Bmc Med Res Methodol
-
Bmc Med Res Methodol · Mar 2015
The impact of standardizing the definition of visits on the consistency of multi-database observational health research.
Use of administrative claims from multiple sources for research purposes is challenged by the lack of consistency in the structure of the underlying data and definition of data across claims data providers. This paper evaluates the impact of applying a standardized revenue code-based logic for defining inpatient encounters across two different claims databases. ⋯ In an effort to improve consistency in research results across database one should review sources of database heterogeneity, such as the way data holders process raw claims data. Our study showed that applying the Observational Medical Outcomes Partnership (OMOP) CDM with a standardized approach for defining inpatient visits during the extract, transfer, and load process can decrease the heterogeneity observed in disease prevalence estimates across two different claims data sources.
-
Bmc Med Res Methodol · Jan 2015
Predictive modeling in pediatric traumatic brain injury using machine learning.
Pediatric traumatic brain injury (TBI) constitutes a significant burden and diagnostic challenge in the emergency department (ED). While large North American research networks have derived clinical prediction rules for the head injured child, these may not be generalizable to practices in countries with traditionally low rates of computed tomography (CT). We aim to study predictors for moderate to severe TBI in our ED population aged < 16 years. ⋯ In this study, we demonstrated the feasibility of using machine learning as a tool to predict moderate to severe TBI. If validated on a large scale, the ML method has the potential not only to guide discretionary use of CT, but also a more careful selection of head injured children who warrant closer monitoring in the hospital.
-
Bmc Med Res Methodol · Jan 2015
Randomized Controlled TrialPersonalized contact strategies and predictors of time to survey completion: analysis of two sequential randomized trials.
Effective strategies for contacting and recruiting study participants are critical in conducting clinical research. In this study, we conducted two sequential randomized controlled trials of mail- and telephone-based strategies for contacting and recruiting participants, and evaluated participant-related variables' association with time to survey completion and survey completion rates. Subjects eligible for this study were survivors of acute lung injury who had been previously enrolled in a 12-month observational follow-up study evaluating their physical, cognitive and mental health outcomes, with their last study visit completed at a median of 34 months previously. ⋯ We found that age ≤40 years and minority race were associated with a longer time to survey completion, but personalized versus generic approaches to mail- and telephone-based contact strategies had no significant effect. Repeating both mail and telephone contact attempts was important for increasing survey completion rate.
-
Bmc Med Res Methodol · Jan 2015
Comparative StudyA randomised controlled trial comparing opt-in and opt-out home visits for tracing lost participants in a prospective birth cohort study.
Attrition is an important problem in cohort studies. Tracing cohort members who have moved or otherwise lost contact with the study is vital. There is some debate about the acceptability and relative effectiveness of opt-in versus opt-out methods of contacting cohort members to re-engage them in this context. We conducted a randomised controlled trial to compare the two approaches in terms of effectiveness (tracing to confirm address and consenting to continue in the study), cost-effectiveness and acceptability. ⋯ Since the opt-in approach yielded very low response rates, and there were no differences in terms of acceptability, we conclude that the opt-out approach is the most effective method of tracing disengaged study members. The gains made in contacting participants must be weighed against the increase in cost using this methodology.
-
Bmc Med Res Methodol · Dec 2014
Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints.
Modern modelling techniques may potentially provide more accurate predictions of binary outcomes than classical techniques. We aimed to study the predictive performance of different modelling techniques in relation to the effective sample size ("data hungriness"). ⋯ Modern modelling techniques such as SVM, NN and RF may need over 10 times as many events per variable to achieve a stable AUC and a small optimism than classical modelling techniques such as LR. This implies that such modern techniques should only be used in medical prediction problems if very large data sets are available.