Indo-Pacific humpback dolphins Sousa chinensis face multiple anthropogenic threats in the coastal waters of Langkawi and the adjacent Perlis–Kedah mainland in north-west Peninsular Malaysia. The area is recognized by the IUCN as an Important Marine Mammal Area and harbours a significant population of humpback dolphins. Understanding their social structure is crucial for identifying conservation units to guide targeted management to preserve the species’ ecological processes, particularly for a species in the data-deficient Southeast Asia region. Association patterns and network analysis from a decade of photo-identification surveys (2010–2020) revealed a fission–fusion society defined by frequent changes in group membership and size, and characterized by loose associations between individuals. Association strength was generally low, although some non-random long-term associations persisted for 5 months to several years. Unusually large groups of humpback dolphins (81–204 individuals) were often observed, comprising travelling mother–calf pairs and functioning as nursery groups. The grouping plasticity and social dynamics reflect the species’ survival strategies in response to local environmental conditions, notably resource availability and predation pressure. Most importantly, our findings confirm that the humpback dolphin population in this region constitutes a stable and well-connected single conservation unit, necessitating coordinated protection by different governmental administrators across the extensive study area. The insights from our study should inform tailored management strategies for humpback dolphins and promote early detection of anthropogenic threats that may impact social-ecological processes and the overall survival of the population.

Early identification of risk for attention-deficit hyperactivity disorder (ADHD) symptoms can enable more timely interventions and improve long-term outcomes. While previous research has linked various maternal and perinatal factors to ADHD, few studies have examined these predictors collectively in a single comprehensive analysis. This study aimed to assess whether later ADHD symptoms can be predicted from information available at birth, specifically ethnicity, maternal metabolic markers, mental health, and socioeconomic status. It additionally aimed to identify the most influential predictors. Using data from the Born in Bradford (BiB) study, we applied multiple linear regression (LR) and machine learning techniques to predict ADHD symptoms as measured by the Hyperactivity/Inattention subscale of the Strengths and Difficulties Questionnaire (SDQ). A 10-fold cross-validated LR model explained 6.97% of the variance in SDQ scores. In the random forest model, infant male sex and maternal smoking during pregnancy emerged as the top predictors. These findings provide proof of principle for early identification of children at risk of ADHD. Future models may benefit from incorporating additional perinatal data to improve predictive accuracy.