Validation of an Algorithm to Identify Infective Endocarditis in People Who Inject Drugs
Bibliographic record
Abstract
INTRODUCTION: Infective endocarditis is associated with high morbidity and mortality. Currently, there is concern that the incidence of infective endocarditis associated with people who inject drugs (PWID) is increasing. However, it is difficult to monitor population-wide trends in PWID-associated infective endocarditis, as there is no International Statistical Classification of Diseases, 10th Revision (ICD-10) code for injection drug use. To address this barrier, we sought to develop a validated algorithm using ICD-10 discharge diagnosis codes. MATERIALS AND METHODS: We constructed a cohort of patients whose hospital discharge diagnosis included infective endocarditis. We reviewed 100 patients with incident infective endocarditis from 2014 to 2016 for their infective endocarditis and injection drug use status. We calculated the operating characteristics for algorithms constructed using permutations of ICD-10 codes associated with injection drug use. We repeated this analysis in a cohort of 100 patients with incident infective endocarditis from 2009 to 2011 to examine the temporal stability of the operating characteristics of each algorithm. RESULTS: We found that a combination of hepatitis C virus, drug use, and mental/behavioral disorder codes yielded the highest sensitivity (93%) and positive predictive value (83%) of the algorithms analyzed. DISCUSSION: We have described the first algorithm, validated against chart review data, for identifying PWID-associated infective endocarditis cases using ICD-10 codes. The high sensitivity and positive predictive value indicate that this algorithm can be used for surveillance and research with confidence. CONCLUSIONS: This algorithm will enable researchers to examine epidemiological trends in PWID-associated infective endocarditis.
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 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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".