Web-Based System to Capture Consistent and Complete Real-world Data of Physical Therapy Interventions Following Total Knee Replacement: Design and Evaluation Study
Bibliographic record
Abstract
BACKGROUND: Electronic health records (EHRs) have the potential to facilitate consistent clinical data capture to support excellence in patient care, quality improvement, and knowledge generation. Despite widespread EHR use, the vision to transform health care system and its data to a "learning health care system" generating knowledge from real-world data is limited by the lack of consistent, structured clinical data. OBJECTIVE: The purpose of this paper was to demonstrate the design of a web-based structured clinical intervention data capture system and its evaluation in practice. The use case was ambulatory physical therapy (PT) treatment after total knee replacement (TKR), one of the most common and costly procedures today. METHODS: To identify the PT intervention type and intensity (or dose) used to treat patients with knee arthritis following TKR, an iterative user-centered design process refined an initial list of PT interventions generated during preliminary chart reviews. Input from practicing physical therapists and national and international experts refined and categorized the interventions. Next, a web-based, hierarchical structured system for intervention and intensity documentation was designed and deployed. RESULTS: The PT documentation system was implemented by 114 physical therapists agreeing to record all interventions at patient visits. Data for 161 patients with 2615 PT visits were entered by 83 physical therapists. No technical problems with data entry were reported, and data entry required less than 2 minutes per visit. A total of 42 (2%) interventions could not be categorized and were recorded using free text. CONCLUSIONS: The use of user-centered design principles provides a road map for developing clinically feasible data capture systems that employ structured collection of uniform data for use by multiple practitioners across institutions to complement and augment existing EHRs. Secondarily, these data can be analyzed to define best practices and disseminate knowledge to practice.
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 | 0.022 | 0.017 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".