BACKGROUND: Human papillomavirus (HPV) infection can lead to serious health issues and remains the most common sexually transmitted infection. Despite availability of effective vaccines, HPV vaccination rates are suboptimal. METHODS: In a cluster randomized trial, an intervention used to target parents of adolescents (11-17 years) eligible for a dose of HPV vaccine, was tested in pediatric clinics part of an urban health system. Parents watched a digital video outlining the risks and benefits of vaccine using a tablet in the examination room. The primary outcome was change in HPV vaccine status 2 weeks after the clinic visit. An intention-to-treat analysis for the primary outcome used generalized estimating equations to accommodate the potential cluster effect of clinics. RESULTS: A total of 1596 eligible adolescents were observed during the 7-month trial. One-third of adolescents visited an intervention clinic. Adolescents who attended an intervention clinic were more likely to be younger (11-12 years) than those who attended a control clinic (72.4% vs 49.8%; P < .001). No differences in race or sex were observed. The proportion of adolescents with an observed change in vaccine status was higher for those attending an intervention clinic (64.8%) versus control clinic (50.1%; odds ratio, 1.82; 95% confidence interval, 1.47-2.25; P < .001). Adolescents whose parents watched the video had a 3-times greater odds of receiving a dose of the HPV vaccine (78.
e18235 Background: Large automated electronic medical record (EMR) databases have the potential to be valuable tools in studying the patterns and effectiveness of treatment. Therefore, the current study sought to develop novel tools to identify bladder cancer cases, their clinical stage, and the chemotherapy they receive in electronic medical records. Methods: EMR data were obtained from Indiana University Health hospitals from 2008 to 2015. We developed 2 novel algorithms using natural language processing on unstructured data to identify (a) bladder cancer cases and clinical stage, and (b) chemotherapy names and line of chemotherapy. Performance characteristics for each algorithm were assessed using sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Each algorithm’s performance for case ascertainment was measured against the gold standard of manual chart review. Results: A total of 2,559 unique bladder cancer patients were identified and stratified using the clinical staging algorithm, defined as metastatic, muscle invasive, or non-muscle invasive. We identified 657 metastatic cases, 567 muscle invasive cases, and 604 non-muscle invasive cases. Next, the treatment algorithm was applied to metastatic patients to identify the type of chemotherapy received and 1st or 2nd line of therapy. The sensitivity, specificity, PPV, and NPV for the clinical staging and treatment algorithm were calculated against the gold standard of manual chart review (Table). Conclusions: The performance of the staging algorithm demonstrates the strength of using innovative approaches. The poor performance of the treatment algorithm sets a framework from which to build upon in future work and suggests that structured approaches may still be the preferable approach. [Table: see text]
We employed natural language processing (NLP) algorithms to extract estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor 2 (HER2) receptor status for females with breast cancer using unstructured (free text) EMR data, and to determine the prevalence of triple negative breast cancer in the Indiana network for patient care (INPC) population. We identified female patients in INPC with a history of breast cancer over a ten year period who had at least five oncology notes or one related pathology document. Based on manual chart review, our NLP algorithms for extracting ER, PR, and HER2 receptor status performed well with sensitivity 87.5% to 92.6%, specificity 88.6% to 95.8%, positive predictive values (PPV) 82.4% to 99.0%, and negative predictive values (NPV) 85.2% to 97.7%. This study confirmed our primary hypothesis that NLP algorithms are effective in identifying important breast cancer biomarkers in patients with breast cancer using unstructured data.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.