Artificial Intelligence (AI) and Machine Learning (ML) are revolutionizing primary care by enhancing diagnostic accuracy, risk prediction, and treatment planning. Integrating clinical data, wearable device data, and Social Determinants of Health with AI/ML allows primary care physicians to uncover hidden patterns, improve outcomes, and address environmental health challenges. The synergy of AI, interdisciplinary learning, and Geographic Information Systems enables personalized interventions and optimized decision making. Clinicians must integrate AI/ML carefully into workflows, overcoming challenges like data interoperability and ensuring transparency. Collaboration is key to creating effective, ethical AI tools that improve health care equity and efficiency.

This article provides an overview of the current use of artificial intelligence (AI) in primary care and administrative medicine. It is divided into 2 main sections. In the first, we explore AI's use in screening, prevention, diagnosis, and treatment-what is already in use and what can be expected in the near future. In the second, we discuss AI's impact on medical administrative tasks and on the broader health care system-patient scheduling, progress notes, prior authorization, patient education, billing, fraud detection, remote health care delivery, and resource allocation and optimization.

Artificial intelligence (AI) is rapidly transforming many areas of life and health care is no exception. Medicine has long relied on the interpretation and analysis of large volumes of data to arrive at a correct diagnosis and to guide clinical decision-making. The modern application of AI has opened new ways for the clinician to treat patients including predictive analytics, improved medical imaging diagnostics and pathology reports, and it is already being utilized in many different medical specialties. Although there are limitations to what AI can provide in clinical decision-making, the future of this field is hopeful.

The integration of technology and artificial intelligence (AI) in clinical practice is rapidly transforming health care delivery. This article explores current AI tools and their applications in clinical settings, highlighting advancements in communication, patient education, clinical decision support, and more. As AI continues to evolve, its role in improving diagnostic accuracy and predictive analytics becomes increasingly significant.

Artificial intelligence (AI) can allow for a new era in patient management not only with the enhancement of decision-making through imaging and pathology interpretation but also through more personalized patient care and reduction in administrative burden. By incorporating previously underutilized genomic data and information from wearable technology, personalized medical care can be given on a scale previously inaccessible. Furthermore, using AI to address administrative burdens, such as intake forms, medical billing and coding, and assessing level of care, can allow for more time in direct patient care for the clinician.

Artificial intelligence (AI) has the capacity to improve patient care through increasing clinical decision-making accuracy and reducing administrative burdens for clinicians. However, AI poses challenges in medical ethics due to its opaque nature, potential for bias, and ties to large amounts of patient data. This article provides a general overview of medical AI ethics and legal regulations at the time of writing. It includes a description of prominent bioethics principles applied to AI, examines ethical challenges present in medical AI, reviews the current state of regulations regarding AI, and provides a list of recommendations for clinicians working with AI tools.

In this article, we will learn about addiction as a chronic disease with relapsing-remitting phases, we will explore screening approaches, diagnostic mechanism, and treatment options for addictive disorders and application of artificial intelligence (AI) in substance use disorder care. We will also learn about sport medicine fellowship and application of AI in sport medicine. The goals of Primary Care Sports Medicine Fellowships are to provide fellows with a strong sports medicine knowledge base, develop their clinical skills and decision-making, foster communication skills as they interact with trainers, athletes, coaches, and ancillary health personnel, and encourage a holistic view of athletes as "whole patients." Additionally, these fellowships promote exercise as medicine for all patients and help cultivate intellectual curiosity and scholarly activities. We will also dive into the current and future role that artificial intelligence (AI) will play in addiction medicine, sports medicine, and other primary care fellowship trainings.

In this article, we explore the transformative potential of artificial intelligence (AI) in medical education and continuing medical education. We discuss the rapid evolution of AI technology, particularly generative AI and large language models, and their implications for teaching and learning. We emphasize the importance of AI literacy, ethical considerations, and evidence-based approaches to integrating AI into medical education. We also highlight the evolving roles of educators and learners in the AI era, advocating for a proactive, collaborative approach to harness AI's potential to personalize learning, enhance clinical decision-making, and ultimately improve patient care.

Artificial intelligence (AI) is ready to transform primary care by enhancing clinical efficiency, supporting decision-making, and improving patient outcomes. This article explores the integration of AI into primary care, highlighting its potential benefits, such as automating administrative tasks, improving diagnostic accuracy, and enabling personalized care through advanced data analysis. Adopting AI also presents significant challenges including ethical concerns and risks to the provider-patient relationship. It is essential to involve primary care physicians in designing and overseeing AI tools. By addressing these challenges and leveraging AI responsibly, primary care can evolve into a more efficient, patient-centered, and equitable health care system.

AI is reshaping health care's fundamental architecture. This article maps 3 intersecting horizons-algorithms decoding biology at record speeds, ambient intelligence embedding predictive care into everyday life, and cognitive networks uniting global health care data into self-learning systems. Together, these advances amplify primary health care providers, accelerate treatments, and shift care toward prevention. Yet, this transformation comes tethered to risk-algorithmic bias, clinical hallucinations, cybersecurity vulnerabilities, and intensive resource demands. Realizing AI's full promise demands visionary leadership, interoperable and auditable models, AI-versed clinician-AI collaborations, and incentive models that prioritize health over interventions.

This article explores the foundations of artificial intelligence (AI) as it relates to the practice of medicine. Priming primary care providers (PCPs) with such technical knowledge is important since current research indicates that clinical AI tools should be built with PCPs participating as integral team members in the process. Physician input is essential to ensure safety, facilitate clinical usability, and to engender trust with providers and patients. This article examines some of the foundational concerns associated with AI's use in medicine and draws conclusions regarding the use of AI in medicine as we move toward an exciting and uncharted future.

Social Determinants of Health (SDoH) are some of the most impacting factors affecting health today, accounting for up to 80% of modifiable health outcomes. This article explores 4 challenges faced by primary care providers in their efforts to screen and intervene patients with suboptimal SDoH: SDoH knowledge limitations; SDoH screening challenges; failure to integrate protective factors; and technical challenges when AI is used to assist with SDoH screening and intervention. Finally, we provide a broad overview of AI's role in capturing and ameliorating deficient SDoH-all to reduce health disparities, improve health outcomes, help inform policymakers, and, foster thriving individuals and populations.

Psoriasis is a chronic, inflammatory skin disease with a significant impact on quality of life. Psoriasis affects about 3% of the US population. Psoriasis is caused by an interaction between genetic and environmental triggers. Lifestyle modification and topical therapies such as emollients, topical corticosteroids, vitamin D analogues, and calcineurin inhibitors are used for limited disease. More severe psoriasis may require systemic therapy with available oral or biologic therapy.

Atopic dermatitis and contact dermatitis are among the most common dermatologic conditions encountered by the primary care clinician. Their presentation varies and can mimic infectious and other noninfectious conditions, making a thorough history essential, with particular emphasis on exposure to environmental and occupational irritants, as well as recognition of commonly affected sites. For all of these conditions, control of symptoms is often the goal of treatment, starting with general supportive care measures like frequent emollient use and often relying on topical steroidal and nonsteroidal agents as first-line therapies.

Acne and related dermatoses encompass a spectrum of conditions that present at different stages in life and are commonly seen in the primary care setting. The primary care clinician should be familiar with the presentation, diagnosis, differentiation and management of acne, perioral dermatitis, rosacea, and hidradenitis suppurativa. Factors such as patient age, genetics, hormones, infections, occupation, habits, cosmetics, and medications may impact the presentation of acne-like eruptions. Clinical presentation offers clues to the physician that help differentiate acneiform conditions like perioral dermatitis, rosacea, and hidradenitis suppurativa. These conditions do not respond to standard acne therapy and require different treatment strategies.

Disorders of pigmentation encompass a wide range of conditions categorized into hyperpigmentation, hypopigmentation, and depigmentation, each with distinct etiologies, clinical presentations, and implications. This article outlines the pathophysiology, clinical features, diagnostic approaches, and management strategies for these pigmentary disorders for primary care physicians. Recognizing systemic associations and rare presentations is also essential for primary care physicians to diagnose and guide treatment or dermatologic referral.

Urticaria is a common dermatologic condition that affects about 20% of the population. It is caused by the release of histamines in response to a trigger. It is subdivided into acute urticaria and chronic urticaria (urticaria lasting more than 6 weeks). First-line treatment is second-generation H1-antihistamines and avoidance of known triggers. Long-term prevention also focuses on minimizing exposure to triggers including hot water, nonsteroidal anti-inflammatory drugs, tight clothing, and known allergens.