Insight into the sorption and desorption pattern of pyrrolizidine alkaloids and their N-oxides in acidic tea (Camellia sinensis) plantation soils.

Pyrrolizidine alkaloids (PAs) and their N-oxides (PANOs) are phytotoxins produced by various plant species and have been emerged as environmental pollutants. The sorption/desorption behaviors of PAs/PANOs in soil are crucial due to the horizontal transfer of these natural products from PA-producing plants to soil and subsequently absorbed by plant roots. This study firstly investigated the sorption/desorption behaviors of PAs/PANOs in tea plantation soils with distinct characteristics. Sorption amounts for seneciphylline (Sp) and seneciphylline-N-oxide (SpNO) in three acidic soils ranged from 2.9 to 5.9 µg/g and 1.7 to 2.8 µg/g, respectively. Desorption percentages for Sp and SpNO were from 22.2% to 30.5% and 36.1% to 43.9%. In the mixed PAs/PANOs systems, stronger sorption of PAs over PANOs was occurred in tested soils. Additionally, the Freundlich models more precisely described the sorption/desorption isotherms. Cation exchange capacity, sand content and total nitrogen were identified as major influencing factors by linear regression models. Overall, the soils exhibiting higher sorption capacities for compounds with greater hydrophobicity. PANOs were more likely to migrate within soils and be absorbed by tea plants. It contributes to the understanding of environmental fate of PAs/PANOs in tea plantations and provides basic data and clues for the development of PAs/PANOs reduction technology.

Diagnostic accuracy of endoscopic ultrasonographic shear wave elastography for assessing early chronic pancreatitis using the Japanese diagnostic criteria 2019.

Background and Aim: Endoscopic ultrasound shear wave elastography (EUS-SWE) can facilitate an objective evaluation of pancreatic fibrosis. Although it is primarily applied in evaluating chronic pancreatitis, its efficacy in assessing early chronic pancreatitis (ECP) remains underinvestigated. This study evaluated the diagnostic accuracy of EUS-SWE for assessing ECP diagnosed using the Japanese diagnostic criteria 2019. Methods: In total, 657 patients underwent EUS-SWE. Propensity score matching was used, and the participants were classified into the ECP and normal groups. ECP was diagnosed using the Japanese diagnostic criteria 2019. Pancreatic stiffness was assessed based on velocity (Vs) on EUS-SWE, and the optimal Vs cutoff value for ECP diagnosis was determined. A practical shear wave Vs value of ≥50% was considered significant. Results: Each group included 22 patients. The ECP group had higher pancreatic stiffness than the normal group (2.31 ± 0.67 m/s vs. 1.59 ± 0.40 m/s, p < 0.001). The Vs cutoff value for the diagnostic accuracy of ECP, as determined using the receiver operating characteristic curve, was 2.24m/s, with an area under the curve of 0.82 (95% confidence interval: 0.69-0.94). A high Vs was strongly correlated with the number of EUS findings (rs = 0.626, p < 0.001). Multiple regression analysis revealed that a history of acute pancreatitis and ≥2 EUS findings were independent predictors of a high Vs. Conclusions: There is a strong correlation between EUS-SWE findings and the Japanese diagnostic criteria 2019 for ECP. Hence, EUS-SWE can be an objective and invaluable diagnostic tool for ECP diagnosis.

A three-stage wavelength selection algorithm for near-infrared spectroscopy calibration.

The near-infrared spectral data is highly high dimensional and contains redundant information, it is necessary to identify the most representative characteristic wavelengths before modeling to improve model accuracy and reliability. At present, there are many methods for selecting the characteristic wavelengths of NIR spectroscopy, but the collinearity among wavelengths is still a main issue that leads to poor model effects. Therefore, this study proposes a three-stage wavelength selection algorithm (Stage III) to reduce redundancy in NIR spectral data and collinearity between wavelength variables, resulting in a simpler and more accurate predictive model. The research uses a public NIR data set of corn samples as its subject. Initially, the wavelengths with the higher correlation coefficients are chosen after calculating the relationship coefficients between every wavelength vector and the concentration vector. On this basis, the correlation coefficients between the vectors of each wavelength point are calculated, and those wavelength points with smaller correlation coefficients with other wavelength points are selected. Ultimately, the stepwise regression analysis selects the wavelengths that provide substantial value to the model as the variables for modeling, leading to the development of a multiple linear regression model. The results show that the model using the three-stage wavelength selection algorithm outperforms those using the full spectrum, Stages I and Stage II, and the coefficient of determination of the test set of the Stage III-MLR model achieved an accuracy of 0.9360. Instead of the successive projections algorithm (SPA), uninformative variable elimination (UVE), and competitive adaptive reweighted sampling (CARS), Stage III is better in the model prediction accuracy. Therefore, the three-stage wavelength selection algorithm is an effective wavelength selection algorithm that can effectively model NIR spectroscopy, reduce the collinearity between the wavelength variables, simplify the complexity of the model, and improve the prediction precision of the model.

Development of an equation to predict delta bilirubin levels using machine learning.

OBJECTIVE: Delta bilirubin (albumin-covalently bound bilirubin) may provide important clinical utility in identifying impaired hepatic excretion of conjugated bilirubin, but it cannot be measured in real-time for diagnostic purposes in clinical laboratories. METHODS: A total of 210 samples were collected, and their delta bilirubin levels were measured four times using high-performance liquid chromatography. Data collected included age, sex, diagnosis code, delta bilirubin, total bilirubin, direct bilirubin, total protein, albumin, globulin, aspartate aminotransferase, alanine transaminase, alkaline phosphatase, gamma-glutamyl transferase, lactate dehydrogenase, hemoglobin, serum hemolysis value, hemolysis index, icterus value (Iv), icterus index (Ii), lipemia value (Lv), and lipemia index. To conduct feature selection and identify the optimal combination of variables, linear regression machine learning was performed 1,000 times. RESULTS: The selected variables were total bilirubin, direct bilirubin, total protein, albumin, hemoglobin, Iv, Ii, and Lv. The best predictive performance for high delta bilirubin concentrations was achieved with the combination of albumin-direct bilirubin-hemoglobin-Iv-Lv. The final equation composed of these variables was as follows: delta bilirubin = 0.35 × Iv + 0.05 × Lv - 0.23 × direct bilirubin - 0.05 × hemoglobin - 0.04 × albumin + 0.10. CONCLUSION: The equation established in this study is practical and can be easily applied in real-time in clinical laboratories.

Discontinuity of psychiatric care among patients with bipolar disorder in the Netherlands.

BACKGROUND: Patients with bipolar disorder benefit from guidelines recommended continuous community-oriented psychiatric and somatic healthcare, but often discontinue psychiatric care. AIMS: The first objective was to identify predictive factors of discontinuity of psychiatric care among patients who had received psychiatric care. The second objective was to examine if practice variation in discontinuity of psychiatric care existed between providers of psychiatric care. METHOD: Registry healthcare data were used in a retrospective cohort study design using logistic regression models to examine potential predictive factors of discontinuity of care. Patient-related predictive factors were: age, sex, urbanization, and previous treatment (type and amount of psychiatric care, alcohol, and opioid treatment). Patients already diagnosed with bipolar disorder were selected if they received psychiatric care in December 2014 to January 2015. Discontinuity of psychiatric care was measured over 2016. RESULTS: A total of 2,355 patients with bipolar disorder were included. In 12.1% discontinuity of care occurred in 2016. Discontinuity was associated with younger age and less outpatient care over 2013 to 2014. Discontinuity of patients who received all eight quarters outpatient care including BD medication was very low at 4%. The final model contained: age, type of psychiatric care, and amount of outpatient care in 2013 to 2014. Practice variation among providers appeared negligible. CONCLUSIONS: The (mental) health service in the Netherlands has few financial or other barriers toward continuity of care for patients with severe mental disorders, such as bipolar disorder. An active network of providers, aim to standardize care. This seems successful. However, 12% discontinuity per year remains problematic and more detailed data on those most at risk to drop out of treatment are necessary.

Unveiling the potential of a novel portable air quality platform for assessment of fine and coarse particulate matter: in-field testing, calibration, and machine learning insights.

Although low-cost air quality sensors facilitate the implementation of denser air quality monitoring networks, enabling a more realistic assessment of individual exposure to airborne pollutants, their sensitivity to multifaceted field conditions is often overlooked in laboratory testing. This gap was addressed by introducing an in-field calibration and validation of three PAQMON 1.0 mobile sensing low-cost platforms developed at the Mining and Metallurgy Institute in Bor, Republic of Serbia. A configuration tailored for monitoring PM2.5 and PM10 mass concentrations along with meteorological parameters was employed for outdoor measurement campaigns in Bor, spanning heating (HS) and non-heating (NHS) seasons. A statistically significant positive linear correlation between raw PM2.5 and PM10 measurements during both campaigns (R > 0.90, p ≤ 0.001) was observed. Measurements obtained from the uncalibrated NOVA SDS011 sensors integrated into the PAQMON 1.0 platforms exhibited a substantial and statistically significant correlation with the GRIMM EDM180 monitor (R > 0.60, p ≤ 0.001). The calibration models based on linear and Random Forest (RF) regression were compared. RF models provided more accurate descriptions of air quality, with average adjR2 values for air quality variables in the range of 0.70 to 0.80 and average NRMSE values between 0.35 and 0.77. RF-calibrated PAQMON 1.0 platforms displayed divergent levels of accuracy across different pollutant concentration ranges, achieving a data quality objective of 50% during both measurement campaigns. For PM2.5, uncertainty ( U r ) was below 50% for concentrations between 9.06 and 34.99 µg/m3 in HS and 5.75 and 17.58 µg/m3 in NHS, while for PM10, it stayed below 50% from 19.11 to 51.13 µg/m3 in HS and 11.72 to 38.86 µg/m3 in NHS.

Dominant role of soil iron and organic matters in arsenic transfer from soil to plant in a mine area in Hunan Province, Central China.

The transfer of arsenic (As) from soil to plant could be significantly influenced by soil parameters through regulating soil As bioavailability. To distinguish the bioavailable As provided by soil and the As uptaken by plants, herein two different soil bioavailable were defined, namely potential soil bioavailable As (evaluated through the bioavailable fraction of As) and actual soil bioavailable As (assessed through plant bioaccumulation factor, BF, and BFavailable). To identify the dominant soil parameters for the two soil bioavailable As forms, soil and plant samples were collected from a former As mine site. The results showed that the potential bioavailable As only accounted for 1.77 to 11.43% in the sampled soils, while the BF and BFavailable in the sampled vegetables ranged from 0.00 to 1.01 and 0.01 to 17.87, respectively. Despite a similar proportion of As in the residual fraction, soil with higher pH and organic matter (OM) content and lower iron (Fe) content showed a higher potential soil bioavailable As. Correlation analysis indicated a relationship between the soil pH and potential soil bioavailable As (r = 0.543, p < 0.01) and between the soil Fe and actual soil bioavailable As (r = - 0.644, p < 0.05, r = - 0.594, p < 0.05). Stepwise multiple linear regression (SMLR) analysis was employed to identify the dominant soil parameters and showed that soil pH and phosphorus (P) content could be used to predict the potential soil bioavailable As (R2 = 0.69, p < 0.001). On the other hand, soil Fe and OM could be used to predict the actual soil bioavailable As (R2 = 0.18-0.86, p < 0.001-0.015, in different vegetables). These results suggest that different soil parameters affect potential and actual soil bioavailable As. Hence, soil Fe and OM are the most important parameters controlling As transfer from soil to plant in the investigated area.

Lymph node dissection does not affect the survival of patients with tumor node metastasis stages I and II colorectal cancer.

BACKGROUND: The effect of the number of lymph node dissections (LNDs) during radical resection for colorectal cancer (CRC) on overall survival (OS) remains controversial. AIM: To investigate the association between the number of LNDs and OS in patients with tumor node metastasis (TNM) stage I-II CRC undergoing radical resection. METHODS: Patients who underwent radical resection for CRC at a single-center hospital between January 2011 and December 2021 were retrospectively analyzed. Cox regression analyses were performed to identify the independent predictors of OS at different T stages. RESULTS: A total of 2850 patients who underwent laparoscopic radical resection for CRC were enrolled. At stage T1, age [P < 0.01, hazard ratio (HR) = 1.075, 95% confidence interval (CI): 1.019-1.134] and tumour size (P = 0.021, HR = 3.635, 95%CI: 1.210-10.917) were independent risk factors for OS. At stage T2, age (P < 0.01, HR = 1.064, 95%CI: 1.032-1.098) and overall complications (P = 0.012, HR = 2.297, 95%CI: 1.200-4.397) were independent risk factors for OS. At stage T3, only age (P < 0.01, HR = 1.047, 95%CI: 1.027-1.066) was an independent risk factor for OS. At stage T4, age (P < 0.01, HR = 1.057, 95%CI: 1.039-1.075) and body mass index (P = 0. 034, HR = 0.941, 95%CI: 0.890-0.995) were independent risk factors for OS. However, there was no association between LNDs and OS in stages I and II. CONCLUSION: The number of LDNs did not affect the survival of patients with TNM stages I and II CRC. Therefore, insufficient LNDs should not be a cause for alarm during the surgery.

Systemic immune-inflammation index combined with pediatric appendicitis score in assessing the severity and prognosis for paediatric appendicitis.

BACKGROUND: Pediatric appendicitis is a common cause of abdominal pain in children and is recognized as a significant surgical emergency. A prompt and accurate diagnosis is essential to prevent complications such as perforation and peritonitis. AIM: To investigate the predictive value of the systemic immune-inflammation index (SII) combined with the pediatric appendicitis score (PAS) for the assessment of disease severity and surgical outcomes in children aged 5 years and older with appendicitis. METHODS: Clinical data of 104 children diagnosed with acute appendicitis were analyzed. The participants were categorized into the acute appendicitis group and chronic appendicitis group based on disease presentation and further stratified into the good prognosis group and poor prognosis group based on prognosis. The SII and PAS were measured, and a joint model using the combined SII and PAS was constructed to predict disease severity and surgical outcomes. RESULTS: Significant differences were observed in the SII and PAS parameters between the acute appendicitis group and chronic appendicitis group. Correlation analysis showed associations among the SII, PAS, and disease severity, with the combined SII and PAS model demonstrating significant predictive value for assessing disease severity [aera under the curve (AUC) = 0.914] and predicting surgical outcomes (AUC = 0.857) in children aged 5 years and older with appendicitis. CONCLUSION: The study findings support the potential of integrating the SII with the PAS for assessing disease severity and predicting surgical outcomes in pediatric appendicitis, indicating the clinical utility of the combined SII and PAS model in guiding clinical decision-making and optimizing surgical management strategies for pediatric patients with appendicitis.

Basic human values and the adoption of cryptocurrency.

Cryptocurrency is an attempt to create an alternative to centralized financial systems using blockchain technology. However, our understanding of the psychological mechanisms that drive cryptocurrency adoption is limited. This study examines the role of basic human values in three stages of cryptocurrency adoption-awareness, intention to buy, and ownership-using the Theory of Planned Behavior (TPB). Logistic regression analysis was conducted on a quota sample of 714 German adults, and the results showed that openness-to-change values increased the likelihood of cryptocurrency awareness, while self-enhancement values increased the likelihood of intention to buy and ownership. These findings were consistent even after controlling for demographic characteristics, attitudinal beliefs, and perceived behavioral control, which are important factors in the TPB. The results suggest that basic human values may influence an individual's decision to adopt cryptocurrency, but the transition from awareness to ownership may be influenced by socio-economic opportunities available to interested individuals.

Establishment and validation of a predictive nomogram for central venous catheter-related thrombosis in cancer patients: a retrospective nested case-control study.

Background: Catheter-related thrombosis (CRT) is a common complication for patients who receive central venous catheter (CVC) placement. This study investigated the risk factors for CRT and developed a nomogram for CRT prediction among cancer patients. Methods: This nested case-control study was conducted in the Third Affiliated Hospital of Kunming Medical University between January 2019 and February 2021. Univariable and multivariable logistic regression analyses were used to identify the risk factors for CRT. A nomogram was developed to predict CRT. Receiver operating curves (ROC), calibration curves, and decision curves were used to evaluate the performance of the nomogram in the training and validation sets. Results: A total of 4,691 cancer patients were included in this study. Among them, 355 (7.57%) had CRT, and 70% of CRTs occurred in the first week of insertion. Among the 3,284 patients in the training set, the multivariable analysis showed that nine characteristics were independently associated with CRT, and a nomogram was constructed based on the multivariable analysis. The ROC analysis indicated good discrimination in the training set (area under the curve [AUC] = 0.832, 95% CI: 0.802-0.862) and the testing set (AUC = 0.827, 95% CI: 0.783-0.871) for the CRT nomogram. The calibration curves showed good calibration abilities, and the decision curves indicated the clinical usefulness of the prediction nomograms. Conclusion: The validated nomogram accurately predicts CRT occurrence in cancer patients. This model may assist clinicians in developing treatment plans for each patient.

Temporal trends of suicidality among hospitalised adolescents during COVID-19 pandemic: A Bayesian framework.

OBJECTIVE: Literature on temporal patterns of suicidality among youths during the COVID-19 pandemic is growing. The present work proposes a Bayesian approach to assess temporal patterns of suicide-related behaviours among inpatient adolescents during the COVID-19 pandemic. METHODOLOGY: Data referred to the first hospital discharge record with ICD9-CM codes related to suicide-related behaviour and/or suicidal ideation among adolescents aged 13-19 between 1 January 2017 and 31 March 2021 were collected in the Piedmont region, Italy (n = 334; median age: 15 years, IQR: 14-16; 80% girls). A Poisson Bayesian regression model performed on pre-COVID-19 data (2017-2020), adjusted by seasonality and stratified by sex, was adopted to provide the probability that the predicted counts exceed the observed ones in each pandemic year quarter. RESULTS: A declining trend of suicidality was observed in April-June 2020 among both sex groups. Among females, an increasing pattern of suicidality was registered in early 2021 (January-March) compared to the pre-pandemic period. CONCLUSION: The present findings contributed to a growing literature on the COVID-19 pandemic's impact on adolescents' suicide-related behaviours from a gender perspective and encouraged wider adoption of Bayesian approaches as valuable tools to explore rare events and deeply enlighten open public health issues.

Trends in the incidence and mortality of cervical, ovarian, and corpus uteri cancers in Wales, UK: A joinpoint regression analysis from 2002 to 2021.

OBJECTIVES: The primary objective of this study was to examine the secular trends of cervical, ovarian, and corpus uteri neoplasm in Wales, UK, over the period from 2002 to 2021. We aimed to identify changes in the incidence and mortality rates of these cancers to inform future healthcare policies and cancer prevention programs. METHODS: We sourced incidence data from 2002 to 2019 and mortality data from 2002 to 2021 from the Welsh Cancer Intelligence and Surveillance Unit. The data were analysed using Joinpoint regression to compute the average annual percentage change (AAPC) in age-standardized incidence rates (ASIR) and mortality rates (ASMR) per 100,000 population for each type of cancer. RESULTS: The results showed that the ASIR for cervical cancer remained stable between 2002 and 2019 (AAPC = -0.5; 95 %CI = -1.4-0.4). However, the ASMR significantly declined from 4.88 in 2002-3.03 in 2021 (AAPC = -2.3; 95 %CI = -3.4 to -1.1). The ASIR for ovarian cancer significantly decreased from 27.39 in 2002-17.87 in 2019 (AAPC = -2.6; 95 %CI = -3.0 to -2.1), and the ASMR showed a statistically significant decreasing trend from 15.92 in 2002-11.2 in 2021 (AAPC = -1.7; 95 %CI = -2.5 to -0.9). In contrast, the ASIR for corpus uteri neoplasm significantly increased from 22.24 in 2002-30.41 in 2019 (AAPC = 2.2; 95 %CI = 1.2-3.4), and ASMR also showed a statistically significant increasing trend from 3.27 in 2002-6.42 in 2021 (AAPC = 3.8; 95 %CI = 2.3-5.3). CONCLUSIONS: The study concludes that while the incidence and mortality rates for cervical and ovarian cancers in Wales have significantly decreased, corpus uteri neoplasm rates have increased during the study period. These findings underscore the need for continued efforts to improve early detection and treatment strategies, including national screening programs and public health initiatives, to mitigate the burden of these cancers.

The spike-and-slab quantile LASSO for robust variable selection in cancer genomics studies.

Data irregularity in cancer genomics studies has been widely observed in the form of outliers and heavy-tailed distributions in the complex traits. In the past decade, robust variable selection methods have emerged as powerful alternatives to the nonrobust ones to identify important genes associated with heterogeneous disease traits and build superior predictive models. In this study, to keep the remarkable features of the quantile LASSO and fully Bayesian regularized quantile regression while overcoming their disadvantage in the analysis of high-dimensional genomics data, we propose the spike-and-slab quantile LASSO through a fully Bayesian spike-and-slab formulation under the robust likelihood by adopting the asymmetric Laplace distribution (ALD). The proposed robust method has inherited the prominent properties of selective shrinkage and self-adaptivity to the sparsity pattern from the spike-and-slab LASSO (Roc̆ková and George, J Am Stat Associat, 2018, 113(521): 431-444). Furthermore, the spike-and-slab quantile LASSO has a computational advantage to locate the posterior modes via soft-thresholding rule guided Expectation-Maximization (EM) steps in the coordinate descent framework, a phenomenon rarely observed for robust regularization with nondifferentiable loss functions. We have conducted comprehensive simulation studies with a variety of heavy-tailed errors in both homogeneous and heterogeneous model settings to demonstrate the superiority of the spike-and-slab quantile LASSO over its competing methods. The advantage of the proposed method has been further demonstrated in case studies of the lung adenocarcinomas (LUAD) and skin cutaneous melanoma (SKCM) data from The Cancer Genome Atlas (TCGA).

The effect of physical exercise on circulating neurotrophic factors in healthy aged subjects: A meta-analysis and meta-regression.

Vascular endothelial growth factor (VEGF), brain-derived neurotrophic factor (BDNF), and insulin-like growth factor-1 (IGF-1) may help the brain resist both functional and structural neurodegeneration, which is critical for maintaining cognitive and neurological health in older adults. This meta-analysis and meta-regression seek to elucidate the impact of physical activity on these biomarker levels in healthy seniors, as well as to examine the influence of several moderator factors, including age, sex, period length, and time, for the first time. The standardized mean effect metric was used to assess the influence of weights, which reflected each group's relative importance in comparison to baseline data. The study looked at potential moderating factors including age, gender, and physical activity levels. The analysis of 11 studies indicated no significant effect of physical activity on VEGF levels [0.328, CI 95 % (-0.871 to 1.52); I2 = 0.00; p = 0.592; Q = 4.14]. Physical activity had a substantial impact on brain-derived neurotrophic factor (0.827, 95 % confidence interval: 0.487 to 1.16; I2 = 0.00; p = 0.00; Q = 78.46), with females showing particularly notable effects (Tau2 = 0.327, Tau = 0.571, I2 = 80.90 %, Q = 68.05, df = 15, p = 0.00). Physical activity also had a substantial effect on insulin-like growth factor 1 (0.276, 95 % confidence interval: 0.065 to 0.487; I2 = 0.00; p = 0.10; Q = 8.35), indicating that it positively influences IGF-1 levels. Overall, while physical exercise has a significant effect on BDNF and IGF-1, more research is needed to fully understand its impact on vascular endothelial growth factor and to investigate how individual characteristics may influence exercise outcomes.

Biomarkers differentiating regression from progression among untreated cervical intraepithelial neoplasia grade 2 lesions.

BACKGROUND: Cervical intraepithelial neoplasia grade 2 (CIN2) is one of the precursor stages before cervical lesions develop into cervical cancer. The spontaneous development of CIN2 is ambiguous. One part of CIN2 lesions will progress to cervical intraepithelial neoplasia grade 3 or worse (CIN3+), another part will regress to cervical intraepithelial neoplasia grade 1 or less (CIN1-), and the last part will persist. Although the guidelines suggest that CIN2 patients with fertility requirements can be treated conservatively to minimize the risk of infertility and obstetric complications, most CIN2 patients undergo surgical treatment to prevent the progression of the disease, which will lead to over-treatment and unnecessary complications. AIM OF REVIEW: The clinical outcome of CIN2 lesions is unpredictable and depends on histopathological examinations. Thus, it is necessary to identify the biomarkers differentiating regression lesions from progression lesions, which is conducive to supporting individualised treatment. The natural history of CIN2 is commonly regulated by the interaction of human papillomavirus (HPV) viral factors (HPV genotype and viral DNA methylation), host factors (p16/Ki-67 status, host gene methylation effects, human leukocyte antigen subtypes and immune microenvironment) and other factors (vaginal microbiota). KEY SCIENTIFIC CONCEPTS OF REVIEW: This review summarized the biomarkers predicting the spontaneous regression of CIN2, which correlated with HPV infection, the (epi)genetic change of host genes and microenvironment change. However, potential biomarkers must be validated with prospective cohort studies, which should be conducted with expanded enrollment, a longer observational period and the tracking of more patients.

Logistic regression analysis and machine learning for predicting post-stroke gait independence: a retrospective study.

This study investigated whether machine learning (ML) has better predictive accuracy than logistic regression analysis (LR) for gait independence at discharge in subacute stroke patients (n = 843) who could not walk independently at admission. We developed prediction models using LR and five ML algorithms-specifically, the decision tree (DT), support vector machine, artificial neural network, ensemble learning, and k-nearest neighbor methods. Functional Independence Measure sub-items were used to evaluate the ability to walk independently. Model predictive accuracies were evaluated using areas under receiver operating characteristic curves (AUCs) as well as accuracy, precision, recall, F1 score, and specificity. The AUC for DT (0.812) was significantly lower than those for the other algorithms (p < 0.01); however, the AUC for LR (0.895) did not differ significantly from those for the other models (0.893-0.903). Other performance metrics showed no substantial differences between LR and ML algorithms. In conclusion, the DT algorithm had significantly low predictive accuracy, and LR showed no significant difference in predictive accuracy compared with the other ML algorithms. As its predictive accuracy is similar to that of ML, LR can continue to be used for predicting the prognosis of gait independence, with additional advantages of being easily understandable and manually computable.

Prediction techniques of movie box office using neural networks and emotional mining.

Box office prediction is of great significance for understanding investment risks, class construction, promotion and distribution, and theater scheduling. However, due to the insufficient selection of influencing factors of movie box office, the currently existing prediction model restricts the prediction accuracy. A total of 34 influencing factors in 11 categories, such as heat index, movie types, release date, creators, first-day box office, were selected to study the prediction technology of movie box office. The Word2vec algorithm is used to construct a feature thesaurus for nouns in movie domain; adjectives and verbs with emotional coloring are used to construct an emotional dictionary based on the movie domain; and the TF-IDF algorithm is integrated to calculate the emotional scores of movie comments. A prediction method based on comments and Multivariate Linear Regression (MLR) is designed to analyze the relationship between the influencing factors and the movie box office, which provides an important basis for the prediction of the total box office, and also provides a decision-making reference for the movie industry and the related management departments. Incorporating comments as feature values to improve the accuracy, a prediction model based on comments and Convolutional Neural Network (CNN) is constructed. The results show that the average prediction accuracy of the MLR without comments, Back-Propagation Neural Network (BPNN), and CNN is 63.4%, 68.3%, and 71.9%, respectively, and after integrating the comments, the average prediction accuracy of the MLR and CNN is improved by 16.1% and 11.8%, respectively, and the prediction accuracy is significantly improved.

Universal penalized regression (Elastic-net) model with differentially methylated promoters for oral cancer prediction.

BACKGROUND: DNA methylation showed notable potential to act as a diagnostic marker in many cancers. Many studies proposed DNA methylation biomarker in OSCC detection, while most of these studies are limited to specific cohorts or geographical location. However, the generalizability of DNA methylation as a diagnostic marker in oral cancer across different geographical locations is yet to be investigated. METHODS: We used genome-wide methylation data from 384 oral cavity cancer and normal tissues from TCGA HNSCC and eastern India. The common differentially methylated CpGs in these two cohorts were used to develop an Elastic-net model that can be used for the diagnosis of OSCC. The model was validated using 812 HNSCC and normal samples from different anatomical sites of oral cavity from seven countries. Droplet Digital PCR of methyl-sensitive restriction enzyme digested DNA (ddMSRE) was used for quantification of methylation and validation of the model with 22 OSCC and 22 contralateral normal samples. Additionally, pyrosequencing was used to validate the model using 46 OSCC and 25 adjacent normal and 21 contralateral normal tissue samples. RESULTS: With ddMSRE, our model showed 91% sensitivity, 100% specificity, and 95% accuracy in classifying OSCC from the contralateral normal tissues. Validation of the model with pyrosequencing also showed 96% sensitivity, 91% specificity, and 93% accuracy for classifying the OSCC from contralateral normal samples, while in case of adjacent normal samples we found similar sensitivity but with 20% specificity, suggesting the presence of early disease methylation signature at the adjacent normal samples. Methylation array data of HNSCC and normal tissues from different geographical locations and different anatomical sites showed comparable sensitivity, specificity, and accuracy in detecting oral cavity cancer with across. Similar results were also observed for different stages of oral cavity cancer. CONCLUSIONS: Our model identified crucial genomic regions affected by DNA methylation in OSCC and showed similar accuracy in detecting oral cancer across different geographical locations. The high specificity of this model in classifying contralateral normal samples from the oral cancer compared to the adjacent normal samples suggested applicability of the model in early detection.

Machine learning approaches for asthma disease prediction among adults in Sri Lanka.

Objectives: Addressing the challenge of cost-effective asthma diagnosis amidst diverse symptom patterns among patients, this study aims to develop a machine learning-based asthma prediction tool for self-detection of asthma. Methods: Data from 6,665 participants in the Sri Lanka Health and Ageing Study (2018-2019) are used for this research. Thirteen machine learning algorithms, including Logistic Regression, Support Vector Machine, Decision Tree, Random Forest, Naïve Bayes, K-Nearest Neighbors, Gradient Boost, XGBoost, AdaBoost, CatBoost, LightGBM, Multi-Layer Perceptron, and Probabilistic Neural Network, are employed. Results: A hybrid version of Logistic Regression and LightGBM outperformed other models, achieving an AUC of 0.9062 and 79.85% sensitivity. Key predictive features for asthma include wheezing, breathlessness with wheezing, shortness of breath attacks, coughing attacks, chest tightness, nasal allergies, physical activity, passive smoking, ethnicity, and residential sector. Conclusion: Combining Logistic Regression and LightGBM models can effectively predict adult asthma based on self-reported symptoms and demographic and behavioural characteristics. The proposed expert system assists clinicians and patients in diagnosing potential asthma cases.