Artificial Intelligence and Colposcopy: Automatic Identification of Vaginal Squamous Cell Carcinoma Precursors.

Background/Objectives: While human papillomavirus (HPV) is well known for its role in cervical cancer, it also affects vaginal cancers. Although colposcopy offers a comprehensive examination of the female genital tract, its diagnostic accuracy remains suboptimal. Integrating artificial intelligence (AI) could enhance the cost-effectiveness of colposcopy, but no AI models specifically differentiate low-grade (LSILs) and high-grade (HSILs) squamous intraepithelial lesions in the vagina. This study aims to develop and validate an AI model for the differentiation of HPV-associated dysplastic lesions in this region. Methods: A convolutional neural network (CNN) model was developed to differentiate HSILs from LSILs in vaginoscopy (during colposcopy) still images. The AI model was developed on a dataset of 57,250 frames (90% training/validation [including a 5-fold cross-validation] and 10% testing) obtained from 71 procedures. The model was evaluated based on its sensitivity, specificity, accuracy and area under the receiver operating curve (AUROC). Results: For HSIL/LSIL differentiation in the vagina, during the training/validation phase, the CNN demonstrated a mean sensitivity, specificity and accuracy of 98.7% (IC95% 96.7-100.0%), 99.1% (IC95% 98.1-100.0%), and 98.9% (IC95% 97.9-99.8%), respectively. The mean AUROC was 0.990 ± 0.004. During testing phase, the sensitivity was 99.6% and 99.7% for both specificity and accuracy. Conclusions: This is the first globally developed AI model capable of HSIL/LSIL differentiation in the vaginal region, demonstrating high and robust performance metrics. Its effective application paves the way for AI-powered colposcopic assessment across the entire female genital tract, offering a significant advancement in women's healthcare worldwide.

Artificial Intelligence in Coloproctology: A Review of Emerging Technologies and Clinical Applications.

Artificial intelligence (AI) has emerged as a transformative tool across several specialties, namely gastroenterology, where it has the potential to optimize both diagnosis and treatment as well as enhance patient care. Coloproctology, due to its highly prevalent pathologies and tremendous potential to cause significant mortality and morbidity, has drawn a lot of attention regarding AI applications. In fact, its application has yielded impressive outcomes in various domains, colonoscopy being one prominent example, where it aids in the detection of polyps and early signs of colorectal cancer with high accuracy and efficiency. With a less explored path but equivalent promise, AI-powered capsule endoscopy ensures accurate and time-efficient video readings, already detecting a wide spectrum of anomalies. High-resolution anoscopy is an area that has been growing in interest in recent years, with efforts being made to integrate AI. There are other areas, such as functional studies, that are currently in the early stages, but evidence is expected to emerge soon. According to the current state of research, AI is anticipated to empower gastroenterologists in the decision-making process, paving the way for a more precise approach to diagnosing and treating patients. This review aims to provide the state-of-the-art use of AI in coloproctology while also reflecting on future directions and perspectives.

Deep learning and automatic differentiation of pancreatic lesions in endoscopic ultrasound - a transatlantic study.

Endoscopic ultrasound (EUS) allows characterization and biopsy of pancreatic lesions. Pancreatic cystic neoplasms (PCN) include in mucinous (M-PCN) and non-mucinous lesions (NM-PCN). Pancreatic ductal adenocarcinoma (P-DAC) is the commonest pancreatic solid lesion (PSL), followed by pancreatic neuroendocrine tumor (P-NET). While EUS is preferred for pancreatic lesion evaluation, its diagnostic accuracy is suboptimal. This multicentric study aims to develop a convolutional neural network (CNN) for detecting and distinguishing PCN (namely M-PCN and NM-PCN) and PSL (particularly P-DAC and P-NET). A CNN was developed with 378 EUS exams from 4 international reference centers (Centro Hospitalar Universitário São João, Hospital Universitario Puerta de Hierro Majadahonda, New York University Hospitals, Hospital das Clínicas FMUSP). 126.000 images were obtained - 19.528 M-PCN, 8.175 NM-PCN, 64.286 P-DAC, 29.153 P-NET and 4.858 normal pancreas images. A trinary CNN differentiated normal pancreas tissue from M-PCN and NM-PCN. A binary CNN distinguished P-DAC from P-NET. The total dataset was divided in a training and testing dataset (used for model's evaluation) in a 90/10% ratio. The model was evaluated through its sensitivity, specificity, positive and negative predictive values and accuracy. The CNN had 99.1% accuracy for identifying normal pancreatic tissue, 99.0% and 99.8% for M-PCN and NM-PCN, respectively. P-DAC and P-NET were distinguished with 94.0% accuracy. Our group developed the first worldwide CNN capable of detecting and differentiating the commonest PCN and PSL in EUS images, using exams from 4 centers in two continents, minimizing the impact of the demographic bias. Larger multicentric studies are needed for technology implementation.

Discovery of Potent Isoquinolinequinone N-Oxides to Overcome Cancer Multidrug Resistance.

Multidrug resistance (MDR) of human tumors has resulted in an immediate need to develop appropriate new drugs. This work outlines the development of 20 potent IQQ N-oxide derivatives in two isomeric families, both exhibiting nanomolar GI50 against human tumor cell lines. Preliminary NCI-60 tumor screening sees the C(6) isomers achieve a mean GI50 > 2 times lower than the corresponding C(7) isomers. MDR evaluation of nine selected compounds reveals that each presents lower GI50 concentrations in two MDR tumor cell lines. Four of the series display nanomolar GI50 values against MDR cells, having selectivity ratios up to 2.7 versus the sensitive (parental) cells. The most potent compound 25 inhibits the activity of drug efflux pumps in MDR cells, causes significant ROS accumulation, and potently inhibits cell proliferation, causing alterations in the cell cycle profile. Our findings are confirmed by 3D spheroid models, providing new candidates for studies against MDR cancers.

Towards a practical threat assessment methodology for crop landraces.

Crop landraces (LR), the traditional varieties of crops that have been maintained for millennia by repeated cycles of planting, harvesting, and selection, are genetically diverse compared to more modern varieties and provide one of the key components for crop improvement due to the ease of trait transfer within the crop species. However, LR diversity is increasingly threatened with genetic erosion and extinction by replacement with improved cultivars, lack of incentives for farmers to maintain traditional agricultural systems, and rising threats from climate change. Their active conservation is necessary to maintain this critical resource. However, as there are hundreds of thousands of LR and millions of LR populations for crops globally, active conservation is complex and resource-intensive. To assist in implementation, it is useful to be able to prioritise LR for conservation action and an obvious means of prioritisation is based on relative threat assessment. There have been several attempts to propose LR threat assessment methods, but none thus far has been widely accepted or applied. The aim of this paper is to present a novel, practical, standardised, and objective methodology for LR threat assessment derived from the widely applied IUCN Red Listing for wild species, involving the collation of time series information for LR population range, LR population trend, market, and farmer characteristics and LR context information. The collated information is compared to a set of threat criteria and an appropriate threat category is assigned to the LR when a threshold level is reached. The proposed methodology can be applied at national, regional, or global levels and any crop group.

From Data to Insights: How Is AI Revolutionizing Small-Bowel Endoscopy?

The role of capsule endoscopy and enteroscopy in managing various small-bowel pathologies is well-established. However, their broader application has been hampered mainly by their lengthy reading times. As a result, there is a growing interest in employing artificial intelligence (AI) in these diagnostic and therapeutic procedures, driven by the prospect of overcoming some major limitations and enhancing healthcare efficiency, while maintaining high accuracy levels. In the past two decades, the applicability of AI to gastroenterology has been increasing, mainly because of the strong imaging component. Nowadays, there are a multitude of studies using AI, specifically using convolutional neural networks, that prove the potential applications of AI to these endoscopic techniques, achieving remarkable results. These findings suggest that there is ample opportunity for AI to expand its presence in the management of gastroenterology diseases and, in the future, catalyze a game-changing transformation in clinical activities. This review provides an overview of the current state-of-the-art of AI in the scope of small-bowel study, with a particular focus on capsule endoscopy and enteroscopy.

Trimethylamine increases intestinal fatty acid absorption: in vitro studies in a Caco-2 cell culture system.

Although elevated blood levels of trimethylamine N-oxide (TMAO) have been associated with atherosclerosis development in humans, the role of its gut microbiota-derived precursor, TMA, in this process has not been yet deciphered. Taking this into account, and the fact that increased intestinal fatty acid absorption contributes to atherosclerosis onset and progression, this study aimed to evaluate the effect of TMA on fatty acid absorption in a cell line that mimics human enterocytes. Caco-2 cells were treated with TMA 250 µM for 24 h. Fatty acid absorption was assessed by measuring the apical-to-basolateral transport and the intracellular levels of BODIPY-C12, a fluorescently labelled fatty acid analogue. Gene expression of the main intestinal fatty acid transporters was evaluated by real-time quantitative reverse transcription PCR. Compared to control conditions, TMA increased, in a time-dependent manner and by 20-50 %, the apical-to-basolateral transport and intracellular levels of BODIPY-C12 fatty acid in Caco-2 cells. Fatty acid transport protein 4 (FATP4) and fatty acid translocase (FAT)/CD36 gene expression were not stimulated by TMA, suggesting that TMA-induced increase in fatty acid transport may be mediated by an increase in FAT/CD36 and/or FATP4 activity and/or fatty acid passive transport. This study demonstrated that TMA increases the intestinal absorption of fatty acids. Future studies are necessary to confirm if this may constitute a novel mechanism that partially explains the existing positive association between the consumption of a diet rich in TMA sources (e.g. red meat) and the increased risk of atherosclerotic diseases.

IPA and its precursors differently modulate the proliferation, differentiation, and integrity of intestinal epithelial cells.

BACKGROUND/OBJECTIVES: Indole-3-propionic acid (IPA) is a tryptophan-derived microbial metabolite that has been associated with protective effects against inflammatory and metabolic diseases. However, there is a lack of knowledge regarding the effects of IPA under physiological conditions and at the intestinal level. MATERIALS/METHODS: Human intestinal epithelial Caco-2 cells were treated for 2, 24, and/or 72 h with IPA or its precursors - indole, tryptophan, and propionate - at 1, 10, 100, 250, or 500 µM to assess cell viability, integrity, differentiation, and proliferation. RESULTS: IPA induced cell proliferation and this effect was associated with a higher expression of extracellular signal-regulated kinase 2 (ERK2) and a lower expression of c-Jun. Although indole and propionate also induced cell proliferation, this involved ERK2 and c-Jun independent mechanisms. On the other hand, both tryptophan and propionate increased cell integrity and reduced the expression of claudin-1, whereas propionate decreased cell differentiation. CONCLUSIONS: In conclusion, these findings suggested that IPA and its precursors distinctly contribute to the proliferation, differentiation, and barrier function properties of human intestinal epithelial cells. Moreover, the pro-proliferative effect of IPA in intestinal epithelial cells was not explained by its precursors and is rather related to its whole chemical structure. Maintaining IPA at physiological levels, e.g., through IPA-producing commensal bacteria, may be important to preserve the integrity of the intestinal barrier and play an integral role in maintaining metabolic homeostasis.

Designer Nucleases: Gene-Editing Therapies using CCR5 as an Emerging Target in HIV.

Acquired Immunodeficiency Syndrome (AIDS), caused by the Human Immunodeficiency Virus (HIV), is a life-threatening disorder that persists worldwide as a severe health problem. Since it was linked with the HIV attachment process, the Chemokine receptor, CCR5, has been at the development leading edge of several gene-based therapies. Given the shortcomings of the current antiretroviral treatment procedure and the non-availability of a licensed vaccine, the aptitude to modify complex genomes with Designer Nucleases has had a noteworthy impact on biotechnology. Over the last years, ZFN, TALEN and CRISPR/Cas9 gene-editing technology have appeared as a promising solution that mimics the naturally occurring CCR5/Δ32 mutation and permanently guarantees the absence of CCR5-expression on the surface of HIV target-cells, leading to a continuous resistance to the virus entry and, ultimately, proving that cellular immunization from infection could be, in fact, a conceivable therapeutic approach to finally achieve the long-awaited functional cure of HIV.

Validity and Reliability of the Portuguese school physical activity environment questionnaire in adolescents / Validação e Fiabilidade da versão portuguesa do questionário de avaliação do ambiente escolar para a atividade física em adolescentes

Abstract The aim of this study is to analyze the psychometric properties and to examine the factorial validity of the Portuguese version of the Questionnaire Assessing School Physical Activity Environment (Q-SPACE) for school-age youth. The translated and adapted version of the questionnaire was applied and resulted in two studies: study I, in which 504 students participated (56% boys), the factorial structure of the scale was examined; in study II, which involved 501 students (53.5% boys), the factorial structure obtained in study I was tested through confirmatory factor analysis. The results of the exploratory factorial analysis, carried out in study I, showed that the Portuguese version of the Q-SPACE is composed of five factors that characterize the students' perception regarding the social and physical school environment for physical activity: equipment and space conditions; recess; school social support; physical education structure; school activity offer. Internal consistency values ranged from 0.60 to 0.89. The confirmatory factor analysis confirmed the applicability of the Portuguese Q-SPACE version, presenting adequate fit indexes: χ2/df = 2.90, GFI = 0.92; CFI = 0.92; RMSEA = 0.06. In conclusion, Q-SPACE showed acceptable validity and reliability for assessing school physical activity environment in Portuguese adolescents.

Resumo O objetivo deste estudo é analisar as propriedades psicométricas e examinar a validade fatorial da versão portuguesa do instrumento "Questionnaire Assessing School Physical Activity Environment" (Q-SPACE) para jovens em idade escolar. A versão traduzida e adaptada da escala foi aplicada e resultaram dois estudos: no estudo I, em que participaram 504 estudantes (56% eram rapazes), foi examinada a estrutura fatorial da escala; no estudo II, em que participaram 501 estudantes (53.5% eram rapazes), foi testada a estrutura fatorial obtida no estudo I através da análise fatorial confirmatória. O resultado da análise fatorial exploratória, efetuada no estudo I, demonstrou que a versão portuguesa da escala Q-SPACE é constituída por cinco fatores que caraterizam a perceção dos estudantes relativamente ao ambiente social e físico escolar para a prática de atividade física: condições dos espaços e material; intervalos; suporte social escolar; organização da educação física; diversidade de atividades. Os valores de consistência interna variaram entre 0.60 e 0.89. A análise fatorial confirmatória, comprovou a aplicabilidade da versão portuguesa do Q-SPACE, apresentando adequados índices de ajustamento: χ2/df = 2.90, GFI = 0.92; CFI = 0.92; RMSEA = 0.06. Em conclusão, a escala Q-SPACE demonstrou uma validade e fiabilidade adequadas para avaliar a perceção do ambiente escolar para a prática de atividade física em adolescentes portugueses.

Impacto de fatores sociodemográficos e comportamentais na prevalência de sobrepeso e obesidade de escolares / Impact of sociodemographic and behavioral factors on the prevalence of overweight and obesity in schoolchildren

O estudo analisou o impacto de fatores sociodemográficos e comportamentais na prevalência de sobrepeso e obesidade em amostra representativa de escolares de Montes Claros, Minas Gerais, Brasil. A amostra foi constituída por 2849 sujeitos (1457 moças e 1392 rapazes), com idades entre 6 e 18 anos. Sobrepeso e obesidade foram definidos mediante o índice de massa corporal, adotando-se pontos-de-corte para gênero e idade sugeridos pela International Obesity Task Force (IOFT). As prevalências nos diferentes estratos associados aos fatores sociodemográficos e comportamentais foram comparadas por intermédio do cálculo de regressão logística, utilizando-se odds ratios ajustadas. Entre as moças, as prevalências de sobrepeso e obesidade encontradas foram de 19,7% e 4,8%, respectivamente, enquanto entre os rapazes, 14,7% e 2,8%. Os resultados encontrados mostram que, emboraas prevalências do sobrepeso e da obesidade sejam comparáveis com estimativas observadas em outras regiões brasileiras e menores que as encontradas em regiões mais industrializadas, a proporção de escolares que apresentaram sobrepeso e são obesos é particularmente preocupante. Os principais fatores sociodemográficos e comportamentais identificados na ocorrência do sobrepeso e da obesidade foram classe econômica, escolaridade dos pais, número de irmãos, tipo de alimentação na escola, distância e meio de transporte entre a casa e a escola, realização de trabalho remunerado e tipo de atividade no lazer e no tempolivre. Os dados mostram que existe urgente necessidade de implementar programas de intervenção educacional direcionados à promoção da prática de atividade física e de hábitos dietéticos adequados.

This study analyzed the impact of sociodemographic and behavioral factors on the prevalence of overweight and obesity in a representative sample of schoolchildren from Montes Claros, Minas Gerais, Brazil. The sample consisted of 2849 children and adolescents (1457girls and 1392 boys), ranging in age from 6 to 18 years. Overweight and obesity were defined based on body mass index according to the cut-off values for gender and age suggested by the International Obesity Task Force (IOTF). The prevalence rates in the different strata associated with sociodemographic and behavioral factors were compared by logistic regression using adjusted odds ratios. The prevalence of overweight and obesity was 19.7% and 4.8%, respectively, among girls, and 14.7% and 2.8% among boys. The results show that, although the prevalenceof overweight and obesity is similar to estimates observed in other Brazilian regions and smaller than those found in more industrialized areas, the proportion of schoolchildren who presented overweight and obesity is a matter of concern. The main sociodemographic and behavioralfactors associated with the occurrence of overweight were economic status, educational level of the parents, number of siblings, school menu, distance and means of transportation between home and school, paid work, and leisure-time activity. The data show an urgent need for theimplementation of educational intervention programs designed to promote physical activity and adequate dietary habits.

Towards an understanding of salient neighborhood boundaries: adolescent reports of an easy walking distance and convenient driving distance.

Numerous studies have examined the association between the surrounding neighborhood environment and physical activity levels in adolescents. Many of these studies use a road network buffer or Euclidean distance buffer around an adolescent's home to represent the appropriate geographic area for study (i.e., neighborhood). However, little empirical research has examined the appropriate buffer size to use when defining this area and there is little consistency across published research as to the buffer size used. In this study, 909 12th grade adolescent girls of diverse racial and geographic backgrounds were asked to report their perceptions of an easy walking distance and a convenient driving distance. These two criterions are often used as the basis for defining one's neighborhood.The mean easy walking distance in minutes reported by adolescent girls was 14.8 minutes (SD = 8.7). The mean convenient driving distance in minutes reported was 17.9 minutes (SD = 10.8). Nested linear multivariate regression models found significant differences in reported 'easy walking distance' across race and BMI. White adolescents reported on average almost 2 minutes longer for an easy walking distance compared to African American adolescents. Adolescents who were not overweight or at risk for overweight reported almost 2 minutes fewer for an easy walking distance relative to those who were overweight or at risk for overweight. Significant differences by urban status were found in the reported 'convenient driving distance'. Those living in non-urban areas reported on average 3.2 minutes more driving time as convenient compared to those living in urban areas. Very little variability in reported walking and driving distances was explained by the predictors used in the models (i.e., age, race, BMI, physical activity levels, urban status and SES).This study suggests the use of a 0.75 mile buffer to represent an older female adolescent's neighborhood, which can be accessed through walking. However, determining the appropriate area inclusive of car travel should be tailored to the geographic location of the adolescent since non-urban adolescents are willing to spend more time driving to destinations. Further research is needed to understand the substantial variability across adolescent perceptions of an easy walking and convenient driving distance.

Factorial validity and invariance of the Physical Self-Description Questionnaire among black and white adolescent girls.

Meaningful comparison of physical self-concept among racial or ethnic groups requires that the measurement instruments used have equivalent measurement properties. We tested the factorial validity and invariance of the Physical Self-Description Questionnaire (PSDQ) among Black (n = 658) and White (n = 479) adolescent girls in the 12th grade. Construct validity was examined by estimating correlations between PSDQ subscales and external criteria (physical activity, physical fitness, body mass index [BMI], and participation in sports). The hypothesized 11-factor model demonstrated adequate overall fit in both groups. Comparison of nested models supported the between-group invariance of the overall factor structure. Convergent and discriminant evidence for construct validity was supported by the pattern of correlations with the external criteria. The results indicate that a meaningful comparison of PSDQ scores can be made between Black and White girls in the 12th grade and that valid inferences from PSDQ scores can be made about specific aspects of physical self-concept. Despite lower levels of physical activity, sport participation, and fitness and higher BMI, Black girls had similar self-esteem and higher physical self-concept and perceived appearance compared to White girls.