Jessica Andrade-Silva

Refractive errors are a leading cause of visual impairment, with substantial economic impact. Digital refraction systems may help improve access to eye care, especially for underserved populations. Considering their relevance, this study evaluated the Apollo™, a novel web-based system for self-assessed refractive error measurement, in estimating spherical equivalent (SEQ) compared to manifest refraction (also known as dry refraction or dynamic refraction) performed by experienced ophthalmologists. A prospective, single-center, single-blind, non-randomized study was conducted with 63 eyes of 64 healthy adults aged 18–40 years. Each participant underwent both manifest subjective refraction and digital refraction using Apollo™. Exclusion criteria included astigmatism exceeding 3.00 diopters (D) in absolute value and SEQ beyond − 4.00 D to + 4.00 D. Primary outcome was the comparison of SEQ between methods. No significant difference was observed between SEQ from Apollo™ (mean − 1.20 ± 1.11 D) and manifest refraction (mean − 1.17 ± 1.14 D; p = 0.67). Bland-Altman analysis showed a bias of 0.03 ± 0.90 D, with 95% limits of agreement (LOA) from − 1.73 to 1.78 D. LOA was narrower in myopic SEQ stratum (-1.48 to 1.35D). The ICC for the total sample SEQ was 0.69 (95% CI: 0.52–0.79), and for the myopic SEQ subgroup was 0.74 (95% CI: 0.58–0.84), indicating moderate to good reliability. The accuracy for detecting the sign of SEQ was 82.5% in the overall cohort and 96.2% in the myopic subgroup. Regression analysis revealed a proportional bias, with the system tending to underestimate refractive error as the magnitude of myopia increases (β = −0.27, p = 0.005). In conclusion, Apollo™ demonstrates moderate-to-good reliability and high diagnostic accuracy (96%) in categorizing refractive status among myopes. These results highlight its potential as a valuable digital screening tool, warranting further large-scale studies to refine its predictive algorithm.

Despite its promising potential to transform medical care, particularly in the field of medical images, the integration of artificial intelligence (AI) into clinical practice remains a complex and multifaceted challenge. In real-world settings, AI tools may demonstrate limited clinical impact, suboptimal performance, and security vulnerabilities, and face regulatory constraints. This viewpoint explores how the principles of design thinking can provide a structured road map for AI implementation in radiology. By emphasizing user-centeredness, fostering multidisciplinary collaboration, and embedding iterative refinement, this approach offers practical guidance for identifying clinical and operational needs, selecting and validating appropriate solutions, and ensuring effective deployment with continuous improvement.

UNSTRUCTURED Despite its promising potential to transform medical care, particularly in the field of medical image, the integration of artificial intelligence (AI) into clinical practice remains a complex and multifaceted challenge. In real-world settings, AI tools may demonstrate limited clinical impact, suboptimal performance, security vulnerabilities, and face regulatory constraints. This article explores how the principles of design thinking can provide a structured roadmap for AI implementation in radiology. By emphasizing user-centeredness, fostering multidisciplinary collaboration, and embedding iterative refinement, this approach offers practical guidance for identifying clinical and operational needs, selecting and validating appropriate solutions, and ensuring effective deployment with continuous improvement.

Background: Nurses face an escalating workload, including tasks not directly related to patient care, such as responding to patients' requests for water or extra blankets, and adjusting room conditions like air conditioning, which can contribute to burnout and pose potential risks for both professionals and patients. Purpose: We aimed to evaluate an artificial intelligence (AI)–driven technology that automates patient requests and directs them to the appropriate teams in other departments instead of to the nurses' station, thereby eliminating the need for nursing intervention. Methods: This retrospective observational study, conducted in the surgical clinic of a large hospital over 30 days, examined data gathered from patients occupying 16 beds (as our focus was on the volume and type of patient requests generated per bed rather than per patient, patient turnover did not affect the study). During this period, the AI-driven platform, known as Neonpass Room, was implemented in addition to the traditional bell-activation request system. Results: During the 30-day implementation of Neonpass Room, 2,113 requests were recorded, mostly from patients, and the AI-powered system directed 35.4% of those requests, which required clinical attention, to the nursing staff. The remaining requests were routed to other appropriate teams, such as housekeeping or maintenance, according to the nature of the requests. Among the top 10 most frequent request types, only two were explicitly directed to the nursing team: “check IV fluids” and “support with restroom use.” The AI platform also measured the response times among the various departments (the nursing team had the shortest response time and the cleaning staff the longest) and enabled the visualization of patterns in patient-initiated requests by request type over a 24-hour period. The AI solution effectively reduced the nursing team's workload by nearly three out of five patient requests, resulting in considerable time savings for nurses. Conclusion: Neonpass Room allowed the nursing staff to improve their focus on patient care by optimizing task delegation. Once integrated into the hospital's operations, an AI-driven platform like Neonpass Room would provide managers with valuable strategic insights into the allocation of hospital services.

The human microbiome plays a pivotal role in influencing various physiological processes and maintaining overall well-being, including the gastric system. Current diagnostic tests for gastric diseases often involve invasive procedures, sampling limitations, and medication effects, leading to potential diagnostic errors and discomfort to patients. Considering the connection between oral and gastric microbiomes, this cross-sectional study aimed to assess the diagnostic potential of the oral bacterial profile in patients undergoing upper digestive endoscopy. Oral samples from 266 participants across two Brazilian sites (Belterra and Sao Paulo) were sequenced and subjected to bioinformatic analysis to identify microbiome composition across endoscopy outcome groups, exploring alpha and beta-diversity, richness, and differential abundance and prevalence. Prevotella, Haemophilus, Fusobacterium, Neisseria, and Streptococcus were the most abundant genera observed. No significant associations were found between alpha diversity profiles and endoscopy outcomes; beta diversity analyses similarly showed no correlations. Overall, the study did not establish the oral microbiome as a reliable marker for gastric health, underscoring the necessity for broader studies in the development of non-invasive diagnostic tests.

Introduction: Melatonin is a pineal hormone that has acquired several unique modes of regulating the physiological effects in mammals due to its characteristic phylogenetic history. While melatonin exhibits immediate nocturnal effects, it also has next-day prospective effects that take place in the absence of this hormone. Besides that, the daily repetition and the annual variation in the duration of its synthesis determine its circadian and seasonal effects that characterize melatonin as a chronobiotic, a molecule that encodes time to the internal environment. Additionally, it presents transgenerational effects that are important for fetal programming, leading to a balanced energy metabolism in the adult life. Areas covered: Physiology, pathophysiology and therapeutic value of melatonin in metabolism and metabolic disorders. Expert opinion: The typical mechanisms of action of melatonin (immediate, prospective, chronobiotic and transgenerational) should be considered to adequately understand its physiological effects on the regulation of metabolism in humans and, as a result, to understand the metabolic pathophysiological consequences caused by its synthesis and/or signaling disturbances. That points to the importance of a broader understanding of melatonin actions, besides the classical endocrinological point of view, that would allow the clinician/research to proper interpret its role in health maintenance.