Empirical comparison of routinely collected electronic health record data for head and neck cancer‐specific survival in machine‐learnt prognostic models

BACKGROUND: Knowledge of the prognostic factors and performance of machine learning predictive models for 2‐year cancer‐specific survival (CSS) is limited in the head and neck cancer (HNC) population. METHODS: Data from our facilities' oncology information system (OIS) collected for routine pra...

Descripción completa

Detalles Bibliográficos
Autores principales: Kotevski, Damian P., Smee, Robert I., Vajdic, Claire M., Field, Matthew
Formato: Online Artículo Texto
Lenguaje:English
Publicado: John Wiley & Sons, Inc. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10100433/
https://www.ncbi.nlm.nih.gov/pubmed/36369773
http://dx.doi.org/10.1002/hed.27241
_version_ 1785025277261250560
author Kotevski, Damian P.
Smee, Robert I.
Vajdic, Claire M.
Field, Matthew
author_facet Kotevski, Damian P.
Smee, Robert I.
Vajdic, Claire M.
Field, Matthew
author_sort Kotevski, Damian P.
collection PubMed
description BACKGROUND: Knowledge of the prognostic factors and performance of machine learning predictive models for 2‐year cancer‐specific survival (CSS) is limited in the head and neck cancer (HNC) population. METHODS: Data from our facilities' oncology information system (OIS) collected for routine practice (OIS dataset, n = 430 patients) and research purposes (research dataset, n = 529 patients) were extracted on adults diagnosed between 2000 and 2017 with squamous cell carcinoma of the head and neck. RESULTS: Machine learning demonstrated excellent performance (area under the curve, AUC) in the whole cohort (AUC = 0.97, research dataset), larynx cohort (AUC = 0.98, both datasets), and oropharynx cohort (AUC = 0.99, both datasets). Tumor site and T classification were identified as predictors of 2‐year CSS in both datasets. Hypothyroidism and fitness for operation were further identified in the research dataset. CONCLUSIONS: Datasets extracted from an OIS for routine clinical practice and research purposes demonstrated high utility for informing 2‐year head and neck CSS.
format Online
Article
Text
id pubmed-10100433
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher John Wiley & Sons, Inc.
record_format MEDLINE/PubMed
spelling pubmed-101004332023-04-14 Empirical comparison of routinely collected electronic health record data for head and neck cancer‐specific survival in machine‐learnt prognostic models Kotevski, Damian P. Smee, Robert I. Vajdic, Claire M. Field, Matthew Head Neck Original Articles BACKGROUND: Knowledge of the prognostic factors and performance of machine learning predictive models for 2‐year cancer‐specific survival (CSS) is limited in the head and neck cancer (HNC) population. METHODS: Data from our facilities' oncology information system (OIS) collected for routine practice (OIS dataset, n = 430 patients) and research purposes (research dataset, n = 529 patients) were extracted on adults diagnosed between 2000 and 2017 with squamous cell carcinoma of the head and neck. RESULTS: Machine learning demonstrated excellent performance (area under the curve, AUC) in the whole cohort (AUC = 0.97, research dataset), larynx cohort (AUC = 0.98, both datasets), and oropharynx cohort (AUC = 0.99, both datasets). Tumor site and T classification were identified as predictors of 2‐year CSS in both datasets. Hypothyroidism and fitness for operation were further identified in the research dataset. CONCLUSIONS: Datasets extracted from an OIS for routine clinical practice and research purposes demonstrated high utility for informing 2‐year head and neck CSS. John Wiley & Sons, Inc. 2022-11-11 2023-02 /pmc/articles/PMC10100433/ /pubmed/36369773 http://dx.doi.org/10.1002/hed.27241 Text en © 2022 The Authors. Head & Neck published by Wiley Periodicals LLC. https://creativecommons.org/licenses/by/4.0/This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
spellingShingle Original Articles
Kotevski, Damian P.
Smee, Robert I.
Vajdic, Claire M.
Field, Matthew
Empirical comparison of routinely collected electronic health record data for head and neck cancer‐specific survival in machine‐learnt prognostic models
title Empirical comparison of routinely collected electronic health record data for head and neck cancer‐specific survival in machine‐learnt prognostic models
title_full Empirical comparison of routinely collected electronic health record data for head and neck cancer‐specific survival in machine‐learnt prognostic models
title_fullStr Empirical comparison of routinely collected electronic health record data for head and neck cancer‐specific survival in machine‐learnt prognostic models
title_full_unstemmed Empirical comparison of routinely collected electronic health record data for head and neck cancer‐specific survival in machine‐learnt prognostic models
title_short Empirical comparison of routinely collected electronic health record data for head and neck cancer‐specific survival in machine‐learnt prognostic models
title_sort empirical comparison of routinely collected electronic health record data for head and neck cancer‐specific survival in machine‐learnt prognostic models
topic Original Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10100433/
https://www.ncbi.nlm.nih.gov/pubmed/36369773
http://dx.doi.org/10.1002/hed.27241
work_keys_str_mv AT kotevskidamianp empiricalcomparisonofroutinelycollectedelectronichealthrecorddataforheadandneckcancerspecificsurvivalinmachinelearntprognosticmodels
AT smeeroberti empiricalcomparisonofroutinelycollectedelectronichealthrecorddataforheadandneckcancerspecificsurvivalinmachinelearntprognosticmodels
AT vajdicclairem empiricalcomparisonofroutinelycollectedelectronichealthrecorddataforheadandneckcancerspecificsurvivalinmachinelearntprognosticmodels
AT fieldmatthew empiricalcomparisonofroutinelycollectedelectronichealthrecorddataforheadandneckcancerspecificsurvivalinmachinelearntprognosticmodels