RT info:eu-repo/semantics/article
T1 A subject-based association network defines new pediatric sleep apnea phenotypes with different odds of recovery after treatment
A1 Gutierrez Tobal, Gonzalo César
A1 Gómez Pilar, Javier
A1 Ferreira Santos, Daniela
A1 Pereira Rodrigues, Pedro
A1 Álvarez González, Daniel
A1 Campo Matias, Félix del
A1 Gozal, David
A1 Hornero Sánchez, Roberto
K1 Association network
K1 Childhood adenotonsillectomy trial
K1 Obstructive sleep apnea
K1 Phenotypes
K1 Explainable artificial intelligence
K1 32 Ciencias Médicas
AB Background and objectives: Timely treatment of pediatric obstructive sleep apnea (OSA) can prevent or reverseneurocognitive and cardiovascular morbidities. However, whether distinct phenotypes exist and account fordivergent treatment effectiveness remains unknown. In this study, our goal is threefold: i) to define new data-driven pediatric OSA phenotypes, ii) to evaluate possible treatment effectiveness differences among them, andiii) to assess phenotypic information in predicting OSA resolution.Methods: We involved 22 sociodemographic, anthropometric, and clinical data from 464 children (5–10 yearsold) from the Childhood Adenotonsillectomy Trial (CHAT) database. Baseline information was used to auto-matically define pediatric OSA phenotypes using a new unsupervised subject-based association network. Follow-up data (7 months later) were used to evaluate the effects of the therapeutic intervention in terms of changes inthe obstructive apnea-hypopnea index (OAHI) and the resolution of OSA (OAHI < 1 event per hour). Anexplainable artificial intelligence (XAI) approach was also developed to assess phenotypic information as OSAresolution predictor at baseline.Results: Our approach identified three OSA phenotypes (PHOSA1-PHOSA3), with PHOSA2 showing significantlylower odds of OSA recovery than PHOSA1 and PHOSA3 when treatment information was not considered (oddsratios, OR: 1.64 and 1.66, 95 % confidence intervals, CI: 1.03–2.62 and 1.01–2.69, respectively). The odds ofOSA recovery were also significantly lower in PHOSA2 than in PHOSA3 when adenotonsillectomy was adopted astreatment (OR: 2.60, 95 % CI: 1.26–5.39). Our XAI approach identified 79.4 % (CI: 69.9–88.0 %) of childrenreaching OSA resolution after adenotonsillectomy, with a positive predictive value of 77.8 % (CI: 70.3 %-86.0%).Conclusions: Our new subject-based association network successfully identified three clinically useful pediatricOSA phenotypes with different odds of therapeutic intervention effectiveness. Specifically, we found that chil-dren of any sex, >6 years old, overweight or obese, and with enlarged neck and waist circumference (PHOSA2)have less odds of recovering from OSA. Similarly, younger female children with no enlarged neck (PHOSA3) havehigher odds of benefiting from adenotonsillectomy.
PB Elsevier
SN 0169-2607
YR 2026
FD 2026
LK https://uvadoc.uva.es/handle/10324/81016
UL https://uvadoc.uva.es/handle/10324/81016
LA eng
NO Computer Methods and Programs in Biomedicine, 2026, vol. 275, p. 109209
NO Producción Científica
DS UVaDOC
RD 11-ene-2026