Sentinel Lymph Node Metastasis on Clinically Negative Patients: Preliminary Results of a Machine Learning Model Based on Histopathological Features

The reported incidence of node metastasis at sentinel lymph node biopsy is generally low, so that the majority of women underwent unnecessary invasive axilla surgery. Although the sentinel lymph node biopsy is time consuming and expensive, it is still the intra-operative exam with the highest perfor...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Annarita Fanizzi, Vito Lorusso, Albino Biafora, Samantha Bove, Maria Colomba Comes, Cristian Cristofaro, Maria Digennaro, Vittorio Didonna, Daniele La Forgia, Annalisa Nardone, Domenico Pomarico, Pasquale Tamborra, Alfredo Zito, Angelo Virgilio Paradiso, Raffaella Massafra
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
T
Acceso en línea:https://doaj.org/article/084b05829b084401907db37b3eb07724
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:084b05829b084401907db37b3eb07724
record_format dspace
spelling oai:doaj.org-article:084b05829b084401907db37b3eb077242021-11-11T15:23:50ZSentinel Lymph Node Metastasis on Clinically Negative Patients: Preliminary Results of a Machine Learning Model Based on Histopathological Features10.3390/app1121103722076-3417https://doaj.org/article/084b05829b084401907db37b3eb077242021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10372https://doaj.org/toc/2076-3417The reported incidence of node metastasis at sentinel lymph node biopsy is generally low, so that the majority of women underwent unnecessary invasive axilla surgery. Although the sentinel lymph node biopsy is time consuming and expensive, it is still the intra-operative exam with the highest performance, but sometimes surgery is achieved without a clear diagnosis and also with possible serious complications. In this work, we developed a machine learning model to predict the sentinel lymph nodes positivity in clinically negative patients. Breast cancer clinical and immunohistochemical features of 907 patients characterized by a clinically negative lymph node status were collected. We trained different machine learning algorithms on the retrospective collected data and selected an optimal subset of features through a sequential forward procedure. We found comparable performances for different classification algorithms: on a hold-out training set, the logistics regression classifier with seven features, i.e., tumor diameter, age, histologic type, grading, multiplicity, in situ component and Her2-neu status reached an AUC value of 71.5% and showed a better trade-off between sensitivity and specificity (69.4 and 66.9%, respectively) compared to other two classifiers. On the hold-out test set, the performance dropped by five percentage points in terms of accuracy. Overall, the histological characteristics alone did not allow us to develop a support tool suitable for actual clinical application, but it showed the maximum informative power contained in the same for the resolution of the clinical problem. The proposed study represents a starting point for future development of predictive models to obtain the probability for lymph node metastases by using histopathological features combined with other features of a different nature.Annarita FanizziVito LorussoAlbino BiaforaSamantha BoveMaria Colomba ComesCristian CristofaroMaria DigennaroVittorio DidonnaDaniele La ForgiaAnnalisa NardoneDomenico PomaricoPasquale TamborraAlfredo ZitoAngelo Virgilio ParadisoRaffaella MassafraMDPI AGarticlesentinel lymph node biopsybreast cancermachine learninghistopathological featuresclinically negative lymph nodeTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10372, p 10372 (2021)
institution DOAJ
collection DOAJ
language EN
topic sentinel lymph node biopsy
breast cancer
machine learning
histopathological features
clinically negative lymph node
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
spellingShingle sentinel lymph node biopsy
breast cancer
machine learning
histopathological features
clinically negative lymph node
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
Annarita Fanizzi
Vito Lorusso
Albino Biafora
Samantha Bove
Maria Colomba Comes
Cristian Cristofaro
Maria Digennaro
Vittorio Didonna
Daniele La Forgia
Annalisa Nardone
Domenico Pomarico
Pasquale Tamborra
Alfredo Zito
Angelo Virgilio Paradiso
Raffaella Massafra
Sentinel Lymph Node Metastasis on Clinically Negative Patients: Preliminary Results of a Machine Learning Model Based on Histopathological Features
description The reported incidence of node metastasis at sentinel lymph node biopsy is generally low, so that the majority of women underwent unnecessary invasive axilla surgery. Although the sentinel lymph node biopsy is time consuming and expensive, it is still the intra-operative exam with the highest performance, but sometimes surgery is achieved without a clear diagnosis and also with possible serious complications. In this work, we developed a machine learning model to predict the sentinel lymph nodes positivity in clinically negative patients. Breast cancer clinical and immunohistochemical features of 907 patients characterized by a clinically negative lymph node status were collected. We trained different machine learning algorithms on the retrospective collected data and selected an optimal subset of features through a sequential forward procedure. We found comparable performances for different classification algorithms: on a hold-out training set, the logistics regression classifier with seven features, i.e., tumor diameter, age, histologic type, grading, multiplicity, in situ component and Her2-neu status reached an AUC value of 71.5% and showed a better trade-off between sensitivity and specificity (69.4 and 66.9%, respectively) compared to other two classifiers. On the hold-out test set, the performance dropped by five percentage points in terms of accuracy. Overall, the histological characteristics alone did not allow us to develop a support tool suitable for actual clinical application, but it showed the maximum informative power contained in the same for the resolution of the clinical problem. The proposed study represents a starting point for future development of predictive models to obtain the probability for lymph node metastases by using histopathological features combined with other features of a different nature.
format article
author Annarita Fanizzi
Vito Lorusso
Albino Biafora
Samantha Bove
Maria Colomba Comes
Cristian Cristofaro
Maria Digennaro
Vittorio Didonna
Daniele La Forgia
Annalisa Nardone
Domenico Pomarico
Pasquale Tamborra
Alfredo Zito
Angelo Virgilio Paradiso
Raffaella Massafra
author_facet Annarita Fanizzi
Vito Lorusso
Albino Biafora
Samantha Bove
Maria Colomba Comes
Cristian Cristofaro
Maria Digennaro
Vittorio Didonna
Daniele La Forgia
Annalisa Nardone
Domenico Pomarico
Pasquale Tamborra
Alfredo Zito
Angelo Virgilio Paradiso
Raffaella Massafra
author_sort Annarita Fanizzi
title Sentinel Lymph Node Metastasis on Clinically Negative Patients: Preliminary Results of a Machine Learning Model Based on Histopathological Features
title_short Sentinel Lymph Node Metastasis on Clinically Negative Patients: Preliminary Results of a Machine Learning Model Based on Histopathological Features
title_full Sentinel Lymph Node Metastasis on Clinically Negative Patients: Preliminary Results of a Machine Learning Model Based on Histopathological Features
title_fullStr Sentinel Lymph Node Metastasis on Clinically Negative Patients: Preliminary Results of a Machine Learning Model Based on Histopathological Features
title_full_unstemmed Sentinel Lymph Node Metastasis on Clinically Negative Patients: Preliminary Results of a Machine Learning Model Based on Histopathological Features
title_sort sentinel lymph node metastasis on clinically negative patients: preliminary results of a machine learning model based on histopathological features
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/084b05829b084401907db37b3eb07724
work_keys_str_mv AT annaritafanizzi sentinellymphnodemetastasisonclinicallynegativepatientspreliminaryresultsofamachinelearningmodelbasedonhistopathologicalfeatures
AT vitolorusso sentinellymphnodemetastasisonclinicallynegativepatientspreliminaryresultsofamachinelearningmodelbasedonhistopathologicalfeatures
AT albinobiafora sentinellymphnodemetastasisonclinicallynegativepatientspreliminaryresultsofamachinelearningmodelbasedonhistopathologicalfeatures
AT samanthabove sentinellymphnodemetastasisonclinicallynegativepatientspreliminaryresultsofamachinelearningmodelbasedonhistopathologicalfeatures
AT mariacolombacomes sentinellymphnodemetastasisonclinicallynegativepatientspreliminaryresultsofamachinelearningmodelbasedonhistopathologicalfeatures
AT cristiancristofaro sentinellymphnodemetastasisonclinicallynegativepatientspreliminaryresultsofamachinelearningmodelbasedonhistopathologicalfeatures
AT mariadigennaro sentinellymphnodemetastasisonclinicallynegativepatientspreliminaryresultsofamachinelearningmodelbasedonhistopathologicalfeatures
AT vittoriodidonna sentinellymphnodemetastasisonclinicallynegativepatientspreliminaryresultsofamachinelearningmodelbasedonhistopathologicalfeatures
AT danielelaforgia sentinellymphnodemetastasisonclinicallynegativepatientspreliminaryresultsofamachinelearningmodelbasedonhistopathologicalfeatures
AT annalisanardone sentinellymphnodemetastasisonclinicallynegativepatientspreliminaryresultsofamachinelearningmodelbasedonhistopathologicalfeatures
AT domenicopomarico sentinellymphnodemetastasisonclinicallynegativepatientspreliminaryresultsofamachinelearningmodelbasedonhistopathologicalfeatures
AT pasqualetamborra sentinellymphnodemetastasisonclinicallynegativepatientspreliminaryresultsofamachinelearningmodelbasedonhistopathologicalfeatures
AT alfredozito sentinellymphnodemetastasisonclinicallynegativepatientspreliminaryresultsofamachinelearningmodelbasedonhistopathologicalfeatures
AT angelovirgilioparadiso sentinellymphnodemetastasisonclinicallynegativepatientspreliminaryresultsofamachinelearningmodelbasedonhistopathologicalfeatures
AT raffaellamassafra sentinellymphnodemetastasisonclinicallynegativepatientspreliminaryresultsofamachinelearningmodelbasedonhistopathologicalfeatures
_version_ 1718435348722221056