2026-10-06T09:17:12Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34074398 2026-10-05T17:59:29Z category_8 category_734 category_811 category_132 portal_5 item_type_3 month_year_10_2026

<p>External validation performance across bacterial dominance boundaries.</p> Cameron G. Celeste (25317419) Carleigh C. Sokolik (25317422) Wambui Gachunga (25317425) Ivana K. Parker (24236370) Microbiology Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Infectious Diseases various adverse obstetric sexually transmitted infections based decision boundaries age women globally 16s rrna data support vector machine random forest models create predictive models machine learning architectures key vaginal flora inform bv diagnostics bv negative outcomes machine learning train models performing models xlink "> term birth six anaerobes rigorous comparison relative abundances patients presenting pathogenesis research important bacteria gradual shifts diagnostic point cervical cancer balanced accuracy bacterial vaginosis anaerobic bacteria <p>This table reports balanced accuracy (BA) from validation analyses comparing pairwise bacterial dominance boundaries (e.g., non-Lactobacillus taxa versus Lactobacillus species and combined Lactobacillus groups). Results are presented for the total sample and stratified population groups, providing an external assessment of model generalizability across taxonomic contrasts and demographic strata.</p> <p>(CSV)</p> 2026-10-05T17:59:24Z Dataset Dataset 10.1371/journal.pcbi.1014767.s004 https://figshare.com/articles/dataset/_p_External_validation_performance_across_bacterial_dominance_boundaries_p_/34074398 CC BY 4.0