Extracting Epilepsy Patient Data with Llama 2

Ben Holgate; Shichao Fang; Anthony Shek; Matthew McWilliam; Pedro Viana; Joel S. Winston; James T. Teo; Mark P. Richardson

Extracting Epilepsy Patient Data with Llama 2

Ben Holgate^*, Shichao Fang, Anthony Shek, Matthew McWilliam, Pedro Viana, Joel S. Winston, James T. Teo, Mark P. Richardson

^*Corresponding author for this work

Research output: Contribution to journal › Conference paper › peer-review

Abstract

We fill a gap in scholarship by applying a generative Large Language Model (LLM) to extract information from clinical free text about the frequency of seizures experienced by people with epilepsy. Seizure frequency is difficult to determine across time from unstructured doctors’ and nurses’ reports of outpatients’ visits that are stored in Electronic Health Records (EHRs) in the United Kingdom’s National Health Service (NHS). We employ Meta’s Llama 2 to mine the EHRs of people with epilepsy and determine, where possible, a person’s seizure frequency at a given point in time. The results demonstrate that the new, powerful generative LLMs may improve outcomes for clinical NLP research in epilepsy and other areas..

Original language	English
Pages (from-to)	526-535
Number of pages	10
Journal	BioNLP 2024 - 23rd Meeting of the ACL Special Interest Group on Biomedical Natural Language Processing, Proceedings of the Workshop and Shared Tasks
Publication status	Published - 1 Aug 2024
Event	23rd Meeting of the ACL Special Interest Group on Biomedical Natural Language Processing, BioNLP 2024 - Bangkok, Thailand Duration: 16 Aug 2024 → …

Cite this

@article{49f5c1d1d16c454c9af3bc5d78021ab3,

title = "Extracting Epilepsy Patient Data with Llama 2",

abstract = "We fill a gap in scholarship by applying a generative Large Language Model (LLM) to extract information from clinical free text about the frequency of seizures experienced by people with epilepsy. Seizure frequency is difficult to determine across time from unstructured doctors{\textquoteright} and nurses{\textquoteright} reports of outpatients{\textquoteright} visits that are stored in Electronic Health Records (EHRs) in the United Kingdom{\textquoteright}s National Health Service (NHS). We employ Meta{\textquoteright}s Llama 2 to mine the EHRs of people with epilepsy and determine, where possible, a person{\textquoteright}s seizure frequency at a given point in time. The results demonstrate that the new, powerful generative LLMs may improve outcomes for clinical NLP research in epilepsy and other areas..",

author = "Ben Holgate and Shichao Fang and Anthony Shek and Matthew McWilliam and Pedro Viana and Winston, {Joel S.} and Teo, {James T.} and Richardson, {Mark P.}",

note = "Publisher Copyright: {\textcopyright}2024 Association for Computational Linguistics.; 23rd Meeting of the ACL Special Interest Group on Biomedical Natural Language Processing, BioNLP 2024 ; Conference date: 16-08-2024",

year = "2024",

month = aug,

day = "1",

language = "English",

pages = "526--535",

journal = "BioNLP 2024 - 23rd Meeting of the ACL Special Interest Group on Biomedical Natural Language Processing, Proceedings of the Workshop and Shared Tasks",

}

TY - JOUR

T1 - Extracting Epilepsy Patient Data with Llama 2

AU - Holgate, Ben

AU - Fang, Shichao

AU - Shek, Anthony

AU - McWilliam, Matthew

AU - Viana, Pedro

AU - Winston, Joel S.

AU - Teo, James T.

AU - Richardson, Mark P.

PY - 2024/8/1

Y1 - 2024/8/1

N2 - We fill a gap in scholarship by applying a generative Large Language Model (LLM) to extract information from clinical free text about the frequency of seizures experienced by people with epilepsy. Seizure frequency is difficult to determine across time from unstructured doctors’ and nurses’ reports of outpatients’ visits that are stored in Electronic Health Records (EHRs) in the United Kingdom’s National Health Service (NHS). We employ Meta’s Llama 2 to mine the EHRs of people with epilepsy and determine, where possible, a person’s seizure frequency at a given point in time. The results demonstrate that the new, powerful generative LLMs may improve outcomes for clinical NLP research in epilepsy and other areas..

AB - We fill a gap in scholarship by applying a generative Large Language Model (LLM) to extract information from clinical free text about the frequency of seizures experienced by people with epilepsy. Seizure frequency is difficult to determine across time from unstructured doctors’ and nurses’ reports of outpatients’ visits that are stored in Electronic Health Records (EHRs) in the United Kingdom’s National Health Service (NHS). We employ Meta’s Llama 2 to mine the EHRs of people with epilepsy and determine, where possible, a person’s seizure frequency at a given point in time. The results demonstrate that the new, powerful generative LLMs may improve outcomes for clinical NLP research in epilepsy and other areas..

UR - http://www.scopus.com/inward/record.url?scp=85204483536&partnerID=8YFLogxK

M3 - Conference paper

AN - SCOPUS:85204483536

SP - 526

EP - 535

JO - BioNLP 2024 - 23rd Meeting of the ACL Special Interest Group on Biomedical Natural Language Processing, Proceedings of the Workshop and Shared Tasks

JF - BioNLP 2024 - 23rd Meeting of the ACL Special Interest Group on Biomedical Natural Language Processing, Proceedings of the Workshop and Shared Tasks

T2 - 23rd Meeting of the ACL Special Interest Group on Biomedical Natural Language Processing, BioNLP 2024

Y2 - 16 August 2024

ER -

Extracting Epilepsy Patient Data with Llama 2

Abstract

Other files and links

Fingerprint

Cite this