A Novel Approach to Characterize State-level Food Environment and Predict Obesity Rate Using Social Media Data: Correlational Study.

BACKGROUND: Community obesity outcomes can reflect the food environment to which the community belongs. Recent studies have suggested that the local food environment can be measured by the degree of food accessibility, and survey data are normally used to calculate food accessibility. However, compared with survey data, social media data are organic, continuously updated, and cheaper to collect. OBJECTIVE: The objective of our study was to use publicly available social media data to learn the relationship between food environment and obesity rates at the state level. METHODS: To characterize the caloric information of the local food environment, we used food categories from Yelp and collected caloric information from MyFitnessPal for each category based on their popular dishes. We then calculated the average calories for each category and created a weighted score for each state. We also calculated 2 other dimensions from the concept of access, acceptability and affordability, to build obesity prediction models. RESULTS: The local food environment characterized using only publicly available social media data had a statistically significant correlation with the state obesity rate. We achieved a Pearson correlation of 0.796 between the predicted obesity rate and the reported obesity rate from the Behavioral Risk Factor Surveillance System across US states and the District of Columbia. The model with 3 generated feature sets achieved the best performance. CONCLUSIONS: Our study proposed a method for characterizing state-level food environments only using continuously updated social media data. State-level food environments were accurately described using social media data, and the model also showed a disparity in the available food between states with different obesity rates. The proposed method should elastically apply to local food environments of different sizes and predict obesity rates effectively.

Healthy vs. Unhealthy Food Images: Image Classification of Twitter Images.

Obesity is a modern public health problem. Social media images can capture eating behavior and the potential implications to health, but research for identifying the healthiness level of the food image is relatively under-explored. This study presents a deep learning architecture that transfers features from a 152 residual layer network (ResNet) for predicting the level of healthiness of food images that were built using images from the Google images search engine gathered in 2020. Features learned from the ResNet 152 were transferred to a second network to train on the dataset. The trained SoftMax layer was stacked on top of the layers transferred from ResNet 152 to build our deep learning model. We then evaluate the performance of the model using Twitter images in order to better understand the generalizability of the methods. The results show that the model is able to predict the images into their respective classes, including Definitively Healthy, Healthy, Unhealthy and Definitively Unhealthy at an F1-score of 78.8%. This finding shows promising results for classifying social media images by healthiness, which could contribute to maintaining a balanced diet at the individual level and also understanding general food consumption trends of the public.

Intern Orthopedic Rotation Versus Emergency Medicine Procedure Month: Which one Derives More Opportunity?

INTRODUCTION: The American College of Graduate Medical Education (ACGME) defines 18 "key procedures" as requirements in emergency medicine (EM) residency programs. The post-graduate year-1 (PGY-1) curriculum provides an early foundation for EM trainees to gain procedural experience, but traditional PGY-1 rotations may not provide robust procedural opportunities. Our objective was to replace a traditional orthopedic rotation with a 4-week rotation that emphasized EM procedure acquisition and comprehension. Although all residents met ACGME procedural requirements before the curricular modification, the purpose of this month was to increase overall procedure numbers. The block contained dedicated procedure shifts in the emergency department as well as an asynchronous, self-directed learning course. We sought to compare the number of procedures performed by PGY-1 residents during their orthopedic rotation (the year before implementation), to the number of procedures performed during their procedure rotation (the year after implementation). METHODS: The total number of procedures performed and logged by PGY-1 residents during the traditional orthopedic rotation (during the year prior to implementation of the new procedure rotation) were compared to the total number of procedures by the first class to undergo the new procedure rotation the following year. Thirty resident logs were reviewed (15 per class). Data were analyzed using SAS NPAR1WAY; Z < 0.05 was considered significant. RESULTS: When compared to the orthopedic rotation, the procedure rotation had statistically significant higher numbers of procedures per resident (22, standard deviation [SD] 12, vs 11.4, SD 7.6; Z = 0.0177). A wide variety of nonorthopedic procedures accounted for the increased numbers, (13.6, SD 10.3, vs 0.9, SD 0.9; Z < 0.001). While the average number of orthopedic procedures was slightly less on the procedure rotation, there was no statistical difference (orthopedic rotation 10.13, procedure rotation 8.26; Z = 0.4605). Notably, fewer procedures were performed when 2 residents were on the procedure rotation at the same time (21 vs 10.1). CONCLUSION: This analysis demonstrated a larger number and a wider variety of procedures performed by PGY-1 residents during a dedicated procedure rotation compared to a traditional orthopedic rotation. Furthermore, exposure to orthopedic procedures did not decline significantly. Limitations of the study include a modest number of subjects. Data may be limited by the consistency of procedure logging by individual residents. Further studies may assess procedural competency after PGY-1 year of training.

Development and validation of an objective structured assessment of technical skill tool for the practice of breech presentation delivery.

OBJECTIVE: To develop and test the validity of an Objective Structured Assessment of Technical Skills (OSATS) tool for breech presentation delivery. MATERIALS AND METHODS: Monocentric prospective study conducted in the Department of Gynecology, Obstetrics, Fetal Medicine and Reproductive Medicine at the University Hospital of Nice. The study consisted of two parts, the development of the OSATS scoring system and its objective validation. Several experts in obstetrics from university hospital centers and private French hospitals were invited to participate in the development phase of the scoring system. For the validation phase, we formed a group of 20 novices and a group of 20 experts, who had to perform a breech presentation delivery on a simulator, according to a standardized scenario. Each participant was filmed and two experts would then evaluate their performance by viewing anonymized videos and using the OSATS score. RESULTS: The scores obtained by the expert group were significantly higher than those of the novice group, with a total score of 21.73/25 versus 6.95/25 (p < 0.0001), a task-specific score of 87.2/110 versus 44.3/110 (p < 0.0001) and an overall score of 108.93/135 versus 51.25/135 (p < 0.0001), respectively. CONCLUSION: The OSATS score developed in this study for breech presentation delivery is a reliable model to assess the competence level in procedural skills using a simulator.

Development and validation of an objective structured assessment of technical skill tool for the practice of vertex presentation delivery.

OBJECTIVE: To develop and test the validity of an objective structured assessment of technical skill (OSATS) tool for vertex presentation delivery simulations. MATERIALS AND METHODS: Monocentric prospective study conducted in the Department of Gynecology, Obstetrics, Fetal Medicine and Reproductive Biology at the University Hospital of Nice. The study consisted of two parts, the development of the scoring system and then its validation. Experts in obstetrics from several academic institutions and private French hospitals were invited to participate in the development phase of the scoring system. For the validation phase, we formed a group of 20 novices and a group of 20 experts, who performed a childbirth simulation according to a standard scenario. Each participant was filmed and then two experts evaluated their performance with the OSATS score by viewing anonymized videos. RESULTS: The scores obtained by the expert group were significantly higher than those of the novice group, whether we compared the total score or each part of the score (task-specific or global) independently. We obtained a p value of 0.03 for the total score, p = 0.036 for the task-specific score, and p < 0.001 for the overall score. CONCLUSION: The OSATS score developed in this study for vertex presentation delivery is a reliable mean to assess the medical students' competence in procedural skills using a simulator.