Automated recommendation for cervical cancer screening and surveillance

Kavishwar B. Wagholikar, Kathy L. Aclaughlin, Petra Casey, Thomas Kastner, Michael Henry, Ronald Hankey, Steve G. Peters, Robert Greenes, Christopher G. Chute, Hongfang Liu, Rajeev Chaudhry

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Because of the complexity of cervical cancer prevention guidelines, clinicians often fail to follow best-practice recommendations. Moreover, existing clinical decision support (CDS) systems generally recommend a cervical cytology every three years for all female patients, which is inappropriate for patients with abnormal findings that require surveillance at shorter intervals. To address this problem, we developed a decision tree-based CDS system that integrates national guidelines to provide comprehensive guidance to clinicians. Validation was performed in several iterations by comparing recommendations generated by the system with those of clinicians for 333 patients. The CDS system extracted relevant patient information from the electronic health record and applied the guideline model with an overall accuracy of 87%. Providers without CDS assistance needed an average of 1 minute 39 seconds to decide on recommendations for management of abnormal findings. Overall, our work demonstrates the feasibility and potential utility of automated recommendation system for cervical cancer screening and surveillance.

Original languageEnglish (US)
JournalCancer Informatics
Volume13
DOIs
StatePublished - Oct 15 2014

Fingerprint

Clinical Decision Support Systems
Early Detection of Cancer
Uterine Cervical Neoplasms
Guidelines
Decision Trees
Electronic Health Records
Practice Guidelines
Cell Biology

Keywords

  • Cervical cancer
  • Clinical decision support
  • Colposcopy
  • Natural language processing
  • Papanicolaou test

ASJC Scopus subject areas

  • Cancer Research
  • Oncology

Cite this

Wagholikar, K. B., Aclaughlin, K. L., Casey, P., Kastner, T., Henry, M., Hankey, R., ... Chaudhry, R. (2014). Automated recommendation for cervical cancer screening and surveillance. Cancer Informatics, 13. https://doi.org/10.4137/CIn.s14035

Automated recommendation for cervical cancer screening and surveillance. / Wagholikar, Kavishwar B.; Aclaughlin, Kathy L.; Casey, Petra; Kastner, Thomas; Henry, Michael; Hankey, Ronald; Peters, Steve G.; Greenes, Robert; Chute, Christopher G.; Liu, Hongfang; Chaudhry, Rajeev.

In: Cancer Informatics, Vol. 13, 15.10.2014.

Research output: Contribution to journalArticle

Wagholikar, KB, Aclaughlin, KL, Casey, P, Kastner, T, Henry, M, Hankey, R, Peters, SG, Greenes, R, Chute, CG, Liu, H & Chaudhry, R 2014, 'Automated recommendation for cervical cancer screening and surveillance', Cancer Informatics, vol. 13. https://doi.org/10.4137/CIn.s14035
Wagholikar KB, Aclaughlin KL, Casey P, Kastner T, Henry M, Hankey R et al. Automated recommendation for cervical cancer screening and surveillance. Cancer Informatics. 2014 Oct 15;13. https://doi.org/10.4137/CIn.s14035
Wagholikar, Kavishwar B. ; Aclaughlin, Kathy L. ; Casey, Petra ; Kastner, Thomas ; Henry, Michael ; Hankey, Ronald ; Peters, Steve G. ; Greenes, Robert ; Chute, Christopher G. ; Liu, Hongfang ; Chaudhry, Rajeev. / Automated recommendation for cervical cancer screening and surveillance. In: Cancer Informatics. 2014 ; Vol. 13.
@article{0a2faaeb61294473a1a6017abb3a141f,
title = "Automated recommendation for cervical cancer screening and surveillance",
abstract = "Because of the complexity of cervical cancer prevention guidelines, clinicians often fail to follow best-practice recommendations. Moreover, existing clinical decision support (CDS) systems generally recommend a cervical cytology every three years for all female patients, which is inappropriate for patients with abnormal findings that require surveillance at shorter intervals. To address this problem, we developed a decision tree-based CDS system that integrates national guidelines to provide comprehensive guidance to clinicians. Validation was performed in several iterations by comparing recommendations generated by the system with those of clinicians for 333 patients. The CDS system extracted relevant patient information from the electronic health record and applied the guideline model with an overall accuracy of 87{\%}. Providers without CDS assistance needed an average of 1 minute 39 seconds to decide on recommendations for management of abnormal findings. Overall, our work demonstrates the feasibility and potential utility of automated recommendation system for cervical cancer screening and surveillance.",
keywords = "Cervical cancer, Clinical decision support, Colposcopy, Natural language processing, Papanicolaou test",
author = "Wagholikar, {Kavishwar B.} and Aclaughlin, {Kathy L.} and Petra Casey and Thomas Kastner and Michael Henry and Ronald Hankey and Peters, {Steve G.} and Robert Greenes and Chute, {Christopher G.} and Hongfang Liu and Rajeev Chaudhry",
year = "2014",
month = "10",
day = "15",
doi = "10.4137/CIn.s14035",
language = "English (US)",
volume = "13",
journal = "Cancer Informatics",
issn = "1176-9351",
publisher = "Libertas Academica Ltd.",

}

TY - JOUR

T1 - Automated recommendation for cervical cancer screening and surveillance

AU - Wagholikar, Kavishwar B.

AU - Aclaughlin, Kathy L.

AU - Casey, Petra

AU - Kastner, Thomas

AU - Henry, Michael

AU - Hankey, Ronald

AU - Peters, Steve G.

AU - Greenes, Robert

AU - Chute, Christopher G.

AU - Liu, Hongfang

AU - Chaudhry, Rajeev

PY - 2014/10/15

Y1 - 2014/10/15

N2 - Because of the complexity of cervical cancer prevention guidelines, clinicians often fail to follow best-practice recommendations. Moreover, existing clinical decision support (CDS) systems generally recommend a cervical cytology every three years for all female patients, which is inappropriate for patients with abnormal findings that require surveillance at shorter intervals. To address this problem, we developed a decision tree-based CDS system that integrates national guidelines to provide comprehensive guidance to clinicians. Validation was performed in several iterations by comparing recommendations generated by the system with those of clinicians for 333 patients. The CDS system extracted relevant patient information from the electronic health record and applied the guideline model with an overall accuracy of 87%. Providers without CDS assistance needed an average of 1 minute 39 seconds to decide on recommendations for management of abnormal findings. Overall, our work demonstrates the feasibility and potential utility of automated recommendation system for cervical cancer screening and surveillance.

AB - Because of the complexity of cervical cancer prevention guidelines, clinicians often fail to follow best-practice recommendations. Moreover, existing clinical decision support (CDS) systems generally recommend a cervical cytology every three years for all female patients, which is inappropriate for patients with abnormal findings that require surveillance at shorter intervals. To address this problem, we developed a decision tree-based CDS system that integrates national guidelines to provide comprehensive guidance to clinicians. Validation was performed in several iterations by comparing recommendations generated by the system with those of clinicians for 333 patients. The CDS system extracted relevant patient information from the electronic health record and applied the guideline model with an overall accuracy of 87%. Providers without CDS assistance needed an average of 1 minute 39 seconds to decide on recommendations for management of abnormal findings. Overall, our work demonstrates the feasibility and potential utility of automated recommendation system for cervical cancer screening and surveillance.

KW - Cervical cancer

KW - Clinical decision support

KW - Colposcopy

KW - Natural language processing

KW - Papanicolaou test

UR - http://www.scopus.com/inward/record.url?scp=84907870467&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907870467&partnerID=8YFLogxK

U2 - 10.4137/CIn.s14035

DO - 10.4137/CIn.s14035

M3 - Article

VL - 13

JO - Cancer Informatics

JF - Cancer Informatics

SN - 1176-9351

ER -