Rethinking PICO in the Machine Learning Era: ML-PICO

Background  Machine learning (ML) has captured the attention of many clinicians who may not have formal training in this area but are otherwise increasingly exposed to ML literature that may be relevant to their clinical specialties. ML papers that follow an outcomes-based research format can be assessed using clinical research appraisal frameworks such as PICO (Population, Intervention, Comparison, Outcome). However, the PICO frameworks strain when applied to ML papers that create new ML models, which are akin to diagnostic tests. There is a need for a new framework to help assess such papers. Objective  We propose a new framework to help clinicians systematically read and evaluate medical ML papers whose aim is to create a new ML model: ML-PICO (Machine Learning, Population, Identification, Crosscheck, Outcomes). We describe how the ML-PICO framework can be applied toward appraising literature describing ML models for health care. Conclusion  The relevance of ML to practitioners of clinical medicine is steadily increasing with a growing body of literature. Therefore, it is increasingly important for clinicians to be familiar with how to assess and best utilize these tools. In this paper we have described a practical framework on how to read ML papers that create a new ML model (or diagnostic test): ML-PICO. We hope that this can be used by clinicians to better evaluate the quality and utility of ML papers.     

Psychological characteristics and physiological reactivity to acute stress in mothers of children with autism spectrum disorder

Stress related to parenting a child with autism spectrum disorder can differently affect caregiver's physiological reactivity to acute stress. Here, parental stress levels, psychological characteristics, and coping strategies were assessed alongside measures of heart rate, heart rate variability, and cortisol during a psychosocial stress test in mothers of children with ASD (M‐ASD, n = 15) and mothers of typically developing children (n = 15). M‐ASD reported significantly higher levels of parental stress, anxiety, negative affectivity, social inhibition, and a larger preference for avoidance strategies. M‐ASD showed larger heart rate and cortisol responses to the psychosocial stress test. A positive relationship was found between parental stress levels and the magnitude of the cortisol stress response in both groups. The present findings indicate exaggerated physiological reactivity to acute psychosocial stress in M‐ASD and prompt further research to explore the role of individual differences in mediating the effects of parental stress on physiological stress responses.