Comparing artificial intelligence to humans for endoscopic diagnosis of gastric neoplasia: An external validation study.

OBJECTIVES: Artificial intelligence (AI) uses deep learning functionalities that may enhance the detection of early gastric cancer during endoscopy. An AI-based endoscopic system for upper endoscopy was recently developed in Japan. We aim to validate this AI-based system in a Singaporean cohort. METHODS: There were 300 de-identified still images prepared from endoscopy video files obtained from subjects that underwent gastroscopy in National University Hospital (NUH). Five specialists and 6 non-specialists (trainees) from NUH were assigned to read and categorize the images into "neoplastic" or "non-neoplastic." Results were then compared with the readings performed by the endoscopic AI system. RESULTS: The mean accuracy, sensitivity, and specificity for the 11 endoscopists were 0.847, 0.525, and 0.872, respectively. These values for the AI-based system were 0.777, 0.591, and 0.791, respectively. While AI in general did not perform better than endoscopists on the whole, in the subgroup of high-grade dysplastic lesions, only 29.1% were picked up by the endoscopist rating, but 80% were classified as neoplastic by AI (P = 0.0011). The average diagnostic time was also faster in AI compared with endoscopists (677.1 s vs 42.02 s (P < 0.001). CONCLUSION: We demonstrated that an AI system developed in another health system was comparable in diagnostic accuracy in the evaluation of static images. AI systems are faster and not fatigable and may have a role in augmenting human diagnosis during endoscopy. With more advances in AI and larger studies to support its efficacy it would likely play a larger role in screening endoscopy in future.

Gender differences in bronchiectasis: a real issue?

Gender differences in chronic respiratory disease, including cystic fibrosis and non-cystic fibrosis bronchiectasis are clinically apparent and of increasing importance. Differences in disease prevalence, severity and outcome are all described, however, the precise cause of the gender dichotomy and their associated underlying mechanisms have been poorly characterised. A lack of dedicated clinical and epidemiological research focused in this area has led to a paucity of data and therefore a lack of understanding of its key drivers. Diagnosis, disease pathogenesis and treatment response are all complex but important aspects of bronchiectasis with an evident gender bias. Broadening our understanding of the interplay between microbiology, host physiology and the environment in the context of chronic lung diseases, such as bronchiectasis, is critical to unravelling mechanisms driving the observed gender differences. In this review, epidemiological, biological and environmental evidence related to gender in bronchiectasis is summarised. This illustrates gender differences as a "real issue" with the objective of mapping out a future framework upon which a gender-tailored medical approach may be incorporated into the diagnosis, monitoring and treatment of bronchiectasis. KEY POINTS: CF and non-CF bronchiectasis are complex, multifactorial chronic pulmonary diseases with gender-specific differences in their prevalence, clinical presentation and disease severity.Microbiology and host physiology (immune and inflammatory responses) are essential aspects of bronchiectasis that are influenced by gender.Sex steroid hormones vary in type, fluctuating pattern and concentration throughout life and between the genders with a potential central role in bronchiectasis-related gender differences.Gender-focused clinical and/or therapeutic intervention has the potential to narrow the observed gender gap occurring in bronchiectasis-related lung disease. EDUCATIONAL AIMS: To summarise the existing knowledge base of gender-related differences in CF and non-CF bronchiectasis.To highlight key areas of importance in the diagnosis, monitoring and treatment of bronchiectasis that is amenable to clinical and/or pharmacological intervention to narrow the existing "gender gap".

The Microbial Endocrinology of Pseudomonas aeruginosa: Inflammatory and Immune Perspectives.

Pseudomonas aeruginosa is a major pathogen responsible for both acute and chronic infection. Known as a colonising pathogen of the cystic fibrosis (CF) lung, it is implicated in other settings such as bronchiectasis. It has the ability to cause acute disseminated or localised infection particularly in the immunocompromised. Human hormones have been highlighted as potential regulators of bacterial virulence through crosstalk between analogous "quorum sensing" (QS) systems present in the bacteria that respond to mammalian hormones. Pseudomonas aeruginosa is known to utilise interconnected QS systems to coordinate its virulence and evade various aspects of the host immune system activated in response to infection. Several human hormones demonstrate an influence on P. aeruginosa growth and virulence. This inter-kingdom signalling, termed "microbial endocrinology" has important implications for host-microbe interaction during infection and, potentially opens up novel avenues for therapeutic intervention. This phenomenon, supported by the existence of sexual dichotomies in both microbial infection and chronic lung diseases such as CF is potentially explained by sex hormones and their influence on the infective process. This review summarises our current understanding of the microbial endocrinology of P. aeruginosa, including its endogenous QS systems and their intersection with human endocrinology, pathogenesis of infection and the host immune system.