Dataset Information

Improving a Secondary Use Health Data Warehouse: Proposing a Multi-Level Data Quality Framework.

ABSTRACT:

Background

Data quality frameworks within information technology and recently within health care have evolved considerably since their inception. When assessing data quality for secondary uses, an area not yet addressed adequately in these frameworks is the context of the intended use of the data.

Methods

After review of literature to identify relevant research, an existing data quality framework was refined and expanded to encompass the contextual requirements not present.

Results

The result is a two-level framework to address the need to maintain the intrinsic value of the data, as well as the need to indicate whether the data will be able to provide the basis for answers in specific areas of interest or questions.

Discussion

Data quality frameworks have always been one dimensional, requiring the implementers of these frameworks to fit the requirements of the data's use around how the framework is designed to function. Our work has systematically addressed the shortcomings of existing frameworks, through the application of concepts synthesized from the literature to the naturalistic setting of data quality management in an actual health data warehouse.

Conclusion

Secondary use of health data relies on contextualized data quality management. Our work is innovative in showing how to apply context around data quality characteristics and how to develop a second level data quality framework, so as to ensure that quality and context are maintained and addressed throughout the health data quality assessment process.

SUBMITTER: Henley-Smith S

PROVIDER: S-EPMC6676919 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundModeling patient data, particularly electronic health records (EHR), is one of the major focuses of machine learning studies in healthcare, as these records provide clinicians with valuable information that can potentially assist them in disease diagnosis and decision-making.MethodsIn this study, we present a multi-level graph-based framework called MedMGF, which models both patient medical profiles extracted from EHR data and their relationship network of health profiles in a single architecture. The medical profiles consist of several layers of data embedding derived from interval records obtained during hospitalization, and the patient-patient network is created by measuring the similarities between these profiles. We also propose a modification to the Focal Loss (FL) function to improve classification performance in imbalanced datasets without the need to imputate the data. MedMGF's performance was evaluated against several Graphical Convolutional Network (GCN) baseline models implemented with Binary Cross Entropy (BCE), FL, class balancing parameter α , and Synthetic Minority Oversampling Technique (SMOTE).ResultsOur proposed framework achieved high classification performance (AUC: 0.8098, ACC: 0.7503, SEN: 0.8750, SPE: 0.7445, NPV: 0.9923, PPV: 0.1367) on an extreme imbalanced pediatric sepsis dataset (n=3,014, imbalance ratio of 0.047). It yielded a classification improvement of 3.81% for AUC, 15% for SEN compared to the baseline GCN+ α FL (AUC: 0.7717, ACC: 0.8144, SEN: 0.7250, SPE: 0.8185, PPV: 0.1559, NPV: 0.9847), and an improvement of 5.88% in AUC and 22.5% compared to GCN+FL+SMOTE (AUC: 0.7510, ACC: 0.8431, SEN: 0.6500, SPE: 0.8520, PPV: 0.1688, NPV: 0.9814). It also showed a classification improvement of 3.86% for AUC, 15% for SEN compared to the baseline GCN+ α BCE (AUC: 0.7712, ACC: 0.8133, SEN: 0.7250, SPE: 0.8173, PPV: 0.1551, NPV: 0.9847), and an improvement of 14.33% in AUC and 27.5% in comparison to GCN+BCE+SMOTE (AUC: 0.6665, ACC: 0.7271, SEN: 0.6000, SPE: 0.7329, PPV: 0.0941, NPV: 0.9754).ConclusionWhen compared to all baseline models, MedMGF achieved the highest SEN and AUC results, demonstrating the potential for several healthcare applications.

Project description:Background: To accelerate progress toward Family Planning 2020 (FP2020) goals, the government of India focused on improving the quality of intrauterine device (IUD) services. EngenderHealth, an international sexual and reproductive health and rights organization, has been supporting the governments of Gujarat and Rajasthan since 2014 through the Expanding Access to IUD Services in India (EAISI) project by building the capacity of service providers, monitoring compliance with standard practices, and strengthening health systems. This study sought to assess whether EAISI-trained providers offer higher quality IUD services than non-EAISI-trained providers, as indicated by a reduction in confirmed IUD complications. Methods: The study team conducted an analytical cross-sectional study of secondary data collected from follow-up registers at 176 intervention facilities (38 in Gujarat and 138 in Rajasthan) during Phase I of the EAISI project. The analysis included follow-up clients who returned to the same facility between April 2018 and March 2019. We performed a multivariate logistic regression to determine factors associated with IUD complications. Results: During the period of assessment, 56,733 clients received IUD insertions, and 10,747 (18.9%) clients returned for follow-up services. Of the returning clients, 49.4% (N=5,305) had received IUDs from EAISI-trained providers, while 50.6% (N=5,442) had received IUDs from non-EAISI-trained providers. A total of 4.0% (N=432) of all returning clients experienced complications (expulsion: 1.3%, missing strings: 1.7%, infection: 1.1%). Clients who received IUDs from non-EAISI-trained providers were 55.5% more likely (95% CI [26.2%, 91.5%], p<0.0005) to have experienced complications than clients who received insertions from EAISI-trained providers. The type of IUD, the timing of the insertion, and the timing of the follow-up visit also affected complication prevalence. Conclusion: Our findings indicate that intensive, practical clinical skills training for IUD insertion can reduce the prevalence of complications.

Project description:Context.—The laboratory total testing process includes preanalytic, analytic, and postanalytic phases, but most laboratory quality improvement efforts address the analytic phase. Expanding quality improvement to preanalytic and postanalytic phases via use of medical data warehouses, repositories that include clinical, utilization, and administrative data, can improve patient care by ensuring appropriate test utilization. Cross-department, multidisciplinary collaboration to address gaps and improve patient and system outcomes is beneficial.Objective.—To demonstrate medical data warehouse utility for characterizing laboratory-associated quality gaps amenable to preanalytic or postanalytic interventions.Design.—A multidisciplinary team identified quality gaps. Medical data warehouse data were queried to characterize gaps. Organizational leaders were interviewed about quality improvement priorities. A decision aid with elements including national guidelines, local and national importance, and measurable outcomes was completed for each gap.Results.—Gaps identified included (1) test ordering; (2) diagnosis, detection, and documentation, and (3) high-risk medication monitoring. After examination of medical data warehouse data including enrollment, diagnoses, laboratory, pharmacy, and procedures for baseline performance, high-risk medication monitoring was selected, specifically alanine aminotransferase, aspartate aminotransferase, complete blood count, and creatinine testing among patients receiving disease-modifying antirheumatic drugs. The test utilization gap was in monitoring timeliness (eg, >60% of patients had a monitoring gap exceeding the guideline recommended frequency). Other contributors to selecting this gap were organizational enthusiasm, regulatory labeling, and feasibility of a significant laboratory role in addressing the gap.Conclusions.—A multidisciplinary process facilitated identification and selection of a laboratory medicine quality gap. Medical data warehouse data were instrumental in characterizing gaps.