AI as an intervention: improving clinical outcomes relies on a causal approach to AI development and validation.

The primary practice of healthcare artificial intelligence (AI) starts with model development, often using state-of-the-art AI, retrospectively evaluated using metrics lifted from the AI literature like AUROC and DICE score. However, good performance on these metrics may not translate to improved clinical outcomes. Instead, we argue for a better development pipeline constructed by working backward from the end goal of positively impacting clinically relevant outcomes using AI, leading to considerations of causality in model development and validation, and subsequently a better development pipeline.

Paediatric Personalized Research Network Switzerland (SwissPedHealth): a joint paediatric national data stream.

Introduction: Children represent a large and vulnerable patient group. However, the evidence base for most paediatric diagnostic and therapeutic procedures remains limited or is often inferred from adults. There is an urgency to improve paediatric healthcare provision based on real-world evidence generation.

A new stepwise approach to minimize phrenic nerve injury during cryoballoon pulmonary vein isolation.

Background: A phrenic nerve injury (PNI) during cryoballoon (CB) pulmonary vein isolation (PVI) continues to represent a limitation of this technique. The objective of this study was to develop a novel technique with the aim of reducing the incidence of PNI.

Methods: We performed a retrospective analysis of data from two hospitals in patients with symptomatic, drug-resistant atrial fibrillation (AF) over 7 years to evaluate the incidence and clinical characteristics of PNI during cryoballoon PVI.

Comparison of 2D and 3D lung lobe quantification with Ventilation/Perfusion Ratio.

In this study, standard 2D lung lobe quantification is compared with two 3D lung lobe quantification software tools to investigate the clinical benefit of a 3D approach. The accuracy of 2D versus 3D lung lobe quantification is evaluated based on the calculated numerical ventilation-perfusion ratio (VQR) using a receiver operating curve (ROC) analysis.A study group of 50 consecutive patients underwent a planar lung scintigraphy (anterior/posterior) as well as ventilation/perfusion single photon emission computed tomography (SPECT/CT) to exclude acute pulmonary embolism.