Linking Free Text Documentation of Functioning and Disability to the ICF With Natural Language Processing

Background: Invaluable information on patient functioning and the complex interactions that define it is recorded in free text portions of the Electronic Health Record (EHR). Leveraging this information to improve clinical decision-making and conduct research requires natural language processing (NL...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Denis Newman-Griffis, Jonathan Camacho Maldonado, Pei-Shu Ho, Maryanne Sacco, Rafael Jimenez Silva, Julia Porcino, Leighton Chan
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	natural language processing clinical coding disability evaluation international classification of functioning disability and health electronic health records artificial intelligence Other systems of medicine RZ201-999 Medical technology R855-855.5
Acceso en línea:	https://doaj.org/article/a5efd6e0efd7416896d6f4f3e9512583
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a5efd6e0efd7416896d6f4f3e9512583
record_format	dspace
spelling	oai:doaj.org-article:a5efd6e0efd7416896d6f4f3e95125832021-11-05T06:19:22ZLinking Free Text Documentation of Functioning and Disability to the ICF With Natural Language Processing2673-686110.3389/fresc.2021.742702https://doaj.org/article/a5efd6e0efd7416896d6f4f3e95125832021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fresc.2021.742702/fullhttps://doaj.org/toc/2673-6861Background: Invaluable information on patient functioning and the complex interactions that define it is recorded in free text portions of the Electronic Health Record (EHR). Leveraging this information to improve clinical decision-making and conduct research requires natural language processing (NLP) technologies to identify and organize the information recorded in clinical documentation.Methods: We used natural language processing methods to analyze information about patient functioning recorded in two collections of clinical documents pertaining to claims for federal disability benefits from the U.S. Social Security Administration (SSA). We grounded our analysis in the International Classification of Functioning, Disability, and Health (ICF), and used the Activities and Participation domain of the ICF to classify information about functioning in three key areas: mobility, self-care, and domestic life. After annotating functional status information in our datasets through expert clinical review, we trained machine learning-based NLP models to automatically assign ICF categories to mentions of functional activity.Results: We found that rich and diverse information on patient functioning was documented in the free text records. Annotation of 289 documents for Mobility information yielded 2,455 mentions of Mobility activities and 3,176 specific actions corresponding to 13 ICF-based categories. Annotation of 329 documents for Self-Care and Domestic Life information yielded 3,990 activity mentions and 4,665 specific actions corresponding to 16 ICF-based categories. NLP systems for automated ICF coding achieved over 80% macro-averaged F-measure on both datasets, indicating strong performance across all ICF categories used.Conclusions: Natural language processing can help to navigate the tradeoff between flexible and expressive clinical documentation of functioning and standardizable data for comparability and learning. The ICF has practical limitations for classifying functional status information in clinical documentation but presents a valuable framework for organizing the information recorded in health records about patient functioning. This study advances the development of robust, ICF-based NLP technologies to analyze information on patient functioning and has significant implications for NLP-powered analysis of functional status information in disability benefits management, clinical care, and research.Denis Newman-GriffisDenis Newman-GriffisJonathan Camacho MaldonadoPei-Shu HoMaryanne SaccoRafael Jimenez SilvaJulia PorcinoLeighton ChanFrontiers Media S.A.articlenatural language processingclinical codingdisability evaluationinternational classification of functioning disability and healthelectronic health recordsartificial intelligenceOther systems of medicineRZ201-999Medical technologyR855-855.5ENFrontiers in Rehabilitation Sciences, Vol 2 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	natural language processing clinical coding disability evaluation international classification of functioning disability and health electronic health records artificial intelligence Other systems of medicine RZ201-999 Medical technology R855-855.5
spellingShingle	natural language processing clinical coding disability evaluation international classification of functioning disability and health electronic health records artificial intelligence Other systems of medicine RZ201-999 Medical technology R855-855.5 Denis Newman-Griffis Denis Newman-Griffis Jonathan Camacho Maldonado Pei-Shu Ho Maryanne Sacco Rafael Jimenez Silva Julia Porcino Leighton Chan Linking Free Text Documentation of Functioning and Disability to the ICF With Natural Language Processing
description	Background: Invaluable information on patient functioning and the complex interactions that define it is recorded in free text portions of the Electronic Health Record (EHR). Leveraging this information to improve clinical decision-making and conduct research requires natural language processing (NLP) technologies to identify and organize the information recorded in clinical documentation.Methods: We used natural language processing methods to analyze information about patient functioning recorded in two collections of clinical documents pertaining to claims for federal disability benefits from the U.S. Social Security Administration (SSA). We grounded our analysis in the International Classification of Functioning, Disability, and Health (ICF), and used the Activities and Participation domain of the ICF to classify information about functioning in three key areas: mobility, self-care, and domestic life. After annotating functional status information in our datasets through expert clinical review, we trained machine learning-based NLP models to automatically assign ICF categories to mentions of functional activity.Results: We found that rich and diverse information on patient functioning was documented in the free text records. Annotation of 289 documents for Mobility information yielded 2,455 mentions of Mobility activities and 3,176 specific actions corresponding to 13 ICF-based categories. Annotation of 329 documents for Self-Care and Domestic Life information yielded 3,990 activity mentions and 4,665 specific actions corresponding to 16 ICF-based categories. NLP systems for automated ICF coding achieved over 80% macro-averaged F-measure on both datasets, indicating strong performance across all ICF categories used.Conclusions: Natural language processing can help to navigate the tradeoff between flexible and expressive clinical documentation of functioning and standardizable data for comparability and learning. The ICF has practical limitations for classifying functional status information in clinical documentation but presents a valuable framework for organizing the information recorded in health records about patient functioning. This study advances the development of robust, ICF-based NLP technologies to analyze information on patient functioning and has significant implications for NLP-powered analysis of functional status information in disability benefits management, clinical care, and research.
format	article
author	Denis Newman-Griffis Denis Newman-Griffis Jonathan Camacho Maldonado Pei-Shu Ho Maryanne Sacco Rafael Jimenez Silva Julia Porcino Leighton Chan
author_facet	Denis Newman-Griffis Denis Newman-Griffis Jonathan Camacho Maldonado Pei-Shu Ho Maryanne Sacco Rafael Jimenez Silva Julia Porcino Leighton Chan
author_sort	Denis Newman-Griffis
title	Linking Free Text Documentation of Functioning and Disability to the ICF With Natural Language Processing
title_short	Linking Free Text Documentation of Functioning and Disability to the ICF With Natural Language Processing
title_full	Linking Free Text Documentation of Functioning and Disability to the ICF With Natural Language Processing
title_fullStr	Linking Free Text Documentation of Functioning and Disability to the ICF With Natural Language Processing
title_full_unstemmed	Linking Free Text Documentation of Functioning and Disability to the ICF With Natural Language Processing
title_sort	linking free text documentation of functioning and disability to the icf with natural language processing
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/a5efd6e0efd7416896d6f4f3e9512583
work_keys_str_mv	AT denisnewmangriffis linkingfreetextdocumentationoffunctioninganddisabilitytotheicfwithnaturallanguageprocessing AT denisnewmangriffis linkingfreetextdocumentationoffunctioninganddisabilitytotheicfwithnaturallanguageprocessing AT jonathancamachomaldonado linkingfreetextdocumentationoffunctioninganddisabilitytotheicfwithnaturallanguageprocessing AT peishuho linkingfreetextdocumentationoffunctioninganddisabilitytotheicfwithnaturallanguageprocessing AT maryannesacco linkingfreetextdocumentationoffunctioninganddisabilitytotheicfwithnaturallanguageprocessing AT rafaeljimenezsilva linkingfreetextdocumentationoffunctioninganddisabilitytotheicfwithnaturallanguageprocessing AT juliaporcino linkingfreetextdocumentationoffunctioninganddisabilitytotheicfwithnaturallanguageprocessing AT leightonchan linkingfreetextdocumentationoffunctioninganddisabilitytotheicfwithnaturallanguageprocessing
_version_	1718444489132998656

Linking Free Text Documentation of Functioning and Disability to the ICF With Natural Language Processing

Ejemplares similares