UNASSIGNED: Large language models (LLMs) have potential to increase the efficiency of information extraction from unstructured clinical notes in electronic medical records.
UNASSIGNED: To assess the utility and reliability of an LLM, ChatGPT-4 (OpenAI), to analyze clinical narratives and identify helmet use status of patients injured in micromobility-related accidents.
UNASSIGNED: This cross-sectional study used publicly available, deidentified 2019 to 2022 data from the US Consumer Product Safety Commission\'s National Electronic Injury Surveillance System, a nationally representative stratified probability sample of 96 hospitals in the US. Unweighted estimates of e-bike, bicycle, hoverboard, and powered scooter-related injuries that resulted in an emergency department visit were used. Statistical analysis was performed from November 2023 to April 2024.
UNASSIGNED: Patient helmet status (wearing vs not wearing vs unknown) was extracted from clinical narratives using (1) a text string search using researcher-generated text strings and (2) the LLM by prompting the system with low-, intermediate-, and high-detail prompts. The level of agreement between the 2 approaches across all 3 prompts was analyzed using Cohen κ test statistics. Fleiss κ was calculated to measure the test-retest reliability of the high-detail prompt across 5 new chat sessions and days. Performance statistics were calculated by comparing results from the high-detail prompt to classifications of helmet status generated by researchers reading the clinical notes (ie, a criterion standard review).
UNASSIGNED: Among 54 569 clinical notes, moderate (Cohen κ = 0.74 [95% CI, 0.73-0.75) and weak (Cohen κ = 0.53 [95% CI, 0.52-0.54]) agreement were found between the text string-search approach and the LLM for the low- and intermediate-detail prompts, respectively. The high-detail prompt had almost perfect agreement (κ = 1.00 [95% CI, 1.00-1.00]) but required the greatest amount of time to complete. The LLM did not perfectly replicate its analyses across new sessions and days (Fleiss κ = 0.91 across 5 trials; P < .001). The LLM often hallucinated and was consistent in replicating its hallucinations. It also showed high validity compared with the criterion standard (n = 400; κ = 0.98 [95% CI, 0.96-1.00]).
UNASSIGNED: This study\'s findings suggest that although there are efficiency gains for using the LLM to extract information from clinical notes, the inadequate reliability compared with a text string-search approach, hallucinations, and inconsistent performance significantly hinder the potential of the currently available LLM.

In the field of industrial safety, wearing helmets plays a vital role in ensuring workers\' health. Aiming at addressing the complex background in the industrial environment, caused by differences in distance, the helmet small target wearing detection methods for misdetection and omission detection problems are needed. An improved YOLOv8 safety helmet wearing detection network is proposed to enhance the capture of details, improve multiscale feature processing and improve the accuracy of small target detection by introducing Dilation-wise residual attention module, atrous spatial pyramid pooling and normalized Wasserstein distance loss function. Experiments were conducted on the SHWD dataset, and the results showed that the mAP of the improved network improved to 92.0%, which exceeded that of the traditional target detection network in terms of accuracy, recall, and other key metrics. These findings further improved the detection of helmet wearing in complex environments and greatly enhanced the accuracy of detection.

OBJECTIVE: During a season of high school football, adolescents with actively developing brains experience a considerable number of head impacts. Our aim was to determine whether repetitive head impacts in the absence of a clinically diagnosed concussion during a season of high school football produce changes in cognitive performance or functional connectivity of the salience network and its central hub, the dorsal anterior cingulate cortex.
METHODS: Football players were instrumented with the Head Impact Telemetry System during all practices and games, and the helmet sensor data were used to compute a risk-weighted exposure metric (RWEcp), accounting for the cumulative risk during the season. Participants underwent MRI and a cognitive battery (ImPACT) before and shortly after the football season. A control group of noncontact/limited-contact-sport athletes was formed from 2 cohorts: one from the same school and protocol and another from a separate, nearly identical study.
RESULTS: Sixty-three football players and 34 control athletes were included in the cognitive performance analysis. Preseason, the control group scored significantly higher on the ImPACT Visual Motor (P = .04) and Reaction Time composites (P = .006). These differences increased postseason (P = .003, P < .001, respectively). Additionally, the control group had significantly higher postseason scores on the Visual Memory composite (P = .001). Compared with controls, football players showed significantly less improvement in the Verbal (P = .04) and Visual Memory composites (P = .01). A significantly greater percentage of contact athletes had lower-than-expected scores on the Verbal Memory (27% versus 6%), Visual Motor (21% versus 3%), and Reaction Time composites (24% versus 6%). Among football players, a higher RWEcp was significantly associated with greater increments in ImPACT Reaction Time (P = .03) and Total Symptom Scores postseason (P = .006). Fifty-seven football players and 13 control athletes were included in the imaging analyses. Postseason, football players showed significant decreases in interhemispheric connectivity of the dorsal anterior cingulate cortex (P = .026) and within-network connectivity of the salience network (P = .018). These decreases in dorsal anterior cingulate cortex interhemispheric connectivity and within-network connectivity of the salience network were significantly correlated with deteriorating ImPACT Total Symptom (P = .03) and Verbal Memory scores (P = .04).
CONCLUSIONS: Head impact exposure during a single season of high school football is negatively associated with cognitive performance and brain network connectivity. Future studies should further characterize these short-term effects and examine their relationship with long-term sequelae.

This study investigates the impact of helmet use on the incidence of facial fractures in bicycle accidents. Analyzing data from hospitalized bicyclists between 2005 and 2016, the research focused on the correlation between helmet usage and various facial fractures. The study included 1256 bicyclists with known helmet use, among whom 277 individuals (22%) were identified with a total of 521 facial fractures. The findings revealed a significant reduction in the likelihood of facial fractures among helmeted cyclists compared with those without helmets (odds ratio, 0.65; confidence interval, 0.50-0.85; P=0.002). Specifically, the odds of sustaining fractures in the zygoma, orbit, nose, and maxilla were decreased by 47%, 46%, 43%, and 33%, respectively, among helmeted cyclists. However, helmet use did not significantly alter the odds of mandible fractures. Overall, the use of helmets in bicycling significantly lowered the risk of midface fractures but showed no notable effect on mandible fractures in severe cycling incidents.

OBJECTIVE: To compare the impact attenuating capabilities between ice hockey helmets manufactured with and without XRD impact protection foam, worn with and without a XRD skullcap, at reducing sub-concussive head accelerations.
METHODS: Quasi-experimental laboratory.
METHODS: Ice hockey helmets were fit onto a Hybrid III 50th Head Form Head and dropped 25 times onto the left temporal side for each condition: XRD foam helmet, XRD foam helmet with XRD skullcap adjunct, non-XRD foam helmet, and non-XRD foam helmet with XRD skullcap adjunct. The helmets were dropped from a height that resulted in sub-concussive linear accelerations (25-80 g\'s). Using a tri-axial accelerometer, peak linear accelerations (g) were measured, and the average was used to compare impact attenuation properties across the four conditions.
RESULTS: The highest linear accelerations were observed in the XRD foam helmet without skullcap (32.97 ± 0.61 g) and were significantly greater (p < 0.001) than the XRD helmet with skullcap (21.38 ± 0.76 g). The helmet without XRD foam elicited the lowest peak linear accelerations (16.10 ± 0.73 g) which were significantly lower than the XRD foam helmet regardless of whether the skullcap was added (p < 0.001).
CONCLUSIONS: Although sub-concussive loads are potentially just as dangerous, much of the research regarding helmet and skullcap efficacy appears to be at high concussive impacts; <70 g\'s. The findings suggest that helmets with incorporated XRD foam, either within the design or added as an adjunct, are less effective at attenuating linear accelerations at sub-concussive levels than the low-density foam helmet.

Using data from the 2022 Korea Community Health Survey (n = 13 320), this study investigated helmet use and related factors among Korean adults using personal mobility devices, without distinguishing between private and hired users. Among mobility device users, 32.1% responded that they always wore a helmet. The proportion of helmet use was 35.2% among men, 25.8% among women, 29.2% among those aged 19-44 years, 42.3% among those aged 45-64 years and 26.6% among those aged 65 years or older. Furthermore, those who drank less frequently and were physically active were more likely to wear helmets. Moreover, people who always wore a seat belt when driving a car or sitting in the rear seat and people who always wore a helmet when riding a motorcycle were more likely to wear a helmet while using electric personal mobility devices. Approximately one-third of users always wore a helmet. The helmet-wearing rate was related to general characteristics such as gender and education level, and to safety behaviors such as wearing a seat belt when driving a car, sitting in the rear seat of a car, or when riding a motorcycle. In addition to considering personal characteristics investigated in this study, the helmet-wearing rate should be improved through policies or systems at the national or regional levels.

This research sought to evaluate the thermal zones of the upper body and firefighter personal protective equipment (PPE) immediately following uncompensable heat stress (0.03 °C increase/min). We hypothesized that the frontal portion of the head and the inside of the firefighter helmet would be the hottest as measured by infrared thermography. This hypothesis was due to previous research demonstrating that the head accounts for ∼8-10% of the body surface area, but it accounts for ∼20% of the overall body heat dissipation during moderate exercise. Twenty participants performed a 21-min graded treadmill exercise protocol (Altered Modified Naughton) in an environmental chamber (35 °C, 50 % humidity) in firefighter PPE. The body areas analyzed were the frontal area of the head, chest, abdomen, arm, neck, upper back, and lower back. The areas of the PPE that were analyzed were the inside of the helmet and the jacket. The hottest areas of the body post-exercise were the frontal area of the head (mean: 37.3 ± 0.4 °C), chest (mean: 37.5 ± 0.3 °C), and upper back (mean: 37.3 ± 0.4 °C). The coldest area of the upper body was the abdomen (mean: 36.1 ± 0.4 °C). The peak temperature of the inside of the helmet increased (p < 0.001) by 9.8 °C from 27.7 ± 1.6 °C to 37.4 ± 0.7 °C, and the inside of the jacket increased (p < 0.001) by 7.3 °C from 29.2 ± 1.7 °C to 36.5 ± 0.4 °C. The results of this study are relevant for cooling strategies for firefighters.

UNASSIGNED: Headgear designed to protect girls\' lacrosse athletes is widely available and permitted for voluntary use; however, it remains unknown how policies mandating headgear use may change the sport and, particularly regarding impacts during game-play. Therefore, this study compares the impact rates and game play characteristics of girls\' high school lacrosse in Florida which mandates headgear use (HM), with states having no headgear mandate (NHM).
UNASSIGNED: Video from 189 randomly-selected games (HM: 64, NHM: 125) were analyzed. Descriptive statistics, Impact Rates (IR), Impact Rate Ratios (IRR), Impact Proportion Ratios (IPR), and 95% Confidence Intervals (CI) were calculated. IRRs and IPRs with corresponding CIs that excluded 1.00 were deemed statistically significant.
UNASSIGNED: 16,340 impacts (HM:5,821 NHM: 10,519; 86.6 impacts/game, CI: 88.6-93.3) were identified using the Lacrosse Incident Analysis Instrument (LIAI). Most impacts directly struck the body (n = 16,010, 98%). A minority of impacts directly struck a player\'s head (n = 330, 2%). The rate of head impacts was significantly higher in the HM cohort than NHM cohort (IRR = 2.1; 95% CI = 1.7-2.6). Most head impacts (n = 271, 82%) were caused by stick contact in both groups. There was no difference in the proportion of penalties administered for head impacts caused by stick contact between the HM and NHM cohorts (IPR IRRHM/NHM = 0.98; CI = 0.79-1.16). However, there was a significantly greater proportion of head impacts caused by player contact that resulted in a penalty administered in the HM cohort (IPR = 1.44 CI = 1.17-1.54).
UNASSIGNED: These findings demonstrate that mandating headgear use was associated with a two-fold greater likelihood of sustaining a head impact during game play compared to NHM states. A majority of head impacts in both HM and NHM states were caused by illegal stick contact that did not result in penalty.
High school girls’ lacrosse athletes participating in a state with a headgear mandate was twice as likely to sustain a head impact than those participating in states without headgear mandates.Stick contact remains the most common mechanism of head impacts in girls’ lacrosse, regardless of mandating headgear.Regardless of whether headgear was or was not mandated, most head impacts caused by stick contact did not result in a penalty.

BACKGROUND: Wearing a helmet reduces the risk of head injuries substantially in the event of a motorcycle crash. Countries around the world are committed to promoting helmet use, but the progress has been slow and uneven. There is an urgent need for large-scale data collection for situation assessment and intervention evaluation.
METHODS: This study proposes a scalable, low-cost algorithm to estimate helmet-wearing rates. Applying the state-of-the-art deep learning technique for object detection to images acquired from Google Street View, the algorithm has the potential to provide accurate estimates at the global level.
RESULTS: Trained on a sample of 3995 images, the algorithm achieved high accuracy. The out-of-sample prediction results for all three object classes (helmets, drivers, and passengers) reveal a precision of 0.927, a recall value of 0.922, and a mean average precision at 50 (mAP50) of 0.956.
CONCLUSIONS: The remarkable model performance suggests the algorithm\'s capacity to generate accurate estimates of helmet-wearing rates from an image source with global coverage. The significant enhancement in the availability of helmet usage data resulting from this approach could bolster progress tracking and facilitate evidence-based policymaking for helmet wearing globally.

Recently, the interest in the Helmet interface during non-invasive respiratory support (NIRS) has increased due to the COVID-19 pandemic. During NIRS, positive end-expiratory pressure (PEEP) can be given as continuous positive airway pressure (CPAP), which maintains a positive airway pressure throughout the whole respiratory cycle with Helmet as an interface (H-CPAP). The main disadvantage of the H-CPAP is the inability to measure tidal volume (VT). Opto-electronic plethysmography (OEP) is a non-invasive technique that is not sensitive to gas compression/expansion inside the helmet. OEP acquisitions were performed on 28 healthy volunteers (14 females and 14 males) at baseline and during Helmet CPAP. The effect of posture (semi-recumbent vs. prone), flow (50 vs. 60 L/min), and PEEP (0 vs. 5 vs. 10 cmH2O) on the ventilatory and thoracic-abdominal pattern and the operational volumes were investigated. Prone position limited vital capacity, abdominal expansion and chest wall recruitment. A constant flow of 60 L/min reduced the need for the subject to ventilate while having a slight recruitment effect (100 mL) in the semi-recumbent position. A progressive increasing recruitment was found with higher PEEP but limited by the prone position. It is possible to accurately measure tidal volume during H-CPAP to deliver non-invasive ventilatory support using opto-electronic plethysmography during different clinical settings.