Unlocking Tomorrow's Health Care: Expanding the Clinical Scope of Wearables by Applying Artificial Intelligence.

As an integral aspect of healthcare, digital technology has enabled modeling of complex relationships to detect, screen, diagnose and predict patient outcomes. With massive datasets, Artificial Intelligence (AI) can have marked impact on three levels: for patients, clinicians, and health systems. In this review, we discuss contemporary AI enabled wearable devices undergoing research in the field of cardiovascular medicine. These include devices such as smart watches, ECG patches and smart textiles such as smart socks and chest sensors for diagnosis, management and prognostication of conditions such as atrial fibrillation (AF) , heart failure (HF) and hypertension as well as monitoring for cardiac rehabilitation. We review the evolution of machine learning algorithms used in wearable devices from random forest models to the use of convolutional neural networks and transformers. We further discuss frameworks for wearable technologies such as the V3 stage process of verification, analytical validation and clinical validation as well as challenges of AI integration in medicine such as data veracity, validity, security and provide a reference framework to maintain fairness and equityy. Lastly clinician and patient perspectives are discussed to highlight the importance of considering end-user feedback in development and regulatory processes.

Cellular senescence contributes to age-dependent changes in circulating extracellular vesicle cargo and function.

Extracellular vesicles (EVs) have emerged as important regulators of inter-cellular and inter-organ communication, in part via the transfer of their cargo to recipient cells. Although circulating EVs have been previously studied as biomarkers of aging, how circulating EVs change with age and the underlying mechanisms that contribute to these changes are poorly understood. Here, we demonstrate that aging has a profound effect on the circulating EV pool, as evidenced by changes in concentration, size, and cargo. Aging also alters particle function; treatment of cells with EV fractions isolated from old plasma reduces macrophage responses to lipopolysaccharide, increases phagocytosis, and reduces endothelial cell responses to vascular endothelial growth factor compared to cells treated with young EV fractions. Depletion studies indicate that CD63+ particles mediate these effects. Treatment of macrophages with EV-like particles revealed that old particles increased the expression of EV miRNAs in recipient cells. Transfection of cells with microRNA mimics recapitulated some of the effects seen with old EV-like particles. Investigation into the underlying mechanisms using bone marrow transplant studies revealed circulating cell age does not substantially affect the expression of aging-associated circulating EV miRNAs in old mice. Instead, we show that cellular senescence contributes to changes in particle cargo and function. Notably, senolytic treatment of old mice shifted plasma particle cargo and function toward that of a younger phenotype. Collectively, these results demonstrate that senescent cells contribute to changes in plasma EVs with age and suggest a new mechanism by which senescent cells can affect cellular functions throughout the body.

Validity of establishing pediatric reference intervals based on hospital patient data: a comparison of the modified Hoffmann approach to CALIPER reference intervals obtained in healthy children.

OBJECTIVES: To compare pediatric reference intervals calculated using hospital-based patient data with those calculated using samples collected from healthy children in the community as part of the CALIPER study. METHODS: Hospital-based data for 13 analytes (calcium, phosphate, iron, ALP, cholesterol, triglycerides, creatinine, direct bilirubin, total bilirubin, ALT, AST, albumin and magnesium), measured on the Vitros 5600, collected between 2007 and 2011 were obtained. The data for each analyte were partitioned by age and gender as previously defined by the CALIPER study. Outliers in each partition were removed using the Tukey method. The cumulative distribution function (cdf) was then determined for each analyte value following which, the inverse cdf values of a standard Gaussian distribution were calculated. The analyte values were plotted against the inverse cdf of the standard Gaussian distribution. Piece-wise regression determined the linear portion of the resulting graph using the statistical software R. Linear regression determined an equation for the linear portion in each partition and reference intervals were calculated by extrapolating to identify the 2.5th and 97.5th centiles in each partition based on the inverse cdf values (which would correspond to the values -1.96 and 1.96 of the Gaussian distribution). Using the 90% confidence intervals for the reference intervals defined by CALIPER and the Reference Change Value (RCV) as the criteria, these calculated reference intervals were compared to those reported previously by CALIPER. Reference samples were also measured on the Vitros 5600 analyzer in an attempt to validate the calculated reference intervals. RESULTS: In general, the reference intervals calculated from hospital-based data were generally wider than those calculated by CALIPER. None of the reference intervals calculated using the Hoffmann approach fell completely within the 90% confidence intervals calculated by CALIPER. CONCLUSIONS: These results suggest that calculating pediatric reference intervals from hospital-based data may be useful, as a guide, in some cases but will likely not replace the need to establish reference intervals in healthy pediatric populations.

Pediatric reference intervals: challenges and recent initiatives.

The clinical laboratory plays a critical role in healthcare delivery by providing objective data on specific biomarkers that directly aid in the diagnosis and monitoring of a wide range of clinical disorders. Reliable and accurate reference intervals for laboratory analyses are integral for correct interpretation of clinical laboratory test results and, therefore, for appropriate clinical decision-making. Ideally, reference intervals should be established based on a healthy population and stratified for key covariates including age, gender and ethnicity. However, establishing reference intervals can be challenging as it requires the collection of large numbers of samples from healthy individuals. This challenge is further augmented in pediatrics, where dynamic changes due to child growth and development markedly affect circulating levels of disease biomarkers. As a result, even larger reference populations are required to reliably calculate reference intervals. In this review, we outline the challenges specific to establishing pediatric reference intervals and highlight recent initiatives aimed at closing existing gaps in current knowledge. We also outline recommended approaches to the development of reference intervals and detail several alternative approaches. Finally, reference intervals for emerging and novel biomarkers of pediatric disease are discussed along with a number of potential alternative sample types.

Personalized medicine in the care of the child with congenital heart disease: discovery to application.

On October 27-28, 2012, the SickKids Labatt Family Heart Centre and the Heart Centre Biobank Registry hosted the second international GenomeHeart symposium in Toronto, Ontario. The symposium featured experts in cardiology, developmental biology, pharmacology, genomics, bioinformatics, stem cell biology, biobanking, and ethics. The theme of this year's symposium was the application of emerging technologies in genomics, proteomics, transcriptomics, and bioinformatics to diagnostics and therapeutics of the child with heart disease. Social, ethical, and economic issues were also discussed in the context of clinical translation. We highlight some of the themes that emerged from this exciting 2-day event.