Digital health and artificial intelligence (AI) are increasingly part of paediatric respiratory clinics, from home-based symptom monitoring and remote consultations to AI-supported test interpretation and large language model (LLM)-supported communication. These tools promise to capture real-world disease and treatment patterns, support self-management, and enhance clinical decisions. Yet for most of these tools, the paediatric evidence base remains limited and fragmented, and the clinical benefit observed in practice is often modest. What has emerged is that effectiveness depends less on the technology itself than on how it fits into the child–parent–clinician triad, on its usability in daily family life, and on its impact on clinical workflow and on equity. Paediatric datasets remain small, heterogeneous and developmental, making extrapolation from adult evidence risky. Over the next 3 years, progress is likely to consolidate rather than expand, with paediatric-specific validation, regulation and routine integration. Clinicians will play a central role: deciding what to adopt, what to question, and what to govern.
Artificial intelligence (AI) and procedure-linked digital health technologies are beginning to transform bronchoscopy across three interconnected domains. In terms of diagnostic accuracy, deep learning models applied to endobronchial ultrasound images and bronchoscopic videos can match or exceed human readers in differentiating benign from malignant lesions, although nearly all evidence remains at the level of test-accuracy metrics rather than clinical outcomes. In real-time navigation, AI-augmented fluoroscopy and tomosynthesis platforms represent the clearest example of clinically deployed AI that improves lesion localisation and diagnostic yield for peripheral pulmonary nodules, while camera-based localisation and shared-control robotic systems remain largely preclinical. In training, multiple randomised controlled trials demonstrate that AI-guided simulators significantly improve performance across experience levels, and that AI-derived metrics can objectively assess competence, although the first attempt to show impact on real-world clinical performance was inconclusive. This review synthesises the current literature across these three domains, distinguishing technologies that are currently used in clinical practice with supportive published evidence from those that remain investigational. It provides practising bronchoscopists and trainees with a balanced appraisal of what AI can realistically offer today, what limitations persist, and what developments are likely over the coming decade.
Social media has become an integral component of modern medical practice, with most healthcare professionals engaging with it in some capacity. Its use has been associated with enhanced knowledge dissemination, professional networking, and increased visibility of research and clinical expertise. For respiratory healthcare professionals, social media offers particular value in navigating rapidly evolving evidence, technological innovation, establishing international collaborations and ongoing public health challenges. This article summarises current evidence and provides practical guidance on how to use social media to amplify professional impact in respiratory medicine, both in a professional context and in clinical practice with patients. We discuss key definitions, opportunities and limitations, with a focus on responsible and effective use to support collaboration, education and patient engagement.
Point-of-care ultrasound (POCUS) is an increasingly utilised tool in pulmonary and critical care medicine, yet its effectiveness remains limited by operator dependency and the required cognitive demands of real-time image acquisition and interpretation. Artificial intelligence (AI) has emerged as a promising approach to augment POCUS by supporting image acquisition, interpretation and quantitative analysis. Given the rapid evolution of this field, clinicians must understand both the capabilities and limitations of AI-enabled POCUS. However, prior reviews have largely catalogued applications without focusing on how these tools integrate into bedside workflows. This narrative review examines AI in cardiopulmonary POCUS through a workflow-based lens relevant to pulmonologists and intensivists. We discuss the role of AI as a bedside coach, interpreter and quantifier, highlighting applications in lung and focused cardiac ultrasound, including pneumothorax detection, B-line analysis, left ventricular function assessment, and identification of other cardiopulmonary pathologies. Across domains, AI demonstrates strong performance in controlled settings, although variability persists in real-world environments due to differences in image quality, patient factors and dataset limitations. Future directions include interactive, clinician-in-the-loop systems, protocol-driven integration, and multimodal data synthesis. A clear understanding of these developments will be essential for clinicians as AI becomes increasingly embedded within bedside patient care.
