RESUMEN

INTRODUCTION: In 2006, the first human papillomavirus (HPV) vaccine was approved by the Food and Drug Administration in the USA based on pre-licensure clinical trials that found it to be highly efficacious at preventing persistent infection and precancerous, high-grade cervical lesions (HGCLs) caused by viral types the vaccine protects against. However, the real-world effectiveness of HPV vaccines as used in clinical practice may be quite different from the efficacy found in pre-licensure clinical trials. More than 10 years have passed since the introduction of the vaccine programme. It is critical to determine if the full benefits of HPV are being realised in real-world settings. METHODS AND ANALYSIS: The objectives of this study were to estimate the effectiveness of HPV vaccines as used in real-world clinical settings and to determine the degree to which the vaccine's effectiveness varies based on age at the time of immunisation and the number of doses received. The study will be a population-based, matched case-control study. Cases will be women with newly diagnosed HGCL associated with HPV types 16 and 18. Matched controls will be women with a normal Pap test result, matched individually to cases in a 2:1 ratio by age, a practice and date of testing. Medical records will be reviewed to determine dates of receipt of the HPV vaccine for all participants. We will use multivariate conditional logistic regression to control for potential confounders. ETHICS AND DISSEMINATION: This protocol presents minimal risk to the subjects. This protocol has received approval from the Institutional Review Board of Yale University (HIC: 1502015308), and a Health Insurance Portability and Accountability Act (HIPAA) Waiver of Authorisation has been granted to allow investigators to recruit subjects for the study. Findings will be disseminated through peer-reviewed, open-access scientific journals and conference presentations.

Asunto(s)

RESUMEN

BACKGROUND: Accurate identification of new diagnoses of human papillomavirus-associated cancers and precancers is an important step toward the development of strategies that optimize the use of human papillomavirus vaccines. The diagnosis of human papillomavirus cancers hinges on a histopathologic report, which is typically stored in electronic medical records as free-form, or unstructured, narrative text. Previous efforts to perform surveillance for human papillomavirus cancers have relied on the manual review of pathology reports to extract diagnostic information, a process that is both labor- and resource-intensive. Natural language processing can be used to automate the structuring and extraction of clinical data from unstructured narrative text in medical records and may provide a practical and effective method for identifying patients with vaccine-preventable human papillomavirus disease for surveillance and research. OBJECTIVE: This study's objective was to develop and assess the accuracy of a natural language processing algorithm for the identification of individuals with cancer or precancer of the cervix and anus. METHODS: A pipeline-based natural language processing algorithm was developed, which incorporated machine learning and rule-based methods to extract diagnostic elements from the narrative pathology reports. To test the algorithm's classification accuracy, we used a split-validation study design. Full-length cervical and anal pathology reports were randomly selected from 4 clinical pathology laboratories. Two study team members, blinded to the classifications produced by the natural language processing algorithm, manually and independently reviewed all reports and classified them at the document level according to 2 domains (diagnosis and human papillomavirus testing results). Using the manual review as the gold standard, the algorithm's performance was evaluated using standard measurements of accuracy, recall, precision, and F-measure. RESULTS: The natural language processing algorithm's performance was validated on 949 pathology reports. The algorithm demonstrated accurate identification of abnormal cytology, histology, and positive human papillomavirus tests with accuracies greater than 0.91. Precision was lowest for anal histology reports (0.87, 95% CI 0.59-0.98) and highest for cervical cytology (0.98, 95% CI 0.95-0.99). The natural language processing algorithm missed 2 out of the 15 abnormal anal histology reports, which led to a relatively low recall (0.68, 95% CI 0.43-0.87). CONCLUSIONS: This study outlines the development and validation of a freely available and easily implementable natural language processing algorithm that can automate the extraction and classification of clinical data from cervical and anal cytology and histology.