Asthma is a chronic inflammatory airway disease resulting in airflow obstruction, which in part can become irreversible to conventional therapies, defining the concept of airway remodeling. The introduction of biologics in severe asthma has led in some patients to the complete normalization of previously considered irreversible airflow obstruction. This highlights the need to distinguish a “fixed” airflow obstruction due to structural changes unresponsive to current therapies, from a “reversible” one as demonstrated by lung function normalization during biological therapies not previously obtained even with high‐dose systemic glucocorticoids. The mechanisms by which exposure to environmental factors initiates the inflammatory responses that trigger airway remodeling are still incompletely understood. Alarmins represent epithelial‐derived cytokines that initiate immunologic events leading to inflammatory airway remodeling. Biological therapies can improve airflow obstruction by addressing these airway inflammatory changes. In addition, biologics might prevent and possibly even revert “fixed” remodeling due to structural changes. Hence, it appears clinically important to separate the therapeutic effects (early and late) of biologics as a new paradigm to evaluate the effects of these drugs and future treatments on airway remodeling in severe asthma.

Introduction: Artificial intelligence (AI) and neuroimaging offer new opportunities for diagnosis and prognosis of dementia.Methods: We systematically reviewed studies reporting AI for neuroimaging in diagnosis and/or prognosis of cognitive neurodegenerative diseases.Results: A total of 255 studies were identified. Most studies relied on the Alzheimer's Disease Neuroimaging Initiative dataset. Algorithmic classifiers were the most commonly used AI method (48%) and discriminative models performed best for differentiating Alzheimer's disease from controls. The accuracy of algorithms varied with the patient cohort, imaging modalities, and stratifiers used. Few studies performed validation in an independent cohort.Discussion: The literature has several methodological limitations including lack of sufficient algorithm development descriptions and standard definitions. We make recommendations to improve model validation including addressing key clinical questions, providing sufficient description of AI methods and validating findings in independent datasets. Collaborative approaches between experts in AI and medicine will help achieve the promising potential of AI tools in practice.Highlights: There has been a rapid expansion in the use of machine learning for diagnosis and prognosis in neurodegenerative disease Most studies (71%) relied on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with no other individual dataset used more than five times There has been a recent rise in the use of more complex discriminative models (e.g., neural networks) that performed better than other classifiers for classification of AD vs healthy controls We make recommendations to address methodological considerations, addressing key clinical questions, and validation We also make recommendations for the field more broadly to standardize outcome measures, address gaps in the literature, and monitor sources of bias

Background: ChatGPT is a large language model that has performed well on professional examinations in the fields of medicine, law, and business. However, it is unclear how ChatGPT would perform on an examination assessing professionalism and situational judgement for doctors. Objective: We evaluated the performance of ChatGPT on the Situational Judgement Test (SJT): a national examination taken by all final-year medical students in the United Kingdom. This examination is designed to assess attributes such as communication, teamwork, patient safety, prioritization skills, professionalism, and ethics. Methods: All questions from the UK Foundation Programme Office’s (UKFPO’s) 2023 SJT practice examination were inputted into ChatGPT. For each question, ChatGPT’s answers and rationales were recorded and assessed on the basis of the official UK Foundation Programme Office scoring template. Questions were categorized into domains of Good Medical Practice on the basis of the domains referenced in the rationales provided in the scoring sheet. Questions without clear domain links were screened by reviewers and assigned one or multiple domains. ChatGPT's overall performance, as well as its performance across the domains of Good Medical Practice, was evaluated. Results: Overall, ChatGPT performed well, scoring 76% on the SJT but scoring full marks on only a few questions (9%), which may reflect possible flaws in ChatGPT’s situational judgement or inconsistencies in the reasoning across questions (or both) in the examination itself. ChatGPT demonstrated consistent performance across the 4 outlined domains in Good Medical Practice for doctors. Conclusions: Further research is needed to understand the potential applications of large language models, such as ChatGPT, in medical education for standardizing questions and providing consistent rationales for examinations assessing professionalism and ethics.

Asthma is one of the most common noncommunicable diseases; in the majority of patients it is well controlled with inhaled bronchodilators and inhaled corticosteroids, but the management of severe asthma has been a significant challenge historically. The introduction of novel biologic drugs in the past few decades has revolutionised the field, presenting physicians with a variety of biologic drugs with different mechanisms for the treatment of severe asthma.It is of crucial importance to evaluate the effectiveness of these drugs by following their “real-life” effectiveness rather than relying solely on their efficacy, established in carefully designed clinical trials, which therefore do not necessarily match the profile of the real-life patient. Understanding the actual effectiveness of the specific drugs in real-life patients is a crucial part of tailoring the right drugs to the right patients. Registries serve as an important tool in obtaining real-life evidence, since they are in effect observational studies, following the entire patient population.

Background and objectives: Neurological immune related adverse events (n-irAEs) reportedly occur in up to 8% of patients treated with immune-checkpoints inhibitors (ICI) of all age groups. We investigated the association between age and n-irAEs in patients treated with ICI, and examined the impact of n-irAEs on survival outcomes in a large cohort of melanoma patients. Methods: We conducted a retrospective analysis of advanced melanoma patients treated with ICI at Ella Institute for Immuno-oncology and Melanoma between 1/1/2015 and 20/04/2022. The outcomes of interest were defined as the investigation of age-related frequency and severity of n-irAE, the need for ICI interruption, the treatment required for n-irAE management, the safety of ICI reintroduction, and n-irAE’s impact on survival. Results: ICI was administered to 937 patients. At least one IrAE occurred in 73.5% (n=689) of them. Amongst the study population, 8% (n=76) developed a n-irAE, with a median age of 66 in females and 68 in males at onset. Median follow-up after n-irAE was 1,147 days (IQR: 1091.5 range: 3938). Fewer irAEs occurred in patients older than 70 years (median: 3 events, p=0.04, CI:2.5-4.7), while specifically colitis and pneumonitis were more common in the 18-60 age group (p=0.03 95% CI:0.8,0.38, p=0.009, 95% CI:0.06,0.2). Grade ≥ 3 toxicity was seen in 35.5% of patients across age groups. Median time from ICI administration to n-irAE development was 48 days across age groups. Common n-irAE phenotypes were myositis (44.7%), encephalitis (10.5%), and neuropathy (10.5%). N-irAE required hospitalization in 40% of patients, and steroids treatment in 46% with a median of 4 days from n-irAE diagnosis to steroids treatment initiation. Nine patients needed second-line immunosuppressive treatment. Rechallenge did not cause additional n-irAE in 71% of patients. Developing n-irAE (HR=0.4, 95% CI:0.32,0.77) or any irAE (HR=0.7195% CI:0.56,0.88) were associated with longer survival. Discussion: Neurological-irAEs are a relatively common complication of ICI (8% of our cohort). Older age was not associated with its development or severity, in contrast with non-neurological-irAE which occurred less frequently in the elderly. Rechallenge did not result in life-threatening AEs. Development of any irAE was associated with longer survival, this association was stronger with n-irAE.