Clinical features-based machine learning models to separate sexually transmitted infections from other skin diagnoses.

INTRODUCTION: Many sexual health services are overwhelmed and cannot cater for all the individuals who present with sexually transmitted infections (STIs). Digital health software that separates STIs from non-STIs could improve the efficiency of clinical services. We developed and evaluated a machine learning model that predicts whether patients have an STI based on their clinical features. METHODS: We manually extracted 25 demographic features and clinical features from 1315 clinical records in the electronic health record system at Melbourne Sexual Health Center. We examined 16 machine learning models to predict a binary outcome of an STI or a non-STI diagnosis. We evaluated the models' performance with the area under the ROC curve (AUC), accuracy and F1-scores. RESULTS: Our study included 1315 consultations, of which 36.8% (484/1315) were diagnosed with STIs and 63.2% (831/1315) had non-STI conditions. The study population predominantly consisted of heterosexual men (49.5%, 651/1315), followed by gay, bisexual and other men who have sex with men (GBMSM) (25.7%), women (21.6%) and unknown gender (3.2%). The median age was 31 years (intra-quartile range (IQR) 26-39). The top 5 performing models were CatBoost (AUC 0.912), Random Forest (AUC 0.917), LightGBM (AUC 0.907), Gradient Boosting (AUC 0.905) and XGBoost (AUC 0.900). The best model, CatBoost, achieved an accuracy of 0.837, sensitivity of 0.776, specificity of 0.831, precision of 0.782 and F1-score of 0.778. The key important features were lesion duration, type of skin lesions, age, gender, history of skin disorders, number of lesions, dysuria duration, anorectal pain and itchiness. CONCLUSIONS: Our best model demonstrates a reasonable performance in distinguishing STIs from non-STIs. However, to be clinically useful, more detailed information such as clinical images, may be required to reach sufficient accuracy.

Determining the screening frequency for sexually transmitted infections for people who use HIV pre-exposure prophylaxis: a systematic review and meta-analysis.

OBJECTIVES: Although the World Health Organization recommends 'frequent' screening of sexually transmitted infections (STI) for people who use pre-exposure prophylaxis for HIV, there is no evidence for optimal frequency. METHODS: We searched five databases and used random-effects meta-analysis to calculate pooled estimates of STI test positivity. We narratively synthesized data on secondary outcomes, including adherence to recommended STI screening frequency and changes in STI epidemiology. RESULTS: Of 7477 studies, we included 38 for the meta-analysis and 11 for secondary outcomes. With 2-3 monthly STI screening, the pooled positivity was 0.20 (95% confidence interval [CI]: 0.15-0.25) for chlamydia, 0.17 (95% CI: 0.12-0.22) for gonorrhea, and 0.07 (95% CI: 0.05-0.08) for syphilis. For chlamydia and gonorrhea, the positivity was approximately 50% and 75% lower, respectively, in studies that screened 4-6 monthly vs 2-3 monthly. There was no significant difference in the positivity for syphilis in studies that screened 4-6 monthly compared to 2-3 monthly. Adherence of clients to recommended screening frequency varied significantly (39-94%) depending on population and country. Modeling studies suggest more frequent STI screening could reduce incidence. CONCLUSION: Although more frequent STI screening could reduce delayed diagnoses and incidence, there remain significant knowledge gaps regarding the optimal STI screening frequency.