Using explainable AI to investigate electrocardiogram changes during healthy aging—From expert features to raw signals

by Gabriel Ott, Yannik Schaubelt, Juan Miguel Lopez Alcaraz, Wilhelm Haverkamp, Nils Strodthoff

Cardiovascular diseases remain the leading global cause of mortality. Age is an important covariate whose effect is most easily investigated in a healthy cohort to properly distinguish the former from disease-related changes. Traditionally, most of such insights have been drawn from the analysis of electrocardiogram (ECG) feature changes in individuals as they age. However, these features, while informative, may potentially obscure underlying data relationships. In this paper we present the following contributions: (1) We employ a deep-learning model and a tree-based model to analyze ECG data from a robust dataset of healthy individuals across varying ages in both raw signals and ECG feature format. (2) We use explainable AI methods to identify the most discriminative ECG features across age groups.(3) Our analysis with tree-based classifiers reveals age-related declines in inferred breathing rates and identifies notably high SDANN values as indicative of elderly individuals, distinguishing them from younger adults. (4) Furthermore, the deep-learning model underscores the pivotal role of the P-wave in age predictions across all age groups, suggesting potential changes in the distribution of different P-wave types with age. These findings shed new light on age-related ECG changes, offering insights that transcend traditional feature-based approaches.

Quantitative changes in the corneal endothelium and central corneal thickness during anterior chamber inflammation: A systematic review and meta-analysis

by Germán Mejía-Salgado, Paula Tatiana Muñoz-Vargas, Carlos Cifuentes-González, Gabriela Flórez-Esparza, Rebeca Paquentín-Jiménez, Miguel Ángel Castro-Monreal, Naomi Medina-Galindo, Gilma Norella Hernández-Herrera, Luz Elena Concha-del-Río, Alejandra de-la-Torre

Purpose

To establish the effects of anterior chamber inflammation (ACI) on the corneal endothelium parameters and central corneal thickness (CCT).

Methods

We conducted a comprehensive literature review using medical databases (PubMed, EMBASE, VHL, and medRxiv) on March 8, 2023, for studies that included patients with ACI who had undergone specular microscopy or pachymetry. Case series with >10 patients, cross-sectional, case-control, and cohort studies were included. The risk of bias was assessed using CLARITY tools and validated scales such as those by Hassan Murad et al. and Hoy et al. A narrative synthesis and a quantitative standardized mean difference meta-analysis, I² heterogeneity assessment, and publication bias tests were conducted. The study was registered in PROSPERO (CRD42023420148) and approved by the Universidad del Rosario ethical committee (DVO005 2277- CV1712).

Results

Thirty-four studies, encompassing 1,388 eyes with ACI, were included. Compared with healthy controls, overall, ACI eyes show significant mean differences in endothelial parameters (endothelial cell density (ECD), coefficient of variation (CV), and hexagonality (HEX)) (P Conclusion

ACI leads to significant alterations in endothelial parameters and CCT. The primary contributors to these changes are increased IOP, uveitis duration, and intraocular surgeries. Further studies are needed to explore the impact of ACI etiology on the endothelium, potential biases in IOP measurements during acute ACI episodes, and the potential necessity for monitoring the endothelial parameters and CCT in patients with chronic ACI.