Development of models for cervical cancer screening: construction in a cross-sectional population and validation in two screening cohorts in China.
TL;DR: In this paper, the authors developed and evaluated a more accurate model for cervical cancer screening using age, cytology, high-risk human papillomavirus (hrHPV) DNA/mRNA, E6 oncoprotein, HPV genotyping, and p16/Ki-67.
Abstract: Current methods for cervical cancer screening result in an increased number of referrals and unnecessary diagnostic procedures. This study aimed to develop and evaluate a more accurate model for cervical cancer screening. Multiple predictors including age, cytology, high-risk human papillomavirus (hrHPV) DNA/mRNA, E6 oncoprotein, HPV genotyping, and p16/Ki-67 were used for model construction in a cross-sectional population including women with normal cervix (N = 1085), cervical intraepithelial neoplasia (CIN, N = 279), and cervical cancer (N = 551) to predict CIN2+ or CIN3+. A base model using age, cytology, and hrHPV was calculated, and extended versions with additional biomarkers were considered. External validations in two screening cohorts with 3-year follow-up were further conducted (NCohort-I = 3179, NCohort-II = 3082). The base model increased the area under the curve (AUC, 0.91, 95% confidence interval [CI] = 0.88–0.93) and reduced colposcopy referral rates (42.76%, 95% CI = 38.67–46.92) compared to hrHPV and cytology co-testing in the cross-sectional population (AUC 0.80, 95% CI = 0.79–0.82, referrals rates 61.62, 95% CI = 59.4–63.8) to predict CIN2+. The AUC further improved when HPV genotyping and/or E6 oncoprotein were included in the base model. External validation in two screening cohorts further demonstrated that our models had better clinical performances than routine screening methods, yielded AUCs of 0.92 (95% CI = 0.91–0.93) and 0.94 (95% CI = 0.91–0.97) to predict CIN2+ and referrals rates of 17.55% (95% CI = 16.24–18.92) and 7.40% (95% CI = 6.50–8.38) in screening cohort I and II, respectively. Similar results were observed for CIN3+ prediction. Compared to routine screening methods, our model using current cervical screening indicators can improve the clinical performance and reduce referral rates.
Citations
More filters
TL;DR: In this article , the authors developed and validated a nomogram which incorporates multiple clinically relevant variables to better identify HSIL+ cases during colposcopic examination. But the model was externally validated with 472 consecutive patients and compared to 422 other patients from two additional hospitals.
Abstract: Abstract Background Colposcopic examination with biopsy is the standard procedure for referrals with abnormal cervical cancer screening results; however, the decision to biopsy is controvertible. Having a predictive model may help to improve high-grade squamous intraepithelial lesion or worse (HSIL+) predictions which could reduce unnecessary testing and protecting women from unnecessary harm. Methods This retrospective multicenter study involved 5,854 patients identified through colposcopy databases. Cases were randomly assigned to a training set for development or to an internal validation set for performance assessment and comparability testing. Least Absolute Shrinkage and Selection Operator (LASSO) regression was used to reduce the number of candidate predictors and select statistically significant factors. Multivariable logistic regression was then used to establish a predictive model which generates risk scores for developing HSIL+. The predictive model is presented as a nomogram and was assessed for discriminability, and with calibration and decision curves. The model was externally validated with 472 consecutive patients and compared to 422 other patients from two additional hospitals. Results The final predictive model included age, cytology results, human papillomavirus status, transformation zone types, colposcopic impressions, and size of lesion area. The model had good overall discrimination when predicting HSIL + risk, which was internally validated (Area Under the Curve [AUC] of 0.92 (95%CI 0.90–0.94)). External validation found an AUC of 0.91 (95%CI 0.88–0.94) across the consecutive sample, and 0.88 (95%CI 0.84–0.93) across the comparative sample. Calibration suggested good coherence between predicted and observed probabilities. Decision curve analysis also suggested this model would be clinically useful. Conclusion We developed and validated a nomogram which incorporates multiple clinically relevant variables to better identify HSIL + cases during colposcopic examination. This model may help clinicians determining next steps and in particular, around the need to refer patients for colposcopy-guided biopsies.
TL;DR: In this paper , the authors used mathematical models to predict the risk of cervical lesion progression and identifying precancerous lesions in patients in northern Thailand by evaluating the expression of multiple biomarkers.
Abstract: The current practice of determining histologic grade with a single molecular biomarker can facilitate differential diagnosis but cannot predict the risk of lesion progression. Cancer is caused by complex mechanisms, and no single biomarker can both make accurate diagnoses and predict progression risk. Modelling using multiple biomarkers can be used to derive scores for risk prediction. Mathematical models (MMs) may be capable of making predictions from biomarker data. Therefore, this study aimed to develop MM–based scores for predicting the risk of precancerous cervical lesion progression and identifying precancerous lesions in patients in northern Thailand by evaluating the expression of multiple biomarkers. The MMs (Models 1–5) were developed in the test sample set based on patient age range (five categories) and biomarker levels (cortactin, p16INK4A, and Ki–67 by immunohistochemistry [IHC], and HPV E6/E7 ribonucleic acid (RNA) by in situ hybridization [ISH]). The risk scores for the prediction of cervical lesion progression (“risk biomolecules”) ranged from 2.56–2.60 in the normal and low–grade squamous intraepithelial lesion (LSIL) cases and from 3.54–3.62 in cases where precancerous lesions were predicted to progress. In Model 4, 23/86 (26.7%) normal and LSIL cases had biomolecule levels that suggested a risk of progression, while 5/86 (5.8%) cases were identified as precancerous lesions. Additionally, histologic grading with a single molecular biomarker did not identify 23 cases with risk, preventing close patient monitoring. These results suggest that biomarker level–based risk scores are useful for predicting the risk of cervical lesion progression and identifying precancerous lesion development. This multiple biomarker–based strategy may ultimately have utility for predicting cancer progression in other contexts.
TL;DR: Wang et al. as mentioned in this paper evaluated the feasibility of machine learning (ML) models for predicting high-grade squamous intraepithelial lesions or worse (HSIL+) in patients referred for colposcopy by combining colposcopic findings with demographic and screening results.
Abstract: Background: Colposcopy plays an essential role in cervical cancer control, but its performance remains unsatisfactory. This study evaluates the feasibility of machine learning (ML) models for predicting high-grade squamous intraepithelial lesions or worse (HSIL+) in patients referred for colposcopy by combining colposcopic findings with demographic and screening results. Methods: In total, 7485 patients who underwent colposcopy examination in seven hospitals in mainland China were used to train, internally validate, and externally validate six commonly used ML models, including logistic regression, decision tree, naïve bayes, support vector machine, random forest, and extreme gradient boosting. Nine variables, including age, gravidity, parity, menopause status, cytological results, high-risk human papillomavirus (HR-HPV) infection type, HR-HPV multi-infection, transformation zone (TZ) type, and colposcopic impression, were used for model construction. Results: Colposcopic impression, HR-HPV results, and cytology results were the top three variables that determined model performance among all included variables. In the internal validation set, six ML models that integrated demographics, screening results, and colposcopic impression showed significant improvements in the area under the curve (AUC) (0.067 to 0.099) and sensitivity (11.55% to 14.88%) compared with colposcopists. Greater increases in AUC (0.087 to 0.119) and sensitivity (17.17% to 22.08%) were observed in the six models with the external validation set. Conclusions: By incorporating demographics, screening results, and colposcopic impressions, ML improved the AUC and sensitivity for detecting HSIL+ in patients referred for colposcopy. Such models could transform the subjective experience into objective judgments to help clinicians make decisions at the time of colposcopy examinations.
References
More filters
TL;DR: A status report on the global burden of cancer worldwide using the GLOBOCAN 2018 estimates of cancer incidence and mortality produced by the International Agency for Research on Cancer, with a focus on geographic variability across 20 world regions.
Abstract: This article provides a status report on the global burden of cancer worldwide using the GLOBOCAN 2018 estimates of cancer incidence and mortality produced by the International Agency for Research on Cancer, with a focus on geographic variability across 20 world regions There will be an estimated 181 million new cancer cases (170 million excluding nonmelanoma skin cancer) and 96 million cancer deaths (95 million excluding nonmelanoma skin cancer) in 2018 In both sexes combined, lung cancer is the most commonly diagnosed cancer (116% of the total cases) and the leading cause of cancer death (184% of the total cancer deaths), closely followed by female breast cancer (116%), prostate cancer (71%), and colorectal cancer (61%) for incidence and colorectal cancer (92%), stomach cancer (82%), and liver cancer (82%) for mortality Lung cancer is the most frequent cancer and the leading cause of cancer death among males, followed by prostate and colorectal cancer (for incidence) and liver and stomach cancer (for mortality) Among females, breast cancer is the most commonly diagnosed cancer and the leading cause of cancer death, followed by colorectal and lung cancer (for incidence), and vice versa (for mortality); cervical cancer ranks fourth for both incidence and mortality The most frequently diagnosed cancer and the leading cause of cancer death, however, substantially vary across countries and within each country depending on the degree of economic development and associated social and life style factors It is noteworthy that high-quality cancer registry data, the basis for planning and implementing evidence-based cancer control programs, are not available in most low- and middle-income countries The Global Initiative for Cancer Registry Development is an international partnership that supports better estimation, as well as the collection and use of local data, to prioritize and evaluate national cancer control efforts CA: A Cancer Journal for Clinicians 2018;0:1-31 © 2018 American Cancer Society
58,675 citations
TL;DR: A new algorithm to search the tree space with user-defined intensity using subtree pruning and regrafting topological moves and a new test to assess the support of the data for internal branches of a phylogeny are introduced.
Abstract: PhyML is a phylogeny software based on the maximum-likelihood principle. Early PhyML versions used a fast algorithm performing nearest neighbor interchanges to improve a reasonable starting tree topology. Since the original publication (Guindon S., Gascuel O. 2003. A simple, fast and accurate algorithm to estimate large phylogenies by maximum likelihood. Syst. Biol. 52:696-704), PhyML has been widely used (>2500 citations in ISI Web of Science) because of its simplicity and a fair compromise between accuracy and speed. In the meantime, research around PhyML has continued, and this article describes the new algorithms and methods implemented in the program. First, we introduce a new algorithm to search the tree space with user-defined intensity using subtree pruning and regrafting topological moves. The parsimony criterion is used here to filter out the least promising topology modifications with respect to the likelihood function. The analysis of a large collection of real nucleotide and amino acid data sets of various sizes demonstrates the good performance of this method. Second, we describe a new test to assess the support of the data for internal branches of a phylogeny. This approach extends the recently proposed approximate likelihood-ratio test and relies on a nonparametric, Shimodaira-Hasegawa-like procedure. A detailed analysis of real alignments sheds light on the links between this new approach and the more classical nonparametric bootstrap method. Overall, our tests show that the last version (3.0) of PhyML is fast, accurate, stable, and ready to use. A Web server and binary files are available from http://www.atgc-montpellier.fr/phyml/.
14,385 citations
TL;DR: The presence of HPV in virtually all cervical cancers implies the highest worldwide attributable fraction so far reported for a specific cause of any major human cancer, and the rationale for HPV testing in addition to, or even instead of, cervical cytology in routine cervical screening.
Abstract: A recent report that 93 per cent of invasive cervical cancers worldwide contain human papillomavirus (HPV) may be an underestimate, due to sample inadequacy or integration events affecting the HPV L1 gene, which is the target of the polymerase chain reaction (PCR)-based test which was used. The formerly HPV-negative cases from this study have therefore been reanalyzed for HPV serum antibodies and HPV DNA. Serology for HPV 16 VLPs, E6, and E7 antibodies was performed on 49 of the 66 cases which were HPV-negative and a sample of 48 of the 866 cases which were HPV-positive in the original study. Moreover, 55 of the 66 formerly HPV-negative biopsies were also reanalyzed by a sandwich procedure in which the outer sections in a series of sections are used for histological review, while the inner sections are assayed by three different HPV PCR assays targeting different open reading frames (ORFs). No significant difference was found in serology for HPV 16 proteins between the cases that were originally HPV PCR-negative and -positive. Type-specific E7 PCR for 14 high-risk HPV types detected HPV DNA in 38 (69 per cent) of the 55 originally HPV-negative and amplifiable specimens. The HPV types detected were 16, 18, 31, 33, 39, 45, 52, and 58. Two (4 per cent) additional cases were only HPV DNA-positive by E1 and/or L1 consensus PCR. Histological analysis of the 55 specimens revealed that 21 were qualitatively inadequate. Only two of the 34 adequate samples were HPV-negative on all PCR tests, as against 13 of the 21 that were inadequate ( p< 0.001). Combining the data from this and the previous study and excluding inadequate specimens, the worldwide HPV prevalence in cervical carcinomas is 99.7 per cent. The presence of HPV in virtually all cervical cancers implies the highest worldwide attributable fraction so far reported for a specific cause of any major human cancer. The extreme rarity of HPV-negative cancers reinforces the rationale for HPV testing in addition to, or even instead of, cervical cytology in routine cervical screening.
8,407 citations
TL;DR: What obstacles there may be to changing the practice of medicine through statistical learning approaches, and how these might be overcome are identified.
Abstract: Spurred by advances in processing power, memory, storage, and an unprecedented wealth of data, computers are being asked to tackle increasingly complex learning tasks, often with astonishing success. Computers have now mastered a popular variant of poker, learned the laws of physics from experimental data, and become experts in video games - tasks that would have been deemed impossible not too long ago. In parallel, the number of companies centered on applying complex data analysis to varying industries has exploded, and it is thus unsurprising that some analytic companies are turning attention to problems in health care. The purpose of this review is to explore what problems in medicine might benefit from such learning approaches and use examples from the literature to introduce basic concepts in machine learning. It is important to note that seemingly large enough medical data sets and adequate learning algorithms have been available for many decades, and yet, although there are thousands of papers applying machine learning algorithms to medical data, very few have contributed meaningfully to clinical care. This lack of impact stands in stark contrast to the enormous relevance of machine learning to many other industries. Thus, part of my effort will be to identify what obstacles there may be to changing the practice of medicine through statistical learning approaches, and discuss how these might be overcome.
2,062 citations
TL;DR: HPV testing has greater sensitivity for the detection of cervical intraepithelial neoplasia than Pap testing, and Triage procedures for Pap or HPV testing resulted in fewer referrals for colposcopy than did either test alone but were less sensitive.
Abstract: Background To determine whether testing for DNA of oncogenic human papillomaviruses (HPV) is superior to the Papanicolaou (Pap) test for cervical-cancer screening, we conducted a randomized trial comparing the two methods. Methods We compared HPV testing, using an assay approved by the Food and Drug Administration, with conventional Pap testing as a screening method to identify high-grade cervical intraepithelial neoplasia in women ages 30 to 69 years in Montreal and St. John's, Canada. Women with abnormal Pap test results or a positive HPV test (at least 1 pg of high-risk HPV DNA per milliliter) underwent colposcopy and biopsy, as did a random sample of women with negative tests. Sensitivity and specificity estimates were corrected for verification bias. Results A total of 10,154 women were randomly assigned to testing. Both tests were performed on all women in a randomly assigned sequence at the same session. The sensitivity of HPV testing for cervical intraepithelial neoplasia of grade 2 or 3 was 94.6%...
989 citations