Classification of anatomic patterns of peripheral artery disease with automated machine learning (AutoML).

AIM: The aim of this study was to investigate the potential of novel automated machine learning (AutoML) in vascular medicine by developing a discriminative artificial intelligence (AI) model for the classification of anatomical patterns of peripheral artery disease (PAD). MATERIAL AND METHODS: Random open-source angiograms of lower limbs were collected using a web-indexed search. An experienced researcher in vascular medicine labelled the angiograms according to the most applicable grade of femoropopliteal disease in the Global Limb Anatomic Staging System (GLASS). An AutoML model was trained using the Vertex AI (Google Cloud) platform to classify the angiograms according to the GLASS grade with a multi-label algorithm. Following deployment, we conducted a test using 25 random angiograms (five from each GLASS grade). Model tuning through incremental training by introducing new angiograms was executed to the limit of the allocated quota following the initial evaluation to determine its effect on the software's performance. RESULTS: We collected 323 angiograms to create the AutoML model. Among these, 80 angiograms were labelled as grade 0 of femoropopliteal disease in GLASS, 114 as grade 1, 34 as grade 2, 25 as grade 3 and 70 as grade 4. After 4.5 h of training, the AI model was deployed. The AI self-assessed average precision was 0.77 (0 is minimal and 1 is maximal). During the testing phase, the AI model successfully determined the GLASS grade in 100% of the cases. The agreement with the researcher was almost perfect with the number of observed agreements being 22 (88%), Kappa = 0.85 (95% CI 0.69-1.0). The best results were achieved in predicting GLASS grade 0 and grade 4 (initial precision: 0.76 and 0.84). However, the AI model exhibited poorer results in classifying GLASS grade 3 (initial precision: 0.2) compared to other grades. Disagreements between the AI and the researcher were associated with the low resolution of the test images. Incremental training expanded the initial dataset by 23% to a total of 417 images, which improved the model's average precision by 11% to 0.86. CONCLUSION: After a brief training period with a limited dataset, AutoML has demonstrated its potential in identifying and classifying the anatomical patterns of PAD, operating unhindered by the factors that can affect human analysts, such as fatigue or lack of experience. This technology bears the potential to revolutionize outcome prediction and standardize evidence-based revascularization strategies for patients with PAD, leveraging its adaptability and ability to continuously improve with additional data. The pursuit of further research in AutoML within the field of vascular medicine is both promising and warranted. However, it necessitates additional financial support to realize its full potential.

The Role of Phosphatidylethanolamine N-Methyltransferase (PEMT) and Its Waist-Hip-Ratio-Associated Locus rs4646404 in Obesity-Related Metabolic Traits and Liver Disease.

In previous genome-wide association studies (GWAS), genetic loci associated with obesity and impaired fat distribution (FD) have been identified. In the present study, we elucidated the role of the PEMT gene, including the waist-hip-ratio-associated single nucleotide polymorphism rs4646404, and its influence on obesity-related metabolic traits. DNA from 2926 metabolically well-characterized subjects was used for genotyping. PEMT expression was analyzed in paired visceral (vis) and subcutaneous (sc) adipose tissue (AT) from a subset of 574 individuals. Additionally, PEMT expression was examined in vis, sc AT and liver tissue in a separate cohort of 64 patients with morbid obesity and liver disease. An in vitro Pemt knockdown was conducted in murine epididymal and inguinal adipocytes. Our findings highlight tissue-specific variations in PEMT mRNA expression across the three studied tissues. Specifically, vis PEMT mRNA levels correlated significantly with T2D and were implicated in the progression of non-alcoholic steatohepatitis (NASH), in contrast to liver tissue, where no significant associations were found. Moreover, sc PEMT expression showed significant correlations with several anthropometric- and metabolic-related parameters. The rs4646404 was associated with vis AT PEMT expression and also with diabetes-related traits. Our in vitro experiments supported the influence of PEMT on adipogenesis, emphasizing its role in AT biology. In summary, our data suggest that PEMT plays a role in regulating FD and has implications in metabolic diseases.

Out-of-Hospital Management of Diabetic Emergencies in Germany: Structural and Process Quality.

AIMS: To collect and analyse representative data of structural and process quality in the management of diabetic emergencies in Germany in 2020. METHODS: A standardised questionnaire comprising detailed items concerning clinically relevant parameters on the structural and process quality of out-of-hospital management of diabetic emergencies was sent nationwide to medical directors of emergency medical service districts (EMSDs). Results were compared with those from a similar study conducted in 2001. RESULTS: The return rate of the questionnaires represented 126 EMSDs, serving a total population of > 40.1 million. Only 4% of ambulances carried glucagon (6% in 2001). In 2020, blood glucose determination increased significantly to 71% of all emergency interventions and to 29% of suspected cardiac emergencies (24% and 15%, respectively, in 2001). In 100% of EMSDs severe hypoglycaemia (SH) was treated by paramedics by administering intravenous dextrose before the arrival of a doctor compared to 63% in 2001. The potential value of nasal glucagon was acknowledged by 43% of responders. In selected patients, treatment of SH was conducted without hospital admission in 78% of EMDs (60% in 2001). Fifty-three percent of medical directors acknowledged the need for further training in diabetic emergencies (47% in 2001). Cooperation for medical education between emergency teams and a diabetes centre was reported by 14% (41% in 2001). CONCLUSION: Structural and process quality of the management of diabetic emergencies in Germany has improved considerably since 2001. Persisting deficiencies could be improved by providing better medical equipment in ambulances and ongoing education to the entire emergency teams.