Mining rich health data from Canadian physician claims: features and face validity
Bibliographic record
Abstract
BACKGROUND: Physician claims data are one of the largest sources of coded health information unique to Canada. There is skepticism from data users about the quality of this data. This study investigated features of diagnostic codes used in the Alberta physician claims database. METHODS: Alberta physician claims from January 1 to March 31, 2011 are analyzed. Claims contain coded diagnoses using the International Classification of Diseases, 9th revision (ICD-9), procedures, physician specialty and service-fee type. Descriptive statistics examined the diversity and frequency of unique ICD-9 diagnostic codes used and the level of code extension (e.g. 3- or 4-digit coding). RESULTS: A total of 7,441,005 claims by 6,601 physicians were analyzed. The average number of claims per physician was 1,079, with ranges between 1,330 for family medicine, 690 for internal medicine, 722 for surgery, 516 for pediatrics and 409 for neurology. Family physicians used an average of 121 diagnostic codes, internal medicine physicians 32, surgery 36, pediatrics 46 and neurology 27. Overall, 43.5% of claims had a more detailed diagnosis (ICD code with >3 digits). Physicians on a fee-for-service plan submitted 1,184 claims and used 88 unique diagnosis codes on average compared to 438 claims and 44 unique diagnosis codes from physicians on an alternative payment plan (APP). CONCLUSIONS: Face validity of diagnosis coded in physician claims is substantially high and the features of diagnosis codes seem to reasonably reflect the clinical specialty. Physicians submit a diverse array of ICD 9 diagnostic codes and nearly half of the ICD-9 diagnostic codes examined were more detailed than required (i.e. ICD code with >3 digits). Finally, guidelines and policies should be explored to assess the submission of shadow billings for physicians on APPs.
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 | 0.014 | 0.086 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.012 | 0.013 |
| Science and technology studies | 0.003 | 0.002 |
| Scholarly communication | 0.005 | 0.001 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| 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".