Unweighted Average Research Articles

Analysis of genetic profiling and diversity in mango cultivar using SSR

The present study was conducted to show genetic variation and investigate inter-relationships between 30 mango genotypes. We are selected 9 SSR markers with 30 genotypes cv. Kalepad, Neelum, Swarnarekha, Alphonso Rumani, Sendura, Banganapalli, Mulgoa and Bangalora etc. The genomic DNA was extracted from mature leaf samples with cetyltrimethylammonium bromide (CTAB) method. Samples were run by Polymerase chain reaction (PCR) they produced 350 amplified products, of which 258 were polymorphic and 132 monomorphic. The sizes of the alleles detected ranged from 120 to 290 bp. SSR markers were highly polymorphic with an average of 3.04 alleles per primers. SSRs gave moderate polymorphic information content (PIC) range value of 0.147 to 0.778. The amplified products varied between 2 (MSSR 152, MSSR 155 andMSSR173) to 3 and 4 (MSSR 106, MSSR140, MSSR146, MSSR156, MSSR160 and MSSR190) bands per primer. We obtained moderate genetic diversity, with Jaccard’s similarity co-efficient values ranging from 0.065 between cluster I and II to 0.25 between clusters II and III. The dendrogram generated from the unweighted pair group arithmetic average (UPGMA) cluster analysis broadly placed 30 mango cultivars into three significant clusters at co-efficient similarity of 0.65. The cluster size varied from 1 to 27 and cluster I was the largest cluster comprising twenty-seven cultivars, followed by cluster II possessing two and clusters I possess one variety. Cluster I had the highest diverse cultivars namely, Mallika, Gundur pacharichi, Rumani, Sajahan, Dillpasanth, Senthuram, Amarapalli, Arka aruna, Banganapalli, Sundar langra, Sothuparai local etc. cluster II contain the cultivar Neelgoa, Arka puneet Cluster III contain the cultivars viz., Neelphonso. Unique fingerprints were identified in the cultivars. The tendency of clustering among mango cultivars revealed that they have a strong affinity towards further breeding programmes.

Efficacy and safety of non‐penetrating surgery versus trabeculectomy in open‐angle glaucoma: A systematic review and meta‐analysis

Aims/Purpose: Whilst trabeculectomies (TE) remain the gold‐standard treatment for open‐angle glaucoma (OAG), non‐penetrating surgery (NPS) are rising in popularity as an alternative. This systematic review and meta‐analysis compared the efficacy and safety of trabeculectomy and NPS for OAG.Methods: The following databases of PubMed, Embase, Medline, Scopus and Cochrane Library were searched for original studies comparing TE to NPS (from inception to 23/01/2024). The primary outcome was IOP reduction, with secondary outcomes including success rate, medication score, visual acuity (BCVA) and complications. A random‐effects model on ReviewManager (RevMan) was used for the meta‐analysis. Sub‐group analyses for concomitant mitomycin C and hyaluronate were performed, unlike current existing reviews.Results: Initially 529 papers were identified. Of these, 20 studies containing 1422 participants (1565 eyes) were included. 16 studies reported higher complete success rates with TE. Meta‐analysis showed that although the IOP reduction was larger in TE, this was not statistically significant (mean difference = ‐1.31, 95% CI: ‐3.12 to 0.50). There was no significant difference in reduction of medications but there was significant improvement in BCVA at 12 months with NPS (unweighted average: TE = 0.078, NPS = ‐0.015, p < 0.00652). The relative risk of complications (hypotony, choroidal detachment, cataract, shallow anterior chamber and hyphaema) were higher in TE than all NPS (RR: 2.80, 95% CI: 2.13 to 3.68, p < 0.0001). However, hyphaema was less likely to occur in TE compared to canaloplasty (NPS) (RR: 0.14, 95% CI: 0.03 to 0.62, p < 0.0090).Conclusions: Findings show trabeculectomy and NPS appear to reduce IOP comparably, a finding not found in previous reviews. However, complication risks increased in trabeculectomy, potentially favouring the use of NPS. However, the training requirement for NPS may limit its universal uptake.

Trajectory of Cardiovascular Health Across Childhood and Adolescence

The American Heart Association put forth the Life's Essential 8 construct to assess cardiovascular health (CVH) based on 8 behavioral and health factors. Few studies have characterized the natural history of CVH in early life or identified its sociodemographic determinants. To characterize CVH trajectories across childhood and adolescence and identify associations with sociodemographic variables. This study used data from the Project Viva prebirth cohort, an ongoing prospective prebirth cohort study conducted in a large multispecialty group practice in eastern Massachusetts among women who were pregnant and enrolled from April 1999 to November 2002. Participant inclusion required 3 or more CVH metrics in early childhood (median [range] age, 3.2 [2.8-6.2] years) or 4 metrics or more in midchildhood (median [range] age, 7.7 [6.6-10.9] years), early adolescence (median [range] age, 13.0 [11.9-16.6] years), or late adolescence (median [range] age, 17.5 [15.4-20.1] years). Of 2218 live births in the original cohort, 1523 were included in the present analysis. Data were analyzed from June to December 2023. Child sex, race, and ethnicity; maternal education; and household income. CVH score (0-100 points) from early childhood to late adolescence, calculated as the unweighted average of all available CVH metrics at each life stage. Among 1523 children, 782 (51.4%) were male; 53 (3.5%) were non-Hispanic Asian, 231 (15.2%) were non-Hispanic Black, 988 (65.0%) were non-Hispanic White, and 175 (11.5%) were non-Hispanic other. The mean (SD) CVH score was 82.6 (8.6) in early childhood, 84.1 (8.3) in midchildhood, 82.0 (9.8) in early adolescence, and 73.8 (11.5) in late adolescence. The estimated mean (SD) age of inflection when CVH score declined was 10.1 (0.7) years for male children and 10.0 (0.6) years for female children; the decline in CVH was associated with health behaviors rather than health factors. Male children (vs female children) had faster CVH score gain before the inflection (β, 0.79 points/year; 95% CI, 0.67 to 0.91) and faster CVH score decline after the inflection (β, -0.33 points/year; 95% CI, -0.44 to -0.22). Non-Hispanic Black children (β, 0.32 years; 95% CI, 0.20 to 0.43) and children of other non-Hispanic races (β, 0.16 years; 95% CI, 0.05 to 0.28) children had later timing of inflection compared with non-Hispanic White children. Children of mothers without (vs with) a college degree or with household income $70 000 per year or less (vs greater than $70 000/year) exhibited lower CVH trajectory throughout childhood. Children of mothers with some college education (vs a college degree) had later timing of inflection (β, 0.16 years; 95% CI, 0.07 to 0.26) and slower CVH score gain before the inflection (β, -0.24 points/year; 95% CI, -0.40 to -0.08). This study provides insight into the trajectory of CVH early in life, which may contribute to CVH disparities in adulthood, and identified modifiable health behaviors for focused prevention efforts to optimize CVH in early life.

Analysis of Bacterial Diversity In Temple Bricks Using Phenetic Numeric Taxonomy Method

Temple bricks-based constructions are known to often face various challenges, including physical, chemical, and biological weathering. Previous studies identified various biological factors contributing to brick weathering including exudate produced by microorganisms, such as bacteria. In addition, bacteria often live synergistically and antagonistically with other species, exhibiting diverse morphological and physiological traits (bacterial diversity). Various methods have been developed to explore bacterial diversity, with phenetic numerical taxonomy being the most popular. Therefore, this study aims to determine bacterial diversity on the surfaces of temple bricks using phenetic numerical taxonomy method. Bacterial isolation was carried out aseptically, followed by labeling and transferring the isolate to the laboratory for further tests. The tests carried out included morphological characterization, biochemical assays, physiological reactions, and potential enzymatic activities. Subsequently, dendrogram was constructed using MVSP (Multi-Variate Statistical Package) software with isolated grouping based on the Unweighted Pair Group Method Averages (UPGMA) algorithm. The similarity between isolates was analyzed using the Simple Matching Coefficient (SSM) similarity value. The dendrogram analysis revealed the presence of 3 clusters namely A (4 isolates), B (1 isolate), and C (2 isolates), with a similarity index of 0,543 to 0,857. Clusters A, B, and C had a similarity index of ≤0.700, indicating the occurrence of distinct species in each cluster. Based on the profile-matching results of key characters, the 7 bacterial isolates were identified as belonging to the genera Bacillus, Corynebacterium, and Mycobacterium.

Life's Essential 8 Trajectories and Risk of Stroke: A Prospective Cohort Study.

Evidence is lacking regarding long-term patterns of change in Life's Essential 8 (LE8) and their association with the risk of stroke. We aim to evaluate LE8 trajectories and examine their association with the risk of stroke in China. This study, conducted in a workplace setting, recruited 26 719 participants (average age, 46.02±11.27 years and a male population of 73.73%) who had no history of stroke and consecutively participated in 6 surveys from 2006 to 2016. Repeated LE8 measurements were determined by taking the unweighted average of the 8 component scores ranging from 0 to 100. People with higher scores had better overall cardiovascular health. By examining the medical records of the participants, stroke cases were identified for the period from 2016 to 2020. A latent mixture model was applied to classify the trajectory clusters of LE8 from 2006 to 2016, and Cox proportional hazard models were used to analyze the data. Five LE8 trajectories were detected between 2006 and 2016. Four hundred ninety-eight incident strokes including 55 (11.04%) hemorrhagic and 458 (91.97%) ischemic strokes were documented. After adjusting for covariates, the hazard ratios and 95% CIs for the association between stable-low, moderate-increasing, moderate-stable, and high-stable trajectories and incident stroke, compared with the moderate-decreasing trajectory, were 1.42 (1.11-1.84), 0.73 (0.56-0.96), 0.49 (0.39-0.62), and 0.19 (0.11-0.32), respectively. Individuals with high LE8 status (LE8≥80) exhibited a significantly reduced risk of stroke compared with those with low one (LE8≤49; P-trend <0.001). A faster annual growth in LE8 was related to a lower risk of stroke. Maintaining high LE8 over an extended period and high baseline LE8 status were related to a decreased risk of stroke. Despite the initial low level of LE8, improvement in LE8 attenuates or even reverses the risk of stroke.

Association of Life's Essential 8 with abdominal aortic calcification and mortality among middle-aged and older individuals.

To assess the association of Life's Essential 8 (LE8) and the presence of abdominal aortic calcification (AAC) with mortality among middle-aged and older individuals. Participants aged older than 40 years were enrolled from the National Health and Nutrition Examination Survey 2013-2014. AAC was assessed using dual-energy X-ray absorptiometry. Mortality data were ascertained through linkage with the National Death Index until 31 December 2019. The LE8 score incorporates eight components: diet, physical activity, nicotine exposure, sleep health, body mass index, blood lipids, blood glucose and blood pressure. The total LE8 score, an unweighted average of all components, was categorized into low (0-49), medium (50-79) and high (80-100) scores. This study included 2567 individuals, with a mean LE8 score of 67.28 ± 0.48 and an AAC prevalence of 28.28%. Participants with low LE8 scores showed a significantly higher prevalence of AAC (odds ratio = 2.12 [1.12-4.19]) compared with those with high LE8 scores. Over a median 6-year follow-up, there were 222 all-cause deaths, and 55 cardiovascular deaths occurred. Participants with AAC had an increased risk of all-cause (hazard ratio [HR] = 2.17 [1.60-2.95]) and cardiovascular (HR = 2.35 [1.40-3.93]) mortality. Moreover, individuals with AAC and low or medium LE8 scores exhibited a 137% (HR = 2.37 [1.58-3.54]) and 119% (HR = 2.19 [1.61-2.99]) higher risk of all-cause mortality, as well as a 224% (HR = 3.24 [1.73-6.04]) and 125% (HR = 2.25 [1.24-4.09]) increased risk of cardiovascular mortality, respectively. The LE8 score correlates with AAC prevalence in middle-aged and older individuals and serves as a valuable tool for evaluating the risk of all-cause and cardiovascular mortality in individuals with AAC.

Association between Life's Essential 8 and Infertility as Well as the Mediating Effects of Oxidative Stress and Inflammatory Factors Among U.S. Women Aged 18-45 Years.

Management of cardiovascular disease in pregnancy is important, yet the association between cardiovascular health and infertility is rarely reported. In this study, we aimed to explore the association between Life's Essential 8 (LE8), a novel cardiovascular health (CVH) measure, and infertility, and to investigate potential mediating mechanisms. This study investigated cross-sectional data from the 2013-2018 National Health and Nutrition Examination Survey. LE8 score (ranging from 0 to 100) was calculated as the unweighted average of eight CVH metrics. The association between LE8 and infertility was explored through weighted multiple logistic regression. Restricted cubic splines were used to explore nonlinear correlation. In addition, mediation analysis was conducted to investigate the role of oxidative stress and inflammatory markers systematically. After strict exclusion criteria, 1703 American women aged 18-45 years were included. After full adjustment, the LE8 score showed a negative correlation with infertility [per 1 SD increase, OR = 0.675, 95% CI: 0.553-0.824], with a linear dose-response relationship (non-linear P = 0.122). Similar linear negative correlations were found between health factor scores and infertility, with higher body mass index and glucose scores having a significantly lower risk of infertility. Stratified analyses showed a stronger inversed relationship between LE8 and infertility in younger populations. Moreover, mediation analysis revealed that uric acid concentration and lymphocyte count mediated the effect of LE8 on infertility (P < 0.05). LE8 and its subscale scores were linearly and negatively associated with infertility, which may be mediated in part through uric acid and lymphocyte count. Focusing on weight management and glycemic control can effectively reduce the risk of infertility.

Abstract P378: Life’s Essential 8 and Personal Income Level in Korean Adults

Introduction: The COVID-19 pandemic has raised global income inequality. This study analyzes the association between personal income level and cardiovascular health matrix (CHM) utilizing AHA life’s essential 8 in Koreans. Methods: This study used the 2019-2021 Korean National Health and Nutrition Examination Survey. Those who have missing data for assessing Life’s essential 8 were excluded. A final total of 12,923 participants were enrolled in this study. We used Life's essential 8 CHM Metrix as exposure, defined by the AHA. Diet redefined them appropriately for the Korean population. The unweighted average of each CHM score was calculated, and the cardiovascular health assessment groups were categorized as "high (80-100)," "medium (50-79)," and "low (0-49)" and then subjected to logistic regression analysis. The results were adjusted for sex, age, education, drinking status, perceived stress, and family history of physician chronic disease diagnosis. Results: Score of diet, physical activity, nicotine exposure, sleep health, body mass index, blood glucose, and blood pressure were positively associated with personal income level (Figure 1). Compared to the middle CVH group and lower income level group, higher income levels were associated with being in the high CVH group before (OR 1.6, 95%CI 1.4-1.8) and after adjusted (OR 1.5, 95%CI 1.2-1.7) confounders. Conclusions: This study showed that personal income was positively associated with the total life’s essential 8 CVH score and individual factors of life’s essential 8. Our results imply that socioeconomic factors, specifically personal income levels, exert influence even within what is considered an individual's realm (diet, physical activity, nicotine exposure, sleep health, body mass index, blood glucose, blood pressure) of control.

Autecology of the extant ostracod fauna of Lake Ohrid and adjacent waters - a key to paleoenvironmental reconstruction

Understanding the ecology of bioindicators such as ostracods is essential in order to reconstruct past environmental and climate change from analysis of fossil assemblages preserved in lake sediment cores. Knowledge of the ecology of ancient Lake Ohrid’s ostracod fauna is very limited and open to debate. In advance of the Ohrid ICDP-Drilling project, which has potential to generate high-resolution long-term paleoenvironmental data of global importance in paleoclimate research, we sampled Lake Ohrid and a wide range of habitat types in its surroundings to assess 1) the composition of ostracod assemblages in lakes, springs, streams, and short-lived seasonal water bodies, 2) the geographical distribution of ostracods, and 3) the ecological characteristics of individual ostracod species. In total, 40 species were collected alive, and seven species were preserved as valves and empty carapaces. Of the 40 ostracod species, twelve were endemic to Lake Ohrid. The most common genus in the lake was Candona, represented by 13 living species, followed by Paralimnocythere, represented by five living species. The most frequent species was Cypria obliqua. Species with distinct distributions included Heterocypris incongruens, Candonopsis kingsleii, and Cypria lacustris. The most common species in shallow, flooded areas was H. incongruens, and the most prominent species in ditches was C. kingsleii. C. lacustris was widely distributed in channels, springs, lakes, and rivers. Statistical analyses were performed on a “Lake Ohrid” dataset, comprising the subset of samples from Lake Ohrid alone, and an “entire” dataset comprising all samples collected. The unweighted pair group mean average (UPGMA) clustering was mainly controlled by species-specific depth preferences. Canonical Correspondence Analysis (CCA) with forward selection identified water depth, water temperature, and pH as variables that best explained the ostracod distribution in Lake Ohrid. The lack of significance of conductivity and dissolved oxygen in CCA of Ohrid data highlight the uniformity across the lake of the well-mixed waters. In the entire area, CCA revealed that ostracod distribution was best explained by water depth, salinity, conductivity, pH, and dissolved oxygen. Salinity was probably selected by CCA due to the presence of Eucypris virens and Bradleystrandesia reticulata in short-lived seasonal water bodies. Water depth is an important, although indirect, influence on ostracod species distribution, which is probably associated with other factors such as sediment texture and food supply. Some species appeared to be indicators for multiple environmental variables, such as lake level and water temperature.

Two-Stage Ensemble Deep Learning Model for Precise Leaf Abnormality Detection in Centella asiatica

Leaf abnormalities pose a significant threat to agricultural productivity, particularly in medicinal plants such as Centella asiatica (Linn.) Urban (CAU), where they can severely impact both the yield and the quality of leaf-derived substances. In this study, we focus on the early detection of such leaf diseases in CAU, a critical intervention for minimizing crop damage and ensuring plant health. We propose a novel parallel-Variable Neighborhood Strategy Adaptive Search (parallel-VaNSAS) ensemble deep learning method specifically designed for this purpose. Our approach is distinguished by a two-stage ensemble model, which combines the strengths of advanced image segmentation and Convolutional Neural Networks (CNNs) to detect leaf diseases with high accuracy and efficiency. In the first stage, we employ U-net, Mask-R-CNN, and DeepNetV3++ for the precise image segmentation of leaf abnormalities. This step is crucial for accurately identifying diseased regions, thereby facilitating a focused and effective analysis in the subsequent stage. The second stage utilizes ShuffleNetV2, SqueezeNetV2, and MobileNetV3, which are robust CNN architectures, to classify the segmented images into different categories of leaf diseases. This two-stage methodology significantly improves the quality of disease detection over traditional methods. By employing a combination of ensemble segmentation and diverse CNN models, we achieve a comprehensive and nuanced analysis of leaf diseases. Our model’s efficacy is further enhanced through the integration of four decision fusion strategies: unweighted average (UWA), differential evolution (DE), particle swarm optimization (PSO), and Variable Neighborhood Strategy Adaptive Search (VaNSAS). Through extensive evaluations of the ABL-1 and ABL-2 datasets, which include a total of 14,860 images encompassing eight types of leaf abnormalities, our model demonstrates its superiority. The ensemble segmentation method outperforms single-method approaches by 7.34%, and our heterogeneous ensemble model excels by 8.43% and 14.59% compared to the homogeneous ensemble and single models, respectively. Additionally, image augmentation contributes to a 5.37% improvement in model performance, and the VaNSAS strategy enhances solution quality significantly over other decision fusion methods. Overall, our novel parallel-VaNSAS ensemble deep learning method represents a significant advancement in the detection of leaf diseases in CAU, promising a more effective approach to maintaining crop health and productivity.

Abstract HUP6: Ideal Cardiovascular Health and the Intersectionality of Race/Ethnicity and Sexual Identity

Introduction: Disparities exist in cardiovascular health (CVH) by sexual identity and race/ethnicity separately, however an understanding of the intersectional effect of these identities has been limited. Objective: To evaluate differences in ideal CVH, as captured in the American Heart Association’s Life’s Essential 8 framework, across race/ethnicity and sexual identity. Methods: This study used data from the National Health and Nutrition Examination Survey (NHANES, 2007-2016). Non-institutionalized adults (18-59 years) without a history of cardiovascular disease/stroke and who were not pregnant at the time of the interview were included. Self-reported race/ethnicity was categorized as non-Hispanic Black (hereafter Black), Hispanic, non-Hispanic White (hereafter White), and another race. Self-reported sexual identity was categorized as straight and sexual minority (SM), which encompassed those who identified as lesbian, gay, bisexual, or something else. The primary outcome was total CVH score (range 0 -100), which is the unweighted average of 8 CVH components, assessed using questionnaire, dietary, and physical examination data. Sex-stratified regression models were developed for the overall CVH score and CVH components, adjusting for age and study year. Results: The sample included 12,256 adults (mean age 39.6 years [SD 11.7]). While Black (ß= -4.9, 95% CI -7.7, -2.0), Hispanic (ß= -4.9, 95% CI -9.6, -0.2), and White (ß = -5.9, 95% CI -8.8, -3.0) SM female adults had lower total CVH scores compared to their straight counterparts, female participants of another race and SM male adults of any race/ethnicity did not. Black SM female individuals had less favorable nicotine (ß= -20.9, 95% CI -32.3, -9.4) and blood pressure (ß= -7.2, 95% CI -13.8, -0.6) scores compared with Black straight females. Hispanic SM female individuals had less favorable body mass index scores (ß= -15.6, 95% CI -28.0, -3.2) compared with Hispanic straight females. Conclusions: CVH differed across racial/ethnic identities in SM females but not SM males. Longitudinal studies are needed to identify mechanisms driving CVH disparities in Black and Hispanic SM females.

Comparison of the associations between Life's Essential 8 and Life's Simple 7 with depression, as well as the mediating role of oxidative stress factors and inflammation: NHANES 2005–2018

BackgroundCardiovascular health (CVH) is closely associated with depression. However, Life's Essential 8 (LE8), a novel CVH measure, has not yet been clearly linked to depression. This study aims to explore the association between LE8 and depression, compare its advantages over Life's Simple 7 (LS7), and investigate the mediating effects of oxidative stress and inflammation. MethodsThis study investigated cross-sectional data of adults aged 20 and above from National Health and Nutrition Examination Survey (NHANES) 2005 to 2018. The LE8 score (ranging from 0 to 100) was derived from the American Heart Association's definition, based on the unweighted average of 8 metrics, classified as low cardiovascular health (CVH) (0–49), moderate CVH (50–79), and high CVH (80–100). Similar to LE8, LS7 scores were categorized into inadequate (0–7), average (8–10), or optimal (11–14) after calculating the unweighted mean of each component. Depression was diagnosed using the Patient Health Questionnaire (PHQ-9), with a score of ≥10 defining depression. Adjusted for sociodemographic factors and other risk factors for depression, weighted logistic regression and restricted cubic spline analysis were used to explore the correlation. Receiver operating characteristic (ROC) curves were used to study the associations between CVH scores and depression. Subsequently, subgroup analysis and sensitivity analysis were conducted, followed by an exploration of the mechanisms involved. ResultsA total of 7 cycles from 2005 to 2018 contained complete data. Weighted logistic regression showed that both LS7 and LE8 were significantly associated with depression. Specifically, for LE8, after adjustment, the risk of depression decreased by 52 % for moderate CVH compared to low CVH (OR: 0.48, 95 % CI: 0.41–0.57, P < 0.0001), while the risk decreased by 80 % for high CVH (OR: 0.20, 95 % CI: 0.15–0.26, P < 0.0001, Ptrend < 0.0001). For LS7, after adjustment, compared with inadequate CVH, the risk of depression decreased by 49 % for average CVH (OR: 0.51, 95 % CI: 0.34–0.78, P = 0.002), and by 55 % for optimal CVH (OR: 0.45, 95 % CI: 0.27–0.74, P = 0.002, Ptrend < 0.0001). Area under ROC curves for predicting depression were 0.672 (95 % CI, 0.66–0.684; P < 0.001) and 0.605 (95 % CI, 0.59–0.619; P < 0.001) for LE8 and LS7 (PDeLong < 0.001), respectively. Sensitivity analysis demonstrated the robustness of the association. GGT and WBC jointly mediated 9.62 % of this association (all P < 0.001). LimitationsThe cross-sectional study cannot infer causality. ConclusionsThe association between Life's Essential 8 and depression was stronger and more practical. Oxidative stress and inflammation mediate this association. Individuals with extremely poor cardiovascular health have a 7-fold increased risk of depression, highlighting the necessity of maintaining at least moderate cardiovascular health.

Heterogeneous ensemble machine learning to predict the asiaticoside concentration in centella asiatica urban

This study proposes a novel heterogeneous ensemble machine learning methodology to predict the concentration of asiaticoside in Centella asiatica (CA-CA) in the context of the lack of an effective prediction method capable of accurately estimating its quantity based on various growing environmental factors. The accurate prediction of the asi-aticoside concentration in CA-CA holds great significance in optimizing cultivation practices and improving the efficacy of the derived medicinal products. The presented approach aims to address this crucial need by employing a diverse ensemble of machine learning techniques. The proposed model integrates several machine learning tech-niques, including the standard long short-term memory (LSTM), gated recurrent unit (GRU), convolutional long short-term memory (ConvLSTM), and attention-based LSTM, by utilizing a differential evolution algorithm to optimize the ensemble model's weights. The developed model is called the heterogeneous ensemble machine learning model (He-ML). Experimental results demonstrate that the He-ML achieves an im-pressive root-mean-square error (RMSE) value of 4.76, which is up to 12.48 % lower than the RMSE. The findings highlight the advantages of employing an ensemble model over a single model, as the ensemble model achieves an RMSE value that is 14.67 % lower than that of the individual machine learning model. The utilization of differential evolution as the decision fusion strategy provides a notable improvement over the unweighted average approach. As a result, the RMSE value achieved is 8.46 % lower than that obtained with the unweighted average (UWA) technique.

Abstract 12026: Life Essential 8 is Positively Associated With a Higher Executive Cognitive Function in US Children - ABCD Study

Background: While the association between cardiovascular health components has been linked to a higher risk of cognitive decline in adults, the relationship between cardiovascular health indicators and executive/cognitive function in US children remains poorly understood. Research Question: Are measures of cardiovascular health associated with executive, cognitive function and in US children? Aims: The purpose of this study was to determine cross-sectional associations of Life Essential 8 components with executive and cognitive function. Methods: This was a baseline analysis from a multicenter, prospective cohort study, known as the Adolescent Brain Cognitive Development (ABCD) study. Data were analyzed from the baseline ABCD data release 1.0. Participants were children aged 9 to 10 years old recruited in 21 US cities. Participants with incomplete questionnaire data for dietary intake, physical activity, nicotine exposure, or sleep health; health evaluation for body mass index, blood lipids, glycated hemoglobin, or blood pressure; or covariate data were excluded. Each cardiovascular health indicator ranges from 0 to 100 points, enabling the calculation of a composite cardiovascular health score as the unweighted average of all components, which also ranges from 0 to 100 points. The National Institutes of Health Toolbox neurocognitive battery assesses general cognitive ability, executive function, and learning/memory using raw scores and age-corrected measures. Results: A total of 978 individuals were analyzed. The mean (SD) age was 9.9 (0.2) years, 44.9% were girls, and 53.4% were White. Individuals with more favorable cardiovascular health behaviors showed better executive cognitive function (β = 0.170; CI 95%, 0.076 to 0.265; p = 0.001), and overall cardiovascular health was associated with higher executive cognitive function (β = 0.209; CI 95%, 0.067 to 0.351; p = 0.002). Conclusions: Cardiovascular health behaviors and overall cardiovascular health were directly linked to cognitive and executive function in 9-10-year-old US children, supporting public health recommendations to promote these behaviors for their potential benefits to cognitive function and brain development.

Patient Health Questionnaire-9 Item Pairing Predictiveness for Prescreening Depressive Symptomatology: Machine Learning Analysis.

Anhedonia and depressed mood are considered the cardinal symptoms of major depressive disorder. These are the first 2 items of the Patient Health Questionnaire (PHQ)-9 and comprise the ultrabrief PHQ-2 used for prescreening depressive symptomatology. The prescreening performance of alternative PHQ-9 item pairings is rarely compared with that of the PHQ-2. This study aims to use machine learning (ML) with the PHQ-9 items to identify and validate the most predictive 2-item depressive symptomatology ultrabrief questionnaire and to test the generalizability of the best pairings found on the primary data set, with 6 external data sets from different populations to validate their use as prescreening instruments. All 36 possible PHQ-9 item pairings (each yielding scores of 0-6) were investigated using ML-based methods with logistic regression models. Their performances were evaluated based on the classification of depressive symptomatology, defined as PHQ-9 scores ≥10. This gave each pairing an equal opportunity and avoided any bias in item pairing selection. The ML-based PHQ-9 items 2 and 4 (phq2&4), the depressed mood and low-energy item pairing, and PHQ-9 items 2 and 8 (phq2&8), the depressed mood and psychomotor retardation or agitation item pairing, were found to be the best on the primary data set training split. They generalized well on the primary data set test split with area under the curves (AUCs) of 0.954 and 0.946, respectively, compared with an AUC of 0.942 for the PHQ-2. The phq2&4 had a higher AUC than the PHQ-2 on all 6 external data sets, and the phq2&8 had a higher AUC than the PHQ-2 on 3 data sets. The phq2&4 had the highest Youden index (an unweighted average of sensitivity and specificity) on 2 external data sets, and the phq2&8 had the highest Youden index on another 2. The PHQ-2≥2 cutoff also had the highest Youden index on 2 external data sets, joint highest with the phq2&4 on 1, but its performance fluctuated the most. The PHQ-2≥3 cutoff had the highest Youden index on 1 external data set. The sensitivity and specificity achieved by the phq2&4 and phq2&8 were more evenly balanced than the PHQ-2≥2 and ≥3 cutoffs. The PHQ-2 did not prove to be a more effective prescreening instrument when compared with other PHQ-9 item pairings. Evaluating all item pairings showed that, compared with alternative partner items, the anhedonia item underperformed alongside the depressed mood item. This suggests that the inclusion of anhedonia as a core symptom of depression and its presence in ultrabrief questionnaires may be incompatible with the empirical evidence. The use of the PHQ-2 to prescreen for depressive symptomatology could result in a greater number of misclassifications than alternative item pairings.

Automated cervical cell segmentation using deep ensemble learning

BackgroundCervical cell segmentation is a fundamental step in automated cervical cancer cytology screening. The aim of this study was to develop and evaluate a deep ensemble model for cervical cell segmentation including both cytoplasm and nucleus segmentation.MethodsThe Cx22 dataset was used to develop the automated cervical cell segmentation algorithm. The U-Net, U-Net + + , DeepLabV3, DeepLabV3Plus, Transunet, and Segformer were used as candidate model architectures, and each of the first four architectures adopted two different encoders choosing from resnet34, resnet50 and denseNet121. Models were trained under two settings: trained from scratch, encoders initialized from ImageNet pre-trained models and then all layers were fine-tuned. For every segmentation task, four models were chosen as base models, and Unweighted average was adopted as the model ensemble method.ResultsU-Net and U-Net + + with resnet34 and denseNet121 encoders trained using transfer learning consistently performed better than other models, so they were chosen as base models. The ensemble model obtained the Dice similarity coefficient, sensitivity, specificity of 0.9535 (95% CI:0.9534–0.9536), 0.9621 (0.9619–0.9622),0.9835 (0.9834–0.9836) and 0.7863 (0.7851–0.7876), 0.9581 (0.9573–0.959), 0.9961 (0.9961–0.9962) on cytoplasm segmentation and nucleus segmentation, respectively. The Dice, sensitivity, specificity of baseline models for cytoplasm segmentation and nucleus segmentation were 0.948, 0.954, 0.9823 and 0.750, 0.713, 0.9988, respectively. Except for the specificity of cytoplasm segmentation, all metrics outperformed the best baseline models (P < 0.05) with a moderate margin.ConclusionsThe proposed algorithm achieved better performances on cervical cell segmentation than baseline models. It can be potentially used in automated cervical cancer cytology screening system.

Distilling Knowledge From an Ensemble of Vision Transformers for Improved Classification of Breast Ultrasound

To develop a deep learning model for the automated classification of breast ultrasound images as benign or malignant. More specifically, the application of vision transformers, ensemble learning, and knowledge distillation is explored for breast ultrasound classification. Single view, B-mode ultrasound images were curated from the publicly available Breast Ultrasound Image (BUSI) dataset, which has categorical ground truth labels (benign vs malignant) assigned by radiologists and malignant cases confirmed by biopsy. The performance of vision transformers (ViT) is compared to convolutional neural networks (CNN), followed by a comparison between supervised, self-supervised, and randomly initialized ViT. Subsequently, the ensemble of 10 independently trained ViT, where the ensemble model is the unweighted average of the output of each individual model is compared to the performance of each ViT alone. Finally, we train a single ViT to emulate the ensembled ViT using knowledge distillation. On this dataset that was trained using five-fold cross validation, ViT outperforms CNN, while self-supervised ViT outperform supervised and randomly initialized ViT. The ensemble model achieves an area under the receiver operating characteristics curve (AuROC) and area under the precision recall curve (AuPRC) of 0.977 and 0.965 on the test set, outperforming the average AuROC and AuPRC of the independently trained ViTs (0.958±0.05 and 0.931±0.016). The distilled ViT achieves an AuROC and AuPRC of 0.972 and 0.960. Both transfer learning and ensemble learning can each offer increased performance independently and can be sequentially combined to collectively improve the performance of the final model. Furthermore, a single vision transformer can be trained to match the performance of an ensemble of a set of vision transformers using knowledge distillation.

Better Life's Essential 8 Is Associated With Lower Risk of Diabetic Kidney Disease: A Community-Based Study.

Background Diabetic kidney disease (DKD) is a common diabetic complication and increases the complexity of diabetes management. No prospective study has focused on the association between DKD and Life's Essential 8 (LE8). Our study aims to examine the association between LE8 and DKD risk. Methods and Results A total of 7605 participants, aged 54.32±9.77 years, and 4688 participants, aged 56.11±10.38 years, were included in the longitudinal and trajectory analyses, respectively, from 2006 to 2020. The DKD was confirmed using data collected during each follow-up. LE8 was based on 4 health behaviors and 4 health factors. The range of each metric was 0 to 100, and the overall LE8 score was calculated as the unweighted average of all 8 component metric scores. The trajectories of LE8 during 2006 to 2010 were classified using latent mixture models. Cox models and restricted cubic splines were applied. After a median follow-up of 12.41 and 6.71 years in longitudinal and trajectory analyses, respectively, the DKD incidence decreased, with the LE8 level increasing (P-trend<0.05), and the linearity assumption for this relationship (P-nonlinear=0.685) had been satisfied. Adjusted hazard ratios (HRs) for the highest tertile were 0.77 (95% CI, 0.69-0.87) and 0.70 (95% CI, 0.62-0.78) in baseline and time-updated LE8 scores, respectively, compared with the lowest tertile. Adjusted HR was 0.53 (95% CI, 0.41-0.69) for the stable-high pattern compared with the stable-low pattern. Conclusions Although LE8 is an indicator of cardiovascular health, the beneficial impact of a high LE8 score is also evident in the protection of renal health among patients with diabetes.

Life’s Essential 8 and Mortality in US Adults with Chronic Kidney Disease

Introduction: The current prevalence of chronic kidney disease (CKD) is substantial, and CKD individuals face a heightened risk of mortality, encompassing both all-cause and cause-specific outcomes. The current study aims to investigate the potential impact of adhering to Life’s Essential 8 (LE8) on reducing mortality among CKD individuals. Methods: Using the National Health and Nutrition Survey (NHANES) data from 2005 to 2018, we analyzed 22,420 US adults (≥20 years old). CKD is defined by urinary albumin-to-creatinine ratio (≥30 mg/g or 3 mg/mmol) and estimated glomerular filtration rate (<60 mL/min/1.73 m²). The components of LE8, including diet, physical activity (PA), nicotine exposure, sleep, body mass index, blood lipids, blood glucose, and blood pressure (BP), were measured and given a score of 0–100. The total LE8 score was the unweighted average of all components and was divided into low cardiovascular health (CVH) (0–49), moderate CVH (50–79), and high CVH (80–100). A Cox proportional hazards regression model was used to explore the associations of LE8 with all-cause, cardiovascular disease (CVD), and cancer mortality, which were followed prospectively by the National Center for Health Statistics until December 31, 2019. Results: In the overall population, individuals with moderate CVH had a 47% lower risk of CKD, while high CVH was linked to a 55% lower risk compared to low CVH. During a median follow-up of 7.58 years, CKD individuals had a 93% higher all-cause mortality rate and a 149% higher CVD mortality rate compared to those without CKD. Among the CKD individuals, every 10-point increase in the LE8 score was associated with reduced risks of 17% for all-cause mortality (especially PA, nicotine exposure, blood glucose, and BP), 18% for CVD mortality (especially PA), and 12% for cancer mortality (especially PA and sleep health). In additional and sensitivity analysis, the results remained significant after further consideration of potential confounding of renal function. Additionally, LE8 demonstrated superior risk stratification for CVD mortality among CKD patients compared with LS7. Interaction was observed between LE8 and age, education level, marital status, and drinking status. Conclusion: The current study demonstrates that adherence to higher LE8 levels within CKD individuals is associated with a reduced risk of both all-cause and cause-specific mortality.

Beyond Heart Murmur Detection: Automatic Murmur Grading From Phonocardiogram.

Murmurs are abnormal heart sounds, identified by experts through cardiac auscultation. The murmur grade, a quantitative measure of the murmur intensity, is strongly correlated with the patient's clinical condition. This work aims to estimate each patient's murmur grade (i.e., absent, soft, loud) from multiple auscultation location phonocardiograms (PCGs) of a large population of pediatric patients from a low-resource rural area. The Mel spectrogram representation of each PCG recording is given to an ensemble of 15 convolutional residual neural networks with channel-wise attention mechanisms to classify each PCG recording. The final murmur grade for each patient is derived based on the proposed decision rule and considering all estimated labels for available recordings. The proposed method is cross-validated on a dataset consisting of 3456 PCG recordings from 1007 patients using a stratified ten-fold cross-validation. Additionally, the method was tested on a hidden test set comprised of 1538 PCG recordings from 442 patients. The overall cross-validation performances for patient-level murmur gradings are 86.3% and 81.6% in terms of the unweighted average of sensitivities and F1-scores, respectively. The sensitivities (and F1-scores) for absent, soft, and loud murmurs are 90.7% (93.6%), 75.8% (66.8%), and 92.3% (84.2%), respectively. On the test set, the algorithm achieves an unweighted average of sensitivities of 80.4% and an F1-score of 75.8%. This study provides a potential approach for algorithmic pre-screening in low-resource settings with relatively high expert screening costs. The proposed method represents a significant step beyond detection of murmurs, providing characterization of intensity, which may provide an enhanced classification of clinical outcomes.