Clinical use of polygenic risk scores for detection of peripheral artery disease and cardiovascular events.

We have previously shown that polygenic risk scores (PRS) can improve risk stratification of peripheral artery disease (PAD) in a large, retrospective cohort. Here, we evaluate the potential of PRS in improving the detection of PAD and prediction of major adverse cardiovascular and cerebrovascular events (MACCE) and adverse events (AE) in an institutional patient cohort. We created a cohort of 278 patients (52 cases and 226 controls) and fit a PAD-specific PRS based on the weighted sum of risk alleles. We built traditional clinical risk models and machine learning (ML) models using clinical and genetic variables to detect PAD, MACCE, and AE. The models' performances were measured using the area under the curve (AUC), net reclassification index (NRI), integrated discrimination improvement (IDI), and Brier score. We also evaluated the clinical utility of our PAD model using decision curve analysis (DCA). We found a modest, but not statistically significant improvement in the PAD detection model's performance with the inclusion of PRS from 0.902 (95% CI: 0.846-0.957) (clinical variables only) to 0.909 (95% CI: 0.856-0.961) (clinical variables with PRS). The PRS inclusion significantly improved risk re-classification of PAD with an NRI of 0.07 (95% CI: 0.002-0.137), p = 0.04. For our ML model predicting MACCE, the addition of PRS did not significantly improve the AUC, however, NRI analysis demonstrated significant improvement in risk re-classification (p = 2e-05). Decision curve analysis showed higher net benefit of our combined PRS-clinical model across all thresholds of PAD detection. Including PRS to a clinical PAD-risk model was associated with improvement in risk stratification and clinical utility, although we did not see a significant change in AUC. This result underscores the potential clinical utility of incorporating PRS data into clinical risk models for prevalent PAD and the need for use of evaluation metrics that can discern the clinical impact of using new biomarkers in smaller populations.

Transparent medical image AI via an image-text foundation model grounded in medical literature.

Building trustworthy and transparent image-based medical artificial intelligence (AI) systems requires the ability to interrogate data and models at all stages of the development pipeline, from training models to post-deployment monitoring. Ideally, the data and associated AI systems could be described using terms already familiar to physicians, but this requires medical datasets densely annotated with semantically meaningful concepts. In the present study, we present a foundation model approach, named MONET (medical concept retriever), which learns how to connect medical images with text and densely scores images on concept presence to enable important tasks in medical AI development and deployment such as data auditing, model auditing and model interpretation. Dermatology provides a demanding use case for the versatility of MONET, due to the heterogeneity in diseases, skin tones and imaging modalities. We trained MONET based on 105,550 dermatological images paired with natural language descriptions from a large collection of medical literature. MONET can accurately annotate concepts across dermatology images as verified by board-certified dermatologists, competitively with supervised models built on previously concept-annotated dermatology datasets of clinical images. We demonstrate how MONET enables AI transparency across the entire AI system development pipeline, from building inherently interpretable models to dataset and model auditing, including a case study dissecting the results of an AI clinical trial.

The Promises and Perils of Foundation Models in Dermatology.

Foundation models (FM), which are large-scale artificial intelligence (AI) models that can complete a range of tasks, represent a paradigm shift in AI. These versatile models encompass large language models, vision-language models, and multimodal models. Although these models are often trained for broad tasks, they have been applied either out of the box or after additional fine tuning to tasks in medicine, including dermatology. From addressing administrative tasks to answering dermatology questions, these models are poised to have an impact on dermatology care delivery. As FMs become more ubiquitous in health care, it is important for clinicians and dermatologists to have a basic understanding of how these models are developed, what they are capable of, and what pitfalls exist. In this paper, we present a comprehensive yet accessible overview of the current state of FMs and summarize their current applications in dermatology, highlight their limitations, and discuss future developments in the field.

Large Language Models in Medicine: The Potentials and Pitfalls : A Narrative Review.

Large language models (LLMs) are artificial intelligence models trained on vast text data to generate humanlike outputs. They have been applied to various tasks in health care, ranging from answering medical examination questions to generating clinical reports. With increasing institutional partnerships between companies producing LLMs and health systems, the real-world clinical application of these models is nearing realization. As these models gain traction, health care practitioners must understand what LLMs are, their development, their current and potential applications, and the associated pitfalls in a medical setting. This review, coupled with a tutorial, provides a comprehensive yet accessible overview of these areas with the aim of familiarizing health care professionals with the rapidly changing landscape of LLMs in medicine. Furthermore, the authors highlight active research areas in the field that promise to improve LLMs' usability in health care contexts.

Principles, applications, and future of artificial intelligence in dermatology.

This paper provides an overview of artificial-intelligence (AI), as applied to dermatology. We focus our discussion on methodology, AI applications for various skin diseases, limitations, and future opportunities. We review how the current image-based models are being implemented in dermatology across disease subsets, and highlight the challenges facing widespread adoption. Additionally, we discuss how the future of AI in dermatology might evolve and the emerging paradigm of large language, and multi-modal models to emphasize the importance of developing responsible, fair, and equitable models in dermatology.

Large language models propagate race-based medicine.

Large language models (LLMs) are being integrated into healthcare systems; but these models may recapitulate harmful, race-based medicine. The objective of this study is to assess whether four commercially available large language models (LLMs) propagate harmful, inaccurate, race-based content when responding to eight different scenarios that check for race-based medicine or widespread misconceptions around race. Questions were derived from discussions among four physician experts and prior work on race-based medical misconceptions believed by medical trainees. We assessed four large language models with nine different questions that were interrogated five times each with a total of 45 responses per model. All models had examples of perpetuating race-based medicine in their responses. Models were not always consistent in their responses when asked the same question repeatedly. LLMs are being proposed for use in the healthcare setting, with some models already connecting to electronic health record systems. However, this study shows that based on our findings, these LLMs could potentially cause harm by perpetuating debunked, racist ideas.

Use of Multi-Modal Data and Machine Learning to Improve Cardiovascular Disease Care.

Today's digital health revolution aims to improve the efficiency of healthcare delivery and make care more personalized and timely. Sources of data for digital health tools include multiple modalities such as electronic medical records (EMR), radiology images, and genetic repositories, to name a few. While historically, these data were utilized in silos, new machine learning (ML) and deep learning (DL) technologies enable the integration of these data sources to produce multi-modal insights. Data fusion, which integrates data from multiple modalities using ML and DL techniques, has been of growing interest in its application to medicine. In this paper, we review the state-of-the-art research that focuses on how the latest techniques in data fusion are providing scientific and clinical insights specific to the field of cardiovascular medicine. With these new data fusion capabilities, clinicians and researchers alike will advance the diagnosis and treatment of cardiovascular diseases (CVD) to deliver more timely, accurate, and precise patient care.

EFFECT OF REOPENING ORDERS ON COVID-19 HOSPITALIZATIONS IN THE US.

Shelter in place (SIP) orders were instituted by states to alleviate the impact of the COVID-19 pandemic. However, states proceeded to reopen as SIPs were noted to be hurting the economy. We evaluated whether these reopenings affected COVID-19 hospitalizations. We collected public data on US state reopening orders and COVID-19 hospitalizations from March 8 to August 8, 2020. We utilized a doubling time metric to compare increase in hospitalizations in line with reopenings and proceeded to quantify the impact of reopening orders on cumulative hospitalizations. We found that some reopenings increased hospitalizations, and this varied by state. We also discovered that the most negatively impactful reopenings overall tended to be restaurants/bars (-92%) and houses of worship (-63.6%). Without data-backed guidance on reopening states, the healthcare burden from COVID-19 will likely persist. State governments should use data to understand the potential effects of these reopenings to guide future policies.

COVID-19 Pandemic: Is Africa Different?

COVID-19 has now spread to all the continents of the world with the possible exception of Antarctica. However, Africa appears different when compared with all the other continents. The absence of exponential growth and the low mortality rates contrary to that experienced in other continents, and contrary to the projections for Africa by various agencies, including the World Health Organization (WHO) has been a puzzle to many. Although Africa is the second most populous continent with an estimated 17.2% of the world's population, the continent accounts for only 5% of the total cases and 3% of the mortality. Mortality for the whole of Africa remains at a reported 19,726 as at August 01, 2020. The onset of the pandemic was later, the rate of rise has been slower and the severity of illness and case fatality rates have been lower in comparison to other continents. In addition, contrary to what had been documented in other continents, the occurrence of the renal complications in these patients also appeared to be much lower. This report documents the striking differences between the continents and within the continent of Africa itself and then attempts to explain the reasons for these differences. It is hoped that information presented in this review will help policymakers in the fight to contain the pandemic, particularly within Africa with its resource-constrained health care systems.

A Systematic Review of Neurosurgical Care in Low-Income Countries.

OBJECTIVE: More than 5 billion individuals lack access to essential surgical care. Neurosurgical care is especially limited in low-income countries (LICs). Studies describing neurosurgical care in LICs are critical for understanding global disparities in access to neurosurgical procedures. To better understand these disparities, we conducted a systematic review of the literature identifying neurosurgical patients in LICs. METHODS: MEDLINE (PubMed), Embase (embase.com), and Cochrane Library (Wiley) databases were systematically searched to retrieve studies describing neurosurgical care in LICs as defined by the World Bank Country and Lending Groups income classification. All databases were searched from their inception; no date or language limits were applied. All the articles were blindly reviewed by 2 individuals. Data from eligible studies were extracted and summarized. RESULTS: Of the 4377 citations screened, 154 studies met inclusion criteria. The number of publications substantially increased over the study period, with 49% (n = 76) of studies published in the last 5 years. Twenty-six percent (n = 40) of studies had a first author, and 30% (n = 46) had a senior author, affiliated with a country different from the LIC of study. The most common neurosurgical diagnosis was traumatic brain injury (24%, n = 37), followed by hydrocephalus (26%, n = 40), and neoplastic intracranial mass (10%, n = 16). Of LICs, 43% (n = 15/35) had no published neurosurgical literature. CONCLUSIONS: There is a significant deficit in the literature on neurosurgical care in LICs. Efforts must focus on supporting research initiatives in LICs to improve publication bias and understand disparities in access to neurosurgical care in the lowest-resource countries.