Dataset Information

Machine Learning Interpretation of Extended Human Papillomavirus Genotyping by Onclarity in an Asian Cervical Cancer Screening Population.

ABSTRACT: This study aimed (i) to compare the performance of the BD Onclarity human papillomavirus (HPV) assay with the Cobas HPV test in identifying cervical intraepithelial neoplasia 2/3 or above (CIN2/3+) in an Asian screening population and (ii) to explore improving the cervical cancer detection specificity of Onclarity by machine learning. We tested 605 stratified random archived samples of cervical liquid-based cytology samples with both assays. All samples had biopsy diagnosis or repeated negative cytology follow-up. Association rule mining (ARM) was employed to discover coinfection likely to give rise to CIN2/3+. Outcome classifiers interpreting the extended genotyping results of Onclarity were built with different underlying models. The sensitivities (Onclarity, 96.32%; Cobas, 95.71%) and specificities (Onclarity, 46.38%; Cobas, 45.25%) of the high-risk HPV (hrHPV) components of the two tests were not significantly different. When HPV16 and HPV18 were used to further interpret hrHPV-positive cases, Onclarity displayed significantly higher specificity (Onclarity, 87.10%; Cobas, 80.77%). Both hrHPV tests achieved the same sensitivities (Onclarity, 90.91%; Cobas, 90.91%) and similar specificities (Onclarity, 48.46%; Cobas, 51.98%) when used for triaging atypical squamous cells of undetermined significance. Positivity in both HPV16 and HPV33/58 of the Onclarity channels entails the highest probability of developing CIN2/3+. Incorporating other hrHPVs into the outcome classifiers improved the specificity of identifying CIN2/3 to up to 94.32%. The extended genotyping of Onclarity therefore can help to highlight patients having the highest risk of developing CIN2/3+, with the potential to reduce unnecessary colposcopy and negative psychosocial impact on women receiving the reports.

SUBMITTER: Wong OGW

PROVIDER: S-EPMC6879281 | biostudies-literature | 2019 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine Learning Interpretation of Extended Human Papillomavirus Genotyping by Onclarity in an Asian Cervical Cancer Screening Population.

Wong Oscar G W OGW Ng Idy F Y IFY Tsun Obe K L OKL Pang Herbert H HH Ip Philip P C PPC Cheung Annie N Y ANY

Journal of clinical microbiology 20191122 12

This study aimed (i) to compare the performance of the BD Onclarity human papillomavirus (HPV) assay with the Cobas HPV test in identifying cervical intraepithelial neoplasia 2/3 or above (CIN2/3+) in an Asian screening population and (ii) to explore improving the cervical cancer detection specificity of Onclarity by machine learning. We tested 605 stratified random archived samples of cervical liquid-based cytology samples with both assays. All samples had biopsy diagnosis or repeated negative ...[more]

PMID: 31511337

Similar Datasets

Project description:BackgroundThe aim of the study was to investigate the risk of human papillomavirus (HPV) genotyping particularly vaccine genotypes and multiple infections for cervical precancer and cancer, which might contribute to developing genotype-specific screening strategy and assessing potential effects of HPV vaccine.MethodsThe HPV genotypes were identified using the Seq HPV assay on self-collected samples. Hierarchical ranking of each genotype was performed according to positive predictive value (PPV) for cervical intraepithelial neoplasia 2/3 or worse (CIN2+/CIN3+). Multivariate logistic regression model was used to estimate the odds ratios (ORs) with 95% confidence interval (CI) of CIN2+ according to multiplicity of types and vaccine types.ResultsA total of 2811 HPV-positive women were analyzed. The five dominant HPV genotypes in high-grade lesions were 16/58/52/33/18. The overall ranking orders were HPV16/33/35/58/31/68/18/ 56/52/66/51/59/45/39 for CIN2+ and HPV16/33/31/58/45/66/52/18/35/56/51/68/59/39 for CIN3+. The risks of single infection versus co-infections with other types lower in the hierarchy having CIN2+ were not statistically significant for HPV16 (multiple infection vs. single infection: OR = 0.8, 95%CI = 0.6-1.1, P = 0.144) or other genotypes (P > 0.0036) after conservative Bonferroni correction. Whether HPV16 was present or not, the risks of single infection versus multiple infection with any number (2, ≥2, or ≥ 3) of types for CIN2+ were not significantly different. In addition, HPV31/33/45/52/58 covered by nonavalent vaccine added 27.5% of CIN2, 23.0% of CIN3, and 12.5% of cancer to the HPV16/18 genotyping. These genotype-groups were at significantly higher risks than genotypes not covered by nonavalent vaccine. Moreover, genotypes covered by nonavalent vaccine contributed to 85.2% of CIN2 lesions, 97.9% of CIN3 and 93.8% of cancers.ConclusionsPartial extended genotyping such as HPV33/31/58 but not multiplicity of HPV infections could serve as a promising triage for HPV-positive self-samples. Moreover, incidence rates of cervical cancer and precancer were substantial attributable to HPV genotypes covered by current nonavalent vaccination.

Dataset Information

Machine Learning Interpretation of Extended Human Papillomavirus Genotyping by Onclarity in an Asian Cervical Cancer Screening Population.

Publications

Machine Learning Interpretation of Extended Human Papillomavirus Genotyping by Onclarity in an Asian Cervical Cancer Screening Population.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets