This study presented by Huang et al., examines the connection between how serotonin, adenosine deaminase (ADA), and multiple sclerosis (MS) affect one another, and ultimately how a machine learning model was utilized to detect the progression of each subset. This research was conducted by using “a two-sample Mendelian randomisation analysis”, (Huang et al., 2025), using inverse variance weighting to assess the severity of serotonin, ADA, and MS. They also used other machine learning models to be able to “identify diagnostic biomarkers” (Huang et al., 2025) to be able to better understand the relationship between serotonin, ADA, and MS. Furthermore, the researchers were able to find that serotonin appears to enhance the progression of MS. This progression is enhanced by way of how ADA and its activity is being prevented or inhibited. This later revealed how there is a significant relationship between the activity levels of ADA and serotonin which is promoting the risk of MS. They also presented how machine learning models were useful for potential use as diagnostic tools for MS, and a greater comprehension for MS management. In essence, by understanding the relationship between ADA, MS, and serotonin via the usage of an “integrative multi-omics approach” (Huang et al., 2025), this paved the way for providing greater diagnostic measures for MS. It also established how ADA and serotonin levels affect MS’s progression, paving the way for further research and hopeful treatment.