Child sleep disorders are increasingly prevalent and understanding early predictors of sleep problems, starting in utero, may meaningfully guide future prevention efforts. Here, we investigated whether prenatal exposure to maternal psychological stress is associated with increased sleep problems in toddlers. We also examined whether fetal brain connectivity has direct or indirect influence on this putative association. Pregnant women underwent fetal resting-state functional connectivity MRI and completed questionnaires on stress, worry, and negative affect. At 3-year follow-up, 64 mothers reported on child sleep problems, and in the subset that have reached 5-year follow-up, actigraphy data (N = 25) has also been obtained. We observe that higher maternal prenatal stress is associated with increased toddler sleep concerns, with actigraphy sleep metrics, and with decreased fetal cerebellar-insular connectivity. Specific mediating effects were not identified for the fetal brain regions examined. The search for underlying mechanisms of the link between maternal prenatal stress and child sleep problems should be continued and extended to other brain areas.

Lung cancer is the leading cause of cancer death worldwide, with non-small cell lung cancer (NSCLC) making up 80% of cases. Some genetic factors leading to NSCLC development include genetic mutations and PD-L1 expression. PD-L1 proteins are targeted in an NSCLC treatment called targeted gene therapy. However, this treatment is effective in a low percentage of patients. This study aimed to create machine learning models to use features like the number of mutations and the level of PD-L1 proteins in cancer cells, along with others, to predict whether a patient will receive clinical benefit from gene therapy treatment. This was done by downloading and merging datasets from cbioportal.org to create a sample size for the model. Features with high correlations to clinical benefit were identified. Three machine-learning models were created using these features to predict clinical benefits in patients, and each model’s accuracy was evaluated. All three models were accurate between 55-85%, with two of the models averaging an accuracy around 75%. Doctors can use these models to more accurately predict whether gene therapy treatment is likely to work in a patient before prescribing it to them.