Feasibility of Identifying Acute Nontraumatic Intracerebral Hemorrhage Events Using Diagnostic Coding Among Veterans with Mild Cognitive Impairment or Alzheimer’s Dementia
Bibliographic record
Abstract
INTRODUCTION: Based on manual review of clinical notes of using the International Classification of Diseases, Tenth Revision coding, we evaluated the feasibility and validity for monitoring, recording, and reporting intracerebral hemorrhage (ICH) events in patients with all-cause mild cognitive impairment or Alzheimer's dementia including, but not limited to, patients eligible for anti-amyloid therapy. METHODS: Principal and first-position hospital discharge codes for ICH events for 200 patients were identified from the Veterans Affairs Health System structured administrative database. Clinician manual review of discharge summary notes assessed and confirmed the presence of coded events. Available documentation of bleed locations was further reviewed, and the extent of event adjudication for potential etiology was assessed. Additionally, 25 acute ICH cases were randomly identified by reviewing discharge notes to confirm corresponding diagnostic code-based reporting. RESULTS: Of the 200 identified patients, 161 with acute ICH events were confirmed, resulting in a positive predictive value (PPV) of 80.5% for ICH event presence identified by diagnostic coding. Bleed locations were described for 151 of 161 patients with confirmed events. Of 110 cases whose diagnostic codes indicated an event location, 79 had location descriptions in discharge summaries that were consistent with the coding (PPV = 71.8%). Possible etiology was described in 56/161 patients' discharge summaries. Among the 25 acute ICH cases identified from discharge notes, 8 had corresponding ICH diagnostic codes. CONCLUSION: This study supports the feasibility and validity of the ICD-10 coding system for monitoring, recording, and reporting ICH event presence. When location is specified in the codes, the ICD-10 coding has an acceptable PPV. Overall, the current diagnostic coding system provides a reasonable framework for initial reporting and may allow for only limited inference of etiology such as differentiating nontraumatic versus traumatic events. Coding accuracy for ICH can be expected to further improve with the availability of guidelines, training, and standardization across clinical practices.
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 | 0.000 |
| 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".