Smoking in pregnancy likely to increase newborn behavioural issues, predicts AI
In a recent study published in The Journal Cells, Researchers from Shinshu University School of Medicine, Japan trained a deep learning system to analyse mouse behavioural experiments automatically, with the aim to investigate nicotine's effects on neurodevelopmental disorders.
For about 50 years, smoking has been recognized as a risk factor for cancer, stroke, and diabetes. Research has highlighted its harmful effects during pregnancy, including high infant mortality, preterm birth, and low birth weight. Prenatal nicotine exposure is also linked to neurodevelopmental disorders like ADHD and ASD.
Now, scientists have devised a deep learning framework to analyse mouse behaviour in nicotine exposure experiments, aiming for more accurate results. They found that prenatal nicotine exposure heightened the risk of autism spectrum and attention-deficit/hyperactivity disorders in newborns, contributing valuable insights into the link between smoking during pregnancy and neurodevelopmental disorders.
“AI tools can label the body parts of animals in a marker-less video footage and precisely estimate their poses using supervised machine learning,” explains Prof. Katsuhiko Tabuchi. “Since animal behaviours are defined as a specific arrangement of body parts over a short period of time, deep-learning toolkits like SimBA can use the pose estimations obtained with DeepLabCut to classify different types of animal behaviours.”
Researchers conducted experiments using prenatal nicotine-exposed (PNE) and control mice to identify ADHD- and ASD-like behaviours. Cliff avoidance reaction tests showed PNE mice exhibited higher impulsivity, similar to ADHD traits in humans. Using a Y-shaped maze, researchers assessed working memory in mice by counting spontaneous arm switches. PNE mice showed decreased alterations, indicating altered working memory, a trait seen in ADHD. Open-field and social-interaction experiments revealed social deficits and increased anxiety in PNE mice, features of ASD traits.
“We validated the accuracy of our behavioural analysis framework by drawing a careful comparison between the results generated by the model and behaviour assessments made by multiple human annotators, which is considered the gold standard.” highlighted Prof. Tabuchi.
Reference: Mengyun Zhou, ORCID,Wen Qiu, Nobuhiko Ohashi, Lihao Sun,Marie-Louis Wronski,Emi Kouyama-Suzuki,Yoshinori Shirai,Toru Yanagawa,Takuma Mori,Katsuhiko Tabuchi; Journal: Cell; DOI:10.3390/cells13030275
Disclaimer: This website is primarily for healthcare professionals. The content here does not replace medical advice and should not be used as medical, diagnostic, endorsement, treatment, or prescription advice. Medical science evolves rapidly, and we strive to keep our information current. If you find any discrepancies, please contact us at corrections@medicaldialogues.in. Read our Correction Policy here. Nothing here should be used as a substitute for medical advice, diagnosis, or treatment. We do not endorse any healthcare advice that contradicts a physician's guidance. Use of this site is subject to our Terms of Use, Privacy Policy, and Advertisement Policy. For more details, read our Full Disclaimer here.
NOTE: Join us in combating medical misinformation. If you encounter a questionable health, medical, or medical education claim, email us at factcheck@medicaldialogues.in for evaluation.