Rathmann, W. | Search bioRxiv

bioRxiv2024

The Interpretable Multimodal Machine Learning (IMML) framework reveals pathological signatures of distal sensorimotor polyneuropathy

Distal sensorimotor polyneuropathy (DSPN) is a common neurological disorder in elderly adults and people with obesity, prediabetes and diabetes and is associated with high morbidity and premature mortality. DSPN is a multifactorial disease and not fully understood yet. Here, we developed the Interpretable Multimodal Machine Learning (IMML) framework for predicting DSPN prevalence and incidence based on sparse multimodal data. Exploiting IMMLs interpretability further empowered biomarker identification. We leveraged the population-based KORA F4/FF4 cohort including 1,091 participants and their deep multimodal characterisation, i.e. clinical data, genomics, methylomics, transcriptomics, proteomics, inflammatory proteins and metabolomics. Clinical data alone is sufficient to stratify individuals with and without DSPN (AUROC = 0.752), whilst predicting DSPN incidence 6.5{+/-}0.2 years later strongly benefits from clinical data complemented with two or more molecular modalities (improved {Delta}AUROC >0.1, achieved AUROC of 0.714). Important and interpretable features of incident DSPN prediction include up-regulation of proinflammatory cytokines, down-regulation of SUMOylation pathway and essential fatty acids, thus yielding novel insights in the disease pathophysiology. These may become biomarkers for incident DSPN, guide prevention strategies and serve as proof of concept for the utility of IMML in studying complex diseases.

bioinformatics↗

bioRxiv2019

Arrhythmic gut microbiome signatures for risk profiling of Type-2 Diabetes

To combat the epidemic increase in Type-2-Diabetes (T2D), risk factors need to be identified. Diet, lifestyle and the gut microbiome are among the most important factors affecting metabolic health. We demonstrate in 1,976 subjects of a prospective population cohort that specific gut microbiota members show diurnal oscillations in their relative abundance and we identified 13 taxa with disrupted rhythmicity in T2D. Prediction models based on this signature classified T2D with an area under the curve of 73%. BMI as microbiota-independent risk marker further improved diagnostic classification of T2D. The validity of this arrhythmic risk signature to predict T2D was confirmed in 699 KORA subjects five years after initial sampling. Shotgun metagenomic analysis linked 26 pathways associated with xenobiotic, amino acid, fatty acid, and taurine metabolism to the diurnal oscillation of gut bacteria. In summary, we determined a cohort-specific risk pattern of arrhythmic taxa which significantly contributes to the classification and prediction of T2D, highlighting the importance of circadian rhythmicity of the microbiome in targeting metabolic human diseases.

microbiology↗

bioRxiv2019

Renal and Renal Sinus Fat Volumes as Quantified by Magnetic Resonance Imaging in Subjects with Prediabetes, Diabetes, and Normal Glucose Tolerance.

PurposeThe aim of this study was to assess the volume of the respective kidney compartments with particular interest in renal sinus fat as an early biomarker and to compare the distribution between individuals with normal glucose levels and individuals with prediabetes and diabetes.\n\nMaterial and MethodsThe sample comprised N = 366 participants who were either normoglycemic (N = 230), had prediabetes (N = 87) or diabetes (N =49), as determined by Oral Glucose Tolerance Test. Other covariates were obtained by standardized measurements and interviews. Whole-body MR measurements were performed on a 3 Tesla scanner. For assessment of the kidneys, a coronal T1w dual-echo Dixon and a coronal T2w single shot fast spin echo sequence were employed. Stepwise semi-automated segmentation of the kidneys on the Dixon-sequences was based on thresholding and geometric assumptions generating volumes for the kidneys and sinus fat. Inter- and intra-reader variability were determined on a subset of 40 subjects. Associations between glycemic status and renal volumes were evaluated by linear regression models, adjusted for other potential confounding variables. Furthermore, the association of renal volumes with visceral adipose tissue was assessed by linear regression models and Pearsons correlation coefficient.\n\nResultsRenal volume, renal sinus volume and renal sinus fat increased gradually from normoglycemic controls to individuals with prediabetes to individuals with diabetes (renal volume: 280.3{+/-}64.7 ml vs 303.7{+/-}67.4 ml vs 320.6{+/-}77.7ml, respectively, p < 0.001). After adjustment for age and sex, prediabetes and diabetes were significantly associated to increased renal volume, sinus volume (e.g. {beta}prediabetes = 10.1, 95% CI: [6.5, 13.7]; p<0.01, {beta}Diabetes = 11.86, 95% CI: [7.2, 16.5]; p<0.01) and sinus fat (e.g. {beta}prediabetes = 7.13, 95% CI: [4.5, 9.8]; p<0.001, {beta}Diabetes = 7.34, 95% CI: [4.0, 10.7]; p<0.001). Associations attenuated after adjustment for additional confounders were only significant for prediabetes and sinus volume ({beta} =4.0 95% CI [0.4, 7.6]; p<0.05). Hypertension was significantly associated with increased sinus volume ({beta} = 3.7, 95% CI: [0.4, 6.9; p<0.05]) and absolute sinus fat volume ({beta} = 3.0, 95%CI: [0.7, 5.2]; p<0.05). GFR and all renal volumes were significantly associated as well as urine albumin levels and renal sinus volume ({beta} = 1.6, 95% CI: [0.2, 3.0]; p<0.05). There was a highly significant association between VAT and the absolute sinus fat volume ({beta} = 2.75, 95% CI: [2.3, 3.2]; p<0.01).\n\nConclusionRenal volume and particularly renal sinus fat volume already increases significantly in prediabetic subjects. There is a significant association between VAT and renal sinus fat, suggesting that there are metabolic interactions between these perivascular fat compartments.

epidemiology↗