Wearable airbag technology and machine learned models to mitigate falls after stroke.

BACKGROUND: Falls are a common complication experienced after a stroke and can cause serious detriments to physical health and social mobility, necessitating a dire need for intervention. Among recent advancements, wearable airbag technology has been designed to detect and mitigate fall impact. However, these devices have not been designed nor validated for the stroke population and thus, may inadequately detect falls in individuals with stroke-related motor impairments. To address this gap, we investigated whether population-specific training data and modeling parameters are required to pre-detect falls in a chronic stroke population. METHODS: We collected data from a wearable airbag's inertial measurement units (IMUs) from individuals with (n = 20 stroke) and without (n = 15 control) history of stroke while performing a series of falls (842 falls total) and non-falls (961 non-falls total) in a laboratory setting. A leave-one-subject-out crossvalidation was used to compare the performance of two identical machine learned models (adaptive boosting classifier) trained on cohort-dependent data (control or stroke) to pre-detect falls in the stroke cohort. RESULTS: The average performance of the model trained on stroke data (recall = 0.905, precision = 0.900) had statistically significantly better recall (P = 0.0035) than the model trained on control data (recall = 0.800, precision = 0.944), while precision was not statistically significantly different. Stratifying models trained on specific fall types revealed differences in pre-detecting anterior-posterior (AP) falls (stroke-trained model's F1-score was 35% higher, P = 0.019). Using activities of daily living as non-falls training data (compared to near-falls) significantly increased the AUC (Area under the receiver operating characteristic) for classifying AP falls for both models (P < 0.04). Preliminary analysis suggests that users with more severe stroke impairments benefit further from a stroke-trained model. The optimal lead time (time interval pre-impact to detect falls) differed between control- and stroke-trained models. CONCLUSIONS: These results demonstrate the importance of population sensitivity, non-falls data, and optimal lead time for machine learned pre-impact fall detection specific to stroke. Existing fall mitigation technologies should be challenged to include data of neurologically impaired individuals in model development to adequately detect falls in other high fall risk populations. Trial registration https://clinicaltrials.gov/ct2/show/NCT05076565 ; Unique Identifier: NCT05076565. Retrospectively registered on 13 October 2021.

Social Media Utilization Trends in Orthopaedic Surgery Residency Programs During the COVID-19 Pandemic.

BACKGROUND: The COVID-19 pandemic has changed the way orthopaedics programs are educating and recruiting residents and applicants. With an increased focus on online and virtual programming, there has been an uptick in social media usage by orthopaedics residencies as a means of communicating with applicants. This study investigated the growth in utilization of social media platforms by residency programs since the beginning of the COVID-19 pandemic. METHODS: Instagram and Twitter were queried for each orthopaedic surgery residency program. It was determined if each program with a corresponding social media account was created before or after March 1, 2020. The number of posts per month were tabulated for accounts that existed prior to March 1, 2020. RESULTS: 187 orthopaedic surgery residency programs were identified using the AAMC ERAS database. Of these programs, 74 (41.6%) were found to have an Instagram profile, and 50 (26.7%) were found to have a Twitter page. Of the 74 Instagram profiles, 45 were created after March 1, 2020, representing a 155% increase. Of the 50 Twitter pages, 15 were created after March 1, 2020, representing a 43% increase. Instagram accounts that were active before the pandemic had a 96% increase in the number of posts per month, on average, after March 1, 2020. CONCLUSION: Over one-third of programs are utilizing social media for recruitment purposes. There has been an 155% increase in Instagram and 43% increase in Twitter usage by residency programs since March 1, 2020. Instagram accounts created prior to the pandemic also demonstrated a near doubling of increased utilization after March. This represents a new, cost-effective way to connect with applicants in a time when in-person interactions are limited.Level of Evidence: III.

Non-invasive terahertz imaging of tissue water content for flap viability assessment.

Accurate and early prediction of tissue viability is the most significant determinant of tissue flap survival in reconstructive surgery. Perturbation in tissue water content (TWC) is a generic component of the tissue response to such surgeries, and, therefore, may be an important diagnostic target for assessing the extent of flap viability in vivo. We have previously shown that reflective terahertz (THz) imaging, a non-ionizing technique, can generate spatially resolved maps of TWC in superficial soft tissues, such as cornea and wounds, on the order of minutes. Herein, we report the first in vivo pilot study to investigate the utility of reflective THz TWC imaging for early assessment of skin flap viability. We obtained longitudinal visible and reflective THz imagery comparing 3 bipedicled flaps (i.e. survival model) and 3 fully excised flaps (i.e. failure model) in the dorsal skin of rats over a postoperative period of 7 days. While visual differences between both models manifested 48 hr after surgery, statistically significant (p < 0.05, independent t-test) local differences in TWC contrast were evident in THz flap image sets as early as 24 hr. Excised flaps, histologically confirmed as necrotic, demonstrated a significant, yet localized, reduction in TWC in the flap region compared to non-traumatized skin. In contrast, bipedicled flaps, histologically verified as viable, displayed mostly uniform, unperturbed TWC across the flap tissue. These results indicate the practical potential of THz TWC sensing to accurately predict flap failure 24 hours earlier than clinical examination.