2026-10-06T15:02:03Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34071400 2026-10-05T17:26:19Z category_7 category_21 category_24 category_64 category_132 category_134 portal_5 item_type_3 month_year_10_2026

<p>Demographics.</p> Xuan Lu (325437) Jennifer Zelnick (19834680) Meng Zhao (54299) Matthew Cummings (290466) Allison K. Wolf (25316743) Kevin Guzman (16474985) Hlengiwe Nyilana (17523621) Rubeshan Perumal (16916139) Kathleen Rivet Amico (25316746) Karl Reis (17523618) Mbali Zulu (17523615) Amrita Daftary (2558608) Boitumelo Seepamore (10820522) Kogieleum Naidoo (558699) Max O’Donnell (17990869) Medicine Biotechnology Evolutionary Biology Cancer Infectious Diseases Virology six thematic clusters side effect management randomized controlled trial level random intercepts fitted linear mixed cosine similarity scores clustered using k 202 &# 8211 170 &# 8211 133 &# 8211 113 &# 8211 limited social support counseling session timing routine counseling notes art adherence declined antiretroviral therapy adherence antiretroviral therapy low support art adherence counseling sessions xlink "> underutilized source temporal proximity substance use south africa semantically matched respectively ), resistant tuberculosis related themes regression models persistent challenge period preceding model fit logistical barriers generate hypotheses fold cross financial stability financial insecurity edm ). cluster membership cluster assignments 76 participants <div> <p>Background</p><p>Medication adherence is a persistent challenge in the treatment of multidrug-resistant tuberculosis (MDR-TB) and HIV. Routine counseling notes are an underutilized source of information on patient adherence context.</p> <p>Methods</p><p>We applied natural language processing (NLP) to routine counseling notes from a randomized controlled trial of MDR-TB/HIV treatment in South Africa. Topics were derived using topic modeling; notes were semantically matched to topics and clustered using K-means. We fitted linear mixed-effects (LME) regression models with participant-level random intercepts and five-fold cross-validation to model adherence to bedaquiline (BDQ) and antiretroviral therapy (ART), measured using cellular-enabled electronic dose monitor (EDM). Cosine similarity scores, cluster assignments, and temporal proximity to counseling sessions were included as covariates. Model fit was assessed using mean absolute error (MAE) and root mean square error (RMSE).</p> <p>Results</p><p>We analyzed 327 counseling notes from 76 participants. Six thematic clusters were derived: substance use, logistical barriers, limited social support, side effect management, financial stability, and financial insecurity/low support. LME showed modest fit. For BDQ adherence, MAE was 0.158 (95% CI 0.113–0.204) and RMSE 0.208 (95% CI 0.133–0.283). For ART, MAE was 0.180 (95% CI 0.170–0.191) and RMSE 0.224 (95% CI 0.202–0.246). Cluster membership was not associated with adherence. In contrast, temporal proximity to counseling was more consistently associated with adherence. Adherence was highest immediately following counseling sessions. Both BDQ and ART adherence declined during the intermediate period (β=−0.048, p = 0.001; β=−0.031, p = 0.022, respectively), and ART adherence declined further in the period preceding the next session (β=−0.032, p = 0.020).</p> <p>Conclusion</p><p>NLP methods structured routine counseling notes into interpretable, adherence-related themes. Temporal proximity to counseling sessions was consistently associated with longitudinal BDQ and ART adherence. These findings offer preliminary insights into adherence dynamics and generate hypotheses about the role of counseling session timing in adherence support.</p></div> 2026-10-05T17:26:03Z Dataset Dataset 10.1371/journal.pone.0355696.t001 https://figshare.com/articles/dataset/_p_Demographics_p_/34071400 CC BY 4.0