Jose Miguel Sequí-Sabater

Systemic sclerosis (SSc) is a rare autoimmune disease defined by immune dysregulation, vasculopathy, and progressive fibrosis of the skin and internal organs. Despite advances in care, major complications such as interstitial lung disease (ILD) and myocardial involvement remain the leading causes of morbidity and mortality. Current assessment tools, such as the modified Rodnan skin score, pulmonary function tests, and nailfold capillaroscopy, are limited by subjectivity and interobserver variability. Artificial intelligence (AI) is reshaping this landscape. Machine learning, deep learning, and radiomics have shown potential to enhance disease phenotyping, risk stratification, and imaging quantification in SSc. AI‐driven high‐resolution computed tomography analysis enables automated fibrosis segmentation and radiomic risk modeling in SSc‐ILD. Computer vision approaches applied to nailfold capillaroscopy achieve expert‐level agreement for microvascular staging, whereas emerging digital tools aim to quantify Raynaud phenomenon dynamics. In skin disease, AI‐assisted ultrasonography, optical imaging, and histopathology provide reproducible quantification of dermal remodeling. However, most applications remain exploratory, based on small or single‐center data sets with limited external validation. Challenges such as data heterogeneity, annotation burden, and the “small data” constraints of rare diseases limit immediate clinical translation. This narrative review critically examines current AI applications in SSc, highlighting methodologic limitations, translational readiness, and future directions toward robust, multicenter, and ethically governed implementation. image

Background: Evoked otoacoustic emissions are one of the most widely employed techniques in assessing neonatal hearing. However, several factors may influence the outcomes of this test. One such factor is gender, as previous research has shown that females tend to exhibit a greater otoacoustic response than males. Aim: This study evaluates whether gender influences the pass rate of the otoacoustic emissions test in neonatal hearing screening, using data from both the general population and twin pairs. Methods: Data from the Newborn Hearing Screening (NHS) program and infant gender were collected between 2002 and 2023 from 22,825 healthy newborns in the maternity or neonatal ward. Of these, 586 cases were from twin pregnancies. A separate analysis was conducted for twins, distinguishing between same-sex and opposite-sex pairs. Results: A highly significant difference (p<0.0001) in NHS pass rates was observed in favor of females, who demonstrated better responses to the test. In the twin subgroup, analysis of the 112 discordant-sex pairs with differing test outcomes revealed a statistically significant result (p<0.023), further supporting the positive effect of female sex on successfully passing the hearing screening test. Conclusion: Female newborns exhibit stronger otoacoustic emission responses and higher pass rates in the NHS test compared to male newborns. These gender-based variations in otoacoustic emission responses may have important implications for the NHS, as otoacoustic emissions are a commonly used screening tool in neonatal hearing assessment. Relevance for patients: Recognizing and accounting for these gender-based differences in otoacoustic emission responses may inform modifications to screening program protocols, potentially improving the identification of hearing impairment in newborns.

Artificial intelligence (AI) is transforming rheumatology research, with a myriad of studies aiming to improve diagnosis, prognosis and treatment prediction, while also showing potential capability to optimise the research workflow, improve drug discovery and clinical trials. Machine learning, a key element of discriminative AI, has demonstrated the ability of accurately classifying rheumatic diseases and predicting therapeutic outcomes by using diverse data types, including structured databases, imaging and text. In parallel, generative AI, driven by large language models, is becoming a powerful tool for optimising the research workflow by supporting with content generation, literature review automation and clinical decision support. This review explores the current applications and future potential of both discriminative and generative AI in rheumatology. It also highlights the challenges posed by these technologies, such as ethical concerns and the need for rigorous validation and regulatory oversight. The integration of AI in rheumatology promises substantial advancements but requires a balanced approach to optimise benefits and minimise potential possible downsides.

Second-level hospitals face peculiarities that hinder the implementation of the hearing rescreening protocol, which are not uncommon in other settings. This study analyzes the hearing rescreening process in this kind of hospital. A total of 1130 individuals were included. In this cohort, 61.07% were newborns in the hospital who failed their first otoemission test after birth (n=679) or were unable to have the test performed (n=11), then being referred to outpatient clinic. The remaining 38.93% were individuals who were born in another hospital with their first test conducted in the outpatient clinic (n=440). A high amount of rescreenings were made outside the recommended time frame, mainly in children referred from another hospital. There was a high rate of lost to follow-up especially with otolaryngologist referrals. Neonatal Hearing screening in second level hospitals is difficult because of the staffing and time constraints. This results in longer than recommended turnaround times and interferes with the timely detection of hearing loss. This is particularly serious in outpatients. Referral of children with impaired screening to out-of-town centers leads to unacceptable loss of follow-up. A legislative support for all these rescreening issues is necessary. We discuss these findings and propose some solutions.

Excessive noise pollution is often a problem for neonatal nurseries. Noise pollution involves not only noise but also vibrations. The main difference between them is that noise can be heard, and vibrations are felt. The human ear cannot detect waves outside the range of 20 Hz–20 KHz. Waves from 0 Hz to 80–100 Hz should be considered vibrations. Both can be transmitted to the neonate through the incubator’s operational mechanisms and other noise sources. Neonatal units’ noise is well studied but very little is known about vibration. This entry focuses on the importance of vibrations reaching the inside of incubators in neonatal nurseries.

Sjögren’s syndrome is one of the most prevalent autoimmune diseases after rheumatoid arthritis, with a preference for middle age, and is characterised by exocrine glandular involvement leading to xerostomia and xerophthalmia. It can have systemic implications with vascular, neurological, renal, and pulmonary involvement, and in some cases, it may evolve to non-Hodgkin’s lymphoma. For a long time, B- and T-lymphocytes have been the focus of research and have been considered key players in Sjögren’s syndrome pathogenesis and evolution. With the development of new technologies, including omics, more insights have been found on the different signalling pathways that lead to inflammation and activation of the immune system. New evidence indicates that a third actor linking innate and adaptive immunity plays a leading role in the Sjögren’s syndrome play: the monocyte. This review summarises the recent insights from transcriptomic, proteomic, and epigenetic studies that help us to understand more about the Sjögren’s syndrome pathophysiology and redefine the involvement of monocytes in this disease.