Classification Categories Research Articles

#3337 ACCURACY OF ESTIMATED GLOMERULAR FILTRATION RATE EQUATIONS IN PATIENTS WITH DISCORDANCES BETWEEN CREATININE AND CYSTATIN C-BASED ESTIMATIONS

Abstract Background and Aims Cystatin C is recommended for use along with creatinine in estimating glomerular filtration rate (eGFR) when precise estimates are needed for clinical decision-making. Although eGFR based on both creatinine and cystatin (eGFRcr-cys) is the most accurate in research studies, it is uncertain as to whether this remains true in real-world settings, particularly when there are large discordances between eGFR based on creatinine (eGFRcr) and that based on cystatin C (eGFRcys). Method We included 6185 adults from the Stockholm Creatinine Measurements (SCREAM) project referred for plasma clearance of iohexol in Stockholm, Sweden, who had 9404 concurrent measurements of creatinine, cystatin C and iohexol clearance. The performance of eGFRcr, eGFRcys and eGFRcr-cys was assessed against mGFR with bias, P30 and correct classification of GFR strata. We stratified analyses within three categories: eGFRcys at least 20% lower than eGFRcr (eGFRcys < eGFRcr), eGFRcys within 20% of eGFRcr (eGFRcys ≈ eGFRcr) and eGFRcys at least 20% higher than eGFRcr (eGFRcys > eGFRcr). Bias was expressed as the median difference in estimated GFR minus mGFR, with negative biases indicating underestimation of mGFR. P30 described the percentage of individuals with eGFR within 30% of mGFR. Correct classification of GFR categories was defined as agreement of eGFR and mGFR categories using the KDIGO GFR categories (<15, 15-29, 30-44, 45-59, 60-89 and ≥90 ml/min/1.73 m2). Results eGFRcr and eGFRcys were similar in 4226 (45%) of samples, and there all three estimating equations displayed similar performance (Table 1). In contrast, eGFRcr-cys was much more accurate in cases of discordance. For example, when eGFRcys < eGFRcr (47% of samples), median biases were 15.0 (overestimation), −8.5 (underestimation) and 0.8 ml/min/1.73 m2 for eGFRcr, eGFRcys and eGFRcr-cys, respectively; P30 was 50%/73%/84%, respectively; and correct classification was 38%/45%/62%, respectively. When eGFRcys > eGFRcr (8% of samples), median biases were −4.5, 8.4, and 1.4 ml/min/1.73 m2. Findings were consistent among individuals with cardiovascular disease, heart failure, diabetes mellitus, liver disease and cancer (Figure 1). Conclusion When large discordances between eGFRcr and eGFRcys are found in clinical practice, eGFRcr-cys is more accurate than either eGFRcr or eGFRcys.

Multi-Task Romanian Email Classification in a Business Context

Email classification systems are essential for handling and organizing the massive flow of communication, especially in a business context. Although many solutions exist, the lack of standardized classification categories limits their applicability. Furthermore, the lack of Romanian language business-oriented public datasets makes the development of such solutions difficult. To this end, we introduce a versatile automated email classification system based on a novel public dataset of 1447 manually annotated Romanian business-oriented emails. Our corpus is annotated with 5 token-related labels, as well as 5 sequence-related classes. We establish a strong baseline using pre-trained Transformer models for token classification and multi-task classification, achieving an F1-score of 0.752 and 0.764, respectively. We publicly release our code together with the dataset of labeled emails.

Effect of passive ankle movement in the sitting position on the symptoms of chronic venous insufficiency with long-term observation.

Chronic venous insufficiency (CVI) is the most common vascular disease. One major risk factor for its development is either long-term sitting or standing in the same position and the nature of the work performed. This study aims to assess the effectiveness of passive ankle movement in the sitting position performed using the Bella Vena robot for the symptoms of CVI with long-term observation. A group of 58 patients (mean age: 59.69 ±14.59 years) with CVI in CEAP (Clinical (C), Etiological (E), Anatomical (A), and Pathophysiological (P)) classification categories 2 and 3, and a group of 37 (mean age: 51.49 ±14.86 years) healthy volunteers performing sedentary work for at least 6 h during the working day were enrolled into the study. The total duration of observation lasted 8 months (8 visits), during which the following parameters were assessed at the beginning and end of this period: pain intensity (according to the visual analogue scale (VAS)), level of saturation on the toe, pulse rate, and lower limb Doppler ultrasound evaluation of reflux parameters. The exercises used in people with CVI resulted in a significant reduction (p ≤ 0.01) in the occurrence of symptoms. Among all respondents, after 8 months of exercise, a significant reduction in pain level according to the VAS of the lower limbs, an improvement in saturation at the toe level, and a reduction in venous reflux was recorded (p ≤ 0.05). Home exercises with the use of an automatic exercise rehabilitation device alleviated significant symptoms in patients with CVI and improved the calf muscle pump.

Identification and analysis of the actual research issue of "Digital transformation of the oil and gas sector"

This paper is devoted to identifying and analyzing one of the actual research issues of the topic "Digital transformation of the oil and gas sector". The actual area and methods of research were determined by the materials of the Society of Petroleum Engineers, and for the disclosure of the scientific aspect of the identified actual issue, publications indexed in the bibliographic and abstract database of peer-reviewed scientific literature Scopus were used. This approach, according to the author of the article, reduces the bias in the selection of relevant scientific issues, as it reflects the interests of both the oil and gas sector and scientific community experts. In this paper, the research issues were determined both by the classification categories of the search.spe.org platform, and by the authors’ keywords of the articles indexed in Scopus. A brief review of the most cited articles revealing the topic of such works was carried out for a more detailed disclosure of the research objectives. The results of the analysis show that within the broad topic of digital transformation of the oil and gas sector, a task relevant to both industry (Society of Petroleum Engineers) and academic institutions, can be disclosed using the term "well drilling" and the random forest method.

Overlapping group screening for binary cancer classification with TCGA high-dimensional genomic data.

Precision medicine has been a global trend of medical development, wherein cancer diagnosis plays an important role. With accurate diagnosis of cancer, we can provide patients with appropriate medical treatments for improving patients' survival. Since disease developments involve complex interplay among multiple factors such as gene-gene interactions, cancer classifications based on microarray gene expression profiling data are expected to be effective, and hence, have attracted extensive attention in computational biology and medicine. However, when using genomic data to build a diagnostic model, there exist several problems to be overcome, including the high-dimensional feature space and feature contamination. In this paper, we propose using the overlapping group screening (OGS) approach to build an accurate cancer diagnosis model and predict the probability of a patient falling into some disease classification category in the logistic regression framework. This new proposal integrates gene pathway information into the procedure for identifying genes and gene-gene interactions associated with the classification of cancer outcome groups. We conduct a series of simulation studies to compare the predictive accuracy of our proposed method for cancer diagnosis with some existing machine learning methods, and find the better performances of the former method. We apply the proposed method to the genomic data of The Cancer Genome Atlas related to lung adenocarcinoma (LUAD), liver hepatocellular carcinoma (LHC), and thyroid carcinoma (THCA), to establish accurate cancer diagnosis models.

ТРАНСНАЦІОНАЛЬНІ АСПЕКТИ ПОЕТИКИ РОМАНУ МАР’ЯНИ ГАПОНЕНКО «ХТО ТАКА МАРТА?»

The article is devoted to researching the creativity of the modern German-speaking writer of Ukrainian origin Marjana Gaponenko. The object of the research is the novel “Who is Martha?” (2012), for which the author received a prestigious literary award in 2013 – the Adelbert von Chamisso Prize. The aim of the research is to carry out a terminological distinction of concepts that since the 90s of the 20th century have been increasingly used to denote literature of migrant authors, as well as to identify and analyze those characteristic features of poetics by which Marjana Gaponenko’s novel can be determined as transnational. The task of the study is to determine the peculiarities of transnational literature and carry out a three-level (biographical-referential, thematic-content and text-structural) decoding of the novel “Who is Martha?” with a focus on narrative techniques of transnational writing. Biographical, historicalliterary, philological, intertextual, intermedial and hermeneutic methods of research were involved in order to achieve the stated aim and solve the tasks. Conclusion. In the postmodern era, traditional concepts of national literature, culture, and identity are being more and more questioned and become conditional. Transnational movements and processes of hybridization level national, ethnic, and cultural boundaries, and migration itself becomes an integral part of existence and often an impetus for literary creativity. Despite the fact that literary texts against the background of the migration experience were written earlier as well, it was in the 1990s that this phenomenon acquired a new expression and sound. Transnational literature with its immanent explicit and implicit reflection on transculturality, separating from the homogenizing essentialist concepts of identity and culture, as well as national and cultural affiliations, overcomes the contradictions between national and minority literature, between “own” and “foreign” and offers a productive approach to texts that were previously assigned to classification categories focused primarily on authors. The cognitive value of this concept lies in its special validity when studying the literary works by transmigrant authors as representatives of a new generation that freely chooses its place of residence and the language of literary expression. The conducted three-level decoding of Marjana Gaponenko’s novel substantiates the thesis that it belongs to transnational literature, the characteristic features of which are manifested at all levels of the artistic organization of the work. At the biographical-referential level, Marjana Gaponenko, taking into account her life and creative path, can be called a transnational author who belongs to postmodern transmigrants. This definition makes it possible to analyze the peculiarities of poetics in the novel “Who is Martha?”, which artistically implements the autobiographical experience of migration at the thematic-content level, but goes beyond these limits. While other migrant authors mostly deal with their own migration, artistic experience of identity crisis, loss and alienation, Marjana Gaponenko explores global essential topics, considering them in a broad cultural, historical and philosophical context. At the text-structural level, characteristic manifestations of transnationality are the spatial structure of the text, the use of dynamic heroes with hybrid identities (Marjana Gaponenko’s characters are postmodern cosmopolitans with inherent linguistic and cultural hybridity, who are searching for and eventually find essential truths beyond various boundaries), the presence of elements of analepsis and prolepsis, involvement of double characters, the inclusion of multilingualism and dialects, the use of stereotypes, tendency to blur genres, etc. Marjana Gaponenko’s novel with its cultural, linguistic and literary hybridity, as well as peculiar manifestations of intertextuality and intermediality, ultimately not only expands the space of reader’s reception and literary knowledge, but also ensures the development of a productive transcultural and transnational dialogue.

Mode of delivery and perinatal outcomes by modified World Health Organization classification of maternal cardiovascular risk in pregnancy

Cardiac disease is a leading cause of maternal morbidity and mortality in the United States, and an increasing number of patients with known cardiac disease are reaching childbearing age. Although guidelines indicate that cesarean deliveries should be reserved for obstetrical indications, rates of cesarean delivery among obstetrical patients with cardiovascular disease are higher than those of the general population. This study aimed to evaluate mode of delivery and perinatal outcomes among patients with low-risk and moderate to high-risk cardiac disease as defined by the modified World Health Organization classification of maternal cardiovascular risk. We performed a retrospective cohort study of obstetrical patients with known cardiac disease, as defined by the modified World Health Organization cardiovascular classification categories in pregnancy, who underwent a perinatal transthoracic echocardiogram at a single academic medical center between October 1, 2017 and May 1, 2022. Demographics, clinical characteristics, and perinatal outcomes were collected. Comparisons were made between patients with low- (modified World Health Organization Class I) and moderate to high-risk (modified World Health Organization Class II-IV) cardiac disease using chi-square, Fisher exact, or Student t-tests. Cohen d tests were used to estimate the effect size between group means. Logistic regression models were used to evaluate the odds of vaginal and cesarean delivery in low- and moderate to high-risk groups. A total of 108 participants were eligible for inclusion, with 41 participants in the low-risk cardiac group and 67 in the moderate to high-risk group. Participants had a mean age of 32.1 (±5.5) years at the time of delivery and a mean pregravid body mass index of 29.9 (±7.8) kg/m2. Chronic hypertension (13.9%) and a history of hypertensive disorder of pregnancy (14.9%) were the most common comorbid medical conditions. In total, 17.1% of the sample had a history of a cardiac event (eg, arrhythmia, heart failure, myocardial infarction). Rates of vaginal and cesarean deliveries were similar between the low- and moderate to high-risk cardiac groups. Patients in the moderate to high-risk cardiac group were more likely to be admitted to the intensive care unit during pregnancy (odds ratio, 7.8; P<.05) and experience severe maternal morbidity compared with patients in the low-risk cardiac group (P<.01). Mode of delivery was not associated with severe maternal morbidity in the higher-risk cardiac group (odds ratio, 3.2; P=.12). In addition, infants of mothers with higher-risk disease were more likely to be admitted to the neonatal intensive care unit (odds ratio, 3.6; P=.06) and have longer neonatal intensive care unit stays (P=.005). There was no difference in mode of delivery by modified World Health Organization cardiac classification, and mode of delivery was not associated with risk of severe maternal morbidity. Despite the overall increased risk of morbidity in the higher-risk group, vaginal delivery should be considered as an option for certain patients with well-compensated cardiac disease. However, larger studies are needed to confirm these findings.

A study of examiner accuracy in cartridge case comparisons. Part 2: Examiner use of the AFTE range of conclusions

This report describes an analysis of how examiners used the Association of Firearm and Toolmark Examiners (AFTE) Range of Conclusions in a controlled study undertaken to estimate examiner error rates in comparing cartridge cases. Results of the error rate analysis are reported in [1]; this paper focuses on a broader analysis of how the entire collection of classification categories, especially those in the Inconclusive range, were used by the participating examiners. Volunteer active examiners with AFTE membership or working in laboratories that participate in Association of Crime Laboratory Directors (ASCLD) were provided with 15 sets of three known and one questioned cartridge cases fired from a collection of 25 new Ruger SR9 handguns. Remington 9-mm Luger (manufacturer designation L9MM3) ammunition was used and comparison sets were made up of cartridge cases fired within 100 cartridges of each other for each gun. Examiners were provided with a background survey, an answer sheet allowing for the AFTE Range of Conclusions, and return shipping materials. The participating examiners were provided with both same-source and different-source comparison sets allowing the study to assess both error rates.Responses were received from 218 participating examiners. The overall rate of false-negatives was estimated as 0.367 % from comparisons known to be from the same firearm but reported as eliminations. The overall rate of false-positives was estimated as 1.01 % from comparisons known to be from different firearms but reported as identifications. In the case of true different-source examinations, it is clear that the three Inconclusive categories and the Elimination category are not used consistently by all examiners. We identify five different apparent patterns of use of the AFTE Range of Conclusions scale, and discuss possible reasons for and implications of these differences.

Natural History of Internal Carotid Artery Stenosis Progression

To investigate the natural history of internal carotid artery (ICA) stenosis progression. This single-institution retrospective cohort study analyzed patients diagnosed with internal carotid artery stenosis of 50% or greater on duplex ultrasound (DUS) from 2015 to 2022. Subjects were drawn from our institutional IAC-accredited noninterventional vascular laboratory database. Progression was defined as an increase in stenosis classification category. Imaging, demographic, and clinical data was obtained from our institutional electronic medical record via a database mining query. Cases were analyzed at the patient level, with severity corresponding to the greatest degree of ICA stenosis on the bilateral index and follow-up studies. Of 1954 unique patients imaged during the study period, 555 were followed with DUS for over 1 year. Table I summarizes demographic and historical factors for the entire cohort, stratified by availability of follow-up data. Patients with follow-up were more likely to have a history of stroke or transient ischemic attack were more likely to be taking antihypertensives, aspirin, statins, and P2Y12 inhibitors, and were more likely to undergo CEA or TCAR after diagnosis. They were less likely to have diabetes and chronic kidney disease. There were no differences in subsequent stroke or transient ischemic attack rates between groups. Of 555 followed patients, 55.3% at the index imaging study had moderate (50%-69%) stenosis, 34.6% had severe (70-99%) stenosis, and 10.1% had ICA occlusions. Patients were followed with DUS for a mean of 3.4 ± 1.8 years, with no significant difference in follow-up between stable and progressing patients. Mean time to progression was 2.2 ± 1.4 years. By the end of the follow-up period, 20.5% of followed patients experienced stenosis progression. Table II compares demographics, histories, and outcomes of stable vs progressing patients, grouped by initial stenosis severity. There were no significant differences between groups regarding comorbidities, medications, or procedure history. At diagnosis, 58.5% of stable patients and 64.9% of progressing patients were on best medical treatment (statin + antiplatelet agent) (P = .21). In both moderate and severe groups, stable patients underwent CEA more frequently than progressing patients. These results suggest that carotid disease progression occurs in a clinically significant portion of patients, affecting one-fifth of our cohort in an average of 26 months. No reliable factors emerged to predict progression or stroke in these patients. Less than two-thirds of these patients were found to be managed with best medical treatment, suggesting opportunities for further optimization.Table IPatient characteristicsDemographicsFollow-up (n = 555)No Follow-up (n = 1399)P valueMean age at diagnosis, years (range)72.9 (25-97)72.1 (18-105).12Female sex249 (44.9%)608 (43.5%).57Comorbidities Prior smoking277 (49.9%)663 (47.4%).32 Hypertension231 (41.6%)616 (44.0%).33 Hyperlipidemia217 (39.1%)601 (43.0%).12 Diabetes mellitus79 (14.2%)286 (20.4%).001 Coronary artery disease169 (30.5%)448 (32.0%).50 Myocardial infarction18 (3.2%)68 (4.9%).12 Chronic kidney disease79 (14.2%)286 (20.4%).001 Stroke or transient ischemic attack320 (57.7%)632 (45.2%).001 Vasculitis9 (1.6%)27 (1.9%).65 Head and neck cancer28 (5.0%)51 (3.6%).16Medications at diagnosis Antihypertensives393 (70.8%)882 (63.0%).001 Aspirin345 (62.2%)732 (52.3%)<.001 Statin392 (70.6%)893 (63.8%).004 P2Y12 inhibitor348 (62.7%)793 (56.7%).015 Anticoagulation54 (9.7%)148 (10.6%).58 Cilostazol15 (2.7%)27 (1.9%).29Procedure history Prior carotid endarterectomy10 (1.8%)29 (2.1%).70 Prior Transcarotid artery revascularization2 (0.4%)13 (0.9%).19 Prior transfemoral carotid stenting5 (0.9%)5 (0.4%).13Outcomes Subsequent CEA98 (17.7%)180 (12.9%).006 Subsequent transcarotid artery revascularization35 (6.3%)54 (3.9%).019 Subsequent transfemoral carotid stenting11 (2.0%)13 (0.9%).06 Subsequent cerebrovascular accident10 (1.8%)19 (1.4%).47 Subsequent transient ischemic attack2 (0.4%)5 (0.4%).99 Open table in a new tab Table IIComparison of stable and progressing patients, stratified by severityDemographicsModerate (50%-69%) StenosisSevere (70%-99%) StenosisP valueStable (n = 196)Progression (n = 111)Stable (n = 189)Progression (n = 3)Age at diagnosis.822Female sex92 (46.9%)49 (44.1%)84 (44.4%)2 (66.7%).832History Stroke or TIA108 (55.1%)72 (64.9%)113 (59.8%)2 (66.7%).402 Prior smoking96 (49.0%)62 (55.9%)91 (48.1%)1 (33.3%).533 Hypertension88 (44.9%)43 (38.7%)83 (43.9%)1 (33.3%).732 Hyperlipidemia81 (41.3%)46 (41.4%)77 (40.7%)0 (0.0%).551 Diabetes mellitus36 (18.4%)14 (12.6%)21 (11.1%)0 (0.0%).172 Chronic kidney disease36 (18.4%)14 (12.6%)21 (11.1%)0 (0.0%).172 Coronary artery disease73 (37.2%)35 (31.5%)48 (25.4%)0 (0.0%).054 Myocardial Infarction10 (5.1%)3 (2.7%)2 (1.1%)0 (0.0%).136 Vasculitis4 (2.0%)1 (0.9%)2 (1.1%)1 (33.3%)<.001a Head and neck cancer11 (5.6%)5 (4.5%)9 (4.8%)0 (0.0%).942Medications at diagnosis Antihypertensives144 (73.5%)84 (75.7%)137 (72.5%)2 (66.7%).93 Aspirin129 (65.8%)75 (67.6%)117 (61.9%)2 (66.7%).763 Statins143 (73.0%)85 (76.6%)139 (73.5%)1 (33.3%).383 P2Y12 inhibitors129 (65.8%)77 (69.4%)118 (62.4%)1 (33.3%).41 Anticoagulation19 (9.7%)11 (9.9%)19 (10.1%)0 (0.0%).952 Cilostazol6 (3.1%)4 (3.6%)3 (1.6%)0 (0.0%).694Procedure history CEA prior to diagnosis5 (2.6%)3 (2.7%)2 (1.1%)0 (0.0%).683 Transcarotid artery revascularization prior to diagnosis2 (1.0%)0 (0.0%)0 (0.0%)0 (0.0%).376 Transfemoral carotid stenting prior to diagnosis3 (1.5%)2 (1.8%)0 (0.0%)0 (0.0%).36Outcomes CEA after diagnosis38 (19.4%)11 (9.9%)45 (23.8%)0 (0.0%).023 Transcarotid artery revascularization after diagnosis12 (6.1%)8 (7.2%)13 (6.9%)0 (0.0%).946 Transfemoral carotid stenting after diagnosis1 (0.5%)3 (2.7%)5 (2.6%)1 (33.3%)<.001a Stroke after diagnosis2 (1.0%)1 (0.9%)3 (1.6%)1 (33.3%)<.001a Transient ischemic attack after diagnosis1 (0.5%)0 (0.0%)1 (0.5%)0 (0.0%).897aAnalysis limited by small sample size. Open table in a new tab

Children’s interstitial lung disease: Multidetector computed tomography patterns and correlations between imaging and histopathology

PurposeChildhood interstitial lung disease (chILD) is an umbrella concept covering a wide range of rare lung diseases, many of which are unique to childhood. The diagnosis is based on clinical presentation, multidetector computed tomography (MDCT), genetic testing, lung-function testing, and lung biopsy. Because knowledge of the usefulness of MDCT pattern recognition in ChILD is at present limited, we examined the occurrence of MDCT patterns in children with histologically confirmed interstitial lung disease. MethodWe searched the biopsy, MDCT, and clinical information database of a single national paediatric referral hospital for 2004–2020. Data were from affected children under age 18. MDCT images we reanalysed while blinded to the identity and referral information. ResultsWe included 90 patients, of whom 63 (70 %) were male. The median age at biopsy was 1.3 years (interquartile range 0.1–16.8). Biopsy findings fell into 26 histological classes covering all nine chILD classification categories. We recognized six distinct MDCT patterns: neuroendocrine cell hyperplasia of infancy (23), organizing pneumonia (5), non-specific interstitial pneumonia (4), bronchiolitis obliterans (3), pulmonary alveolar proteinosis (2), and bronchopulmonary dysplasia (n = 2). Of the total 90, in 51 (57 %) children, none of these six MDCT patterns appeared. Of those 39 children with a recognizable MDCT pattern, in 34 (87 %), that pattern predicted their final diagnosis. ConclusionsAmong cases of chILD, we identified a specific predefined MDCT pattern in only 43 %. However, when such a recognizable pattern occurred, it was predictive of the final chILD diagnosis.

RDJCNN: A micro-convolutional neural network for radar active jamming signal classification

Timely awareness of jamming situations and classification of jamming categories are vital for radars to suppress jamming, ensure viability, and maintain functions in complex electromagnetic environments. To satisfy strict time requirements for radars on embedded devices, a micro-dynamic convolutional neural network for jamming signal classification is proposed in this paper. The proposed network takes the range-Doppler distribution obtained from built-in radar signal processing as input. The proposed data augmentation algorithm, together with the attention mechanism and the efficient convolutional architecture, improves the generalization capability and reduces the computational complexity. In addition, we propose a dynamic depth mechanism based on a task difficulty evaluator that enables the network to be adjusted automatically and further reduces the average computational complexity of classification. Simulation results verify the advantages of our approach in size, accuracy, and efficiency. The proposed network achieved 98.82% and 85.00% top-1 accuracy in two datasets with only 1.73 M multiply–accumulate operations.

Genetic data visualization using literature text-based neural networks: Examples associated with myocardial infarction

Data visualization is critical to unraveling hidden information from complex and high-dimensional data. Interpretable visualization methods are critical, especially in the biology and medical fields, however, there are limited effective visualization methods for large genetic data. Current visualization methods are limited to lower-dimensional data and their performance suffers if there is missing data. In this study, we propose a literature-based visualization method to reduce high-dimensional data without compromising the dynamics of the single nucleotide polymorphisms (SNP) and textual interpretability. Our method is innovative because it is shown to (1) preserves both global and local structures of SNP while reducing the dimension of the data using literature text representations, and (2) enables interpretable visualizations using textual information. For performance evaluations, we examined the proposed approach to classify various classification categories including race, myocardial infarction event age groups, and sex using several machine learning models on the literature-derived SNP data. We used visualization approaches to examine clustering of data as well as quantitative performance metrics for the classification of the risk factors examined above. Our method outperformed all popular dimensionality reduction and visualization methods for both classification and visualization, and it is robust against missing and higher-dimensional data. Moreover, we found it feasible to incorporate both genetic and other risk information obtained from literature with our method.

Phytoremediation Mechanism for Emerging Pollutants : A Review

As a result of urbanization and industrialization, emerging pollutants have become a global concern due to contamination and their potential adverse effects on the ecosystem and human health. However, the characteristics and environmental fate of emerging pollutants remain unclear due to the limitations of current technologies. Emerging pollutants are predominantly released into the environment through anthropogenic activities and accumulate in water, soil, air, and dust. Despite their typically low concentrations in the environment, exposure to these pollutants can result in endocrine disruption and other health impacts on the human body, as well as oxidative stress in organisms. Phytoremediation is a green biotechnology that utilizes plants in association with microorganisms to mitigate pollutants in contaminated areas through various mechanisms. It represents a cost-effective and environmentally friendly approach, although its efficacy can be hindered by both the biological condition of plants and ecological factors. Moreover, phytoremediation generally requires a longer remediation timeframe compared to alternative technologies. The remediation of emerging pollutants aligns with the "green liver model" theory, which encompasses translocation, internal transformation and conjugation, and sequestration as classification categories. Presently, several challenges are being encountered in this field, including a lack of information regarding emerging pollutants and their metabolism in plants, the absence of a modeling framework and standardized monitoring practices, limitations in sampling and analysis technologies, as well as phytoremediation technologies. Therefore, further research is warranted to delve into the behavior of emerging pollutants and their interactions with plants, aiming to develop or enhance existing technologies. Additionally, the concept of phytomanagement should be considered, as it offers a sustainable approach to environmental remediation.

Automated extraction of seed morphological traits from images

Abstract The description of biological objects, such as seeds, mainly relies on manual measurements of few characteristics, and on visual classification of structures, both of which can be subjective, error prone and time‐consuming. Image analysis tools offer means to address these shortcomings, but we currently lack a method capable of automatically handling seeds from different taxa with varying morphological attributes and obtaining interpretable results. Here, we provide a simple image acquisition and processing protocol and introduce Traitor, an open‐source software available as a command‐line interface (CLI), which automates the extraction of seed morphological traits from images. The workflow for trait extraction consists of scanning seeds against a high‐contrast background, correcting image colours, and analysing images with the software. Traitor is capable of processing hundreds of images of varied taxa simultaneously with just three commands, and without a need for training, manual fine‐tuning or thresholding. The software automatically detects each object in the image and extracts size measurements, traditional morphometric descriptors widely used by scientists and practitioners, standardised shape coordinates, and colorimetric measurements. The method was tested on a dataset comprising of 91,667 images of seeds from 1228 taxa. Traitor's extracted average length and width values closely matched the average manual measurements obtained from the same collection (concordance correlation coefficient of 0.98). Further, we used a large image dataset to demonstrate how Traitor's output can be used to obtain representative seed colours for taxa, determine the phylogenetic signal of seed colour, and build objective classification categories for shape with high levels of visual interpretability. Our approach increases productivity and allows for large‐scale analyses that would otherwise be unfeasible. Traitor enables the acquisition of data that are readily comparable across different taxa, opening new avenues to explore functional relevance of morphological traits and to advance on new tools for seed identification.

Classification Categories and Clinical Spectrum of Diabetes Mellitus in Young: An Indian Tertiary Care Center Experience

Abstract Background: Younger people are being afflicted with the pandemic of diabetes mellitus (DM). Although DM is conventionally classified based on insulin requirement at a primary level, there is a large spectrum of DM in young. All subtypes of DM have their exclusive management strategy and ‘one size fits all’ strategy can lead to adverse clinical outcomes. Hence, all efforts should be put to differentiate individual entities of DM subtypes by applying appropriate clinical and laboratory tools. Materials and Methods: This observational cross-sectional study was conducted between December 2020 to March 2022 in 30 patients of age &lt;35 years with established diagnosis of DM as per American Diabetes Association (ADA) criteria. Their clinical profile, Anti-GAD-65 Ab, abdominal imaging and genetics tests were used for the classification of DM and studying their clinical peculiarities. Results: The mean age of patients was 30.53 ± 5.6 years and the group was male predominant, consisting of 22 (73.33%) males and 8 (26.67%) females with a ratio of 2.75:1. The main subtypes of DM detected in this study after application of the study protocol was as follows type 1 DM (T1DM) in 12 (40%), type 2 DM (T2DM) 11 (36%), pancreatogenic DM 3 (10%), maturity-onset diabetes of the young (MODY) 1 (3.3%), Cushing’s syndrome 1 (3.3%) out of 30 patients, and 1 (3.3%) patient could not be classified. The most common comorbidity noted was primary hypertension in 3 (10.0%), followed by primary autoimmune hypothyroidism in 1 (3.3%). All patients having primary hypertension had T2DM, whereas primary autoimmune hypothyroidism was seen in a T1DM patient. T1DM had higher glycosylated hemoglobin (HbA1c) levels (average HbA1c &gt;8.9%) and ketosis 10 (83%) and 6 (50%) out of 12 patients, respectively, as compared to T2DM patients in which lower HbA1c levels (average HbA1c &lt;9%) and lower incidence of ketosis seen in 3 (27.2%) and 2 (18.1%) out of 11 patients, respectively. Conclusion: Various clues in history, clinical examination, and laboratory evaluation help in classification and establishing diagnosis among young DM patients. Apart from T1DM and T2DM, other subtypes of DM also need to be considered in young DM patients.

Identification of Patients With Elevated Urine Albumin-to-Creatinine Ratio Levels in a Type 2 Diabetes Mellitus Cohort Based on Data Submitted by Patients via a Smartphone App (SMART-Finder): Protocol for an Observational Study.

Despite effective treatment options, chronic kidney disease (CKD) has become a major cause of mortality worldwide due to the ever-increasing number of patients with type 2 diabetes mellitus (T2DM). Guideline-compliant, at least, annual screening of patients with T2DM is crucial to prevent renal disease progression. However, data on the prevalence of CKD in patients with T2DM and on screening frequency are limited. SMART-Finder is the first study to exclusively use data provided directly by patients via an adherence app to collect information on the prevalence of CKD, risk factors, disease management, and quality of life of patients with T2DM in Germany. The primary objective of this study is to determine the proportion of patients with T2DM and an elevated urine albumin-to-creatinine ratio (UACR; albumin-to-creatinine ratio stage A2 and A3) at baseline and after 12 (±3) months. Secondary objectives include the proportion of patients who remain in or switch to another albumin-to-creatinine ratio classification category after 12 months, information on quality of life, disease awareness, and adherence rates, as well as the proportion of patients without any UACR-screening data. Recruitment occurs via push notification among MyTherapy app users with T2DM. This is a single-arm, retrospective/prospective, observational, digital, patient-centered cohort study, with recruitment and data documentation via a health app. Required routine laboratory data are provided by treating physicians to their patients for data entry. The study population includes adult patients with T2DM documenting their data in the MyTherapy app using their own smartphone or tablet. Study participants are provided with a specifically developed electronic case report form containing questions on demographic and general data, quality of life, disease awareness, and laboratory values including estimated glomerular filtration rate, UACR, hemoglobin 1Ac, and blood pressure. Apart from demographic and general data, all data are collected at baseline and 12 months after the last UACR assessment. An automatically generated push notification reminds participants of the second data entry. The extracted and pseudonymized data are analyzed descriptively. The enrollment period for this study started in February 2023 and shall end after 12 months or after the enrollment of 5000 patients. An interim analysis is planned 3 months after the inclusion of the first patient and the final analysis after 12 months of follow-up. Overall, the study will contribute to minimizing the existing data gap on the prevalence of CKD in patients with T2DM in Germany, provide important insights into the current disease management of patients with T2DM in everyday clinical practice in Germany, and support guideline-based care for the participating patients. PRR1-10.2196/44996.

EchoAI: A deep-learning based model for classification of echinoderms in global oceans

IntroductionIn response to the need for automated classification in global marine biological studies, deep learning is applied to image-based classification of marine echinoderms.MethodsImages of marine echinoderms are collected and classified according to their systematic taxonomy. The images belong to 5 classes, 38 orders, 145 families, 459 genera, and 1021 species, respectively. The deep learning model, EfficientNetV2, outperforms the competing model and is chosen for developing the automated classification tool, EchoAI. Then, the EfficientNetV2-based tool, EchoAI is applied to each taxonomic level.ResultsThe accuracy for the test dataset was 0.980 (class), 0.876 (order), 0.738 (family), 0.612 (genus), and 0.469 (species), respectively. Online prediction service is provided.DiscussionThe EchoAI model and results are facilitated for investigating the diversity, abundance and distribution of species at the global scale, and the methodological strategy can also be applied to image classification of other categories of marine organisms, which is of great significance for global marine studies. EchoAI is freely available at http://www.csbio.sjtu.edu.cn/bioinf/EchoAI/ for academic use.

Implementation Of K-Nearest Neighbor Algorithm With SMOTE For Hotel Reviews Sentiment Analysis

Indonesia has considerable tourism development potential, this phenomenon is in accordance with the number of foreign tourist visits to Indonesia from January to September 2022 recorded by Badan Pusat Statistik many as 2,397,181 visitors. This research focuses on super-priority destinations in Labuan Bajo, East Nusa Tenggara, based on the government's plan that the focus of developing this destination is to increase hotel development to meet the need for an additional 2,000 hotel rooms. Thus, the available hotel rooms are still limited. Then for need to choose a hotel based on the November 2021 survey by the Populix website, 76% of 1,012 respondents chose to book hotels online with the majority using the Traveloka website. However, making decisions in choosing hotels using the reviews feature in the Traveloka website still raises various problems, such as biased information and even the rating values ​​given do not match the reviews submitted. So that users to know what becomes the perception of positive and negative ratings, it is necessary to do in-depth research on satisfaction factors to find out positive and negative sentiments of hotel visitors. This study uses the k-nearest neighbor algorithm with SMOTE on the research objects of the three most popular hotels in Labuan Bajo. Data testing uses a value of k = 3 so that it produces an accuracy value of 87.71% - 93.47% with a maximum error tolerance of 12.29%. In addition, the performance of accuracy results is validated by the appropriate AUC value, namely the good classification category.

PD30-07 DECONSTRUCTING AND QUANTIFYING LIVE SURGICAL FEEDBACK IN THE OPERATING ROOM

You have accessJournal of UrologyCME1 Apr 2023PD30-07 DECONSTRUCTING AND QUANTIFYING LIVE SURGICAL FEEDBACK IN THE OPERATING ROOM Elyssa Y. Wong, Cherine H. Yang, Istabraq S. Dalieh, Daniela C. Sotelo, Jasper A. Laca, Runzhuo Ma, Timothy N. Chu, Rafal Kocielnik, Mitchell G. Goldenberg, Jamal A. Nabhani, Steven Cen, and Andrew J. Hung Elyssa Y. WongElyssa Y. Wong More articles by this author , Cherine H. YangCherine H. Yang More articles by this author , Istabraq S. DaliehIstabraq S. Dalieh More articles by this author , Daniela C. SoteloDaniela C. Sotelo More articles by this author , Jasper A. LacaJasper A. Laca More articles by this author , Runzhuo MaRunzhuo Ma More articles by this author , Timothy N. ChuTimothy N. Chu More articles by this author , Rafal KocielnikRafal Kocielnik More articles by this author , Mitchell G. GoldenbergMitchell G. Goldenberg More articles by this author , Jamal A. NabhaniJamal A. Nabhani More articles by this author , Steven CenSteven Cen More articles by this author , and Andrew J. HungAndrew J. Hung More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003316.07AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Feedback is essential in surgical training. While all trainees meet case minimums, the feedback they receive can vary in content and quality. We capture the intraoperative feedback provided to trainees during live urologic robotic cases and propose a standardized deconstruction for feedback. METHODS: Eight attending surgeons and nine trainees were prospectively recorded during robotic surgeries at our institution from April-August 2022. Endoscopic video was captured directly from the surgeon console. Dialogue between experts and trainees was recorded with clip-on microphones. A schematic flow for feedback and a classification system for Triggers, Feedback Elements, and Outcomes was developed (Figure 1a) and inter-rater reliability between three trained raters was calculated using prevalence-adjusted and bias-adjusted kappa (PABAK). To examine differences in these classification categories by trainee experience level, we first used generalized estimating equations to estimate weighted average rates across residents and fellows. Next, we used rate ratio (RR) to compare differences in these categories between surgical tasks (dissection vs suturing). RESULTS: Raters had moderate agreement in identifying Trigger, Feedback, and Outcome categories (PABAK 0.6-1.0). In total, 25 robotic teaching cases yielded 3,067 unique lines of feedback. A clear trigger was identified most of the time (59.6%, 95% Confidence Interval [CI] 55.4%, 64.2%). The most frequent trigger was trainee error (28.3%, 95% CI [24.4%, 32.8%]). Most feedback was purely technical (52.3%, 95% CI [46.3%, 59.1%]). The most often combined feedback elements were anatomic and technical components (20.3%, CI [17.3%, 23.8%]). Trainees received more anatomic feedback when performing dissection (RR 2.1, 95% CI [1.7, 2.5]) and more technical feedback when suturing (RR 1.1, 95% CI [1.0, 1.3]) (Figure 1b). Notably, experts repeated feedback less frequently for fellows than residents (RR 0.6, 95% CI [0.1, 1.1]). CONCLUSIONS: We developed a novel framework for feedback that not only captures the dynamic interaction between trainee and expert but accounts for resulting changes in behavior. Investigation into the relationships between Triggers, Feedback, and Outcomes may reveal avenues for optimizing feedback and skill acquisition in different teaching scenarios. Source of Funding: None © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e833 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Elyssa Y. Wong More articles by this author Cherine H. Yang More articles by this author Istabraq S. Dalieh More articles by this author Daniela C. Sotelo More articles by this author Jasper A. Laca More articles by this author Runzhuo Ma More articles by this author Timothy N. Chu More articles by this author Rafal Kocielnik More articles by this author Mitchell G. Goldenberg More articles by this author Jamal A. Nabhani More articles by this author Steven Cen More articles by this author Andrew J. Hung More articles by this author Expand All Advertisement PDF downloadLoading ...

In memoriam Klaus Kubitzki (1933–2022)

In memoriam Klaus Kubitzki (1933–2022)