Dataset Information

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.

SUBMITTER: Wagholikar KB

PROVIDER: S-EPMC4214690 | biostudies-literature | 2014

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automated recommendation for cervical cancer screening and surveillance.

Wagholikar Kavishwar B KB MacLaughlin Kathy L KL Casey Petra M PM Kastner Thomas M TM Henry Michael R MR Hankey Ronald A RA Peters Steve G SG Greenes Robert A RA Chute Christopher G CG Liu Hongfang H Chaudhry Rajeev R

Cancer informatics 20141015 Suppl 3

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 co ...[more]

PMID: 25368505

Similar Datasets

Project description:BackgroundAlthough cervical cancer is largely preventable through screening, detection and treatment of precancerous abnormalities, it remains one of the top causes of cancer-related morbidity and mortality globally.ObjectivesThe objective of this systematic review is to understand the evidence of the effect of cervical cancer education compared to control conditions on cervical cancer screening rates in eligible women population at risk of cervical cancer. We also sought to understand the effect of provider recommendations for screening to eligible women on cervical cancer screening (CCS) rates compared to control conditions in eligible women population at risk of cervical cancer.MethodsWe used the PICO (Problem or Population, Interventions, Comparison and Outcome) framework as described in the Cochrane Collaboration Handbook to develop our search strategy. The details of our search strategy has been described in our systematic review protocol published in the International Prospective Register of systematic reviews (PROSPERO). The protocol registration number is CRD42016045605 available at: http://www.crd.york.ac.uk/prospero/display_record.asp?src=trip&ID=CRD42016045605. The search string was used in Pubmed, Embase, Cochrane Systematic Reviews and Cochrane CENTRAL register of controlled trials to retrieve study reports that were screened for inclusion in this review. Our data synthesis and reporting was guided by the Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA). We did a qualitative synthesis of evidence and, where appropriate, individual study effects were pooled in meta-analyses using RevMan 5.3 Review Manager. The Higgins I2 was used to assess for heterogeneity in studies pooled together for overall summary effects. We did assessment of risk of bias of individual studies included and assessed risk of publication bias across studies pooled together in meta-analysis by Funnel plot.ResultsOut of 3072 study reports screened, 28 articles were found to be eligible for inclusion in qualitative synthesis (5 of which were included in meta-analysis of educational interventions and 8 combined in meta-analysis of HPV self-sampling interventions), while 45 were excluded for various reasons. The use of theory-based educational interventions significantly increased CCS rates by more than double (OR, 2.46, 95% CI: 1.88, 3.21). Additionally, offering women the option of self-sampling for Human Papillomavirus (HPV) testing increased CCS rates by nearly 2-fold (OR = 1.71, 95% CI: 1.32, 2.22). We also found that invitation letters alone (or with a follow up phone contact), making an appointment, and sending reminders to patients who are due or overdue for screening had a significant effect on improving participation and CCS rates in populations at risk.ConclusionOur findings supports the implementation of theory-based cervical cancer educational interventions to increase women's participation in cervical cancer screening programs, particularly when targeting communities with low literacy levels. Additionally, cervical cancer screening programs should consider the option of offering women the opportunity for self-sample collection particularly when such women have not responded to previous screening invitation or reminder letters for Pap smear collection as a method of screening.

Project description:BackgroundCervical cancer screening (CCS) is an important health service intervention for prevention of morbidity and mortality from invasive cervical cancer. The role of provider recommendation and referral is critical in utilization of this services particularly in settings where screening is largely opportunistic. We sought to understand how patient-reported human immunodeficiency virus (HIV) infection status is associated with provider referral in an opportunistic screening setting.MethodsWe performed a cross-sectional analysis of data on a sample of women who had received a CCS at the "Operation Stop" cervical cancer (OSCC) screening service in Jos, Nigeria over a 10-year time period (2006-2016). We used the de-identified records of women who had their first CCS to analyze the association between patient-reported HIV and likelihood of provider-referral at first CCS. We performed descriptive statistics with relevant test of association using Student t-test (t-test) for continuous variables and Pearson chi square or Fisher exact test where applicable for categorical variables. We also used a bivariable and multivariable logistic regression models to estimate the independent association of patient-reported HIV on provider referral. All statistical tests were performed using STATA version 14.1, College Station, Texas, USA. Level of statistical significance was set at 0.05.ResultsDuring the 10-year period, 14,088 women had their first CCS. The reported HIV prevalence in the population was 5.0%; 95% CI: 4.6, 5.4 (703/14,088). The median age of women who were screened was 37 years (IQR; 30-45). Women who were HIV infected received more referrals from providers compared to women who were HIV uninfected (68.7% versus 49.2%), p-value < 0.001. Similarly, we found an independent effect of patient-reported HIV infection on the likelihood for provider-referral in the screened sample (aOR = 2.35; 95% CI: 1.95, 2.82).ConclusionOur analysis supports the design of health systems that facilitates providers' engagement and provision of necessary counseling for CCS in the course of routine clinical care. The practice of offering recommendation and referrals for CCS to women at high risk of cervical cancer, such as HIV infected women should be supported.

Project description:BackgroundHuman papillomavirus vaccination and cervical screening are lacking in most lower resource settings, where approximately 80% of more than 500 000 cancer cases occur annually. Visual inspection of the cervix following acetic acid application is practical but not reproducible or accurate. The objective of this study was to develop a "deep learning"-based visual evaluation algorithm that automatically recognizes cervical precancer/cancer.MethodsA population-based longitudinal cohort of 9406 women ages 18-94 years in Guanacaste, Costa Rica was followed for 7 years (1993-2000), incorporating multiple cervical screening methods and histopathologic confirmation of precancers. Tumor registry linkage identified cancers up to 18 years. Archived, digitized cervical images from screening, taken with a fixed-focus camera ("cervicography"), were used for training/validation of the deep learning-based algorithm. The resultant image prediction score (0-1) could be categorized to balance sensitivity and specificity for detection of precancer/cancer. All statistical tests were two-sided.ResultsAutomated visual evaluation of enrollment cervigrams identified cumulative precancer/cancer cases with greater accuracy (area under the curve [AUC] = 0.91, 95% confidence interval [CI] = 0.89 to 0.93) than original cervigram interpretation (AUC = 0.69, 95% CI = 0.63 to 0.74; P < .001) or conventional cytology (AUC = 0.71, 95% CI = 0.65 to 0.77; P < .001). A single visual screening round restricted to women at the prime screening ages of 25-49 years could identify 127 (55.7%) of 228 precancers (cervical intraepithelial neoplasia 2/cervical intraepithelial neoplasia 3/adenocarcinoma in situ [AIS]) diagnosed cumulatively in the entire adult population (ages 18-94 years) while referring 11.0% for management.ConclusionsThe results support consideration of automated visual evaluation of cervical images from contemporary digital cameras. If achieved, this might permit dissemination of effective point-of-care cervical screening.

Dataset Information

Automated recommendation for cervical cancer screening and surveillance.

Publications

Automated recommendation for cervical cancer screening and surveillance.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets