Search

BackgroundQuality patient care requires comprehensive health care data from a broad set of sources. However, missing data in medical records and matching field selection are 2 real-world challenges in patient-record linkage. ObjectiveIn this study, we aimed to evaluate the extent to which incorporating the missing at random (MAR)–assumption in the Fellegi-Sunter model and using data-driven selected fields improve patient-matching accuracy using real-world use cases. MethodsWe adapted the Fellegi-Sunter model to accommodate missing data using the MAR assumption and compared the adaptation to the common strategy of treating missing values as disagreement with matching fields specified by experts or selected by data-driven methods. We used 4 use cases, each containing a random sample of record pairs with match statuses ascertained by manual reviews. Use cases included health information exchange (HIE) record deduplication, linkage of public health registry records to HIE, linkage of Social Security Death Master File records to HIE, and deduplication of newborn screening records, which represent real-world clinical and public health scenarios. Matching performance was evaluated using the sensitivity, specificity, positive predictive value, negative predictive value, and F1-score. ResultsIncorporating the MAR assumption in the Fellegi-Sunter model maintained or improved F1-scores, regardless of whether matching fields were expert-specified or selected by data-driven methods. Combining the MAR assumption and data-driven fields optimized the F1-scores in the 4 use cases. ConclusionsMAR is a reasonable assumption in real-world record linkage applications: it maintains or improves F1-scores regardless of whether matching fields are expert-specified or data-driven. Data-driven selection of fields coupled with MAR achieves the best overall performance, which can be especially useful in privacy-preserving record linkage.

BackgroundThe COVID-19 pandemic has highlighted the inability of health systems to leverage existing system infrastructure in order to rapidly develop and apply broad analytical tools that could inform state- and national-level policymaking, as well as patient care delivery in hospital settings. The COVID-19 pandemic has also led to highlighted systemic disparities in health outcomes and access to care based on race or ethnicity, gender, income-level, and urban-rural divide. Although the United States seems to be recovering from the COVID-19 pandemic owing to widespread vaccination efforts and increased public awareness, there is an urgent need to address the aforementioned challenges. ObjectiveThis study aims to inform the feasibility of leveraging broad, statewide datasets for population health–driven decision-making by developing robust analytical models that predict COVID-19–related health care resource utilization across patients served by Indiana’s statewide Health Information Exchange. MethodsWe leveraged comprehensive datasets obtained from the Indiana Network for Patient Care to train decision forest-based models that can predict patient-level need of health care resource utilization. To assess these models for potential biases, we tested model performance against subpopulations stratified by age, race or ethnicity, gender, and residence (urban vs rural). ResultsFor model development, we identified a cohort of 96,026 patients from across 957 zip codes in Indiana, United States. We trained the decision models that predicted health care resource utilization by using approximately 100 of the most impactful features from a total of 1172 features created. Each model and stratified subpopulation under test reported precision scores >70%, accuracy and area under the receiver operating curve scores >80%, and sensitivity scores approximately >90%. We noted statistically significant variations in model performance across stratified subpopulations identified by age, race or ethnicity, gender, and residence (urban vs rural). ConclusionsThis study presents the possibility of developing decision models capable of predicting patient-level health care resource utilization across a broad, statewide region with considerable predictive performance. However, our models present statistically significant variations in performance across stratified subpopulations of interest. Further efforts are necessary to identify root causes of these biases and to rectify them.

Objective: To determine self-reported incidences of health and safety hazards among persons who ride rentable electric scooters (e-scooters), knowledge of e-scooter laws, and attitudes and perceptions of the health and safety of e-scooter usage. Methods: A cross-sectional survey of n= 561 e-scooter riders and non-riders was conducted during June of 2019. Results: Almost half of respondents (44%) report that e-scooters pose a threat to the health and safety of riders. Riders and non-riders disagree regarding the hazards that e-scooters pose to pedestrians. Among riders, 15% report crashing or falling off an e-scooter. Only 2.5% of e-scooter riders self-report that they always wear a helmet while riding. Conclusions: E-scooter riders report substantial rates of harmful behavior and injuries. Knowledge of e-scooter laws is limited, and e-scooters introduce threats to the health and safety of riders, pedestrians on sidewalks, and automobile drivers. Enhanced public health interventions are needed to educate about potential health risks and laws associated with e-scooter use and to ensure health in all policies. Additionally, greater consideration should be given to public health, safety, and injury prevention when passing relevant state and local e-scooter laws.

Abstract Background Prescription opioids have been linked to over half of the 28,000 opioid overdose deaths in 2014. High rates of prescription opioid non-medical use have continued despite nearly all states implementing large-scale prescription drug monitoring programs (PDMP), which points to the need to examine the impact of state PDMP’s on curbing inappropriate opioid prescribing. In the short-term, PDMPs have been associated with short-term prescribing declines. Yet little is known about how such policies differentially impact patient subgroups or are interpreted by prescribing providers. Our objective was to compare volumes of prescribed opioids before and after Indiana implemented opioid prescribing emergency rules and stratify the changes in opioid prescribing by patient and provider subgroups. Methods An interrupted time series analysis was conducted using data obtained from the Indiana PDMP. Prescription level data was merged with census data to characterize patient socioeconomic status. Analyses were stratified by patients’ gender, age, opioid dosage, and payer. The primary outcome indicator was the total morphine equivalent dose (MED) of dispensed opioids per day in the state of Indiana. Also considered were number of unique patients, unique providers, and prescriptions; MED per transaction and per day; and number of days supplied. Results After controlling for time trends, we found that total MED for opioids decreased after implementing the new emergency rules, differing by patient gender, age, and payer. The effect was larger for males than females and almost 10 times larger for 0–20 year olds as compared to the 60+ age range. Medicare and Medicaid patients experienced more decline in prescribing than patients with private insurance. Patients with prescriptions paid for by workers’ comp experienced the most significant decline. The emergency rules were associated with decline in both the number of prescribers and the number of day supply. Conclusions Although the Indiana opioid prescribing emergency rules impacted statewide prescribing behavior across all individual patient and provider characteristics, the emergency rules’ effect was not consistent across patient characteristics. Further studies are needed to assess how individual patient characteristics influence the interpretation and application of state policies on opioid prescribing.