Methods to Enhance Causal Inference for Assessing Impact of Clinical Informatics Platform Implementation
Bibliographic record
Abstract
Background: Hospitals are increasingly likely to implement clinical informatics tools to improve quality of care, necessitating rigorous approaches to evaluate effectiveness. We leveraged a multi-institutional data repository and applied causal inference methods to assess implementation of a commercial data visualization software in our pediatric cardiac intensive care unit. Methods: Natural experiment in the University of Michigan (UM) Cardiac Intensive Care Unit pre and postimplementation of data visualization software analyzed within the Pediatric Cardiac Critical Care Consortium clinical registry; we identified N=21 control hospitals that contributed contemporaneous registry data during the study period. We used the platform during multiple daily rounds to visualize clinical data trends. We evaluated outcomes—case-mix adjusted postoperative mortality, cardiac arrest and unplanned readmission rates, and postoperative length of stay—most likely impacted by this change. There were no quality improvement initiatives focused specifically on these outcomes nor any organizational changes at UM in either era. We performed a difference-in-differences analysis to compare changes in UM outcomes to those at control hospitals across the pre versus postimplementation eras. Results: We compared 1436 pre versus 779 postimplementation admissions at UM to 19 854 (pre) versus 14 160 (post) at controls. Admission characteristics were similar between eras. Postimplementation at UM we observed relative reductions in cardiac arrests among medical admissions, unplanned readmissions, and postoperative length of stay by −14%, −41%, and −18%, respectively. The difference-in-differences estimate for each outcome was statistically significant ( P <0.05), suggesting the difference in outcomes at UM pre versus postimplementation is statistically significantly different from control hospitals during the same time. Conclusions: Clinical registries provide opportunities to thoroughly evaluate implementation of new informatics tools at single institutions. Borrowing strength from multi-institutional data and drawing ideas from causal inference, our analysis solidified greater belief in the effectiveness of this software across our institution.
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 | 0.275 | 0.558 |
| Meta-epidemiology (narrow) | 0.005 | 0.002 |
| Meta-epidemiology (broad) | 0.004 | 0.015 |
| Bibliometrics | 0.010 | 0.007 |
| Science and technology studies | 0.003 | 0.005 |
| Scholarly communication | 0.005 | 0.006 |
| Open science | 0.006 | 0.006 |
| Research integrity | 0.004 | 0.008 |
| Insufficient payload (model declined to judge) | 0.013 | 0.001 |
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; the direct Gemma label and the distilled Codex classifier agree on what is shown here.
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".