Using text mining techniques to extract prostate cancer predictive information (Gleason score) from semi-structured narrative laboratory reports in the Gauteng province, South Africa

Abstract Background Prostate cancer (PCa) is the leading male neoplasm in South Africa with an age-standardised incidence rate of 68.0 per 100,000 population in 2018. The Gleason score (GS) is the strongest predictive factor for PCa treatment and is embedded within semi-structured prostate biopsy na...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Naseem Cassim, Michael Mapundu, Victor Olago, Turgay Celik, Jaya Anna George, Deborah Kim Glencross
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Prostate cancer Gleason score Late presentation Text mining Algorithm Public health Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/e5c0a2466a1d4101804a3a3151c4cc73
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e5c0a2466a1d4101804a3a3151c4cc73
record_format	dspace
spelling	oai:doaj.org-article:e5c0a2466a1d4101804a3a3151c4cc732021-11-28T12:26:20ZUsing text mining techniques to extract prostate cancer predictive information (Gleason score) from semi-structured narrative laboratory reports in the Gauteng province, South Africa10.1186/s12911-021-01697-21472-6947https://doaj.org/article/e5c0a2466a1d4101804a3a3151c4cc732021-11-01T00:00:00Zhttps://doi.org/10.1186/s12911-021-01697-2https://doaj.org/toc/1472-6947Abstract Background Prostate cancer (PCa) is the leading male neoplasm in South Africa with an age-standardised incidence rate of 68.0 per 100,000 population in 2018. The Gleason score (GS) is the strongest predictive factor for PCa treatment and is embedded within semi-structured prostate biopsy narrative reports. The manual extraction of the GS is labour-intensive. The objective of our study was to explore the use of text mining techniques to automate the extraction of the GS from irregularly reported text-intensive patient reports. Methods We used the associated Systematized Nomenclature of Medicine clinical terms morphology and topography codes to identify prostate biopsies with a PCa diagnosis for men aged > 30 years between 2006 and 2016 in the Gauteng Province, South Africa. We developed a text mining algorithm to extract the GS from 1000 biopsy reports with a PCa diagnosis from the National Health Laboratory Service database and validated the algorithm using 1000 biopsies from the private sector. The logical steps for the algorithm were data acquisition, pre-processing, feature extraction, feature value representation, feature selection, information extraction, classification, and discovered knowledge. We evaluated the algorithm using precision, recall and F-score. The GS was manually coded by two experts for both datasets. The top five GS were reported, with the remaining scores categorised as “Other” for both datasets. The percentage of biopsies with a high-risk GS (≥ 8) was also reported. Results The first output reported an F-score of 0.99 that improved to 1.00 after the algorithm was amended (the GS reported in clinical history was ignored). For the validation dataset, an F-score of 0.99 was reported. The most commonly reported GS were 5 + 4 = 9 (17.6%), 3 + 3 = 6 (17.5%), 4 + 3 = 7 (16.4%), 3 + 4 = 7 (14.7%) and 4 + 4 = 8 (14.2%). For the validation dataset, the most commonly reported GS were: (i) 3 + 3 = 6 (37.7%), (ii) 3 + 4 = 7 (19.4%), (iii) 4 + 3 = 7 (14.9%), (iv) 4 + 4 = 8 (10.0%) and (v) 4 + 5 = 9 (7.4%). A high-risk GS was reported for 31.8% compared to 17.4% for the validation dataset. Conclusions We demonstrated reliable extraction of information about GS from narrative text-based patient reports using an in-house developed text mining algorithm. A secondary outcome was that late presentation could be assessed.Naseem CassimMichael MapunduVictor OlagoTurgay CelikJaya Anna GeorgeDeborah Kim GlencrossBMCarticleProstate cancerGleason scoreLate presentationText miningAlgorithmPublic healthComputer applications to medicine. Medical informaticsR858-859.7ENBMC Medical Informatics and Decision Making, Vol 21, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Prostate cancer Gleason score Late presentation Text mining Algorithm Public health Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Prostate cancer Gleason score Late presentation Text mining Algorithm Public health Computer applications to medicine. Medical informatics R858-859.7 Naseem Cassim Michael Mapundu Victor Olago Turgay Celik Jaya Anna George Deborah Kim Glencross Using text mining techniques to extract prostate cancer predictive information (Gleason score) from semi-structured narrative laboratory reports in the Gauteng province, South Africa
description	Abstract Background Prostate cancer (PCa) is the leading male neoplasm in South Africa with an age-standardised incidence rate of 68.0 per 100,000 population in 2018. The Gleason score (GS) is the strongest predictive factor for PCa treatment and is embedded within semi-structured prostate biopsy narrative reports. The manual extraction of the GS is labour-intensive. The objective of our study was to explore the use of text mining techniques to automate the extraction of the GS from irregularly reported text-intensive patient reports. Methods We used the associated Systematized Nomenclature of Medicine clinical terms morphology and topography codes to identify prostate biopsies with a PCa diagnosis for men aged > 30 years between 2006 and 2016 in the Gauteng Province, South Africa. We developed a text mining algorithm to extract the GS from 1000 biopsy reports with a PCa diagnosis from the National Health Laboratory Service database and validated the algorithm using 1000 biopsies from the private sector. The logical steps for the algorithm were data acquisition, pre-processing, feature extraction, feature value representation, feature selection, information extraction, classification, and discovered knowledge. We evaluated the algorithm using precision, recall and F-score. The GS was manually coded by two experts for both datasets. The top five GS were reported, with the remaining scores categorised as “Other” for both datasets. The percentage of biopsies with a high-risk GS (≥ 8) was also reported. Results The first output reported an F-score of 0.99 that improved to 1.00 after the algorithm was amended (the GS reported in clinical history was ignored). For the validation dataset, an F-score of 0.99 was reported. The most commonly reported GS were 5 + 4 = 9 (17.6%), 3 + 3 = 6 (17.5%), 4 + 3 = 7 (16.4%), 3 + 4 = 7 (14.7%) and 4 + 4 = 8 (14.2%). For the validation dataset, the most commonly reported GS were: (i) 3 + 3 = 6 (37.7%), (ii) 3 + 4 = 7 (19.4%), (iii) 4 + 3 = 7 (14.9%), (iv) 4 + 4 = 8 (10.0%) and (v) 4 + 5 = 9 (7.4%). A high-risk GS was reported for 31.8% compared to 17.4% for the validation dataset. Conclusions We demonstrated reliable extraction of information about GS from narrative text-based patient reports using an in-house developed text mining algorithm. A secondary outcome was that late presentation could be assessed.
format	article
author	Naseem Cassim Michael Mapundu Victor Olago Turgay Celik Jaya Anna George Deborah Kim Glencross
author_facet	Naseem Cassim Michael Mapundu Victor Olago Turgay Celik Jaya Anna George Deborah Kim Glencross
author_sort	Naseem Cassim
title	Using text mining techniques to extract prostate cancer predictive information (Gleason score) from semi-structured narrative laboratory reports in the Gauteng province, South Africa
title_short	Using text mining techniques to extract prostate cancer predictive information (Gleason score) from semi-structured narrative laboratory reports in the Gauteng province, South Africa
title_full	Using text mining techniques to extract prostate cancer predictive information (Gleason score) from semi-structured narrative laboratory reports in the Gauteng province, South Africa
title_fullStr	Using text mining techniques to extract prostate cancer predictive information (Gleason score) from semi-structured narrative laboratory reports in the Gauteng province, South Africa
title_full_unstemmed	Using text mining techniques to extract prostate cancer predictive information (Gleason score) from semi-structured narrative laboratory reports in the Gauteng province, South Africa
title_sort	using text mining techniques to extract prostate cancer predictive information (gleason score) from semi-structured narrative laboratory reports in the gauteng province, south africa
publisher	BMC
publishDate	2021
url	https://doaj.org/article/e5c0a2466a1d4101804a3a3151c4cc73
work_keys_str_mv	AT naseemcassim usingtextminingtechniquestoextractprostatecancerpredictiveinformationgleasonscorefromsemistructurednarrativelaboratoryreportsinthegautengprovincesouthafrica AT michaelmapundu usingtextminingtechniquestoextractprostatecancerpredictiveinformationgleasonscorefromsemistructurednarrativelaboratoryreportsinthegautengprovincesouthafrica AT victorolago usingtextminingtechniquestoextractprostatecancerpredictiveinformationgleasonscorefromsemistructurednarrativelaboratoryreportsinthegautengprovincesouthafrica AT turgaycelik usingtextminingtechniquestoextractprostatecancerpredictiveinformationgleasonscorefromsemistructurednarrativelaboratoryreportsinthegautengprovincesouthafrica AT jayaannageorge usingtextminingtechniquestoextractprostatecancerpredictiveinformationgleasonscorefromsemistructurednarrativelaboratoryreportsinthegautengprovincesouthafrica AT deborahkimglencross usingtextminingtechniquestoextractprostatecancerpredictiveinformationgleasonscorefromsemistructurednarrativelaboratoryreportsinthegautengprovincesouthafrica
_version_	1718407987567001600

Using text mining techniques to extract prostate cancer predictive information (Gleason score) from semi-structured narrative laboratory reports in the Gauteng province, South Africa

Ejemplares similares