Screening for Chlamydia and Gonorrhea

Underlying Reasons for Primary Care Visits Where Chlamydia Testing Was Performed in the United States, 2019 to 2022

BACKGROUND

In the United States, most chlamydia cases are reported from non-sexually transmitted disease clinics, and there is limited information focusing on the reasons for chlamydia testing in private settings. These analyses describe clinical visits to primary care providers where chlamydia testing was performed to help discern between screening and diagnostic testing for chlamydia.

METHODS

Using the largest primary care clinical registry in the United States, the PRIME registry, chlamydia tests were identified using Current Procedural Terminology procedure codes and categorized as diagnostic testing for sexually transmitted infection (STI)-related symptoms, screening for chlamydia, or "other," based on Classification of Diseases, Tenth Revision Evaluation and Management codes selected for visits.

RESULTS

Of 120,013 clinical visits with chlamydia testing between January 1, 2019, and December 31, 2022, 70.4% were women; 20.6% were with STI-related symptoms, 59.9% were for screening, and 19.5% for "other" reasons. Of those 120,013 clinical visits with chlamydia testing, the logit model showed that patients were significantly more likely to have STI-related symptoms if they were female than male, non-Hispanic Black than non-Hispanic White, aged 15 to 24 years than aged ≥45 years, and resided in the South than in the Northeast.

CONCLUSION

It is important to know what proportion of chlamydial infections is identified through screening programs and to have this information stratified by demographics. The inclusion of laboratory results could further facilitate a better understanding of the impact of chlamydia screening programs on the identification and treatment of chlamydia in private office settings in the United States.

A Machine Learning-Based Analytic Pipeline Applied to Clinical and Serum IgG Immunoproteome Data To Predict Chlamydia trachomatis Genital Tract Ascension and Incident Infection in Women

We developed a reusable and open-source machine learning (ML) pipeline that can provide an analytical framework for rigorous biomarker discovery. We implemented the ML pipeline to determine the predictive potential of clinical and immunoproteome antibody data for outcomes associated with Chlamydia trachomatis (Ct) infection collected from 222 cis-gender females with high Ct exposure. We compared the predictive performance of 4 ML algorithms (naive Bayes, random forest, extreme gradient boosting with linear booster [xgbLinear], and k-nearest neighbors [KNN]), screened from 215 ML methods, in combination with two different feature selection strategies, Boruta and recursive feature elimination. Recursive feature elimination performed better than Boruta in this study. In prediction of Ct ascending infection, naive Bayes yielded a slightly higher median value of are under the receiver operating characteristic curve (AUROC) 0.57 (95% confidence interval [CI], 0.54 to 0.59) than other methods and provided biological interpretability. For prediction of incident infection among women uninfected at enrollment, KNN performed slightly better than other algorithms, with a median AUROC of 0.61 (95% CI, 0.49 to 0.70). In contrast, xgbLinear and random forest had higher predictive performances, with median AUROC of 0.63 (95% CI, 0.58 to 0.67) and 0.62 (95% CI, 0.58 to 0.64), respectively, for women infected at enrollment. Our findings suggest that clinical factors and serum anti-Ct protein IgGs are inadequate biomarkers for ascension or incident Ct infection. Nevertheless, our analysis highlights the utility of a pipeline that searches for biomarkers and evaluates prediction performance and interpretability. IMPORTANCE Biomarker discovery to aid early diagnosis and treatment using machine learning (ML) approaches is a rapidly developing area in host-microbe studies. However, lack of reproducibility and interpretability of ML-driven biomarker analysis hinders selection of robust biomarkers that can be applied in clinical practice. We thus developed a rigorous ML analytical framework and provide recommendations for enhancing reproducibility of biomarkers. We emphasize the importance of robustness in selection of ML methods, evaluation of performance, and interpretability of biomarkers. Our ML pipeline is reusable and open-source and can be used not only to identify host-pathogen interaction biomarkers but also in microbiome studies and ecological and environmental microbiology research.