A Systematic Framework for Analyzing Observation Data in Patient-Centered Registries: Case Study for Patients With Depression
Bibliographic record
Abstract
BACKGROUND: Patient-centered registries are essential in population-based clinical care for patient identification and monitoring of outcomes. Although registry data may be used in real time for patient care, the same data may further be used for secondary analysis to assess disease burden, evaluation of disease management and health care services, and research. The design of a registry has major implications for the ability to effectively use these clinical data in research. OBJECTIVE: This study aims to develop a systematic framework to address the data and methodological issues involved in analyzing data in clinically designed patient-centered registries. METHODS: The systematic framework was composed of 3 major components: visualizing the multifaceted and heterogeneous patient-centered registries using a data flow diagram, assessing and managing data quality issues, and identifying patient cohorts for addressing specific research questions. RESULTS: Using a clinical registry designed as a part of a collaborative care program for adults with depression at Mayo Clinic, we were able to demonstrate the impact of the proposed framework on data integrity. By following the data cleaning and refining procedures of the framework, we were able to generate high-quality data that were available for research questions about the coordination and management of depression in a primary care setting. We describe the steps involved in converting clinically collected data into a viable research data set using registry cohorts of depressed adults to assess the impact on high-cost service use. CONCLUSIONS: The systematic framework discussed in this study sheds light on the existing inconsistency and data quality issues in patient-centered registries. This study provided a step-by-step procedure for addressing these challenges and for generating high-quality data for both quality improvement and research that may enhance care and outcomes for patients. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/18366.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.387 | 0.419 |
| Meta-epidemiology (narrow) | 0.001 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.005 |
| Bibliometrics | 0.012 | 0.011 |
| Science and technology studies | 0.004 | 0.008 |
| Scholarly communication | 0.006 | 0.008 |
| Open science | 0.004 | 0.007 |
| Research integrity | 0.004 | 0.003 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".