| 1. |
- Dietz, Benedikt, et al.
(författare)
-
Detection of diabetes from whole-body MRI using deep learning
- 2021
-
Ingår i: JCI Insight. - : American Society for Clinical Investigation. - 2379-3708. ; 6:21
-
Tidskriftsartikel (refereegranskat)abstract
- Obesity is one of the main drivers of type 2 diabetes, but it is not uniformly associated with the disease. The location of fat accumulation is critical for metabolic health. Specific patterns of body fat distribution, such as visceral fat, are closely related to insulin resistance. There might be further, hitherto unknown, features of body fat distribution that could additionally contribute to the disease. We used machine learning with dense convolutional neural networks to detect diabetes-related variables from 2371 T1-weighted whole-body MRI data sets. MRI was performed in participants undergoing metabolic screening with oral glucose tolerance tests. Models were trained for sex, age, BMI, insulin sensitivity, HbA1c, and prediabetes or incident diabetes. The results were compared with those of conventional models. The area under the receiver operating characteristic curve was 87% for the type 2 diabetes discrimination and 68% for prediabetes, both superior to conventional models. Mean absolute regression errors were comparable to those of conventional models. Heatmaps showed that lower visceral abdominal regions were critical in diabetes classification. Subphenotyping revealed a group with high future diabetes and microalbuminuria risk. Our results show that diabetes is detectable from whole-body MRI without additional data. Our technique of heatmap visualization identifies plausible anatomical regions and highlights the leading role of fat accumulation in the lower abdomen in diabetes pathogenesis.
|
|
| 2. |
|
|
| 3. |
|
|
| 4. |
- Wagner, Róbert, et al.
(författare)
-
Nonsuppressed glucagon after glucose challenge as a potential predictor for glucose tolerance
- 2017
-
Ingår i: Diabetes. - : American Diabetes Association. - 0012-1797 .- 1939-327X. ; 66:5, s. 1373-1379
-
Tidskriftsartikel (refereegranskat)abstract
- Glucagon levels are classically suppressed after glucose challenge. It is still not clear as to whether a lack of suppression contributes to hyperglycemia and thus to the development of diabetes. We investigated the association of postchallenge change in glucagon during oral glucose tolerance tests (OGTTs), hypothesizing that higher postchallenge glucagon levels are observed in subjects with impaired glucose tolerance (IGT). Glucagon levels were measured during OGTT in a total of 4,194 individuals without diabetes in three large European cohorts. Longitudinal changes in glucagon suppression were investigated in 50 participants undergoing a lifestyle intervention. Only 66-79% of participants showed suppression of glucagon at 120 min (fold change glucagon120/0 <1) during OGTT, whereas 21-34% presented with increasing glucagon levels (fold change glucagon120/0 ≥1). Participants with nonsuppressed glucagon120 had a lower risk of IGT in all cohorts (odds ratio 0.44-0.53, P < 0.01). They were also leaner and more insulin sensitive and had lower liver fat contents. In the longitudinal study, an increase of fold change glucagon120/0 was associated with an improvement in insulin sensitivity (P = 0.003). We characterize nonsuppressed glucagon120 during the OGTT. Lower glucagon suppression after oral glucose administration is associated with a metabolically healthier phenotype, suggesting that it is not an adverse phenomenon.
|
|
