Search

Objectives: We evaluated the applicability of a machine learning based Low-density lipoprotein-cholesterol (LDL-C) estimation method and the influence of the characteristics of the training datasets. Methods: Three training datasets were chosen from training datasets: health check-up participants at the Resource Center for Health Science (N = 2664), clinical patients at Gifu University Hospital (N = 7409), and clinical patients at Fujita Health University Hospital (N = 14842). Nine different machine learning models were constructed through hyperparameter tuning and 10-fold cross-validation. Another test dataset of another 3711 clinical patients at Fujita Health University Hospital was selected as the test set used for comparing and validating the model against the Friedewald formula and the Martin method. Results: The coefficients of determination of the models trained on the health check-up dataset produced coefficients of determination that were equal to or inferior to those of the Martin method. In contrast, the coefficients of determination of several models trained on clinical patients exceeded those of the Martin method. The means of the differences and the convergences to the direct method were higher for the models trained on the clinical patients' dataset than for those trained on the health check-up participants' dataset. The models trained on the latter dataset tended to overestimate the 2019 ESC/EAS Guideline for LDL-cholesterol classification. Conclusion: Although machine learning models provide valuable method for LDL-C estimates, they should be trained on datasets with matched characteristics. The versatility of machine learning methods is another important consideration.

Summary A surface marker that distinctly identifies cardiac progenitors (CPs) is essential for the robust isolation of these cells, circumventing the necessity of genetic modification. Here, we demonstrate that a Glycosylphosphatidylinositol-anchor containing neurotrophic factor receptor, Glial cell line-derived neurotrophic factor receptor alpha 2 (Gfra2), specifically marks CPs. GFRA2 expression facilitates the isolation of CPs by fluorescence activated cell sorting from differentiating mouse and human pluripotent stem cells. Gfra2 mutants reveal an important role for GFRA2 in cardiomyocyte differentiation and development both in vitro and in vivo. Mechanistically, the cardiac GFRA2 signaling pathway is distinct from the canonical pathway dependent on the RET tyrosine kinase and its established ligands. Collectively, our findings establish a platform for investigating the biology of CPs as a foundation for future development of CP transplantation for treating heart failure., Graphical Abstract, Highlights • Gfra2 is specific for cardiac progenitors (CPs) among mesodermal cells • GFRA2 enables isolation of multipotent or unipotent CPs in mouse and human • Gfra2 and the related molecule Gfra1 play a vital role in heart development • The GFRA1/2 signal in heart development is independent of established ligands, Ishida et al. show that GPI-anchored neurotrophic factor receptor Gfra2 specifically marks cardiac progenitor cells (CPs) in mouse and human, providing a method for isolating CPs. Unexpectedly, Gfra2 plays a significant role in heart development via a non-canonical signaling pathway that is independent of known ligands and the co-receptor RET tyrosine kinase.