Bibliographic record
Abstract
Prospective randomized experiments are conducted to evaluate the efficacy (or safety) of a treatment (or an intervention). However, clinical trials are expensive and prone to recruitment challenges especially when detecting rare adverse events. In these circumstances, large observational healthcare repositories, such as those comprised of electronic health record (EHR) data collected in routine primary care, may provide an alternative source to address such causal objectives. The overarching aim of this dissertation is to emulate randomized experiments using a causal framework with methodological considerations for treatment-confounder feedback with informative observation process and subject-specific (time-invariant) unmeasured covariates, high-dimensional propensity score estimation with surrogate covariates, and continuous-time causal inference with marked point processes. First, we applied a longitudinal causal inference framework using calibrated weights with non-overlapping time-intervals to evaluate the effectiveness of glucose-lowering medications using glycemic index of Hemoglobin A1c as the primary outcome. Second, we constructed marginal structural models estimated through calibrated weights obtained via several machine learning algorithms, amalgamated with the SuperLearner method for the estimation of diabetes care provisions. This work was then extended to an article on continuous-time causal inference using optimal weights to assess the long-term adverse effects of glucose lowering medication (e.g., sodium-glucose cotransporter 2 inhibitor) for the recurrent outcome of urinary tract infection. This dissertation follows the idea that events and processes influence each other using the hypothetical (or counterfactual) constructs with some temporal latency between the exposure and the outcome. From a pragmatic perspective, the utility of this dissertation is to describe the estimation of causal effects through specific events and processes available in primary care EHRs.
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 | 0.075 | 0.266 |
| Meta-epidemiology (narrow) | 0.001 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.003 | 0.005 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.004 | 0.006 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.003 | 0.004 |
| Insufficient payload (model declined to judge) | 0.006 | 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; 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".