A Pilot Report on Extracting Symptom Onset Date and Time From Clinical Notes in Patients Presenting With Chest Pain

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.