@inproceedings{chan-etal-2026-overview,
title = "Overview of {\#}{SMM}4{H}-{H}ea{RD} 2026 - Task 2: Detection of Insomnia in Clinical Notes",
author = "Chan, Joey and
Gryboski, Lauren D. and
Lopez-Garcia, Guillermo and
Gonzalez-Hernandez, Graciela",
editor = "Lopez-Garcia, Guillermo and
Gonzalez-Hernandez, Graciela",
booktitle = "Proceedings of the 11th Social Media Mining for Health Research and Applications ({SMM}4{H}-{H}ea{RD} 2026) Workshop and Shared Tasks",
month = jul,
year = "2026",
address = "San Diego, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.smm4h-1.52/",
pages = "345--352",
ISBN = "979-8-89176-432-3",
abstract = "This paper provides an overview of Task 2 from the Social Media Mining for Health and Health Real-World Data ({\#}SMM4H-HeaRD) 2026 Workshop and Shared Tasks, which focused on the detection of insomnia in clinical notes derived from the MIMIC-III dataset. The task consisted of two subtasks: binary text classification to determine whether a patient is likely experiencing insomnia (Subtask 1), and multi-label classification combined with character-level evidence extraction to identify supporting evidence for specific insomnia crite- ria (Subtask 2). Eight teams participated, using approaches ranging from large language model (LLM) prompting and fine-tuned encoder mod- els to hybrid rule-based pipelines. Results demonstrated that structured LLM pipelines with deterministic post-processing achieved the strongest overall performance, while character-level span extraction remained substantially harder than classification across all systems. These findings highlight both the promise of NLP for identifying underdiagnosed conditions in electronic health records and the ongoing difficulty of producing interpretable, evidence-grounded clinical predictions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chan-etal-2026-overview">
<titleInfo>
<title>Overview of #SMM4H-HeaRD 2026 - Task 2: Detection of Insomnia in Clinical Notes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joey</namePart>
<namePart type="family">Chan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lauren</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Gryboski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillermo</namePart>
<namePart type="family">Lopez-Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graciela</namePart>
<namePart type="family">Gonzalez-Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guillermo</namePart>
<namePart type="family">Lopez-Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graciela</namePart>
<namePart type="family">Gonzalez-Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-432-3</identifier>
</relatedItem>
<abstract>This paper provides an overview of Task 2 from the Social Media Mining for Health and Health Real-World Data (#SMM4H-HeaRD) 2026 Workshop and Shared Tasks, which focused on the detection of insomnia in clinical notes derived from the MIMIC-III dataset. The task consisted of two subtasks: binary text classification to determine whether a patient is likely experiencing insomnia (Subtask 1), and multi-label classification combined with character-level evidence extraction to identify supporting evidence for specific insomnia crite- ria (Subtask 2). Eight teams participated, using approaches ranging from large language model (LLM) prompting and fine-tuned encoder mod- els to hybrid rule-based pipelines. Results demonstrated that structured LLM pipelines with deterministic post-processing achieved the strongest overall performance, while character-level span extraction remained substantially harder than classification across all systems. These findings highlight both the promise of NLP for identifying underdiagnosed conditions in electronic health records and the ongoing difficulty of producing interpretable, evidence-grounded clinical predictions.</abstract>
<identifier type="citekey">chan-etal-2026-overview</identifier>
<location>
<url>https://aclanthology.org/2026.smm4h-1.52/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>345</start>
<end>352</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Overview of #SMM4H-HeaRD 2026 - Task 2: Detection of Insomnia in Clinical Notes
%A Chan, Joey
%A Gryboski, Lauren D.
%A Lopez-Garcia, Guillermo
%A Gonzalez-Hernandez, Graciela
%Y Lopez-Garcia, Guillermo
%Y Gonzalez-Hernandez, Graciela
%S Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, United States
%@ 979-8-89176-432-3
%F chan-etal-2026-overview
%X This paper provides an overview of Task 2 from the Social Media Mining for Health and Health Real-World Data (#SMM4H-HeaRD) 2026 Workshop and Shared Tasks, which focused on the detection of insomnia in clinical notes derived from the MIMIC-III dataset. The task consisted of two subtasks: binary text classification to determine whether a patient is likely experiencing insomnia (Subtask 1), and multi-label classification combined with character-level evidence extraction to identify supporting evidence for specific insomnia crite- ria (Subtask 2). Eight teams participated, using approaches ranging from large language model (LLM) prompting and fine-tuned encoder mod- els to hybrid rule-based pipelines. Results demonstrated that structured LLM pipelines with deterministic post-processing achieved the strongest overall performance, while character-level span extraction remained substantially harder than classification across all systems. These findings highlight both the promise of NLP for identifying underdiagnosed conditions in electronic health records and the ongoing difficulty of producing interpretable, evidence-grounded clinical predictions.
%U https://aclanthology.org/2026.smm4h-1.52/
%P 345-352
Markdown (Informal)
[Overview of #SMM4H-HeaRD 2026 - Task 2: Detection of Insomnia in Clinical Notes](https://aclanthology.org/2026.smm4h-1.52/) (Chan et al., SMM4H 2026)
ACL