Search

Abstract Chronic kidney disease (CKD) is a global health concern with early detection playing a pivotal role in effective management. Machine learning models demonstrate promise in CKD detection, yet the impact on detection and classification using different sets of clinical features remains under-explored. In this study, we focus on CKD classification and creatinine prediction using three sets of features: at-home, monitoring, and laboratory. We employ artificial neural networks (ANNs) and random forests (RFs) on a dataset of 400 patients with 25 input features, which we divide into three feature sets. Using 10-fold cross-validation, we calculate metrics such as accuracy, true positive rate (TPR), true negative rate (TNR), and mean squared error. Our results reveal RF achieves superior accuracy (92.5%) in at-home CKD classification over ANNs (82.9%). ANNs achieve a higher TPR (92.0%), but a lower TNR (67.9%) compared with RFs (90.0% and 95.8%, respectively). For monitoring and laboratory features, both methods achieve accuracies exceeding 98%. The R2 score for creatinine regression is approximately 0.3 higher with laboratory features than at-home features. Feature importance analysis identifies the key clinical variables hemoglobin and blood urea, and key comorbidities hypertension and diabetes mellitus, in agreement with previous studies. Machine learning models, particularly RFs, exhibit promise in CKD diagnosis and highlight significant features in CKD detection. Moreover, such models may assist in screening a general population using at-home features—potentially increasing early detection of CKD, thus improving patient care and offering hope for a more effective approach to managing this prevalent health condition.

Quality of Life (QoL) assessment has evolved over time, encompassing diverse aspects of human existence beyond just health. This paper presents a comprehensive review of the integration of Deep Learning (DL) techniques in QoL assessment, focusing on the analysis of wearable data. QoL, as defined by the World Health Organisation, encompasses physical, mental, and social well-being, making it a multifaceted concept. Traditional QoL assessment methods, often reliant on subjective reports or informal questioning, face challenges in quantification and standardization. To address these challenges, DL, a branch of machine learning inspired by the human brain, has emerged as a promising tool. DL models can analyze vast and complex datasets, including patient-reported outcomes, medical images, and physiological signals, enabling a deeper understanding of factors influencing an individual's QoL. Notably, wearable sensory devices have gained prominence, offering real-time data on vital signs and enabling remote healthcare monitoring. This review critically examines DL's role in QoL assessment through the use of wearable data, with particular emphasis on the subdomains of physical and psychological well-being. By synthesizing current research and identifying knowledge gaps, this review provides valuable insights for researchers, clinicians, and policymakers aiming to enhance QoL assessment with DL. Ultimately, the paper contributes to the adoption of advanced technologies to improve the well-being and QoL of individuals from diverse backgrounds.

Background Prelacteal feeding disrupts early breastfeeding initiation and exclusive breastfeeding, and increases the risk of childhood illnesses and under-five mortality. Despite its negative health outcomes, newborns are given prelacteal feeds in Papua New Guinea (PNG). This study investigated the factors associated with prelacteal feeding practices among women in PNG.Design A population-based cross-sectional study based on Demographic and Health Survey (DHS) data. Multivariable logistic regression using complex sample analysis was performed to control for the effects of potential confounders. Variables with p ≤ 0.05 were considered statistically significant.Setting Papua New Guinea.Participants A total weighted sample of 4399 women was included in the study.Outcome measure Prelacteal feeds.Results About 10% of women provided prelacteal feeds to their infants. The most frequently reported prelacteal feed was plain water (71.7%), followed by grain-based (eg, noodles) (47.1%), dark green leafy vegetables (42.1%) and soup (39.7%). Women with no formal (Adjusted Odds Ratio (AOR) 1.4, 95% CI: 1.0–3.0) or primary (AOR 1.5, 95% CI: 1.0–2.9) education, who had a caesarean section (AOR 4.1, 95% CI: 2.4–7.2), had given birth at home or in the village (AOR 3.7, 95% CI: 2.1–6.8) and from the Islands region (AOR 2.3, 95% CI: 1.5–3.5) had higher odds of providing prelacteal feeds.Conclusion Our study revealed that providing prelacteal feeds is common in PNG. Tailored health education and behaviour change communication are necessary to address this harmful infant feeding practice. Furthermore, the promotion of facility-based births and early breastfeeding practices should be prioritised using existing strategies, especially for disadvantaged and rural women.

Abstract The gut–brain axis plays a pivotal role in the finely tuned orchestration of food intake, where both homeostatic and hedonic processes collaboratively control our dietary decisions. This interplay involves the transmission of mechanical and chemical signals from the gastrointestinal tract to the appetite centers in the brain, conveying information on meal arrival, quantity, and chemical composition. These signals are processed in the brain eventually leading to the sensation of satiety and the termination of a meal. However, the regulation of food intake and appetite extends beyond the realms of pure physiological need. Hedonic mechanisms, including sensory perception (i.e., through sight, smell, and taste), habitual behaviors, and psychological factors, exert profound influences on food intake. Drawing from studies in animal models and human research, this comprehensive review summarizes the physiological mechanisms that underlie the gut–brain axis and its interplay with the reward network in the regulation of appetite and satiety. The recent advancements in neuroimaging techniques, with a focus on human studies that enable investigation of the neural mechanisms underpinning appetite regulation are discussed. Furthermore, this review explores therapeutic/pharmacological strategies that hold the potential for controlling food intake.

The objective of this study is to investigate whether specific socioeconomic and attitudinal factors impact consumer receptivity to sustainable food packaging, with a particular focus on edible cups. A total of 1028 respondents completed an online questionnaire, and the data were analyzed using descriptive analysis and binary probit regression. The results reveal that demographic factors, such as household size and household economic position, have a positive influence on consumers’ intention to consume edible packages. Additionally, attitudinal factors were found to be significant, with food technology neophobia negatively affecting consumers’ willingness to try edible cups, while beliefs about the development of the sustainable packaging industry positively influence intention.

This paper presents the methodology of an applied geophysical and remote sensing research at river deltas for their subsurface and surface structure and its application in the deltaic plain of Pineios River (Thessaly, Greece). The scope is to primarily calculate the thickness of deltaic post alpine deposits, with the contribution of Transient Electromagnetic Method (TEM), but also identify the surficial characteristics (biotic/ abiotic) of the area with the appropriate combination of spectral bands and spectral indices. Regarding the remote sensing approach, some geomorphological features were outlined. This was managed from six false color composites of the area, produced by combining spectral bands and additional five false color composites by combining several spectral indices. • The results of the TEM method along with their statistical analysis provided important information regarding the spatial distribution and thickness of the lithological units along the deltaic plain. • The combination of spectral bands 8, 7, 6 seems to adumbrate the hydrographic network of the area and even detects possible changes in the inflow. • The combination of spectral indices MSAVI2, WV-BI, WV-WI was helpful enough to geomorphological mapping of the deltaic plain.

Goal: To develop a cardiovascular virtual population using statistical modeling and computational biomechanics. Methods: A clinical data augmentation algorithm is implemented to efficiently generate virtual clinical data using a real clinical dataset. An atherosclerotic plaque growth model is employed to 3D reconstructed coronary arterial segments to generate virtual coronary arterial geometries (geometrical data). Last, the combination of the virtual clinical and geometrical data is achieved using a methodology that allows for the generation of a realistic virtual population which can be used in in silico clinical trials. Results: The results show good agreement between real and virtual clinical data presenting a mean gof 0.1 ± 0.08. 400 virtual coronary arteries were generated, while the final virtual population includes 10,000 patients. Conclusions: The virtual arterial geometries are efficiently matched to the generated clinical data, both increasing and complementing the variability of the virtual population.

Lefkada and Corfu old towns are located in the western part of Greece, in the Ionian Sea. Their proximity to the Hellenic subduction zone (HSZ) is the reason for their intense seismicity. The main goal of this study was the estimation of the geotechnical characteristics of the subsurface, with the contribution of applied geophysical techniques. Therefore, seismic refraction tomography (SRT) and multichannel analysis of surface waves (MASW) were applied. A total of thirty-three (33) seismic and geoelectrical profiles were performed in both towns in order to evaluate the geotechnical characteristics of the subsurface formations. Additionally, subsurface resistivity distributions were investigated with the application of electrical resistivity tomography (ERT). Some important elastic moduli were calculated through the combination of estimated seismic wave velocities and laboratory density measurements. The horizontal distribution of seismic velocities and mechanical properties (σ, E, K, G) of Corfu town was illustrated in maps, for the depth of 5 m. The geophysical interpretation also revealed that Lefkada’s subsurface consists of only one compact geological formation, with little or no variation of its geophysical-geotechnical characteristics. Beyond that, the ground type classifications for the two towns were determined according to the European Committee for Standardization Eurocode 8, based on VS30 values.

Aim: Current dietary assessment methods are prone to subjective bias, highlighting the demand for an objective marker of fruit and vegetable (F/V) intake. Carotenoids from F/V consumption deposit in skin and adipose tissue, contributing to changes in skin colour. Results from research in females have highlighted positive associations between skin colour assessed by reflectance spectroscopy and F/V intake. The aim of this study was to determine the relationship between (i) F/V intake, (ii) carotenoid intake and skin colour in young Caucasian men. Methods: In this cross-sectional study reflectance spectroscopy was used to quantify skin colour in young Caucasian men. Skin colour was assessed at eight sun-exposed and unexposed body locations. A food frequency questionnaire was administered to assess F/V intake over the past month. Partial correlations were done to assess the associations between skin yellowness, F/V intake (grams) and carotenoid intake (milligrams), both with and without controlling for skin lightness. Results: Carotenoid intake was strongly associated with F/V intake (r = 0.8, p

The particle morphology and surface texture play a major role in influencing mechanical and hydraulic behaviors of sandy soils. This paper presents the use of digital image analysis combined with fractal theory as a tool to quantify the particle morphology and surface texture of two types of quartz sands widely used in the region of Vitória, Espírito Santo, southeast of Brazil. The two investigated sands are sampled from different locations. The purpose of this paper is to present a simple, straightforward, reliable and reproducible methodology that can identify representative sandy soil texture parameters. The test results of the soil samples of the two sands separated by sieving into six size fractions are presented and discussed. The main advantages of the adopted methodology are its simplicity, reliability of the results, and relatively low cost. The results show that sands from the coastal spit (BS) have a greater degree of roundness and a smoother surface texture than river sands (RS). The values obtained in the test are statistically analyzed, and again it is confirmed that the BS sand has a slightly greater degree of sphericity than that of the RS sand. Moreover, the RS sand with rough surface texture has larger specific surface area values than the similar BS sand, which agree with the obtained roughness fractal dimensions. The consistent experimental results demonstrate that image analysis combined with fractal theory is an accurate and efficient method to quantify the differences in particle morphology and surface texture of quartz sands.

Heart failure is a serious condition with high prevalence (about 2% in the adult population in developed countries, and more than 8% in patients older than 75 years). About 3–5% of hospital admissions are linked with heart failure incidents. Heart failure is the first cause of admission by healthcare professionals in their clinical practice. The costs are very high, reaching up to 2% of the total health costs in the developed countries. Building an effective disease management strategy requires analysis of large amount of data, early detection of the disease, assessment of the severity and early prediction of adverse events. This will inhibit the progression of the disease, will improve the quality of life of the patients and will reduce the associated medical costs. Toward this direction machine learning techniques have been employed. The aim of this paper is to present the state-of-the-art of the machine learning methodologies applied for the assessment of heart failure. More specifically, models predicting the presence, estimating the subtype, assessing the severity of heart failure and predicting the presence of adverse events, such as destabilizations, re-hospitalizations, and mortality are presented. According to the authors' knowledge, it is the first time that such a comprehensive review, focusing on all aspects of the management of heart failure, is presented. Keywords: Heart failure, Diagnosis, Prediction, Severity estimation, Classification, Data mining

This study examines the relationship between trait emotional intelligence (trait EI) and general health (General Health; GHQ-28) in two samples of Greek parents with (n = 52; Mage = 39.78; SDage = 6.68; 41 men and 11 women) and without (n = 51; Mage = 43.53; SDage = 4.61; 40 men and 11 women) addiction problems. In addition, it compares the trait EI scores of their offspring (N = 81; Mage = 11.71; SDage = 2.15; 51 boys and 30 girls). Results showed that parents with drug addiction exhibited lower levels of trait EI and poorer general health than peers. In addition, global trait EI and two of its subscales, Well-being and Emotionality, had stronger correlations with depression in the addiction than in the comparison group. Well-being was a significant predictor of general health and its subscales (Somatic symptoms, Anxiety/insomnia, Social dysfunction, and severe depression) in both groups. No differences were found between the offspring of the two groups.

Chronic kidney disease (CKD) is a global health concern with early detection playing a pivotal role in effective management. Machine learning models demonstrate promise in CKD detection, yet the impact on detection and classification using different sets of clinical features remains under-explored. In this study, we focus on CKD classification and creatinine prediction using three sets of features: at-home, monitoring, and laboratory. We employ artificial neural networks (ANNs) and random forests (RFs) on a dataset of 400 patients with 25 input features, which we divide into three feature sets. Using 10-fold cross-validation, we calculate metrics such as accuracy, true positive rate (TPR), true negative rate (TNR), and mean squared error. Our results reveal RF achieves superior accuracy (92.5%) in at-home CKD classification over ANNs (82.9%). ANNs achieve a higher TPR (92.0%), but a lower TNR (67.9%) compared with RFs (90.0% and 95.8%, respectively). For monitoring and laboratory features, both methods achieve accuracies exceeding 98%. The R2 score for creatinine regression is approximately 0.3 higher with laboratory features than at-home features. Feature importance analysis identifies the key clinical variables hemoglobin and blood urea, and key comorbidities hypertension and diabetes mellitus, in agreement with previous studies. Machine learning models, particularly RFs, exhibit promise in CKD diagnosis and highlight significant features in CKD detection. Moreover, such models may assist in screening a general population using at-home features—potentially increasing early detection of CKD, thus improving patient care and offering hope for a more effective approach to managing this prevalent health condition. [ABSTRACT FROM AUTHOR]

Food intake and activity adapt during pregnancy to meet the increased energy demands. In comparison to non‐pregnant females, pregnant mice consume more food, eating larger meals during the light phase, and reduce physical activity. How pregnancy changes the circadian timing of behaviour was less clear. We therefore randomised female C57BL/6J mice to mating for study until early (n = 10), mid‐ (n = 10) or late pregnancy (n = 11) or as age‐matched, non‐pregnant controls (n = 12). Mice were housed individually in Promethion cages with a 12 h light–12 h dark cycle [lights on at 07.00 h, Zeitgeber (ZT)0] for behavioural analysis. Food intake between ZT10 and ZT11 was greater in pregnant than non‐pregnant mice on days 6.5–12.5 and 12.5–17.5. In mice that exhibited a peak in the last 4 h of the light phase (ZT8–ZT12), peaks were delayed by 1.6 h in the pregnant compared with the non‐pregnant group. Food intake immediately after dark‐phase onset (ZT13–ZT14) was greater in the pregnant than non‐pregnant group during days 12.5–17.5. Water intake patterns corresponded to food intake. From days 0.5–6.5 onwards, the pregnant group moved less during the dark phase, with decreased probability of being awake, in comparison to the non‐pregnant group. The onset of dark‐phase activity, peaks in activity, and wakefulness were all delayed during pregnancy. In conclusion, increased food intake during pregnancy reflects increased amplitude of eating behaviour, without longer duration. Decreases in activity also contribute to positive energy balance in pregnancy, with delays to all measured behaviours evident from mid‐pregnancy onwards. Key points: Circadian rhythms synchronise daily behaviours including eating, drinking and sleep, but how these change in pregnancy is unclear.Food intake increased, with delays in peaks of food intake behaviour late in the light phase from days 6.5 to 12.5 of pregnancy, in comparison to the non‐pregnant group.The onset of activity after lights off (dark phase) was delayed in pregnant compared with non‐pregnant mice.Activity decreased by ∼70% in the pregnant group, particularly in the dark (active) phase, with delays in peaks of wakefulness evident from days 0.5–6.5 of pregnancy onwards.These behavioural changes contribute to positive energy balance during pregnancy.Delays in circadian behaviours during mouse pregnancy were time period and pregnancy stage specific, implying different regulatory mechanisms. [ABSTRACT FROM AUTHOR]