Cargando…
Prediction of Atypical Ductal Hyperplasia Upgrades Through a Machine Learning Approach to Reduce Unnecessary Surgical Excisions
PURPOSE: Surgical excision is currently recommended for all occurrences of atypical ductal hyperplasia (ADH) found on core needle biopsies for malignancy diagnoses and treatment of lesions. The excision of all ADH lesions may lead to overtreatment, which results in invasive surgeries for benign lesi...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
American Society of Clinical Oncology
2018
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6874044/ https://www.ncbi.nlm.nih.gov/pubmed/30652620 http://dx.doi.org/10.1200/CCI.18.00083 |
_version_ | 1783472765782720512 |
---|---|
author | Harrington, Lia diFlorio-Alexander, Roberta Trinh, Katherine MacKenzie, Todd Suriawinata, Arief Hassanpour, Saeed |
author_facet | Harrington, Lia diFlorio-Alexander, Roberta Trinh, Katherine MacKenzie, Todd Suriawinata, Arief Hassanpour, Saeed |
author_sort | Harrington, Lia |
collection | PubMed |
description | PURPOSE: Surgical excision is currently recommended for all occurrences of atypical ductal hyperplasia (ADH) found on core needle biopsies for malignancy diagnoses and treatment of lesions. The excision of all ADH lesions may lead to overtreatment, which results in invasive surgeries for benign lesions in many women. A machine learning method to predict ADH upgrade may help clinicians and patients decide whether combined active surveillance and hormonal therapy is a reasonable alternative to surgical excision. METHODS: The following six machine learning models were developed to predict ADH upgrade from core needle biopsy: gradient-boosting trees, random forest, radial support vector machine (SVM), weighted K-nearest neighbors (KNN), logistic elastic net, and logistic regression. The study cohort consisted of 128 lesions from 124 women at a tertiary academic care center in New Hampshire who had ADH on core needle biopsy and who underwent an associated surgical excision from 2011 to 2017. RESULTS: The best-performing models were gradient-boosting trees (area under the curve [AUC], 68%; accuracy, 78%) and random forest (AUC, 67%; accuracy, 77%). The top five most important features that determined ADH upgrade were age at biopsy, lesion size, number of biopsies, needle gauge, and personal and family history of breast cancer. Using the random forest model, 98% of all malignancies would have been diagnosed through surgical biopsies, whereas 16% of unnecessary surgeries on benign lesions could have been avoided (ie, 87% sensitivity at 45% specificity). CONCLUSION: These results add to the growing body of support for machine learning models as useful aids for clinicians and patients in decisions about the clinical management of ADH. |
format | Online Article Text |
id | pubmed-6874044 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2018 |
publisher | American Society of Clinical Oncology |
record_format | MEDLINE/PubMed |
spelling | pubmed-68740442019-12-03 Prediction of Atypical Ductal Hyperplasia Upgrades Through a Machine Learning Approach to Reduce Unnecessary Surgical Excisions Harrington, Lia diFlorio-Alexander, Roberta Trinh, Katherine MacKenzie, Todd Suriawinata, Arief Hassanpour, Saeed JCO Clin Cancer Inform Original Report PURPOSE: Surgical excision is currently recommended for all occurrences of atypical ductal hyperplasia (ADH) found on core needle biopsies for malignancy diagnoses and treatment of lesions. The excision of all ADH lesions may lead to overtreatment, which results in invasive surgeries for benign lesions in many women. A machine learning method to predict ADH upgrade may help clinicians and patients decide whether combined active surveillance and hormonal therapy is a reasonable alternative to surgical excision. METHODS: The following six machine learning models were developed to predict ADH upgrade from core needle biopsy: gradient-boosting trees, random forest, radial support vector machine (SVM), weighted K-nearest neighbors (KNN), logistic elastic net, and logistic regression. The study cohort consisted of 128 lesions from 124 women at a tertiary academic care center in New Hampshire who had ADH on core needle biopsy and who underwent an associated surgical excision from 2011 to 2017. RESULTS: The best-performing models were gradient-boosting trees (area under the curve [AUC], 68%; accuracy, 78%) and random forest (AUC, 67%; accuracy, 77%). The top five most important features that determined ADH upgrade were age at biopsy, lesion size, number of biopsies, needle gauge, and personal and family history of breast cancer. Using the random forest model, 98% of all malignancies would have been diagnosed through surgical biopsies, whereas 16% of unnecessary surgeries on benign lesions could have been avoided (ie, 87% sensitivity at 45% specificity). CONCLUSION: These results add to the growing body of support for machine learning models as useful aids for clinicians and patients in decisions about the clinical management of ADH. American Society of Clinical Oncology 2018-12-18 /pmc/articles/PMC6874044/ /pubmed/30652620 http://dx.doi.org/10.1200/CCI.18.00083 Text en © 2018 by American Society of Clinical Oncology https://creativecommons.org/licenses/by/4.0/ Licensed under the Creative Commons Attribution 4.0 License: https://creativecommons.org/licenses/by/4.0/ |
spellingShingle | Original Report Harrington, Lia diFlorio-Alexander, Roberta Trinh, Katherine MacKenzie, Todd Suriawinata, Arief Hassanpour, Saeed Prediction of Atypical Ductal Hyperplasia Upgrades Through a Machine Learning Approach to Reduce Unnecessary Surgical Excisions |
title | Prediction of Atypical Ductal Hyperplasia Upgrades Through a Machine Learning Approach to Reduce Unnecessary Surgical Excisions |
title_full | Prediction of Atypical Ductal Hyperplasia Upgrades Through a Machine Learning Approach to Reduce Unnecessary Surgical Excisions |
title_fullStr | Prediction of Atypical Ductal Hyperplasia Upgrades Through a Machine Learning Approach to Reduce Unnecessary Surgical Excisions |
title_full_unstemmed | Prediction of Atypical Ductal Hyperplasia Upgrades Through a Machine Learning Approach to Reduce Unnecessary Surgical Excisions |
title_short | Prediction of Atypical Ductal Hyperplasia Upgrades Through a Machine Learning Approach to Reduce Unnecessary Surgical Excisions |
title_sort | prediction of atypical ductal hyperplasia upgrades through a machine learning approach to reduce unnecessary surgical excisions |
topic | Original Report |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6874044/ https://www.ncbi.nlm.nih.gov/pubmed/30652620 http://dx.doi.org/10.1200/CCI.18.00083 |
work_keys_str_mv | AT harringtonlia predictionofatypicalductalhyperplasiaupgradesthroughamachinelearningapproachtoreduceunnecessarysurgicalexcisions AT diflorioalexanderroberta predictionofatypicalductalhyperplasiaupgradesthroughamachinelearningapproachtoreduceunnecessarysurgicalexcisions AT trinhkatherine predictionofatypicalductalhyperplasiaupgradesthroughamachinelearningapproachtoreduceunnecessarysurgicalexcisions AT mackenzietodd predictionofatypicalductalhyperplasiaupgradesthroughamachinelearningapproachtoreduceunnecessarysurgicalexcisions AT suriawinataarief predictionofatypicalductalhyperplasiaupgradesthroughamachinelearningapproachtoreduceunnecessarysurgicalexcisions AT hassanpoursaeed predictionofatypicalductalhyperplasiaupgradesthroughamachinelearningapproachtoreduceunnecessarysurgicalexcisions |