Automated Cervical Screening and Triage, Based on HPV Testing and Computer-Interpreted Cytology

Kai Yu, Noorie Hyun, Barbara Fetterman, Thomas Lorey, Tina R. Raine-Bennett, Han Zhang, Robin E. Stamps, Nancy E. Poitras, William Wheeler, Brian Befano, Julia C. Gage, Philip E. Castle, Nicolas Wentzensen, Mark Schiffman

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Background: State-of-the-art cervical cancer prevention includes human papillomavirus (HPV) vaccination among adolescents and screening/treatment of cervical precancer (CIN3/AIS and, less strictly, CIN2) among adults. HPV testing provides sensitive detection of precancer but, to reduce overtreatment, secondary "triage" is needed to predict women at highest risk. Those with the highest-risk HPV types or abnormal cytology are commonly referred to colposcopy; however, expert cytology services are critically lacking in many regions. Methods: To permit completely automatable cervical screening/triage, we designed and validated a novel triage method, a cytologic risk score algorithm based on computer-scanned liquid-based slide features (FocalPoint, BD, Burlington, NC). We compared it with abnormal cytology in predicting precancer among 1839 women testing HPV positive (HC2, Qiagen, Germantown, MD) in 2010 at Kaiser Permanente Northern California (KPNC). Precancer outcomes were ascertained by record linkage. As additional validation, we compared the algorithm prospectively with cytology results among 243 807 women screened at KPNC (2016-2017). All statistical tests were two-sided. Results: Among HPV-positive women, the algorithm matched the triage performance of abnormal cytology. Combined with HPV16/18/45 typing (Onclarity, BD, Sparks, MD), the automatable strategy referred 91.7% of HPV-positive CIN3/AIS cases to immediate colposcopy while deferring 38.4% of all HPV-positive women to one-year retesting (compared with 89.1% and 37.4%, respectively, for typing and cytology triage). In the 2016-2017 validation, the predicted risk scores strongly correlated with cytology (P < .001). Conclusions: High-quality cervical screening and triage performance is achievable using this completely automated approach. Automated technology could permit extension of high-quality cervical screening/triage coverage to currently underserved regions.

Original languageEnglish (US)
Pages (from-to)1222-1228
Number of pages7
JournalJournal of the National Cancer Institute
Volume110
Issue number11
DOIs
StatePublished - Nov 1 2018

Fingerprint

Triage
Cell Biology
Colposcopy
Uterine Cervical Neoplasms
Vaccination
Technology

ASJC Scopus subject areas

  • Oncology
  • Cancer Research

Cite this

Yu, K., Hyun, N., Fetterman, B., Lorey, T., Raine-Bennett, T. R., Zhang, H., ... Schiffman, M. (2018). Automated Cervical Screening and Triage, Based on HPV Testing and Computer-Interpreted Cytology. Journal of the National Cancer Institute, 110(11), 1222-1228. https://doi.org/10.1093/jnci/djy044

Automated Cervical Screening and Triage, Based on HPV Testing and Computer-Interpreted Cytology. / Yu, Kai; Hyun, Noorie; Fetterman, Barbara; Lorey, Thomas; Raine-Bennett, Tina R.; Zhang, Han; Stamps, Robin E.; Poitras, Nancy E.; Wheeler, William; Befano, Brian; Gage, Julia C.; Castle, Philip E.; Wentzensen, Nicolas; Schiffman, Mark.

In: Journal of the National Cancer Institute, Vol. 110, No. 11, 01.11.2018, p. 1222-1228.

Research output: Contribution to journalArticle

Yu, K, Hyun, N, Fetterman, B, Lorey, T, Raine-Bennett, TR, Zhang, H, Stamps, RE, Poitras, NE, Wheeler, W, Befano, B, Gage, JC, Castle, PE, Wentzensen, N & Schiffman, M 2018, 'Automated Cervical Screening and Triage, Based on HPV Testing and Computer-Interpreted Cytology', Journal of the National Cancer Institute, vol. 110, no. 11, pp. 1222-1228. https://doi.org/10.1093/jnci/djy044
Yu, Kai ; Hyun, Noorie ; Fetterman, Barbara ; Lorey, Thomas ; Raine-Bennett, Tina R. ; Zhang, Han ; Stamps, Robin E. ; Poitras, Nancy E. ; Wheeler, William ; Befano, Brian ; Gage, Julia C. ; Castle, Philip E. ; Wentzensen, Nicolas ; Schiffman, Mark. / Automated Cervical Screening and Triage, Based on HPV Testing and Computer-Interpreted Cytology. In: Journal of the National Cancer Institute. 2018 ; Vol. 110, No. 11. pp. 1222-1228.
@article{b20715c05bc1411299b1cb48c07a042a,
title = "Automated Cervical Screening and Triage, Based on HPV Testing and Computer-Interpreted Cytology",
abstract = "Background: State-of-the-art cervical cancer prevention includes human papillomavirus (HPV) vaccination among adolescents and screening/treatment of cervical precancer (CIN3/AIS and, less strictly, CIN2) among adults. HPV testing provides sensitive detection of precancer but, to reduce overtreatment, secondary {"}triage{"} is needed to predict women at highest risk. Those with the highest-risk HPV types or abnormal cytology are commonly referred to colposcopy; however, expert cytology services are critically lacking in many regions. Methods: To permit completely automatable cervical screening/triage, we designed and validated a novel triage method, a cytologic risk score algorithm based on computer-scanned liquid-based slide features (FocalPoint, BD, Burlington, NC). We compared it with abnormal cytology in predicting precancer among 1839 women testing HPV positive (HC2, Qiagen, Germantown, MD) in 2010 at Kaiser Permanente Northern California (KPNC). Precancer outcomes were ascertained by record linkage. As additional validation, we compared the algorithm prospectively with cytology results among 243 807 women screened at KPNC (2016-2017). All statistical tests were two-sided. Results: Among HPV-positive women, the algorithm matched the triage performance of abnormal cytology. Combined with HPV16/18/45 typing (Onclarity, BD, Sparks, MD), the automatable strategy referred 91.7{\%} of HPV-positive CIN3/AIS cases to immediate colposcopy while deferring 38.4{\%} of all HPV-positive women to one-year retesting (compared with 89.1{\%} and 37.4{\%}, respectively, for typing and cytology triage). In the 2016-2017 validation, the predicted risk scores strongly correlated with cytology (P < .001). Conclusions: High-quality cervical screening and triage performance is achievable using this completely automated approach. Automated technology could permit extension of high-quality cervical screening/triage coverage to currently underserved regions.",
author = "Kai Yu and Noorie Hyun and Barbara Fetterman and Thomas Lorey and Raine-Bennett, {Tina R.} and Han Zhang and Stamps, {Robin E.} and Poitras, {Nancy E.} and William Wheeler and Brian Befano and Gage, {Julia C.} and Castle, {Philip E.} and Nicolas Wentzensen and Mark Schiffman",
year = "2018",
month = "11",
day = "1",
doi = "10.1093/jnci/djy044",
language = "English (US)",
volume = "110",
pages = "1222--1228",
journal = "Journal of the National Cancer Institute",
issn = "0027-8874",
publisher = "Oxford University Press",
number = "11",

}

TY - JOUR

T1 - Automated Cervical Screening and Triage, Based on HPV Testing and Computer-Interpreted Cytology

AU - Yu, Kai

AU - Hyun, Noorie

AU - Fetterman, Barbara

AU - Lorey, Thomas

AU - Raine-Bennett, Tina R.

AU - Zhang, Han

AU - Stamps, Robin E.

AU - Poitras, Nancy E.

AU - Wheeler, William

AU - Befano, Brian

AU - Gage, Julia C.

AU - Castle, Philip E.

AU - Wentzensen, Nicolas

AU - Schiffman, Mark

PY - 2018/11/1

Y1 - 2018/11/1

N2 - Background: State-of-the-art cervical cancer prevention includes human papillomavirus (HPV) vaccination among adolescents and screening/treatment of cervical precancer (CIN3/AIS and, less strictly, CIN2) among adults. HPV testing provides sensitive detection of precancer but, to reduce overtreatment, secondary "triage" is needed to predict women at highest risk. Those with the highest-risk HPV types or abnormal cytology are commonly referred to colposcopy; however, expert cytology services are critically lacking in many regions. Methods: To permit completely automatable cervical screening/triage, we designed and validated a novel triage method, a cytologic risk score algorithm based on computer-scanned liquid-based slide features (FocalPoint, BD, Burlington, NC). We compared it with abnormal cytology in predicting precancer among 1839 women testing HPV positive (HC2, Qiagen, Germantown, MD) in 2010 at Kaiser Permanente Northern California (KPNC). Precancer outcomes were ascertained by record linkage. As additional validation, we compared the algorithm prospectively with cytology results among 243 807 women screened at KPNC (2016-2017). All statistical tests were two-sided. Results: Among HPV-positive women, the algorithm matched the triage performance of abnormal cytology. Combined with HPV16/18/45 typing (Onclarity, BD, Sparks, MD), the automatable strategy referred 91.7% of HPV-positive CIN3/AIS cases to immediate colposcopy while deferring 38.4% of all HPV-positive women to one-year retesting (compared with 89.1% and 37.4%, respectively, for typing and cytology triage). In the 2016-2017 validation, the predicted risk scores strongly correlated with cytology (P < .001). Conclusions: High-quality cervical screening and triage performance is achievable using this completely automated approach. Automated technology could permit extension of high-quality cervical screening/triage coverage to currently underserved regions.

AB - Background: State-of-the-art cervical cancer prevention includes human papillomavirus (HPV) vaccination among adolescents and screening/treatment of cervical precancer (CIN3/AIS and, less strictly, CIN2) among adults. HPV testing provides sensitive detection of precancer but, to reduce overtreatment, secondary "triage" is needed to predict women at highest risk. Those with the highest-risk HPV types or abnormal cytology are commonly referred to colposcopy; however, expert cytology services are critically lacking in many regions. Methods: To permit completely automatable cervical screening/triage, we designed and validated a novel triage method, a cytologic risk score algorithm based on computer-scanned liquid-based slide features (FocalPoint, BD, Burlington, NC). We compared it with abnormal cytology in predicting precancer among 1839 women testing HPV positive (HC2, Qiagen, Germantown, MD) in 2010 at Kaiser Permanente Northern California (KPNC). Precancer outcomes were ascertained by record linkage. As additional validation, we compared the algorithm prospectively with cytology results among 243 807 women screened at KPNC (2016-2017). All statistical tests were two-sided. Results: Among HPV-positive women, the algorithm matched the triage performance of abnormal cytology. Combined with HPV16/18/45 typing (Onclarity, BD, Sparks, MD), the automatable strategy referred 91.7% of HPV-positive CIN3/AIS cases to immediate colposcopy while deferring 38.4% of all HPV-positive women to one-year retesting (compared with 89.1% and 37.4%, respectively, for typing and cytology triage). In the 2016-2017 validation, the predicted risk scores strongly correlated with cytology (P < .001). Conclusions: High-quality cervical screening and triage performance is achievable using this completely automated approach. Automated technology could permit extension of high-quality cervical screening/triage coverage to currently underserved regions.

UR - http://www.scopus.com/inward/record.url?scp=85056610893&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056610893&partnerID=8YFLogxK

U2 - 10.1093/jnci/djy044

DO - 10.1093/jnci/djy044

M3 - Article

VL - 110

SP - 1222

EP - 1228

JO - Journal of the National Cancer Institute

JF - Journal of the National Cancer Institute

SN - 0027-8874

IS - 11

ER -