PMID- 30652620
OWN - NLM
STAT- MEDLINE
DCOM- 20191009
LR  - 20210109
IS  - 2473-4276 (Electronic)
IS  - 2473-4276 (Linking)
VI  - 2
DP  - 2018 Dec
TI  - Prediction of Atypical Ductal Hyperplasia Upgrades Through a Machine Learning 
      Approach to Reduce Unnecessary Surgical Excisions.
PG  - 1-11
LID - 10.1200/CCI.18.00083 [doi]
LID - CCI.18.00083
AB  - 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.
FAU - Harrington, Lia
AU  - Harrington L
AD  - Lia Harrington, Todd MacKenzie, and Saeed Hassanpour, Geisel School of Medicine 
      at Dartmouth College, Hanover; Roberta diFlorio-Alexander, Katherine Trinh, and 
      Arief Suriawinata, Dartmouth-Hitchcock Medical Center, Lebanon, NH.
FAU - diFlorio-Alexander, Roberta
AU  - diFlorio-Alexander R
AD  - Lia Harrington, Todd MacKenzie, and Saeed Hassanpour, Geisel School of Medicine 
      at Dartmouth College, Hanover; Roberta diFlorio-Alexander, Katherine Trinh, and 
      Arief Suriawinata, Dartmouth-Hitchcock Medical Center, Lebanon, NH.
FAU - Trinh, Katherine
AU  - Trinh K
AD  - Lia Harrington, Todd MacKenzie, and Saeed Hassanpour, Geisel School of Medicine 
      at Dartmouth College, Hanover; Roberta diFlorio-Alexander, Katherine Trinh, and 
      Arief Suriawinata, Dartmouth-Hitchcock Medical Center, Lebanon, NH.
FAU - MacKenzie, Todd
AU  - MacKenzie T
AD  - Lia Harrington, Todd MacKenzie, and Saeed Hassanpour, Geisel School of Medicine 
      at Dartmouth College, Hanover; Roberta diFlorio-Alexander, Katherine Trinh, and 
      Arief Suriawinata, Dartmouth-Hitchcock Medical Center, Lebanon, NH.
FAU - Suriawinata, Arief
AU  - Suriawinata A
AD  - Lia Harrington, Todd MacKenzie, and Saeed Hassanpour, Geisel School of Medicine 
      at Dartmouth College, Hanover; Roberta diFlorio-Alexander, Katherine Trinh, and 
      Arief Suriawinata, Dartmouth-Hitchcock Medical Center, Lebanon, NH.
FAU - Hassanpour, Saeed
AU  - Hassanpour S
AD  - Lia Harrington, Todd MacKenzie, and Saeed Hassanpour, Geisel School of Medicine 
      at Dartmouth College, Hanover; Roberta diFlorio-Alexander, Katherine Trinh, and 
      Arief Suriawinata, Dartmouth-Hitchcock Medical Center, Lebanon, NH.
LA  - eng
GR  - WT_/Wellcome Trust/United Kingdom
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
PL  - United States
TA  - JCO Clin Cancer Inform
JT  - JCO clinical cancer informatics
JID - 101708809
SB  - IM
MH  - Carcinoma, Intraductal, Noninfiltrating/*etiology/pathology
MH  - Cohort Studies
MH  - Female
MH  - Humans
MH  - Hyperplasia/*etiology/pathology
MH  - Machine Learning/*standards
PMC - PMC6874044
COIS- The following represents disclosure information provided by authors of this 
      manuscript. All relationships are considered compensated. Relationships are 
      self-held unless noted. I = Immediate Family Member, Inst = My Institution. 
      Relationships may not relate to the subject matter of this manuscript. For more 
      information about ASCO's conflict of interest policy, please refer to 
      www.asco.org/rwc or ascopubs.org/jco/site/ifc. LIA HARRINGTON: No relationship to 
      disclose ROBERTA DIFLORIO-ALEXANDER: No relationship to disclose KATHERINE TRINH: 
      No relationship to disclose TODD MACKENZIE: No relationship to disclose ARIEF 
      SURIAWINATA: No relationship to disclose SAEED HASSANPOUR: No relationship to 
      disclose
EDAT- 2019/01/18 06:00
MHDA- 2019/10/11 06:00
PMCR- 2018/12/18
CRDT- 2019/01/18 06:00
PHST- 2019/01/18 06:00 [entrez]
PHST- 2019/01/18 06:00 [pubmed]
PHST- 2019/10/11 06:00 [medline]
PHST- 2018/12/18 00:00 [pmc-release]
AID - 1800083 [pii]
AID - 10.1200/CCI.18.00083 [doi]
PST - ppublish
SO  - JCO Clin Cancer Inform. 2018 Dec;2:1-11. doi: 10.1200/CCI.18.00083.