ABSTRACT
Opiates used for acute pain are an established risk factor for chronic opioid use (COU). Patient characteristics contribute to progression from acute opioid use to COU, but most are not clinically modifiable. To develop and validate machine-learning algorithms that use claims data to predict progression from acute to COU in the Medicaid population, Adult opioid naïve Medicaid patients from 6 anonymized states who received an opioid prescription between 2015 and 2019 were included. Five machine learning (ML) Models were developed, and model performance assessed by area under the receiver operating characteristic curve (auROC), precision and recall. In the study, 29.9% (53820/180000) of patients transitioned from acute opioid use to COU. Initial opioid prescriptions in COU patients had increased morphine milligram equivalents (MME) (33.2 vs. 23.2), tablets per prescription (45.6 vs. 36.54), longer prescriptions (26.63 vs 24.69 days), and higher proportions of tramadol (16.06% vs. 13.44%) and long acting oxycodone (0.24% vs 0.04%) compared to non- COU patients. The top performing model was XGBoost that achieved average precision of 0.87 and auROC of 0.63 in testing and 0.55 and 0.69 in validation, respectively. Top-ranking prescription-related features in the model included quantity of tablets per prescription, prescription length, and emergency department claims. In this study, the Medicaid population, opioid prescriptions with increased tablet quantity and days supply predict increased risk of progression from acute to COU in opioid-naïve patients. Future research should evaluate the effects of modifying these risk factors on COU incidence.
ABSTRACT
PURPOSE: Aquatic activities are some of the most widely enjoyed sports and recreational activities in the United States. This study aimed to analyze the risks and types of craniofacial injuries associated with various aquatic activities. METHODS: We retrospectively analyzed aquatic activity-related craniofacial injuries between 2010 and 2019 using the National Electronic Injury Surveillance System database. Aquatic activities included swimming, diving, surfing, water skiing, and water tubing. Risks and types of craniofacial injuries were analyzed according to the types of aquatic activities, age, and sex. RESULTS: Among 48,112 patients with aquatic activity-related injuries, 9,529 (19.8%) had craniofacial injuries. In decreasing order of frequency, the causes of craniofacial injuries were swimming (79.6%), diving (7.5%), surfing (5.9%), water skiing (3.6%), and water tubing (3.5%). The proportion of craniofacial injuries among all injuries was higher in males than in females (22.8 vs 16.3%, P < .001), and decreased with age: 27.7% in 0 to 5 years, 21.5% in 6 to 11 years, 20.5% in 12 to 17 years, and 15.2% in ≥18 years (P < .001). Additionally, the proportion of craniofacial injuries was highest in diving (38.7%), and lowest in swimming (18.1%, P < .001). The male-to-female ratio in the proportion of patients with craniofacial injuries was highest in swimming at 1.42, and close to unity (0.97-1.13) in other activities. The most common type of craniofacial injury was laceration (43.5%), followed by concussion/internal organ injury (38.9%), contusion/abrasion (11.3%), and fracture (3%). Among all craniofacial injuries, the proportion of craniofacial fractures was highest in water tubing (8.5%) and lowest in swimming (2.2%, P < .001). CONCLUSIONS: Craniofacial injuries are a frequent cause of morbidity related to aquatic activities. Substantial variability exists in the risk and pattern of craniofacial injuries depending on the type of activity, age, and sex. These findings may aid in instituting educational programs and preventive measures against aquatic activity-related craniofacial injuries.
