The increasing prevalence of type 2 diabetes mellitus (T2DM) and its associated health complications highlight the need to develop predictive models for early diagnosis and intervention. While many artificial intelligence (AI) models for T2DM risk prediction have emerged, a comprehensive review of their advancements and challenges is currently lacking. This scoping review maps out the existing literature on AI-based models for T2DM prediction, adhering to the PRISMA extension for Scoping Reviews guidelines. A systematic search of longitudinal studies was conducted across four databases, including PubMed, Scopus, IEEE-Xplore, and Google Scholar. Forty studies that met our inclusion criteria were reviewed. Classical machine learning (ML) models dominated these studies, with electronic health records (EHR) being the predominant data modality, followed by multi-omics, while medical imaging was the least utilized. Most studies employed unimodal AI models, with only ten adopting multimodal approaches. Both unimodal and multimodal models showed promising results, with the latter being superior. Almost all studies performed internal validation, but only five conducted external validation. Most studies utilized the area under the curve (AUC) for discrimination measures. Notably, only five studies provided insights into the calibration of their models. Half of the studies used interpretability methods to identify key risk predictors revealed by their models. Although a minority highlighted novel risk predictors, the majority reported commonly known ones. Our review provides valuable insights into the current state and limitations of AI-based models for T2DM prediction and highlights the challenges associated with their development and clinical integration.

The outstanding performance of an elite athlete might be associated with changes in their blood metabolic profile. The aims of this study were to compare the blood metabolic profiles between moderate- and high-power and endurance elite athletes and to identify the potential metabolic pathways underlying these differences. Metabolic profiling of serum samples from 191 elite athletes from different sports disciplines (121 high- and 70 moderate-endurance athletes, including 44 high- and 144 moderate-power athletes), who participated in national or international sports events and tested negative for doping abuse at anti-doping laboratories, was performed using non-targeted metabolomics-based mass spectroscopy combined with ultrahigh-performance liquid chromatography. Multivariate analysis was conducted using orthogonal partial least squares discriminant analysis. Differences in metabolic levels between high- and moderate-power and endurance sports were assessed by univariate linear models. Out of 743 analyzed metabolites, gamma-glutamyl amino acids were significantly reduced in both high-power and high-endurance athletes compared to moderate counterparts, indicating active glutathione cycle. High-endurance athletes exhibited significant increases in the levels of several sex hormone steroids involved in testosterone and progesterone synthesis, but decreases in diacylglycerols and ecosanoids. High-power athletes had increased levels of phospholipids and xanthine metabolites compared to moderate-power counterparts. This pilot data provides evidence that high-power and high-endurance athletes exhibit a distinct metabolic profile that reflects steroid biosynthesis, fatty acid metabolism, oxidative stress, and energy-related metabolites. Replication studies are warranted to confirm differences in the metabolic profiles associated with athletes’ elite performance in independent data sets, aiming ultimately for deeper understanding of the underlying biochemical processes that could be utilized as biomarkers with potential therapeutic implications.

Macro- and microvascular complications of type 2 diabetes (T2D), obesity, and dyslipidemia share common metabolic pathways. In this study, using a total of 1,300 metabolites from 996 Qatari adults (57% with T2D) and 1,159 metabolites from an independent cohort of 2,618 individuals from the Qatar BioBank (11% with T2D), we identified 373 metabolites associated with T2D, obesity, retinopathy, dyslipidemia, and lipoprotein levels, 161 of which were novel. Novel metabolites included phospholipids, sphingolipids, lysolipids, fatty acids, dipeptides, and metabolites of the urea cycle and xanthine, steroid, and glutathione metabolism. The identified metabolites enrich pathways of oxidative stress, lipotoxicity, glucotoxicity, and proteolysis. Second, we identified 15 patterns we defined as “metabo-clinical signatures.” These are clusters of patients with T2D who group together based on metabolite levels and reveal the same clustering in two or more clinical variables (obesity, LDL, HDL, triglycerides, and retinopathy). These signatures revealed metabolic pathways associated with different clinical patterns and identified patients with extreme (very high/low) clinical variables associated with extreme metabolite levels in specific pathways. Among our novel findings are the role of N-acetylmethionine in retinopathy in conjunction with dyslipidemia and the possible roles of N-acetylvaline and pyroglutamine in association with high cholesterol levels and kidney function.

Metabolomics-genome-wide association studies (mGWAS) have uncovered many metabolic quantitative trait loci (mQTLs) influencing human metabolic individuality, though predominantly in European cohorts. By combining whole-exome sequencing with a high-resolution metabolomics profiling for a highly consanguineous Middle Eastern population, we discover 21 common variant and 12 functional rare variant mQTLs, of which 45% are novel altogether. We fine-map 10 common variant mQTLs to new metabolite ratio associations, and 11 common variant mQTLs to putative protein-altering variants. This is the first work to report common and rare variant mQTLs linked to diseases and/or pharmacological targets in a consanguineous Arab cohort, with wide implications for precision medicine in the Middle East.

Background: T2D is of high prevalence in the middle east and thus studying its mechanisms is of a significant importance. Using 1026 Qatar BioBank samples, epigenetics, whole genome sequencing and metabolomics were combined to further elucidate the biological mechanisms of T2D in a population with a high prevalence of T2D. Methods: An epigenome-wide association study (EWAS) with T2D was performed using the Infinium 850K EPIC array, followed by whole genome-wide sequencing SNP-CpG association analysis (> 5.5 million SNPs) and a methylome-metabolome (CpG-metabolite) analysis of the identified T2D sites. Results: A total of 66 T2D-CpG associations were identified, including 63 novel sites in pathways of fructose and mannose metabolism, insulin signaling, galactose, starch and sucrose metabolism, and carbohydrate absorption and digestion. Whole genome SNP associations with the 66 CpGs resulted in 688 significant CpG-SNP associations comprising 22 unique CpGs (33% of the 66 CPGs) and included 181 novel pairs or pairs in novel loci. Fourteen of the loci overlapped published GWAS loci for diabetes related traits and were used to identify causal associations of HK1 and PFKFB2 with HbA1c. Methylome-metabolome analysis identified 66 significant CpG-metabolite pairs among which 61 pairs were novel. Using the identified methylome-metabolome associations, methylation QTLs, and metabolic networks, a multi-omics network was constructed which suggested a number of metabolic mechanisms underlying T2D methylated genes. 1-palmitoyl-2-oleoyl-GPE (16:0/18:1) – a triglyceride-associated metabolite, shared a common network with 13 methylated CpGs, including TXNIP, PFKFB2, OCIAD1, and BLCAP. Mannonate – a food component/plant shared a common network with 6 methylated genes, including TXNIP, BLCAP, THBS4 and PEF1, pointing to a common possible cause of methylation in those genes. A subnetwork with alanine, glutamine, urea cycle (citrulline, arginine), and 1-carboxyethylvaline linked to PFKFB2 and TXNIP revealed associations with kidney function, hypertension and triglyceride metabolism. The pathway containing STYXL1-POR was associated with a sphingosine-ceramides subnetwork associated with HDL-C and LDL-C and point to steroid perturbations in T2D. Conclusions: This study revealed several novel methylated genes in T2D, with their genomic variants and associated metabolic pathways with several implications for future clinical use of multi-omics associations in disease and for studying therapeutic targets.

Supplements are widely used among elite athletes to maintain health and improve performance. Despite multiple studies investigating use of dietary supplements by athletes, a comprehensive profiling of serum supplement metabolites in elite athletes is still lacking. This study aims to analyze the presence of various xenobiotics in serum samples from elite athletes of different sports, focusing on metabolites that potentially originate from nutritional supplements. Profiling of xenobiotics in serum samples from 478 elite athletes from different sports (football, athletics, cycling, rugby, swimming, boxing and rowing) was performed using non-targeted metabolomics-based mass spectroscopy combined with ultrahigh-performance liquid chromatography. Multivariate analysis was performed using orthogonal partial least squares discriminant analysis. Differences in metabolic levels among different sport groups were identified by univariate linear models. Out of the 102 detected xenobiotics, 21 were significantly different among sport groups including metabolites that potentially prolong exercise tolerance (caffeic acid), carry a nootropic effect (2-pyrrolidinone), exert a potent anti-oxidant effect (eugenol, ferulic acid 4 sulfate, thioproline, retinol), or originate from drugs for different types of injuries (ectoine, quinate). Using Gaussian graphical modelling, a metabolic network that links various sport group-associated xenobiotics was constructed to further understand their metabolic pathways. This pilot data provides evidence that athletes from different sports exhibit a distinct xenobiotic profile that may reflect their drug/supplement use, diet and exposure to various chemicals. Because of limitation in the study design, replication studies are warranted to confirm results in independent data sets, aiming ultimately for better assessment of dietary supplement use by athletes.