A Pilot Report on Extracting Symptom Onset Date and Time From Clinical Notes in Patients Presenting With Chest Pain
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
The timing of clinical events is important information in understanding disease progression and its critical context and relationship to treatment and patient outcomes. However, time information documentation in the electronic health record (EHR) is inconsistent, hindering its utility in research and clinical care. In research where event timing is crucial, such as symptom onset in acute coronary syndrome, automated tools can expedite data collection, reducing the reliance on labor-intensive manual reviews. We aimed to apply natural language processing (NLP) methods for extracting date and time (DateTime) information from free-text EHR clinical notes. Two off-the-shelf NLP pipelines, parsedatetime and regular expression ( regex ), were pilot tested on 71 annotated clinical notes: History and Physical (n=49), Emergency Department Screening (n=3), and Triage Notes (n=19). Parsedatetime identified correct DateTime information in 36 notes (50.7%) with an F1-score of 0.31 (low performance), while regex failed to produce any accurate outputs. Despite parsedatetime outperforming regex , its performance remains inadequate. Both approaches required significant refinement and customization to improve efficacy. To optimize automated DateTime extraction, future research should focus on advanced rule-based NLP methods capable of handling complex narratives. Consistent time documentation by clinicians, adhering to standardized formats, remains essential for improving the downstream usability of EHR data.
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 | 0.002 | 0.001 |
| 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 | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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