Background: Health care practitioners use clinical decision support systems (CDSS) as an aid in the crucial task of clinical reasoning and decision-making. Traditional CDSS are online repositories (ORs) and clinical practice guidelines (CPG). Recently, large language models (LLMs) such as ChatGPT have emerged as potential alternatives. They have proven to be powerful, innovative tools, yet they are not devoid of worrisome risks. Objective: This study aims to explore how medical students perform in an evaluated clinical case through the use of different CDSS tools. Methods: The authors randomly divided medical students into 3 groups, CPG, n=6 (38%); OR, n=5 (31%); and ChatGPT, n=5 (31%); and assigned each group a different type of CDSS for guidance in answering prespecified questions, assessing how students’ speed and ability at resolving the same clinical case varied accordingly. External reviewers evaluated all answers based on accuracy and completeness metrics (score: 1‐5). The authors analyzed and categorized group scores according to the skill investigated: differential diagnosis, diagnostic workup, and clinical decision-making. Results: Answering time showed a trend for the ChatGPT group to be the fastest. The mean scores for completeness were as follows: CPG 4.0, OR 3.7, and ChatGPT 3.8 ( P =.49). The mean scores for accuracy were as follows: CPG 4.0, OR 3.3, and ChatGPT 3.7 ( P =.02). Aggregating scores according to the 3 students’ skill domains, trends in differences among the groups emerge more clearly, with the CPG group that performed best in nearly all domains and maintained almost perfect alignment between its completeness and accuracy. Conclusions: This hands-on session provided valuable insights into the potential perks and associated pitfalls of LLMs in medical education and practice. It suggested the critical need to include teachings in medical degree courses on how to properly take advantage of LLMs, as the potential for misuse is evident and real.

Purpose: To describe a case of rubella retinopathy complicated by bilateral choroidal neovascularization (CNV) and late development of large choroidal excavation (LCE). Methods: A 19-year-old woman with a diagnosis of rubella retinopathy underwent her annual ophthalmologic examination, including visual acuity testing and slit-lamp biomicroscopy with dilated fundus examination. Color fundus photography, spectral-domain optical coherence tomography (SD-OCT) scans, and optical coherence tomography angiography were acquired to complete the investigation of her ocular condition. The main findings are described in this case report. Results: This woman came to our attention in 2010 with a history of rubella retinopathy, complicated by bilateral CNV and treated with photodynamic therapy (PDT) in 2006. After 6 years of annual follow-up examinations, her visual acuity remained stable in both eyes (20/100), whereas SD-OCT scans uncovered the development of a bilateral LCE in the macular area, associated with a macular hole in the right eye. Optical coherence tomography angiography revealed a vascular network surrounding the choroidal excavation. Conclusions: Large choroidal excavation is a rare finding that has been described in few chorioretinal diseases, e.g., North Carolina macular dystrophy and toxoplasmosis. We propose to include rubella retinopathy complicated by CNV in the differential diagnosis of LCE, although we recognize the possibility that PDT might have induced or facilitated its formation.

Background: To date, performance comparisons between men and machines have been carried out in many health domains. Yet machine learning (ML) models and human performance comparisons in audio-based respiratory diagnosis remain largely unexplored. Objective: The primary objective of this study was to compare human clinicians and an ML model in predicting COVID-19 from respiratory sound recordings. Methods: In this study, we compared human clinicians and an ML model in predicting COVID-19 from respiratory sound recordings. Prediction performance on 24 audio samples (12 tested positive) made by 36 clinicians with experience in treating COVID-19 or other respiratory illnesses was compared with predictions made by an ML model trained on 1162 samples. Each sample consisted of voice, cough, and breathing sound recordings from 1 subject, and the length of each sample was around 20 seconds. We also investigated whether combining the predictions of the model and human experts could further enhance the performance in terms of both accuracy and confidence. Results: The ML model outperformed the clinicians, yielding a sensitivity of 0.75 and a specificity of 0.83, whereas the best performance achieved by the clinicians was 0.67 in terms of sensitivity and 0.75 in terms of specificity. Integrating the clinicians’ and the model’s predictions, however, could enhance performance further, achieving a sensitivity of 0.83 and a specificity of 0.92. Conclusions: Our findings suggest that the clinicians and the ML model could make better clinical decisions via a cooperative approach and achieve higher confidence in audio-based respiratory diagnosis.

Artificial Intelligence (AI) represents an innovative technological support for clinical practice. The Italian Society of Internal Medicine (SIMI) emphasizes the need for clear guidance on the use of AI in medicine, recognizing that knowledge in this field is continuously evolving. This position paper presents a comprehensive vision for the responsible integration of AI into clinical practice. AI should serve as a support tool—not a replacement—for clinicians. It has the potential to improve diagnostic accuracy, reduce administrative workload, and strengthen the physician–patient relationship. In the light of these characteristics, SIMI advocates for transparency, data privacy, equity, and sustainability in the development and implementation of AI systems. SIMI also highlights several ethical, legal, and methodological challenges that must be addressed, including algorithmic bias, environmental impact, and disparities in access. Ultimately, SIMI envisions a future in which AI augments human expertise, enabling more efficient, personalized, and compassionate care. SIMI calls for active clinician participation in the co-design and validation of AI tools to ensure alignment with real-world clinical needs. Key recommendations include the preferential use of certified AI systems, the integration of AI education into medical training, and continuous monitoring after deployment.

Air pollution remains one of the leading environmental determinants of health, yet the short-term effects of fine particulate matter (PM₂.₅) on early respiratory symptoms are poorly characterized owing to the limited availability of high-resolution, population-scale data. Enabled by global mobile sensing through a widely used application (Sleep Cycle) and AI algorithms that automatically detect coughs from nocturnal audio recordings, we derived nighttime cough frequency across 34 cities in 12 countries on five continents over 500 consecutive days, conducting the first multi-city assessment linking daily PM₂.₅ exposure to nocturnal respiratory symptoms. Single-city generalized additive models, multi-city panel regressions adjusting for meteorological variables and influenza rates, and quasi-experimental analyses consistently showed that same-day PM₂.₅ exposure was associated with higher cough frequency (relative risk = 1.004, 95% CI 1.001–1.008 per 10 μg/m³), with amplified effects during influenza peaks. The exposure–response curve was monotonic but nonlinear, with measurable risks evident even below the World Health Organization 24-hour guideline (15 μg/m³) and sharply increasing risks above 50 μg/m³. These findings provide real-world, population-level, multi-city evidence of acute respiratory effects from short-term PM₂.₅ exposure, reveal the absence of a safe threshold, and underscore the urgency of stringent air-quality interventions to protect respiratory health. This study also demonstrates how large-scale, AI-based mobile sensing can transform real-time environmental epidemiology by enabling population-level monitoring of early respiratory symptoms worldwide.

Background: Machine Learning (ML) applied to healthcare Real World Data (RWD) may improve patient management. RWD, however, requires extensive preprocessing to make it ML-ready. Our aim was to explore the impact of preprocessing on ML models applied to RWD from 20 years of type 2 diabetes patients visits. Methods: Our cohort consisted of patients with at least two glycated hemoglobin (HbA1c) measurements three years apart. We set up three different experimental settings consisting of different data preprocessing pipelines. Logistic Regression (LR), XGBoost and a Decision Tree Classifier (DTC) were then applied and tuned to optimize precision. Results: The final dataset comprised 12 variables from 1,651 patients treated between 2003 and 2023. 921 (56%) patients had a HbA1c decrease at three years. This group had a higher baseline HbA1c, higher BMI and shorter first visit gap from the date of diagnosis ( p < 0.0001). Precision scores for LR, XGBoost did not vary across different experimental conditions while DTC benefitted from missing data imputation. Shapley Additive Explanations confirmed the Exploratory Data Analysis findings, with worse baseline values being predictors of HbA1c decrease at three years. Conclusions: ML models' performance and their explanation did not vary substantially across experimental conditions, with worse baseline values being predictors of HbA1c decrease at three years. Insights such as this, extracted by ML application to RWD, enable clinical discussion and may foster improvements in patient management.