@inproceedings{barlow-etal-2026-using,
    title = "Using Synthetic Records to Improve Automated Identification of Seizure Freedom in Clinical Text about People with Epilepsy",
    author = "Barlow, Stephen  and
      Gan, Yujian  and
      Davies, Joe  and
      Winston, Joel  and
      Teo, James  and
      Richardson, Mark  and
      Holgate, Ben",
    editor = "Demner-Fushman, Dina  and
      Ananiadou, Sophia  and
      Roberts, Kirk  and
      Tsujii, Junichi",
    booktitle = "{B}io{NLP} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.bionlp-1.3/",
    pages = "20--30",
    ISBN = "979-8-89176-434-7",
    abstract = "Seizure freedom is a key clinical outcome for people with epilepsy (PWE) yet it is primarily recorded in free-text notes and letters in the United Kingdom, making it difficult to aggregate and track at scale. This paper introduces a generative LLM-based pipeline boosted by synthetic data to identify a PWE{'}s seizure freedom status in clinicians' records. We fine-tuned seven different LLMs with between 4-14 billion parameters using LoRA to compare models trained on synthetic records against those trained on expert annotated records. The best performing configuration, based on Qwen-2.5-14B, was trained entirely on synthetic records and used chain-of-thought (CoT) reasoning (both generated by GPT-5). This achieved an F1 score of 0.90{\ensuremath{\pm}}0.02 on double-annotated test data and outperformed the equivalent model trained on authentic clinician records, which achieved 0.87{\ensuremath{\pm}}0.04. The synthetically trained models also have the benefit of outputting their CoT reasoning process for greater decision-making transparency and can also make use of the unused supervised training data for significantly increased test examples. This work has implications for monitoring a key treatment outcome for PWE automatically and at scale."
}