Stephanie Ryall

Objective To provide a practical approach for primary care physicians counselling female athletes on contraception choice. Sources of information A targeted literature search was conducted in PubMed and Google Scholar for articles published until December 2025 and integrated key current research, including a 2024 cross-sectional study on female athletes’ experiences with contraceptive selection and the 2023 International Olympic Committee’s consensus statement on relative energy deficiency in sport (REDs). Main message Athletes frequently report sport-specific concerns are overlooked during contraceptive counselling with their physicians, leading to dissatisfaction and information seeking outside of medical settings. While evidence on the impact of contraceptives on athletic performance is limited, clinicians should address known performance-related factors such as iron status, menstrual symptom management, cycle timing manipulation, body composition concerns, and potential injury risk. Awareness of REDs is also essential, as hormonal contraception can impact menstrual changes that signal low energy availability. Conclusion Contraceptive counselling that incorporates an athlete’s sport and performance-related considerations can enhance confidence in contraceptive choice while helping to optimize both health and performance.

Objectif Fournir une approche pratique aux médecins de soins primaires qui conseillent des femmes athlètes sur le choix d’une méthode contraceptive. Sources de l’information Une recherche documentaire ciblée a été effectuée dans PubMed et Google Scholar pour trouver des articles publiés jusqu’en décembre 2025 ainsi que d’importants travaux de recherche intégrée récents, notamment une étude transversale de 2024 sur les expériences de femmes athlètes dans la sélection d’une méthode de contraception et la déclaration de consensus du Comité international olympique de 2023 sur le déficit énergétique relatif dans le sport (RED-S). Message principal Les athlètes signalent fréquemment que leurs inquiétudes liées au sport sont rarement prises en compte durant le counseling sur la contraception avec leur médecin, ce qui entraîne de l’insatisfaction et incite à rechercher de l’information hors du monde médical. Bien que les données probantes sur les impacts des moyens de contraception sur la performance des athlètes soient limitées, les cliniciens devraient se pencher sur les facteurs connus relatifs à la performance, comme le statut en fer, la prise en charge des symptômes menstruels, la manipulation de la chronologie du cycle, les préoccupations concernant la composition corporelle et d’éventuels risques de blessures. De plus, il est essentiel de connaître le RED-S, parce que la contraception hormonale peut influer sur les changements menstruels évocateurs d’une faible disponibilité énergétique. Conclusion Un counseling sur la contraception qui tient compte des considérations relatives aux sports et à la performance d’une athlète peut accroître la confiance quant au choix de la méthode tout en aidant à optimiser la santé et la performance.

Objective: To compare the predictive performance of supervised machine learning models to logistic regression in identifying youth with eating disorders at risk of a complex clinical course based on clinical characteristics from the first treatment episode. Methods: Clinical data from 327 youth treated at any level of care at the Children's Hospital of Eastern Ontario Eating Disorders Program (2018–2024) were extracted. Complex clinical course outcome was defined as either readmission after discharge or a treatment trajectory deviating from the expected step‐down in intensity, including return to the same or escalation to a higher level of care. Thirty‐four intake and discharge variables from the first treatment episode were used to train seven machine learning models and logistic regression using repeated nested cross‐validation. Performance was assessed by AUC and brier scores. Models using intake‐only versus intake plus discharge data were compared. A parsimonious model using the top 10 predictors was also evaluated. Results: Random forest model with intake and discharge data achieved the best performance ( AUC = 0.723; Brier = 0.176) that was significantly superior to logistic regression. Models trained on intake‐only data showed poor discrimination ( AUCs < 0.6). Including discharge data improved model performance across all algorithms. The most important predictor was weight change throughout treatment. Random forest performance declined when restricted to the top 10 predictors. Discussion: Supervised machine learning demonstrates improved predictive performance for eating disorder disease course outcomes compared to traditional statistical methods, especially in higher‐dimensionality settings. These findings support future application of machine learning to complex biopsychosocial datasets to advance precision medicine initiatives in the eating disorder field and better understand the etiology of disease trajectory.

Background: While there are several prescribed contraceptive methods available, limited evidence exists to guide contraceptive decision-making in the context of endurance sport. Objectives: Study objectives were to characterize current and previous use, perceived impacts, and the decision process around contraceptives in endurance athletes. Methods: This was an online survey study with female endurance athletes recruited through social media and emails to university/club coaches and sport organizations. Quantitative and qualitative data were analyzed with descriptive statistics and conventional content analysis, respectively. Results: A total of 323 female endurance athletes participated. Among current contraception users (n = 182), 51% used hormonal intrauterine devices (hIUDs), 29% oral contraceptive pills (OCPs), and 13% nonhormonal IUDs (nhIUDs). hIUD users had the highest perceived positive training (39%) and competition (29%) impacts, citing reduced menstrual bleeding and symptoms as positive side effects. OCP and nhIUD users had higher rates of perceived negative training impacts (OCPs 10%, nhIUDs 30%). For OCP users, 31% reported perceived adverse body composition outcomes and 37% reported negative mood changes. Among nhIUD users, 74% experienced heavier, more irregular menstrual bleeding. Over half of participants were unsure about the impact of their current method on performance. For contraceptive selection, 95% felt that information from physicians was important, yet 32% felt performance was inadequately considered during counseling discussion. Athletes reported less frustration with their contraception choice when counseled in the context of sport. Conclusions: This exploratory study quantifies and qualifies the lived experiences of female endurance athletes with contraception. hIUDs were the most currently used and well-tolerated contraceptives among participants. This research offers valuable insights for athletes seeking contraception and looking to optimize both performance and health, along with the healthcare professionals guiding them.