500, 750mL), medium-volume (1000, 1250, 1500mL), and high-volume (2000, 2250, 2500mL) inspiration. A machine learning model was trained on these sequences, learning to recognize patterns in chest wall motion associated with each incentive lung volume category (low, medium, or high). A leave-one-out validation strategy was used to assess the model performance.

Results, Conclusions, and Discussions: All subjects (n=6: 3 males, 3 females) included in this initial pilot study were healthy volunteers with no known respiratory conditions. Movement in the y-axis corresponded to movement perpendicular to the chest wall (outward motion) and z-axis signal corresponded to movement in the upwards and outwards (diagonal, direction). There were visible differences in waveform amplitude in the y and z axes as participants took higher-volume breaths (Figure 1). When the model was tested against traditional incentive spirometry volumes of inspiration, the average AUC across all 6 participants was 0.80 (range 0.68-0.92). The model performed best at identifying low-volume breaths (average AUC 0.85) and high-volume breaths (average AUC 0.80).

This proof-of-concept, feasibility study demonstrated the potential of wearable motion sensors to assess volume of inspiration under sedentary conditions. These findings suggest that movement of the thorax during inspiration may predict or correlate with the volume of air inhaled, suggesting a promising application for artificial intelligence (AI). The data presented is small-scale and still preliminary. However, it highlights an opportunity to leverage simple and cost-effective wearable technology with advanced computational models, to enhance the imperfect practice of incentive spirometry. With more research and development, this wearable technology offers the potential to automatically remind patients to complete breathing exercises via timed vibrations and offers the ability for providers to interact with, document, and analyze longitudinal spirometry data.

This study is limited by measurement in a limited cohort size, lack of controlling for height or weight, inclusion of healthy participants only, and measurement exclusively in the sedentary position. Future studies underway include a larger population, post-operative patients, consideration of body habitus, and measurement in supine and seated positions.

These results, while limited, suggest that wearable technology and corresponding custom models are capable of determining volume of inspiration from chest wall motion alone. As such, this technology could be used to improve compliance and potentially even clinical outcomes by offering more standardized and consistent monitoring, documentation, and data analysis. Further research involving a broader and more diverse patient population is underway to fully pilot and examine these hypotheses in real-world clinical settings.

Acknowledgements (Optional):