Introduction: Narrow, unidimensional measures of poverty often fail to measure true poverty and inadequately capture its drivers. Multidimensional indices of poverty more accurately capture the diversity of poverty. There is little research regarding the association between multidimensional poverty and depression. Methods: A cross-sectional survey was administered in five sub-locations in Migori County, Kenya. A total of 4,765 heads of household were surveyed. Multidimensional poverty indices were used to determine the association of poverty with depression using the Patient Health Questionnaire (PHQ-8) depression screening tool. Results: Across the geographic areas surveyed, the overall prevalence of household poverty (deprivation headcount) was 19.4%, ranging from a low of 13.6% in Central Kamagambo to a high of 24.6% in North Kamagambo. Overall multidimensional poverty index varied from 0.053 in Central Kamagambo to 0.098 in North Kamagambo. Of the 3,939 participants with depression data available, 481 (12.2%) met the criteria for depression based on a PHQ-8 depression score ≥10. Poverty showed a dose-response association with depression. Conclusions: Multidimensional poverty indices can be used to accurately capture poverty in rural Kenya and to characterize differences in poverty across areas. There is a clear association between multidimensional poverty and depressive symptoms, including a dose effect with increasing poverty intensity. This supports the importance of multifaceted poverty policies and interventions to improve wellbeing and reduce depression.
Background: Numerous pressure injury prediction models have been developed using electronic health record data, yet hospital-acquired pressure injuries (HAPIs) are increasing, which demonstrates the critical challenge of implementing these models in routine care. Objective: To help bridge the gap between development and implementation, we sought to create a model that was feasible, broadly applicable, dynamic, actionable, and rigorously validated and then compare its performance to usual care (ie, the Braden scale). Methods: We extracted electronic health record data from 197,991 adult hospital admissions with 51 candidate features. For risk prediction and feature selection, we used logistic regression with a least absolute shrinkage and selection operator (LASSO) approach. To compare the model with usual care, we used the area under the receiver operating curve (AUC), Brier score, slope, intercept, and integrated calibration index. The model was validated using a temporally staggered cohort. Results: A total of 5458 HAPIs were identified between January 2018 and July 2022. We determined 22 features were necessary to achieve a parsimonious and highly accurate model. The top 5 features included tracheostomy, edema, central line, first albumin measure, and age. Our model achieved higher discrimination than the Braden scale (AUC 0.897, 95% CI 0.893-0.901 vs AUC 0.798, 95% CI 0.791-0.803). Conclusions: We developed and validated an accurate prediction model for HAPIs that surpassed the standard-of-care risk assessment and fulfilled necessary elements for implementation. Future work includes a pragmatic randomized trial to assess whether our model improves patient outcomes.
6 January 2022 in Journal of the American Pharmacists Association
Accelerometers are increasingly being used in biomedical research, but the analysis of accelerometry data is often complicated by both the massive size of the datasets and the collection of unwanted data from the process of delivery to study participants. Current methods for removing delivery data involve arduous manual review of dense datasets. We aimed to develop models for the classification of days in accelerometry data as activity from human wear or the delivery process. These models can be used to automate the cleaning of accelerometry datasets that are adulterated with activity from delivery. We developed statistical and machine learning models for the classification of accelerometry data in a supervised learning context using a large human activity and delivery labeled accelerometry dataset. Model performances were assessed and compared using Monte Carlo cross-validation. We found that a hybrid convolutional recurrent neural network performed best in the classification task with an F1 score of 0.960 but simpler models such as logistic regression and random forest also had excellent performance with F1 scores of 0.951 and 0.957, respectively. The best performing models and related data processing techniques are made publicly available in the R package, Physical Activity.