@inproceedings{mcinerney-etal-2023-chill,
title = "{CH}i{LL}: Zero-shot Custom Interpretable Feature Extraction from Clinical Notes with Large Language Models",
author = "McInerney, Denis and
Young, Geoffrey and
van de Meent, Jan-Willem and
Wallace, Byron",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.568",
doi = "10.18653/v1/2023.findings-emnlp.568",
pages = "8477--8494",
abstract = "We propose CHiLL (Crafting High-Level Latents), an approach for natural-language specification of features for linear models. CHiLL prompts LLMs with expert-crafted queries to generate interpretable features from health records. The resulting noisy labels are then used to train a simple linear classifier. Generating features based on queries to an LLM can empower physicians to use their domain expertise to craft features that are clinically meaningful for a downstream task of interest, without having to manually extract these from raw EHR. We are motivated by a real-world risk prediction task, but as a reproducible proxy, we use MIMIC-III and MIMIC-CXR data and standard predictive tasks (e.g., 30-day readmission) to evaluate this approach. We find that linear models using automatically extracted features are comparably performant to models using reference features, and provide greater interpretability than linear models using {``}Bag-of-Words{''} features. We verify that learned feature weights align well with clinical expectations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mcinerney-etal-2023-chill">
<titleInfo>
<title>CHiLL: Zero-shot Custom Interpretable Feature Extraction from Clinical Notes with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Denis</namePart>
<namePart type="family">McInerney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Geoffrey</namePart>
<namePart type="family">Young</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan-Willem</namePart>
<namePart type="family">van de Meent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Byron</namePart>
<namePart type="family">Wallace</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose CHiLL (Crafting High-Level Latents), an approach for natural-language specification of features for linear models. CHiLL prompts LLMs with expert-crafted queries to generate interpretable features from health records. The resulting noisy labels are then used to train a simple linear classifier. Generating features based on queries to an LLM can empower physicians to use their domain expertise to craft features that are clinically meaningful for a downstream task of interest, without having to manually extract these from raw EHR. We are motivated by a real-world risk prediction task, but as a reproducible proxy, we use MIMIC-III and MIMIC-CXR data and standard predictive tasks (e.g., 30-day readmission) to evaluate this approach. We find that linear models using automatically extracted features are comparably performant to models using reference features, and provide greater interpretability than linear models using “Bag-of-Words” features. We verify that learned feature weights align well with clinical expectations.</abstract>
<identifier type="citekey">mcinerney-etal-2023-chill</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.568</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.568</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>8477</start>
<end>8494</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CHiLL: Zero-shot Custom Interpretable Feature Extraction from Clinical Notes with Large Language Models
%A McInerney, Denis
%A Young, Geoffrey
%A van de Meent, Jan-Willem
%A Wallace, Byron
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F mcinerney-etal-2023-chill
%X We propose CHiLL (Crafting High-Level Latents), an approach for natural-language specification of features for linear models. CHiLL prompts LLMs with expert-crafted queries to generate interpretable features from health records. The resulting noisy labels are then used to train a simple linear classifier. Generating features based on queries to an LLM can empower physicians to use their domain expertise to craft features that are clinically meaningful for a downstream task of interest, without having to manually extract these from raw EHR. We are motivated by a real-world risk prediction task, but as a reproducible proxy, we use MIMIC-III and MIMIC-CXR data and standard predictive tasks (e.g., 30-day readmission) to evaluate this approach. We find that linear models using automatically extracted features are comparably performant to models using reference features, and provide greater interpretability than linear models using “Bag-of-Words” features. We verify that learned feature weights align well with clinical expectations.
%R 10.18653/v1/2023.findings-emnlp.568
%U https://aclanthology.org/2023.findings-emnlp.568
%U https://doi.org/10.18653/v1/2023.findings-emnlp.568
%P 8477-8494
Markdown (Informal)
[CHiLL: Zero-shot Custom Interpretable Feature Extraction from Clinical Notes with Large Language Models](https://aclanthology.org/2023.findings-emnlp.568) (McInerney et al., Findings 2023)
ACL