Collaborative large language models for automated data extraction in living systematic reviews.

Objective: Data extraction from the published literature is the most laborious step in conducting living systematic reviews (LSRs). We aim to build a generalizable, automated data extraction workflow leveraging large language models (LLMs) that mimics the real-world 2-reviewer process.

Materials And Methods: A dataset of 10 trials (22 publications) from a published LSR was used, focusing on 23 variables related to trial, population, and outcomes data.

Preventing unrestricted and unmonitored AI experimentation in healthcare through transparency and accountability.

The integration of large language models (LLMs) into electronic health records offers potential benefits but raises significant ethical, legal, and operational concerns, including unconsented data use, lack of governance, and AI-related malpractice accountability. Sycophancy, feedback loop bias, and data reuse risk amplifying errors without proper oversight. To safeguard patients, especially the vulnerable, clinicians must advocate for patient-centered education, ethical practices, and robust oversight to prevent harm.

Uncertainty estimation in diagnosis generation from large language models: next-word probability is not pre-test probability.

Objective: To evaluate large language models (LLMs) for pre-test diagnostic probability estimation and compare their uncertainty estimation performance with a traditional machine learning classifier.

Materials And Methods: We assessed 2 instruction-tuned LLMs, Mistral-7B-Instruct and Llama3-70B-chat-hf, on predicting binary outcomes for Sepsis, Arrhythmia, and Congestive Heart Failure (CHF) using electronic health record (EHR) data from 660 patients. Three uncertainty estimation methods-Verbalized Confidence, Token Logits, and LLM Embedding+XGB-were compared against an eXtreme Gradient Boosting (XGB) classifier trained on raw EHR data.

The TRIPOD-LLM reporting guideline for studies using large language models.

Large language models (LLMs) are rapidly being adopted in healthcare, necessitating standardized reporting guidelines. We present transparent reporting of a multivariable model for individual prognosis or diagnosis (TRIPOD)-LLM, an extension of the TRIPOD + artificial intelligence statement, addressing the unique challenges of LLMs in biomedical applications. TRIPOD-LLM provides a comprehensive checklist of 19 main items and 50 subitems, covering key aspects from title to discussion.

Gender, Racial, and Fitzpatrick Skin Type Representation in Melasma Clinical Trials.

Melasma, a symmetric pigmentary disorder, is more prevalent in women and individuals with darker skin tones. Despite its global prevalence, there is a notable gap in the understanding of gender, racial, and Fitzpatrick skin type (FST) representation in melasma clinical trials. We conducted a comprehensive search of the United States (US) National Library of Medicine clinical trials database (ClinicalTrials.

A community-based analysis of security practices regarding over-the-counter skincare products in nationwide retail drug stores.

Access to over-the-counter (OTC) skincare products is critical for managing a wide range of dermatologic conditions, yet recent trends in urban retail stores may jeopardize this accessibility and exacerbate healthcare disparities. However, the emerging trend of securing skincare products behind security glass in urban retail environments poses significant risks to healthcare equity and accessibility. Herein, we aim to quantify the prevalence of skincare products behind security glass in pharmacies within a 25-mile radius of Times Square, New York City.

LCD benchmark: long clinical document benchmark on mortality prediction for language models.

Objectives: The application of natural language processing (NLP) in the clinical domain is important due to the rich unstructured information in clinical documents, which often remains inaccessible in structured data. When applying NLP methods to a certain domain, the role of benchmark datasets is crucial as benchmark datasets not only guide the selection of best-performing models but also enable the assessment of the reliability of the generated outputs. Despite the recent availability of language models capable of longer context, benchmark datasets targeting long clinical document classification tasks are absent.

Artificial intelligence research in radiation oncology: a practical guide for the clinician on concepts and methods.

The use of artificial intelligence (AI) holds great promise for radiation oncology, with many applications being reported in the literature, including some of which are already in clinical use. These are mainly in areas where AI provides benefits in efficiency (such as automatic segmentation and treatment planning). Prediction models that directly impact patient decision-making are far less mature in terms of their application in clinical practice.

The potential cutaneous benefits of bentonites and montmorillonites.

Bentonites and montmorillonites, natural clay minerals originating from volcanic ash, possess unique properties that have traditionally been utilized in industrial applications. Recently, their potential biomedical applications, particularly in dermatology, have garnered significant interest. This review explores the cutaneous benefits of bentonites and montmorillonites, highlighting their anti-inflammatory, wound-healing, oil-absorbing, drug delivery, photoprotective, and anti-aging effects.

Collaborative Large Language Models for Automated Data Extraction in Living Systematic Reviews.

Objective: Data extraction from the published literature is the most laborious step in conducting living systematic reviews (LSRs). We aim to build a generalizable, automated data extraction workflow leveraging large language models (LLMs) that mimics the real-world two-reviewer process.

Materials And Methods: A dataset of 10 clinical trials (22 publications) from a published LSR was used, focusing on 23 variables related to trial, population, and outcomes data.

The role of IL-17 and Th17 cells in keloid pathogenesis.

Keloids are characterized histologically by excessive fibroblast proliferation and connective tissue deposition, and clinically by scar tissue extending beyond the original site of skin injury. These scars can cause pruritus, pain, physical disfigurement, anxiety, and depression. As a result, keloid patients often have a diminished quality of life with a disproportionate burden on ethnic minorities.

Ethical debates amidst flawed healthcare artificial intelligence metrics.

Healthcare AI faces an ethical dilemma between selective and equitable deployment, exacerbated by flawed performance metrics. These metrics inadequately capture real-world complexities and biases, leading to premature assertions of effectiveness. Improved evaluation practices, including continuous monitoring and silent evaluation periods, are crucial.

Systematic review of dupilumab safety and efficacy for treatment of keloid scars.

Keloids, characterized by excessive scar formation following dermal inflammation, pose a therapeutic challenge due to high recurrence rates. Radiation therapy, contraindicated in children, can minimize recurrence post-surgical removal. Dupilumab, which inhibits the pro-fibrotic interleukin-4/interleukin-13 axis, may effectively manage keloids when intralesional corticosteroid injections are unsuccessful.

Outstanding user reported satisfaction for light emitting diodes under-eye rejuvenation.

The under-eye region is an area of significant cosmetic concern. Photobiomodulation (PBM) has emerged as an effective, safe, inexpensive, and convenient treatment for skin rejuvenation. Herein, we aim to evaluate the safety and efficacy of a LED under-eye device for under-eye rejuvenation, as measured by objective and patient reported outcomes.

Investigating the Relationship Between Acne and Vasodilatory Medications in a Hospital-Wide Adult Population.

Acne vulgaris is a common chronic dermatological condition characterized by obstruction and inflammation of pilosebaceous units. Recent research on a different dermatologic condition has demonstrated that the use of vasodilatory medications is associated with a decreased relative risk of rosacea. This finding is significant due to the overlapping inflammatory pathways involved in rosacea and acne.

Sunscreen Practices and Preferences of Skin of Color Patients.

Sunscreen is an essential way to protect against photodamage from ultraviolet (UV) radiation. Despite the recognized benefits of sunscreen in preventing skin damage from UV light, its use varies across different patient groups. This cross-sectional, questionnaire-based study aims to uncover the sunscreen usage patterns, preferences, and barriers among non-Hispanic White (NHW) and skin of color (SOC) individuals.

Navigating the Complexities of Artificial Intelligence-Enabled Real-World Data Collection for Oncology Pharmacovigilance.

This new editorial discusses the promise and challenges of successful integration of natural language processing methods into electronic health records for timely, robust, and fair oncology pharmacovigilance.

LCD Benchmark: Long Clinical Document Benchmark on Mortality Prediction for Language Models.

Objective: The application of Natural Language Processing (NLP) in the clinical domain is important due to the rich unstructured information in clinical documents, which often remains inaccessible in structured data. When applying NLP methods to a certain domain, the role of benchmark datasets is crucial as benchmark datasets not only guide the selection of best-performing models but also enable the assessment of the reliability of the generated outputs. Despite the recent availability of language models (LMs) capable of longer context, benchmark datasets targeting long clinical document classification tasks are absent.

Systematic review of randomized controlled trials of topicals for actinic keratosis field therapy.

Cutaneous field cancerization in dermatology describes the anatomic region of photodamaged skin with actinic keratoses (AKs) or cutaneous squamous cell carcinoma (cSCC) that is surrounded by cellular atypia, forming a dysplastic field. The concept of field cancerization is especially relevant in dermatology, as actinic keratoses and the surrounding dysplastic region can progress to carcinomas, necessitating the treatment of the field. Recent research has focused on field-directed therapy using topical agents.