Search

Background: Routine Data Quality Assessments (RDQAs) were developed to measure and improve facility-level electronic medical record (EMR) data quality. We assessed if RDQAs were associated with improvements in data quality in KenyaEMR, an HIV care and treatment EMR used at 341 facilities in Kenya. Methods: RDQAs assess data quality by comparing information recorded in paper records to KenyaEMR. RDQAs are conducted during a one-day site visit, where approximately 100 records are randomly selected and 24 data elements are reviewed to assess data completeness and concordance. Results are immediately provided to facility staff and action plans are developed for data quality improvement. For facilities that had received more than one RDQA (baseline and follow-up), we used generalized estimating equation models to determine if data completeness or concordance improved from the baseline to the follow-up RDQAs. Results: 27 facilities received two RDQAs and were included in the analysis, with 2369 and 2355 records reviewed from baseline and follow-up RDQAs, respectively. The frequency of missing data in KenyaEMR declined from the baseline (31% missing) to the follow-up (13% missing) RDQAs. After adjusting for facility characteristics, records from follow-up RDQAs had 0.43-times the risk (95% CI: 0.32–0.58) of having at least one missing value among nine required data elements compared to records from baseline RDQAs. Using a scale with one point awarded for each of 20 data elements with concordant values in paper records and KenyaEMR, we found that data concordance improved from baseline (11.9/20) to follow-up (13.6/20) RDQAs, with the mean concordance score increasing by 1.79 (95% CI: 0.25–3.33). Conclusions: This manuscript demonstrates that RDQAs can be implemented on a large scale and used to identify EMR data quality problems. RDQAs were associated with meaningful improvements in data quality and could be adapted for implementation in other settings. [ABSTRACT FROM AUTHOR]

Broken water pumps continue to impede efforts to deliver clean and economically-viable water to the global poor. The literature has demonstrated that customers’ health benefits and willingness to pay for clean water are best realized when clean water infrastructure performs extremely well (>99% uptime). In this paper, we used sensor data from 42 Afridev-brand handpumps observed for 14 months in western Kenya to demonstrate how sensors and supervised ensemble machine learning could be used to increase total fleet uptime from a best-practices baseline of about 70% to >99%. We accomplish this increase in uptime by forecasting pump failures and identifying existing failures very quickly. Comparing the costs of operating the pump per functional year over a lifetime of 10 years, we estimate that implementing this algorithm would save 7% on the levelized cost of water relative to a sensor-less scheduled maintenance program. Combined with a rigorous system for dispatching maintenance personnel, implementing this algorithm in a real-world program could significantly improve health outcomes and customers’ willingness to pay for water services. [ABSTRACT FROM AUTHOR]

Objective: We set out to adapt the Beck Depression Inventory (BDI)-II in Kenya and examine its factorial structure. Methods: In the first phase we carried out in-depth interviews involving 29 adult members of the community to elicit their understanding of depression and identify aspects of the BDI-II that required adaptation. In the second phase, a modified version of BDI-II was administered to 221 adults randomly selected from the community to allow for the evaluation of its psychometric properties. In the third phase of the study we evaluated the discriminative validity of BDI-11 by comparing a randomly chosen community sample (n = 29) with caregivers of adolescents affected by HIV (n = 77). Results: A considerable overlap between the BDI symptoms and those generated in the interviews was observed. Relevant idioms and symptoms such as ‘thinking too much’ and ‘Kuchoka moyo (having a tired heart)’ were identified. The administration of the BDI had to be modified to make it suitable for the low literacy levels of our participants. Fit indices for several models (one factorial, two-factor model and a three factor model) were all within acceptable range. Evidence indicated that while multidimensional models could be fitted, the strong correlations between the factors implied that a single factor model may be the best suited solution (alpha [0.89], and a significant correlation with locally identified items [r = 0.51]) confirmed the good psychometric properties of the adapted BDI-II. No evidence was found to support the hypothesis that somatization was more prevalent. Lastly, caregivers of HIV affected adolescents had significantly higher scores compared to adults randomly selected from the community F(1, 121) = 23.31, p < .001 indicating the discriminative validity of the adapted BDI = II. Conclusions: With an adapted administration procedure, the BDI-II provides an adequate measure of depressive symptoms which can be used alongside other measures for proper diagnosis in a low literacy population. [ABSTRACT FROM AUTHOR]