0
0
A groundbreaking study conducted by researchers from the Department of Molecular and Cellular Physiology at Shinshu University School of Medicine in Japan has unveiled a potential connection between prenatal nicotine exposure (PNE) and neurodevelopmental disorders like attention deficit/hyperactivity disorder (ADHD) and autism spectrum disorder (ASD) in mice. Published in Cells on February 1, 2024, the study employed a novel deep learning-based framework to automatically analyze and classify mouse behavior, eliminating human bias and producing more accurate results.
Led by graduate student Mengyun Zhou, Assistant Professor Takuma Mori, and Professor Katsuhiko Tabuchi, the research team developed an artificial intelligence (AI) system capable of analyzing footage from behavioral experiments on mice. By leveraging open-source toolkits like DeepLabCut and Simple Behavioral Analysis (SimBA), the AI system accurately observed and classified behaviors, shedding light on the effects of PNE on neurodevelopment.
Using a series of behavioral tests, including cliff avoidance reaction tests and Y-shaped maze experiments, the researchers found compelling evidence linking PNE to ADHD-like behaviors in mice. PNE mice exhibited increased impulsivity and altered working memory, consistent with symptoms of ADHD in humans. Additionally, open-field and social-interaction experiments revealed social behavioral deficits and increased anxiety in PNE mice, characteristics associated with ASD. Histological analysis of brain tissue confirmed decreased neurogenesis, a hallmark of ASD, further supporting the findings.
The AI-based framework demonstrated high reliability compared to manual observations, laying the groundwork for future behavioral studies. “We validated the accuracy of our behavioral analysis framework by drawing a careful comparison between the results generated by the model and behavior assessments made by multiple human annotators, which is considered the gold standard,” explained Prof. Tabuchi.
These findings offer new insights into the impact of PNE on neurodevelopment and highlight the potential role of AI in behavioral research. With continued research, the study aims to deepen our understanding of neurodevelopmental disorders and pave the way for improved diagnostic and therapeutic strategies.
The study represents a significant step forward in unraveling the complexities of neurodevelopmental disorders and underscores the importance of exploring alternative approaches to behavioral analysis. As researchers continue to harness the power of AI, the future holds promise for advancements in the field of neuroscience and the development of targeted interventions for individuals affected by these conditions.
