Machine learning application for prediction of locoregional recurrences in early oral tongue cancer: a Web-based prognostic tool

Rasheed Omobolaji Alabi, Mohammed Elmusrati, Iris Sawazaki-Calone, Luiz Paulo Kowalski, Caj Haglund, Ricardo D. Coletta, Antti A. Mäkitie, Tuula Salo, Ilmo Leivo, Alhadi Almangush

Tutkimustuotos: ArtikkelijulkaisuArtikkeliTieteellinenvertaisarvioitu

Kuvaus

Estimation of risk of recurrence in early-stage oral tongue squamous cell carcinoma (OTSCC) remains a challenge in the field of head and neck oncology. We examined the use of artificial neural networks (ANNs) to predict recurrences in early-stage OTSCC. A Web-based tool available for public use was also developed. A feedforward neural network was trained for prediction of locoregional recurrences in early OTSCC. The trained network was used to evaluate several prognostic parameters (age, gender, T stage, WHO histologic grade, depth of invasion, tumor budding, worst pattern of invasion, perineural invasion, and lymphocytic host response). Our neural network model identified tumor budding and depth of invasion as the most important prognosticators to predict locoregional recurrence. The accuracy of the neural network was 92.7%, which was higher than that of the logistic regression model (86.5%). Our online tool provided 88.2% accuracy, 71.2% sensitivity, and 98.9% specificity. In conclusion, ANN seems to offer a unique decision-making support predicting recurrences and thus adding value for the management of early OTSCC. To the best of our knowledge, this is the first study that applied ANN for prediction of recurrence in early OTSCC and provided a Web-based tool.
Alkuperäiskielienglanti
LehtiVirchows Archiv
Sivut489-497
Sivumäärä9
ISSN1432-2307
DOI - pysyväislinkit
TilaJulkaistu - 17 elokuuta 2019
OKM-julkaisutyyppiA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä, vertaisarvioitu

Tieteenalat

  • 3122 Syöpätaudit
  • 113 Tietojenkäsittely- ja informaatiotieteet

Lainaa tätä

Alabi, Rasheed Omobolaji ; Elmusrati, Mohammed ; Sawazaki-Calone, Iris ; Kowalski, Luiz Paulo ; Haglund, Caj ; Coletta, Ricardo D. ; Mäkitie, Antti A. ; Salo, Tuula ; Leivo, Ilmo ; Almangush, Alhadi. / Machine learning application for prediction of locoregional recurrences in early oral tongue cancer: a Web-based prognostic tool. Julkaisussa: Virchows Archiv. 2019 ; Sivut 489-497.
@article{f2ae2d5e6d8346beb69be78f5dd72402,
title = "Machine learning application for prediction of locoregional recurrences in early oral tongue cancer: a Web-based prognostic tool",
abstract = "Estimation of risk of recurrence in early-stage oral tongue squamous cell carcinoma (OTSCC) remains a challenge in the field of head and neck oncology. We examined the use of artificial neural networks (ANNs) to predict recurrences in early-stage OTSCC. A Web-based tool available for public use was also developed. A feedforward neural network was trained for prediction of locoregional recurrences in early OTSCC. The trained network was used to evaluate several prognostic parameters (age, gender, T stage, WHO histologic grade, depth of invasion, tumor budding, worst pattern of invasion, perineural invasion, and lymphocytic host response). Our neural network model identified tumor budding and depth of invasion as the most important prognosticators to predict locoregional recurrence. The accuracy of the neural network was 92.7{\%}, which was higher than that of the logistic regression model (86.5{\%}). Our online tool provided 88.2{\%} accuracy, 71.2{\%} sensitivity, and 98.9{\%} specificity. In conclusion, ANN seems to offer a unique decision-making support predicting recurrences and thus adding value for the management of early OTSCC. To the best of our knowledge, this is the first study that applied ANN for prediction of recurrence in early OTSCC and provided a Web-based tool.",
keywords = "3122 Cancers, 113 Computer and information sciences",
author = "Alabi, {Rasheed Omobolaji} and Mohammed Elmusrati and Iris Sawazaki-Calone and Kowalski, {Luiz Paulo} and Caj Haglund and Coletta, {Ricardo D.} and M{\"a}kitie, {Antti A.} and Tuula Salo and Ilmo Leivo and Alhadi Almangush",
year = "2019",
month = "8",
day = "17",
doi = "10.1007/s00428-019-02642-5",
language = "English",
pages = "489--497",
journal = "Virchows Archiv",
issn = "0945-6317",
publisher = "Springer",

}

Machine learning application for prediction of locoregional recurrences in early oral tongue cancer: a Web-based prognostic tool. / Alabi, Rasheed Omobolaji; Elmusrati, Mohammed; Sawazaki-Calone, Iris; Kowalski, Luiz Paulo; Haglund, Caj; Coletta, Ricardo D.; Mäkitie, Antti A.; Salo, Tuula; Leivo, Ilmo; Almangush, Alhadi.

julkaisussa: Virchows Archiv, 17.08.2019, s. 489-497.

Tutkimustuotos: ArtikkelijulkaisuArtikkeliTieteellinenvertaisarvioitu

TY - JOUR

T1 - Machine learning application for prediction of locoregional recurrences in early oral tongue cancer: a Web-based prognostic tool

AU - Alabi, Rasheed Omobolaji

AU - Elmusrati, Mohammed

AU - Sawazaki-Calone, Iris

AU - Kowalski, Luiz Paulo

AU - Haglund, Caj

AU - Coletta, Ricardo D.

AU - Mäkitie, Antti A.

AU - Salo, Tuula

AU - Leivo, Ilmo

AU - Almangush, Alhadi

PY - 2019/8/17

Y1 - 2019/8/17

N2 - Estimation of risk of recurrence in early-stage oral tongue squamous cell carcinoma (OTSCC) remains a challenge in the field of head and neck oncology. We examined the use of artificial neural networks (ANNs) to predict recurrences in early-stage OTSCC. A Web-based tool available for public use was also developed. A feedforward neural network was trained for prediction of locoregional recurrences in early OTSCC. The trained network was used to evaluate several prognostic parameters (age, gender, T stage, WHO histologic grade, depth of invasion, tumor budding, worst pattern of invasion, perineural invasion, and lymphocytic host response). Our neural network model identified tumor budding and depth of invasion as the most important prognosticators to predict locoregional recurrence. The accuracy of the neural network was 92.7%, which was higher than that of the logistic regression model (86.5%). Our online tool provided 88.2% accuracy, 71.2% sensitivity, and 98.9% specificity. In conclusion, ANN seems to offer a unique decision-making support predicting recurrences and thus adding value for the management of early OTSCC. To the best of our knowledge, this is the first study that applied ANN for prediction of recurrence in early OTSCC and provided a Web-based tool.

AB - Estimation of risk of recurrence in early-stage oral tongue squamous cell carcinoma (OTSCC) remains a challenge in the field of head and neck oncology. We examined the use of artificial neural networks (ANNs) to predict recurrences in early-stage OTSCC. A Web-based tool available for public use was also developed. A feedforward neural network was trained for prediction of locoregional recurrences in early OTSCC. The trained network was used to evaluate several prognostic parameters (age, gender, T stage, WHO histologic grade, depth of invasion, tumor budding, worst pattern of invasion, perineural invasion, and lymphocytic host response). Our neural network model identified tumor budding and depth of invasion as the most important prognosticators to predict locoregional recurrence. The accuracy of the neural network was 92.7%, which was higher than that of the logistic regression model (86.5%). Our online tool provided 88.2% accuracy, 71.2% sensitivity, and 98.9% specificity. In conclusion, ANN seems to offer a unique decision-making support predicting recurrences and thus adding value for the management of early OTSCC. To the best of our knowledge, this is the first study that applied ANN for prediction of recurrence in early OTSCC and provided a Web-based tool.

KW - 3122 Cancers

KW - 113 Computer and information sciences

U2 - 10.1007/s00428-019-02642-5

DO - 10.1007/s00428-019-02642-5

M3 - Article

SP - 489

EP - 497

JO - Virchows Archiv

JF - Virchows Archiv

SN - 0945-6317

ER -