Predicting future ocular <i>Chlamydia trachomatis</i> infection prevalence using serological, clinical, molecular, and geospatial data

ABSTRACT Trachoma is an infectious disease characterized by repeated exposures to Chlamydia trachomatis ( Ct ) that may ultimately lead to blindness. District-level estimates of clinical disease are currently used to guide control programs. However, clinical trachoma is a subjective indicator. Serological markers present an objective, scalable alternative for monitoring and targeting of more intensive control efforts. We hypothesized that IgG seroprevalence in combination with geospatial layers, machine learning, and model-based geostatistics would be able to accurately predict future community-level ocular Ct infections detected by PCR. Among 40 communities in the hyperendemic Amhara region of Ethiopia, median Ct infection prevalence among children 0-5 years old increased from 6% at enrollment to 29% at month 36. Seroprevalence was the strongest concurrent predictor of infection prevalence at month 36 among children 0-5 years old (cross-validated R 2 = 0.75, 95% CI: 0.58-0.85), though predictive performance declined substantially with increasing temporal lag between predictor and outcome measurements. Geospatial variables, a spatial Gaussian process, and stacked ensemble machine learning did not meaningfully improve predictions. Serological markers among children 0-5 years old may be a promising programmatic tool for identifying communities with high levels of active ocular Ct infections, but accurate, future prediction in the context of changing transmission remains a challenge.