Exploring Robust Methods for Evaluating Treatment and Comparison Groups in Chronic Care Management Programs
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Evaluation of chronic care management (CCM) programs is necessary to determine the behavioral, clinical, and financial value of the programs. Financial outcomes of members who are exposed to interventions (treatment group) typically are compared to those not exposed (comparison group) in a quasi-experimental study design. However, because member assignment is not randomized, outcomes reported from these designs may be biased or inefficient if study groups are not comparable or balanced prior to analysis. Two matching techniques used to achieve balanced groups are Propensity Score Matching (PSM) and Coarsened Exact Matching (CEM). Unlike PSM, CEM has been shown to yield estimates of causal (program) effects that are lowest in variance and bias for any given sample size. The objective of this case study was to provide a comprehensive comparison of these 2 matching methods within an evaluation of a CCM program administered to a large health plan during a 2-year time period. Descriptive and statistical methods were used to assess the level of balance between comparison and treatment members pre matching. Compared with PSM, CEM retained more members, achieved better balance between matched members, and resulted in a statistically insignificant Wald test statistic for group aggregation. In terms of program performance, the results showed an overall higher medical cost savings among treatment members matched using CEM compared with those matched using PSM (-$25.57 versus -$19.78, respectively). Collectively, the results suggest CEM is a viable alternative, if not the most appropriate matching method, to apply when evaluating CCM program performance.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it