Machine learning approach to predict subtypes of primary aldosteronism is helpful to estimate indication of adrenal vein sampling.

INTRODUCTION: Primary aldosteronism (PA) is a common disease. Especially in unilateral PA (UPA), the risk of cardiovascular disease is high and proper localization is important. Adrenal vein sampling (AVS) is commonly used to localize PA, but its availability is limited. Therefore, it is important to predict the unilateral or bilateral PA and to choose the appropriate cases for AVS or watchful observation. AIM: The purpose of this study is to develop a model using machine learning to predict bilateral or unilateral PA to extract cases for AVS or watchful observation. METHODS: We retrospectively analyzed 154 patients diagnosed with PA and who underwent AVS at our hospital between January 2010 and June 2021. Based on machine learning, we determined predictors of PA subtypes diagnosis from the results of blood and loading tests. RESULTS: The accuracy of the machine learning was 88% and the top predictors of the UPA were plasma aldosterone concentration after the saline infusion test, aldosterone to renin ratio after the captopril challenge test, serum potassium and aldosterone-to-renin ratio. By using these factors, the accuracy, sensitivity, specificity and the area under the curve (AUC) were 91%, 70%, 99% and 0.91, respectively. Furthermore, we examined the surgical outcomes of UPA and found that the group diagnosed as unilateral by the predictors showed improvement in clinical findings, while the group diagnosed as bilateral by the predictors showed no improvement. CONCLUSION: Our predictive model based on machine learning can support to choose the performance of adrenal vein sampling or watchful observation.

Robust and highly efficient hiPSC generation from patient non-mobilized peripheral blood-derived CD34+ cells using the auto-erasable Sendai virus vector.

BACKGROUND: Disease modeling with patient-derived induced pluripotent stem cells (iPSCs) is a powerful tool for elucidating the mechanisms underlying disease pathogenesis and developing safe and effective treatments. Patient peripheral blood (PB) cells are used for iPSC generation in many cases since they can be collected with minimum invasiveness. To derive iPSCs that lack immunoreceptor gene rearrangements, hematopoietic stem and progenitor cells (HSPCs) are often targeted as the reprogramming source. However, the current protocols generally require HSPC mobilization and/or ex vivo expansion owing to their sparsity at the steady state and low reprogramming efficiencies, making the overall procedure costly, laborious, and time-consuming. METHODS: We have established a highly efficient method for generating iPSCs from non-mobilized PB-derived CD34+ HSPCs. The source PB mononuclear cells were obtained from 1 healthy donor and 15 patients and were kept frozen until the scheduled iPSC generation. CD34+ HSPC enrichment was done using immunomagnetic beads, with no ex vivo expansion culture. To reprogram the CD34+-rich cells to pluripotency, the Sendai virus vector SeVdp-302L was used to transfer four transcription factors: KLF4, OCT4, SOX2, and c-MYC. In this iPSC generation series, the reprogramming efficiencies, success rates of iPSC line establishment, and progression time were recorded. After generating the iPSC frozen stocks, the cell recovery and their residual transgenes, karyotypes, T cell receptor gene rearrangement, pluripotency markers, and differentiation capability were examined. RESULTS: We succeeded in establishing 223 iPSC lines with high reprogramming efficiencies from 15 patients with 8 different disease types. Our method allowed the rapid appearance of primary colonies (~ 8 days), all of which were expandable under feeder-free conditions, enabling robust establishment steps with less workload. After thawing, the established iPSC lines were verified to be pluripotency marker-positive and of non-T cell origin. A majority of the iPSC lines were confirmed to be transgene-free, with normal karyotypes. Their trilineage differentiation capability was also verified in a defined in vitro assay. CONCLUSION: This robust and highly efficient method enables the rapid and cost-effective establishment of transgene-free iPSC lines from a small volume of PB, thus facilitating the biobanking of patient-derived iPSCs and their use for the modeling of various diseases.