Obstructive sleep apnea (OSA) affects almost a billion people worldwide and is associated with a myriad of adverse health outcomes. Among the most prevalent and morbid are cardiovascular diseases (CVDs). Nonetheless, randomized controlled trials (RCTs) of OSA treatment have failed to show improvements in CVD outcomes. A major limitation in our field is the lack of precision in defining OSA and specifically subgroups with the potential to benefit from therapy. Further, this has called into question the validity of using the time-honored apnea–hypopnea index as the ultimate defining criteria for OSA. Recent applications of advanced statistical methods and machine learning have brought to light a variety of OSA endotypes and phenotypes. These methods also provide an opportunity to understand the interaction between OSA and comorbid diseases for better CVD risk stratification. Lastly, machine learning and specifically heterogeneous treatment effects modeling can help uncover subgroups with differential outcomes after treatment initiation. In an era of data sharing and big data, these techniques will be at the forefront of OSA research. Advanced data science methods, such as machine-learning analyses and artificial intelligence, will improve our ability to determine the unique influence of OSA on CVD outcomes and ultimately allow us to better determine precision medicine approaches in OSA patients for CVD risk reduction. In this narrative review, we will highlight how team science via machine learning and artificial intelligence applied to existing clinical data, polysomnography, proteomics, and imaging can do just that.

Functional imaging provides hemodynamic and metabolic information and is increasingly being incorporated into clinical diagnostic and research studies. Typically functional images have reduced signal-to-noise ratio and spatial resolution compared to other non-functional cross sectional images obtained as part of a routine clinical protocol. We hypothesized that enhancing visualization and interpretation of functional images with anatomic information could provide preferable quality and superior diagnostic value. In this work, we implemented five methods (frequency addition, frequency multiplication, wavelet transform, nonsubsampled contourlet transform and intensity-hue-saturation) and a newly proposed ShArpening by Local Similarity with Anatomic images (SALSA) method to enhance the visualization of functional images, while preserving the original functional contrast and quantitative signal intensity characteristics over larger spatial scales. Arterial spin labeling blood flow MR images of the brain were visualization enhanced using anatomic images with multiple contrasts. The algorithms were validated on a numerical phantom and their performance on images of brain tumor patients were assessed by quantitative metrics and neuroradiologist subjective ratings. The frequency multiplication method had the lowest residual error for preserving the original functional image contrast at larger spatial scales (55%-98% of the other methods with simulated data and 64%-86% with experimental data). It was also significantly more highly graded by the radiologists (p<;0.005 for clear brain anatomy around the tumor). Compared to other methods, the SALSA provided 11%-133% higher similarity with ground truth images in the simulation and showed just slightly lower neuroradiologist grading score. Most of these monochrome methods do not require any prior knowledge about the functional and anatomic image characteristics, except the acquired resolution. Hence, automatic implementation on clinical images should be readily feasible.

Background: Accurate quantification of visceral (VAT) and subcutaneous adipose tissue (SAT) is critical for understanding the cardiometabolic consequences of obstructive sleep apnea (OSA) and other chronic diseases. This study validates a customization framework using pre-trained networks for the development of automated VAT/SAT segmentation models using hybrid positron emission tomography (PET)/magnetic resonance imaging (MRI) data from OSA patients. While the widespread adoption of deep learning models continues to accelerate the automation of repetitive tasks, establishing a customization framework is essential for developing models tailored to specific research questions. Methods: A UNet-ResNet50 model, pre-trained on RadImageNet, was iteratively trained on 59, 157, and 328 annotated scans within a closed-loop system on the Discovery Viewer platform. Model performance was evaluated against manual expert annotations in 10 independent test cases (with 80–100 MR slices per scan) using Dice similarity coefficients, segmentation time, intraclass correlation coefficients (ICC) for volumetric and metabolic agreement (VAT/SAT volume and standardized uptake values [SUVmean]), and Bland–Altman analysis to evaluate the bias. Results: The proposed deep learning pipeline substantially improved segmentation efficiency. Average annotation time per scan was 121.8 min (manual segmentation), 31.8 min (AI-assisted segmentation), and only 1.2 min (fully automated AI segmentation). Segmentation performance, assessed on 10 independent scans, demonstrated high Dice similarity coefficients for masks (0.98 for VAT and SAT), though lower for contours/boundary delineation (0.43 and 0.54). Agreement between AI-derived and manual volumetric and metabolic VAT/SAT measures was excellent, with all ICCs exceeding 0.98 for the best model and with minimal bias. Conclusions: This scalable and accurate pipeline enables efficient abdominal fat quantification using hybrid PET/MRI for simultaneous volumetric and metabolic fat analysis. Our framework streamlines research workflows and supports clinical studies in obesity, OSA, and cardiometabolic diseases through multi-modal imaging integration and AI-based segmentation. This facilitates the quantification of depot-specific adipose metrics that may strongly influence clinical outcomes.

We assessed changes in vascular inflammation and monosodium urate (MSU)-coded deposits after administration of Pegloticase in the vasculature of tophaceous gout patients using ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) Positron emission tomography/computed tomography (PET/CT) and dual-energy CT (DECT). Ten patients with tophaceous gout, intolerant or refractory to urate-lowering therapy (ULT), were treated with Pegloticase every two weeks for six months. ¹⁸F-FDG PET/CT and DECT were performed at baseline and after Pegloticase therapy to detect vessel wall inflammation (Standard uptake value, SUVmean, and SUVmax) and vascular MSU-coded deposition (MSU volume). Data were summarized using means and standard deviations. Baseline and follow-up values were compared for each variable using mixed-effect models. Significant decreases in SUVmean (p = 0.0003) and SUVmax (p = 0.009) were found with a trend towards a decrease in vessel wall MSU volume after treatment. There was a significant decrease in serum urate, correlating with reduction in SUVmean (R² = 0.65), with a trend towards a decrease in CRP and blood pressure in all patients. Despite the small sample size, we were able to demonstrate a decrease in vessel wall inflammation and a trend towards a decrease in MSU volume by intensively lowering serum urate. These findings suggest that MSU-coded deposits and hyperuricemia may play a role in vascular wall inflammation. It remains to be seen whether this correlates with a decrease in adverse cardiovascular outcomes.