RESUMEN
This study investigates brain network alterations in the default mode-like network (DMLN) at early stages of disease progression in a rat model of Alzheimer's disease (AD) with application in the development of early diagnostic biomarkers of AD in translational studies. Thirteen male TgF344-AD (TG) rats, and eleven male wild-types (WT) littermates underwent longitudinal resting-state fMRI at the age of 4 and 6 months (pre and early-plaque stages of AD). Alterations in connectivity within DMLN were characterized by calculating the nodal degree (ND), a graph theoretical measure of centrality. The ND values of the left CA2 subregion of the hippocampus was found to be significantly lower in the 4-month-old TG cohort compared to the age-matched WT littermates. Moreover, a lower ND value (hypo-connectivity) was observed in the right prelimbic cortex (prL) and basal forebrain in the 6-month-old TG cohort, compared to the same age WT cohort. Indeed, the ND pattern in the DMLN in both TG and WT cohorts showed significant differences across the two time points that represent pre-plaque and early plaque stages of disease progression. Our findings indicate that lower nodal degree (hypo-connectivity) in the left CA2 in the pre-plaque stage of AD and hypo-connectivity between the basal forebrain and the DMLN regions in the early-plaque stage demonstrated differences in comparison to healthy controls. These results suggest that a graph-theoretical measure such as the nodal degree, can characterize brain networks and improve our insights into the mechanisms underlying Alzheimer's disease.
RESUMEN
Background: Federated learning (FL) is a technique for learning prediction models without sharing records between hospitals. Compared to centralized training approaches, the adoption of FL could negatively impact model performance. Aim: This study aimed to evaluate four types of multicenter model development strategies for predicting 30-day mortality for patients undergoing transcatheter aortic valve implantation (TAVI): (1) central, learning one model from a centralized dataset of all hospitals; (2) local, learning one model per hospital; (3) federated averaging (FedAvg), averaging of local model coefficients; and (4) ensemble, aggregating local model predictions. Methods: Data from all 16 Dutch TAVI hospitals from 2013 to 2021 in the Netherlands Heart Registration (NHR) were used. All approaches were internally validated. For the central and federated approaches, external geographic validation was also performed. Predictive performance in terms of discrimination [the area under the ROC curve (AUC-ROC, hereafter referred to as AUC)] and calibration (intercept and slope, and calibration graph) was measured. Results: The dataset comprised 16,661 TAVI records with a 30-day mortality rate of 3.4%. In internal validation the AUCs of central, local, FedAvg, and ensemble models were 0.68, 0.65, 0.67, and 0.67, respectively. The central and local models were miscalibrated by slope, while the FedAvg and ensemble models were miscalibrated by intercept. During external geographic validation, central, FedAvg, and ensemble all achieved a mean AUC of 0.68. Miscalibration was observed for the central, FedAvg, and ensemble models in 44%, 44%, and 38% of the hospitals, respectively. Conclusion: Compared to centralized training approaches, FL techniques such as FedAvg and ensemble demonstrated comparable AUC and calibration. The use of FL techniques should be considered a viable option for clinical prediction model development.