Explainable machine learning analysis reveals sex and gender differences in the phenotypic and neurobiological markers of Cannabis Use Disorder.

Cannabis Use Disorder (CUD) has been linked to a complex set of neuro-behavioral risk factors. While many studies have revealed sex and gender differences, the relative importance of these risk factors by sex and gender has not been described. We used an "explainable" machine learning approach that combined decision trees [gradient tree boosting, XGBoost] with factor ranking tools [SHapley's Additive exPlanations (SHAP)] to investigate sex and gender differences in CUD. We confirmed that previously identified environmental, personality, mental health, neurocognitive, and brain factors highly contributed to the classification of cannabis use levels and diagnostic status. Risk factors with larger effect sizes in men included personality (high openness), mental health (high externalizing, high childhood conduct disorder, high fear somaticism), neurocognitive (impulsive delay discounting, slow working memory performance) and brain (low hippocampal volume) factors. Conversely, risk factors with larger effect sizes in women included environmental (low education level, low instrumental support) factors. In summary, environmental factors contributed more strongly to CUD in women, whereas individual factors had a larger importance in men.

Neurocognition across the spectrum of mucopolysaccharidosis type I: Age, severity, and treatment.

OBJECTIVES: Precise characterization of cognitive outcomes and factors that contribute to cognitive variability will enable better understanding of disease progression and treatment effects in mucopolysaccharidosis type I (MPS I). We examined the effects on cognition of phenotype, genotype, age at evaluation and first treatment, and somatic disease burden. METHODS: Sixty patients with severe MPS IH (Hurler syndrome treated with hematopoietic cell transplant and 29 with attenuated MPS I treated with enzyme replacement therapy), were studied with IQ measures, medical history, genotypes. Sixty-seven patients had volumetric MRI. Subjects were grouped by age and phenotype and MRI and compared to 96 normal controls. RESULTS: Prior to hematopoietic cell transplant, MPS IH patients were all cognitively average, but post-transplant, 59% were below average, but stable. Genotype and age at HCT were associated with cognitive ability. In attenuated MPS I, 40% were below average with genotype and somatic disease burden predicting their cognitive ability. White matter volumes were associated with IQ for controls, but not for MPS I. Gray matter volumes were positively associated with IQ in controls and attenuated MPS I patients, but negatively associated in MPS IH. CONCLUSIONS: Cognitive impairment, a major difficulty for many MPS I patients, is associated with genotype, age at treatment and somatic disease burden. IQ association with white matter differed from controls. Many attenuated MPS patients have significant physical and/or cognitive problems and receive insufficient support services. Results provide direction for future clinical trials and better disease management.