Purpose: This review aims to explore the clinical and research applications of artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), in understanding, predicting, and managing obesity. It assesses the use of AI tools to identify obesity-related risk factors, predict outcomes, personalize treatments, and improve healthcare interventions for obesity. Methods: A comprehensive literature search was conducted using PubMed and Google Scholar, with keywords including “artificial intelligence”, “machine learning”, “deep learning”, “obesity”, “obesity management”, and related terms. Studies focusing on AI’s role in obesity research, management, and therapeutic interventions were reviewed, including observational studies, systematic reviews, and clinical applications. Results: This review identifies numerous AI-driven models, such as ML and DL, used in obesity prediction, patient stratification, and personalized management strategies. Applications of AI in obesity research include risk prediction, early detection, and individualization of treatment plans. AI has facilitated the development of predictive models utilizing various data sources, such as genetic, epigenetic, and clinical data. However, AI models vary in effectiveness, influenced by dataset type, research goals, and model interpretability. Performance metrics such as accuracy, precision, recall, and F1-score were evaluated to optimize model selection. Conclusions: AI offers promising advancements in obesity management, enabling more personalized and efficient care. While technology presents considerable potential, challenges such as data quality, ethical considerations, and technical requirements remain. Addressing these will be essential to fully harness AI’s potential in obesity research and treatment, supporting a shift toward precision healthcare.

The cause of Parkinson’s disease (PD) remains elusive, but environmental chemical exposures have been postulated to be involved in the etiology of PD. We examined the association between the persistent organochlorine pesticides (OCPs) and PD in the North Indian population. This case control study included 70 PD and 75 control subjects in the age group of 50 to 85 years. Blood samples were collected and high-purity grade hexane and acetone (2 : 1 ratio) were used for extraction of organochlorine residues. OCPs (hexachlorocyclohexane (HCH), aldrin, dieldrin, endosulfan, pp′-Dichlorodiphenyldichloroethylene (pp′-DDE), op′-DDE, pp′- Dichlorodiphenyltrichloroethane (pp′-DDT), op′-DDT, pp′-dichlorodiphenyldichloroethane (pp′-DDD) and op′-DDD) were quantitatively estimated by using gas chromatography. The most frequently detected OCP was dieldrin, which was present in 9.3% of control and 61.4% of PD. The strongest predictor was β-hexachlorocyclohexane (β-HCH), which reported an odds ratio of 2.566, indicating that for every additional one unit of β-HCH, patients had 2.566 times more chances of presence of PD. This study indicates that increased level of β-HCH and dieldrin may be associated with the risk of PD.

Background: HLA-B*51 has been universally associated with Behcet's disease (BD) susceptibility, while different alleles of HLA-A have also been identified as independent BD susceptibility loci in various ethnic populations. The objective of this study was to investigate associations of HLA-A and - B alleles with BD in Saudi patients. Materials and Methods: Genotyping for HLA-A and HLA-B was performed using HLA genotyping kit (Lab type ^(R) SSO) in 120 Saudi subjects, including 60 BD patients and 60 matched healthy controls. Results: Our results revealed that frequencies of HLA-A*26, -A*31, and - B*51 were significantly higher in BD patients than in controls, suggesting that HLA-A*26, -A*31, and - B*51 are associated with BD. The frequency of HLA-B*15 was significantly lower in BD patients than in controls. Stratification of genotyping results into active and nonactive forms of BD revealed that the frequency of HLA-A*31 was significantly higher in the nonactive form than in the active form of BD, while there was no significant difference in the distribution of other alleles between the two forms of BD. Conclusion: This study suggests that HLA-A*26, -A*31, and - B*51 are associated with susceptibility risk to BD, while HLA-B*15 may be protective in Saudi patients. However, larger scale studies are needed to confirm these findings.

Obesity is a multifactorial condition projected to affect over half of the global population by 2035, posing significant clinical and socioeconomic challenges. Traditional metrics such as body mass index lack precision in predicting individual risk, disease progression, and therapeutic response due to the heterogeneous nature of obesity. Advances in omics technologies such as genomics, epigenomics, transcriptomics, proteomics, and metabolomics have enabled the identification of molecular subtypes and candidate biomarkers that offer deeper insights into obesity pathophysiology. Genomic studies have revealed hundreds of loci associated with obesity related traits, while polygenic risk scores offer modest improvements in early risk prediction. Epigenomic profiling, particularly deoxy ribose nucleic acid (DNA) methylation signatures such as those at carnitine palmitoyl transferase 1A (CPT1A) and hypoxia inducible factor 3 subunit alpha (HIF3A), has uncovered modifiable pathways linked to adiposity and metabolic dysfunction. These findings are increasingly being integrated with other omics layers to improve stratification and therapeutic targeting. Metabolomic subtypes, including ceramide driven insulin resistance and branched chain amino acid (BCAA) dominant dysregulation, have shown potential in guiding treatment selection, such as sodium glucose cotransporter 2 (SGLT2) inhibitors or glucagon like peptide-1 (GLP-1) agonists. Proteomic markers like proprotein convertase subtilisin/kexin type 9 (PCSK9) and retinol binding protein 4 (RBP4) are being evaluated for cardiovascular risk stratification independent of body mass index (BMI). Integrative multiomics frameworks and AI driven models are beginning to bridge molecular data with clinical phenotypes, enabling patient stratification and risk modeling. However, most findings remain in research grade environments, and clinical translation is limited by cohort diversity, data harmonization challenges, and the lack of standardized validation protocols. This review synthesizes evidence from single and multiomics studies, highlights emerging biomarkers and molecular subtypes, and discusses the potential of omics guided frameworks to inform precision obesity care.

Obesity is a global health challenge characterized by significant heterogeneity in causes and treatment responses, complicating sustainable management. This narrative review explores the genomic architecture of obesity and its implications for personalized interventions, focusing on how genetic variations influence key biological pathways and treatment outcomes. A comprehensive literature search, guided by the authors’ expertise, was conducted to identify key publications on the genomics of obesity and personalized approaches. The selection of articles prioritized those that provided direct insights into the genomic basis of obesity and its potential for informing tailored strategies. Genomic studies reveal both monogenic and polygenic influences on obesity, identifying numerous susceptibility loci. Genome-wide association studies (GWASs) have linked common variants in genes like FTO and MC4R to increased BMI and appetite dysregulation, respectively. Epigenetic research highlights the role of DNA methylation and other modifications in gene–environment interactions. Genetic and polygenic risk scores (GRSs and PRSs) show potential for refining risk stratification and predicting treatment response. The gut microbiome and metabolome also contribute to obesity pathogenesis, offering novel targets for intervention. Personalized medicine offers significant potential for improving obesity management through tailored interventions based on an individual’s genetic and ‘omics’ profile. Future research should focus on elucidating the functional consequences of identified variants, exploring gene–environment interactions, and developing strategies to overcome current limitations in clinical translation. With continued advancements, precision medicine can enhance treatment efficacy, increase sustainability, and help reduce the global burden of obesity-related diseases.