Classification Tree Method Research Articles

A hybrid machine learning with process analytics for predicting customer experience in online insurance services industry

It is essential to innovate and improve service levels by predicting possible process outcomes due to the growth of online service providers. This study estimates the customer satisfaction level based on customer experience analysis. In doing so, we answer recent calls for research about a more thorough exploration of customer behavior using predictive process monitoring techniques. In particular, a hybrid framework of supervised/unsupervised machine learning methods is proposed to predict the outcomes of customers’ experiences while dealing with the problem of high intra-class variance. This problem occurs due to the large dispersion of traces identified in the customer journeys. In this regard, customer journeys are first matched with the event log format aiming to implement a Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering technique based on the similarity between the customer journeys. After summarizing the journeys by removing low-value activities, the multi-class decision tree classification method is applied, and the level of customer satisfaction is predicted. Due to the imbalanced nature of the data, the oversampling for imbalanced classification is applied to achieve good results in accuracy indicators such as recall, precision, and F1-score. Finally, the proposed approach has been evaluated on a real-life event log, BPI Challenge 2016, to investigate unsatisfied customers. The results of the machine learning models on the test data show a high degree of accuracy in predicting customer dissatisfaction.

Analisis Financial Distress pada Bank Syariah di Indonesia Menggunakan Metode Classification and Regression Tree (CART)

Using the Grover and Classification and Regression Tree (CART) techniques, this research aims to evaluate the factors that influence the financial conditions of Islamic banks from 2010 to 2021. The sample for this research was taken using a purposive sampling technique from five banks registered in OJK from 2010 to 2021. The results of this research using Grover analysis show that no bank has experienced bankruptcy with an accuracy value of 100%. On the other hand, according to decision tree regression using the Classification and Regression Trees (CART) method, FDR, NPM and CAR are the three factors that influence financial bankruptcy. And it is known that of the three ratios, FDR is the most significant.

Hybrid Machine Learning and Experimental Studies of Antiviral Potential of Ionic Liquids against P100, MS2, and Phi6.

Viruses are a group of widespread organisms that are often responsible for very dangerous diseases, as most of them follow a mechanism to multiply and infect their hosts as quickly as possible. Pathogen viruses also mutate regularly, with the result that measures to prevent virus transmission and recover from the disease caused are often limited. The development of new substances is very time-consuming and highly budgeted and requires the sacrifice of many living organisms. Computational chemistry methods allow faster analysis at a much lower cost and, most importantly, reduce the number of living organisms sacrificed experimentally to a minimum. Ionic liquids (ILs) are a group of chemical compounds that could potentially find a wide range of applications due to their potential virucidal activity. In our study, we conducted a complex computational analysis to predict the antiviral activity of ionic liquids against three surrogate viruses: two nonenveloped viruses, Listeria monocytogenes phage P100 and Escherichia coli phage MS2, and one enveloped virus, Pseudomonas syringae phage Phi6. Based on experimental data of toxic activity (logEC90), we assigned activity classes to 154 ILs. Prediction models were created and validated according to the Organization for Economic Co-operation and Development (OECD) recommendations using the Classification Tree method. Further, we performed an external validation of our models through virtual screening on a set of 1277 theoretically generated ionic liquids and then selected 10 active ionic liquids, which were synthesized to verify their activity against the analyzed viruses. Our study proved the effectiveness and efficiency of computational methods to predict the antiviral activity of ionic liquids. Thus, computational models are a cost-effective alternative approach compared with time-consuming experimental studies where live animals are involved.

Factors influencing the multinational banks’ decisions to curtail operations in russia: Does ESG matter?

The paper is devoted to an under-researched topic of the international business community’s reaction to russia’s armed aggression against Ukraine. It aims to evaluate how G7 and EU financial sanctions, institutional pressure, ESG ratings, and asset value of multinational banks in russia influence their decisions to reduce activities in the invading country. The study used the Yale CELI database of companies leaving and staying in Russia for the classification tree method. The results show that none of the banks headquartered in G7 and EU member states that had no or relatively little assets in russia before the invasion are doing business there on a pre-war scale. Unlike banks headquartered in other countries, most either curtailed their presence in that market or exited the market. This indicates that financial sanctions imposed by G7 and EU member states and institutional pressure on banks in these countries to withdraw from the russian market have proven effective to a certain extent. However, these factors do not meaningfully influence the business of multinational banks with significant assets in russia. The study has not confirmed the hypothesis that a bank with higher ESG ratings is more likely to curtail its operations in the market of an aggressor country and withdraw. However, nearly all banks that scaled back significant activities or even pulled out of russia have better ESG indicators than the industry average. The results suggest the feasibility of improving the methodologies of ESG rating providers for accurately measuring business reactions to aggression and war crimes.

Deep-Learning-Based Automatic Extraction of Aquatic Vegetation from Sentinel-2 Images—A Case Study of Lake Honghu

Aquatic vegetation is an important component of aquatic ecosystems; therefore, the classification and mapping of aquatic vegetation is an important aspect of lake management. Currently, the decision tree (DT) classification method based on spectral indices has been widely used in the extraction of aquatic vegetation data, but the disadvantage of this method is that it is difficult to fix the threshold value, which, in turn, affects the automatic classification effect. In this study, Sentinel-2 MSI data were used to produce a sample set (about 930 samples) of aquatic vegetation in four inland lakes (Lake Taihu, Lake Caohai, Lake Honghu, and Lake Dongtinghu) using the visual interpretation method, including emergent, floating-leaved, and submerged vegetation. Based on this sample set, a DL model (Res-U-Net) was used to train an automatic aquatic vegetation extraction model. The DL model achieved a higher overall accuracy, relevant error, and kappa coefficient (90%, 8.18%, and 0.86, respectively) compared to the DT method (79%, 23.07%, and 0.77) and random forest (78%,10.62% and 0.77) when utilizing visual interpretation results as the ground truth. When utilizing measured point data as the ground truth, the DL model exhibited accuracies of 59%, 78%, and 91% for submerged, floating-leaved, and emergent vegetation, respectively. In addition, the model still maintains good recognition in the presence of clouds with the influence of water bloom. When applying the model to Lake Honghu from January 2017 to October 2023, the obtained temporal variation patterns in the aquatic vegetation were consistent with other studies. The study in this paper shows that the proposed DL model has good application potential for extracting aquatic vegetation data.

Impact of The Covid-19 Pandemic on Student Learning Styles: Naïve Bayes and Decision Tree Classification in Education

The Covid-19 pandemic significantly changed education with social distancing and changes in the learning environment. In this study, one strong reason for the significance of the research is the urgency of changes in students' learning styles during the Covid-19 pandemic. Investigating differences in learning styles before and during the pandemic not only provides deep insight into students' adaptation to these changes, but also provides a foundation for the development of more inclusive and adaptive learning strategies in the future. This study aims to analyze the effect of the Covid-19 pandemic on students' learning styles in an educational context, focusing on the comparison of two classification methods, Naïve Bayes and Decision Tree. The study was conducted by collecting data on students' learning styles before and during the Covid-19 pandemic, using various relevant indicators. The data was obtained based on school survey results and online platforms, involving student characteristics and learning preferences. The data was then analyzed using Naïve Bayes and Decision Tree classification methods to identify significant changes in students' learning styles. The results showed the prediction accuracy of learning style changes with Naïve Bayes 68.75% and Decision Tree 87.50%. Recommendations for educators and education policy makers are to develop inclusive and adaptive learning strategies to meet diverse learning preferences.

Treatment gap and barriers to access mental healthcare among women with postpartum depression symptoms in Pakistan.

Postpartum depression (PPD) is prevalent among women after childbirth, but accessing mental healthcare for PPD is challenging. This study aimed to assess the treatment gap and barriers to mental healthcare access for women with PPD symptoms living in Punjab, Pakistan. A multicenter cross-sectional study was conducted in five populous cities of Punjab from January to June 2023 by administering the questionnaire to the women using stratified random sampling. A total of 3,220 women in first 6 months postpartum were screened using the Edinburgh Postnatal Depression Scale. Of them, 1,503 women scored thirteen or above, indicating potential depressive disorder. Interviews were conducted to explore help-seeking behavior and barriers to accessing mental healthcare. Descriptive statistics along with nonparametric tests (e.g., Kruskal-Wallis, Mann-Whitney U) were used and group differences were examined. Scatter plot matrices with fitted lines were used to explore associations between variables. Classification and regression tree methods were used to classify the importance and contribution of different variables for the intensity of PPD. Only 2% of women (n=33) with high PPD symptoms sought mental healthcare, and merely 5% of women (n=75) had been in contact with a health service since the onset of their symptoms. 92.80% of women with PPD symptoms did not seek any medical attention. The majority of women, 1,215 (81%), perceived the need for mental health treatment; however, 91.23% of them did not seek treatment from healthcare services. Women who recently gave birth to a female child had higher mean depression scores compared to those who gave birth to a male child. Age, education, and birth location of newborn were significantly associated (p<0.005) with mean barrier scores, mean social support scores, mean depression scores and treatment gap. The results of classification and regression decision tree model showed that instrumental barrier scores are the most important in predicting mean PPD scores. Women with PPD symptoms encountered considerable treatment gap and barriers to access mental health care. Integration of mental health services into obstetric care as well as PPD screening in public and private hospitals of Punjab, Pakistan is critically needed to overcome the treatment gap and barriers.

Employee adaptation in a socially responsible organization

Purpose: The beginning work in a new place for an employee means a lot of stress resulting from confrontation with unfamiliar surroundings and people. The process of introducing an employee to work should involve not only the employer, but also the entire team, emphasizing care, willingness to help and support at such an important initial stage. The main aim of the research is to examine whether the adaptation of new employees in a trade enterprise is effective. An attempt has been made to identify the conditions in the process of social and professional adaptation of a new employee through the prism of corporate social responsibility. Design/methodology/approach: The paper is consisted with 2 parts. The first is about a theoretical context of CSR in small trade company level and personnel management issues and the adaptation of a new employe. The second part includes findings on research. The case study was used to develop research problem. The research questions included the issue of stress in the adaptation process and the role of the introducer. The study covered 100% of the study population. Data were analyzed using descriptive and non-parametric statistics methods (e.g. classification trees method to identify the importance of predictors). Findings: The research results indicate that the adaptation of a new employee is an important element of his/her quality of professional life, and for the organization it is an important aspect of implementing the social responsibility strategy. Taking into account the needs of employees, as internal stakeholders of the company, is an expression of the implementation of socially responsible management. The implementation of the CSR strategy can be assessed by the degree of employee satisfaction with the quality of work life, which results from the effectiveness of fulfilling tasks in the adaptation process. Research limitations/implications: Due to the fact that research is limited to the one chosen company results can not be uncritically generalized. This study covers only a narrow part from a wide range of problems in shaping social responsibility in business. It only applies to actions taken towards employees in the adaptation process. Due to this implication, research should be deepened and expanded to include additional aspects both in terms of responsibility towards employees and other stakeholder groups. Practical implications: The research results can be a source of information for managers about factors important in shaping the personnel function of a socially responsible organization, primarily in the field of social and professional adaptation. Social implications: The article contributes to the development of knowledge and dissemination of good practices in the field of corporate social responsibility. Originality/value: The article presents a new approach to managing the personnel function in a business organization through the prism of the principles of social responsibility. Previous research does not directly or comprehensively take into account possible connections between corporate social responsibility and the adaptation process. Keywords: corporate social responsibility, socio-professional adaptation, quality of professional life, trade enterprise. Category of the paper: Research paper.

Utilization and Management of Technology in Making Decisions to Assist Owners in First Aid for Dogs

Dogs are one of the pets that have a close relationship with humans, due to various factors including following the word, easy to be a human playmate, and even being docile to live with humans. However, in dog keeping, disease-related problems for dogs are harmful, not only to them but also to their owners. Difficult situations in obtaining treatment also often occur, where due to the distance of the veterinary clinic, the limited number of animal specialist clinics and the owner's desire to carry out the treatment on his own. Therefore, advanced technology needs to be introduced in diagnosing and giving recommendations to dog owners for first aid in providing fast and appropriate treatment to dogs. Therefore, here an expert mobile system-based application is introduced, that uses a decision tree classification method and a forward chaining algorithm. The application was tested for user acceptance using a Likert scale that yielded 94.4% for the ease of understanding the application, 92% for the ease of use of the application, 88% for the accuracy of providing information about symptoms and diseases, 93.6% for the attractiveness of the application display and 92.8% for the benefits for application users.

Green Entrepreneurship: Knowledge and Perception of Students and Professionals from Poland and Slovakia

The purpose of this paper is to review the understanding of the term “green entrepreneurship” in contemporary management sciences and its interpretation by people who are or soon will be professionally active. Investigating the phenomenon from a historical perspective will allow an evolutionary approach to the category to indicate contemporary challenges. Apart from a review of the literature on the subject, the interpretations of the term by the target group are recognized in the environmental, social, and governance (ESG) context. The research methods used in the article include a critical analysis of the literature on the subject and field research presented in the empirical part. Primary research was carried out in two countries: Poland and Slovakia, among students and professionals working, as well as those professionally active in the private and public sectors. The study aimed to generally identify the knowledge of the concept of “green entrepreneurship”. Based on the results, the responses were delimited and those indicated by less than 5% of the respondents were considered irrelevant. Based on the remaining answers, a new survey questionnaire was created, which was used to conduct the second stage of the research. To simplify the research tool, it was assumed that the questions would be binary (“yes” or “no” answers), and the resulting survey would consist of 22 phrases (marked with alphanumeric symbols) and a form. The respondents’ answers from the second stage of the study allowed us to identify characteristic groups of variables with which the respondents associated the term “green entrepreneurship” and the groups of respondents who indicated an understanding of green entrepreneurship in a specific aspect. It also allowed for the identification the determinants of these indications, as well as similarities and differences between Poles and Slovaks in this respect. For this purpose, the classification and regression tree method (C&amp;RT) was used. For the purposes of this study, JASP 0.18.1 software was used to create the tree. The results show that perceptions and knowledge of green entrepreneurship differ in both surveyed countries.

Determination of model maps for the potential distribution of Anatolian black pine (Pinus nigra Arnold.) in natural forest areas in the Central Black Sea region

Özdemir ŞENTÜRK 1*, Serkan GÜLSOY 2, Mehmet Güvenç NEGİZ 3, Fatih KARAKAYA 2 ORCID: https://orcid.org/0000-0003-2513-6070; https://orcid.org/0000-0003-2011-8324; https://orcid.org/0000-0002-6338-3307; https://orcid.org/0000-0002-6534-6382 1 Gölhisar Vocational School, Departmant of Forestry, Burdur Mehmet Akif Ersoy University, Gölhisar, Burdur, Turkey 2 Faculty of Forestry, Department of Forest Engineering, Isparta University of Applied Sciences, Isparta, Turkey 3 Sütçüler Prof. Dr. Hasan GÜRBÜZ Vocational School, Department of Forest Engineering, Isparta University of Applied Sciences, Sütçüler, Isparta, Turkey *Corresponding author: e-mail: osenturk@mehmetakif.edu.tr Abstract The purpose of this study was to determine potential distribution modeling and mapping of Anatolian black pine in the Vezirköprü district. Presence / absence data of the species was collected from 586 sample areas. Environmental variables (elevation, slope, bedrock, radiation index etc.) were obtained from the digital maps. In addition, climatic variables were downloaded from WorldClim database. Generalized Additive Model and Classification and Regression Tree were used for potential distribution modeling of the species. The validation value of Generalized Additive Model was 0.84 while the cross-validation test value was found to be 0.82. Also, the ROC values of the tree model were found to be 0.804 for the training data set and 0.750 for the testing data set. According to the Classification and Regression Tree method, the locations above 650 m and without meta-sandstone are suitable for the potential distribution of the species. Under the condition that there is meta-sandstone, the areas where the temperature is between 7.6-11.0 °C and the slope degree is more than 23% coincide with the potential distribution of the species. Also, Generalized Additive Model showed that places where gabbro, ophiolitic melange, serpentine, and mixed material were seen as main bedrock type, sloping sites where average elevation was from 600 to 1150 m and temperature is between approximately 8.5-11.3 °C were the most suitable conditions for the potential distribution of the species in the district. In both models, it was determined that especially rock formations, climatic variable, and altitude are effective in the potential distribution of the species. On the other hand, although there are some differences in the variables in the models, the potential distribution maps formed by these variables overlapped quite. As a result, the information obtained in the study is important for the forestry practices such as afforestation, regeneration and the monitoring the species under future climate change conditions. Keywords: generalized additive model; classification and regression tree; species distribution model; Vezirköprü

APPLICATION OF BAGGING CART IN THE CLASSIFICATION OF ON-TIME GRADUATION OF STUDENTS IN THE STATISTICS STUDY PROGRAM OF TANJUNGPURA UNIVERSITY

The timeliness of graduation is used as the success of students in pursuing education which can be seen from the time taken and measured by the predicate of graduation obtained. The characteristics of students who tend to graduate not or on time can be analyzed using classification techniques. Classification and Regression Tree (CART) is one of the classification tree methods. There is a weakness in CART, which is less stable in predicting a single classification tree. The weaknesses in CART can be improved by using Ensemble methods, one of which is Bootstrap Aggregating (Bagging) which can reduce classification errors and increase accuracy in a single classification model. This study aims to classify and determine the accuracy of Bagging CART in the case of the accuracy of student graduation classification. The number of samples used is 140 data on the graduation status of Untan Statistics Study Program students from Period I of the 2017/2018 academic year to Period II of the 2022/2023 academic year. The variables used are the timeliness of graduation which is categorized into two namely Not and On Time, Gender, Semester 1 GPA, Semester 2 GPA, Semester 3 GPA, Semester 4 GPA, Region of Origin Domicile, High School Accreditation, Entry Path, Scholarship, and first TUTEP. A good classification can be seen from the accuracy value. The CART method obtained an accuracy value of 70%. While using the CART Bagging method obtained an accuracy value of 85.71%. Based on the accuracy value obtained, the application of the CART Bagging method can increase accuracy and correct classification errors on a single CART classification tree by 15.71% by resampling 25 times.

A new approach to extract the upright maize straw from Sentinel-2 satellite imagery using new straw indices

Unharvested upright maize straw is highly susceptible to burning in winter or in spring of the following year, contributing significantly to air pollution. The rapid and accurate acquisition of the spatial distribution of upright maize straw holds great importance for agricultural and environmental protection departments. This study introduces a new approach that focuses on extracting upright maize straw using Sentinel-2 satellite images. Initially, the Sentinel-2 images from the Botou and Hejian regions underwent preprocessing. To minimize interference during straw extraction, the normalized difference vegetation index (NDVI) was utilized to extract and eliminate built-up land and woodland areas. Subsequently, utilizing the spectral characteristics of maize straw across various bands including short-wave infrared, red edge, and near-infrared, three new indices were proposed and computed: the accumulation infrared straw index (AIRSI), the product near-infrared straw index (PNISI), and the normalized difference short-wave infrared straw index (NDSSI). Finally, the decision tree classification method was implemented to establish classification rules and extract the spatial distribution of upright maize straw. The study results revealed that the proposed new straw indices achieved an extraction accuracy of over 90% for upright maize straw. This new approach effectively enhances the identification accuracy of upright maize straw, providing valuable support for scientific supervision, comprehensive utilization, and prevention and control measures against maize straw burning.

Characterization of the shape of aggregates using image analysis and machine learning classification tools

ABSTRACT Engineering applications including pervious concrete require effective packing of aggregates to optimize strength. Size and shape distribution of aggregates significantly affect the performance. Computational methods numerically represent shape of aggregates, from image analysis, the effectiveness of has not been compared and verified. This study aims to analyse the representability of shape aspects of aggregates by different computational methods. Crushed aggregates were grouped into 5 clusters, and each group was milled in a Los Angeles machine for different degrees (0–2000) to induce morphological changes on the aggregates. Aggregates ranging from 5 to 30mm in diameter were obtained (7191 in total). imageJTM, was used to compute dimensions and shape factors of aggregates from 14 computational methods. Statistical tests, Pearson’s Correlations and Principal Components Analysis and machine learning classification tools, Decision-tree, Random-Forest, Naïve-Bayes, Support-Vector-Machines, K-Nearest-Neighbours and Perceptron were employed to assess. In conclusion, no shape factor could be singularly used to numerically represent the morphological changes on aggregate particles but a combination of shape factors is required. Data matrix had three primary dimensions. Combination of Circularity, Kumbrein-Solidity and Barksdale-Shape-Factor yield best representation of aggregate shape. Regression Tree classification method had the highest accuracy (0.9) in classifying milled and unmilled aggregates.

Прогнозирование риска неблагоприятного исхода при COVID‑19 с помощью метода деревьев классификации с учетом возраста и количества коморбидной патологии по данным инфекционного госпиталя.

Objective: to determine the probability of the risk of an unfavorable outcome using the classification tree method in patients with COVID‑19 who were treated in an infectious hospital based on the analysis of the contribution of such predictors as age and the amount of comorbid pathology. Materials and methods. The data of outpatient records of 5304 patients who were treated in an infectious diseases hospital with a diagnosis of COVID‑19 from January 1, 2021 to January 1, 2022 were analyzed. The age of the examined patients was 62 [56–66] years. Among 5,304 patients, there were 2,891 males (54,5%) and 2,413 females (45,5%). The patients were divided into age groups according to the WHO classification. The frequency of comorbid pathology was analyzed taking into account the nosological unit of the disease registered in at least 1% of the patients included in the study. Results. In the studied sample, the elderly prevailed in a larger percentage – 46.8%. The presence of one or more comorbid pathology was revealed in the prevailing number of hospitalized – in 5,244 people (98,9%). The most common comorbid pathology in the examined patients was arterial hypertension in 2038 people (38,4%), coronary heart disease in 1997 people (37,7%) and type 2 diabetes mellitus in 1629 people (30,7%). A classification tree was constructed to predict the risk of the probability of an unfavorable outcome in patients with COVID‑19.The minimum number of observations in the parent node in the classification tree was 400 people, in the child node – 200 people. In the resulting classification tree, 8 terminal nodes were observed. Conclusion. The probability of the risk of an unfavorable outcome in the analyzed sample of patients increases with an increase in the number of comorbid pathology and the age of patients. According to the forecast using the classification tree method, the greatest probability of risk (3,2 times) of an unfavorable outcome in relation to the general sample was among elderly persons+centenarians with more than three comorbid pathology. The developed classification tree showed a high probability of correct predictions (80%). The sensitivity of the resulting model was 77,9%, the specificity was 64,2%.

State of Perception and Knowledge of Bioeconomy in Selected European Universities

Abstract Sustainable bioeconomy is one of the concepts that makes it possible to achieve the European Green Deal. A similar understanding of the term bioeconomy gives the opportunity to simultaneously take proportionate actions leading to the implementation of the Sustainable Development Goals in EU countries. Parallel understanding of the concept of bioeconomy is crucial for achieving a common consensus on actions aimed at introducing optimal plans for the development of green technologies. Therefore, the goal of the paper was to compare knowledge and perception about the bioeconomy in different countries. Realization of the work's objective was possible thanks to the use of the C&amp;RT classification tree method. It was shown that the level of knowledge of respondents working or studying at selected universities was similar, while their perception of the bioeconomy differed significantly.

Determination of cut-off points for the Move4 accelerometer in children aged 8–13 years

BackgroundTo assess physical activity (PA) there is a need of objective, valid and reliable measurement methods like accelerometers. Before these devices can be used for research, they need to be calibrated and validated for specific age groups as the locomotion differs between children and adults, for instance. Therefore, the aim of the present study was the calibration and validation of the Move4 accelerometer for children aged 8–13 years.Methods53 normal weighted children (52% boys, 48%girls) aged 8–13 years (mean age = 10.69 ± 1.46, mean BMI = 17.93 kg/m− 2, 60th percentile), wore the Move4 sensor at four different body positions (thigh, hip, wrist and the Move4ecg including heart rate measurement at the chest). They completed nine activities that considered the four activity levels (sedentary behavior (SB), light PA (LPA), moderate PA (MPA) and vigorous PA (VPA)) within a test-retest design. Intensity values were determined using the mean amplitude deviation (MAD) as well as the movement acceleration intensity (MAI) metrics. Determination of activities and energy expenditure was validated using heart rate. After that, cut-off points were determined in Matlab by using the Classification and Regression Trees (CART) method. The agreement for the cut-off points between T1 and T2 was analyzed.ResultsMAD and MAI accelerometer values were lowest when children were lying on the floor and highest when running or doing jumping jacks. The mean correlation coefficient between acceleration values and heart rate was 0.595 (p = 0.01) for MAD metric and 0.611 (p = 0.01) for MAI metric, indicating strong correlations. Further, the MAD cut-off points for SB-LPA are 52.9 mg (hip), 62.4 mg (thigh), 86.4 mg (wrist) and 45.9 mg (chest), for LPA-MPA they are 173.3 mg (hip), 260.7 mg (thigh), 194.4 mg (wrist) and 155.7 mg (chest) and for MPA-VPA the cut-off points are 543.6 mg (hip), 674.5 mg (thigh), 623.4 mg (wrist) and 545.5 mg (chest). Test-retest comparison indicated good values (mean differences = 9.8%).ConclusionThis is the first study investigating cut-off points for children for four different sensor positions using raw accelerometer metrics (MAD/MAI). Sensitivity and specificity revealed good values for all positions. Nevertheless, depending on the sensor position, metric values differ according to the different involvement of the body in various activities. Thus, the sensor position should be carefully chosen depending on the research question of the study.

Homelessness and Emergency Department Use: Wait Time Disparities Across Triage Acuity Levels.

Introduction Certain patient groups perceive specific barriers to accessing primary care, resulting in increased emergency department (ED) use for non-emergency conditions. There is evidence coming from other countries that homeless people are treated differently in accessing emergency services.Examination of ED wait time by demographic characteristics provides pertinent information to identify subgroups that are more subject to the consequences or causes of access block and delayed treatment. Methods We analyzed five years of Emergency Department Information System (EDIS) visit records of the largest tertiary care center in Atlantic Canada. The wait time from triage to seeing a physician was the outcome, housing status was the main exposure, and age and gender were the predictors. Quantile regressions were carried out to identify the influence of homeless visits in meeting the Canadian Association of Emergency Physicians (CAEP) wait time benchmarks for each Canadian Triage and Acuity Scale (CTAS) level. The classification and regression tree method was used to quantify and classify the demographic subgroups contributing to wait time disparities across CTAS levels. Results Homeless visit medianwait times that exceeded the three-hour CAEP benchmark were significantly longer for urgent (by 40 minutes, CI: 25-55), semi-urgent (by 31 minutes, CI: 17-45), and non-urgent (by 57 minutes, CI: 25-89) than acuity level-matched domiciled visitwait times. At the 50th percentile, one-hourbenchmark homeless triaged as semi-urgent waited (median=20 minutes, CI: 12-28) longer, and no other triage-level differences were found at this benchmark. Homeless emergent-level visits that exceeded the three-hour benchmark were 28 minutes, on average, shorter than domiciled patients of the same acuity level. Homeless females above 40 stayed the longest for non-urgent care (mean=173 minutes), 82 minutes longer (p=0.0001) than age-gender-acuity level-matched domiciled patients. Homelessness was the most prominent ED wait time classifier for non-urgent, ED visits.Overall, homeless patients triaged as CTAS-5 waited 30 minutes longer (p=0.0001) than domiciled patients triaged as CTAS-5.Homeless male 16-20-year-olds waited the shortest time of 72 minutes. Conclusion Homelessness-related wait time disparities exist in the low acuity non-urgent-level ED visits more than in the other levels, supporting the theory that lack of primary care access is a driver of ED use in this group. Our acuity level analysis supports that homeless people of a certain age (older) and gender groups (female) wait longer than their age-gender-matched domiciled patients to be seen by a physician in low acuity level presentations. Given the pattern of the homeless being seen earlier or statistically similar in emergent-level visits compared to matched domiciled patients and that 16-20-year-old homeless males were seen on average within 72 minutes (the shortest mean wait time reported for the triage level CTAS-5), we decline the notion of discrimination at the study site ED. If homeless patients' non-urgent needs were met elsewhere, pressure on the ED to meet benchmarks might be reduced.

Identification of new potential candidates to inhibit EGF via machine learning algorithm

One of the cost-effective alternative methods to find new inhibitors has been the repositioning approach of existing drugs. The advantage of computational drug repositioning method is saving time and cost to remove the pre-clinical step and accelerate the drug discovery process. Hence, an ensemble computational-experimental approach, consisting of three steps, a machine learning model, simulation of drug-target interaction and experimental characterization, was developed. The machine learning type used here was a different tree classification method, which is one of the best randomize machine learning model to identify potential inhibitors from weak inhibitors. This model was trained more than one-hundred times, and forty top trained models were extracted for the drug repositioning step. The machine learning step aimed to discover the approved drugs with the highest possible success rate in the experimental step. Therefore, among all the identified molecules with more than 0.9 probability in more than 70% of the models, nine compounds, were selected. Besides, out of the nine chosen drugs, seven compounds have been confirmed to inhibit EGF in the published articles since 2019. Hence, two identified compounds, in addition to gefitinib, as a positive control, five weak-inhibitors and one neutral, were considered via molecular docking study. Finally, the eight proposed drugs, including gefitinib, were investigated using MTT assay and In-Cell ELISA to characterize the drugs' effect on A431 cell growth and EGF-signaling. From our experiments, we could conclude that salicylic acid and piperazine could play an EGF-inhibitor role like gefitinib.

Risk profiles for smoke behavior in COVID-19: a classification and regression tree analysis approach

BackgroundCOVID-19 pandemic emerged worldwide at the end of 2019, causing a severe global public health threat, and smoking is closely related to COVID-19. Previous studies have reported changes in smoking behavior and influencing factors during the COVID-19 period, but none of them explored the main influencing factor and high-risk populations for smoking behavior during this period.MethodsWe conducted a nationwide survey and obtained 21,916 valid data. Logistic regression was used to examine the relationships between each potential influencing factor (sociodemographic characteristics, perceived social support, depression, anxiety, and self-efficacy) and smoking outcomes. Then, variables related to smoking behavior were included based on the results of the multiple logistic regression, and the classification and regression tree (CART) method was used to determine the high-risk population for increased smoking behavior during COVID-19 and the most profound influencing factors on smoking increase. Finally, we used accuracy to evaluated the performance of the tree.ResultsThe strongest predictor of smoking behavior during the COVID-19 period is acceptance degree of passive smoking. The subgroup with a high acceptation degree of passive smoking, have no smokers smoked around, and a length of smoking of ≥ 30 years is identified as the highest smoking risk (34%). The accuracy of classification and regression tree is 87%.ConclusionThe main influencing factor is acceptance degree of passive smoking. More knowledge about the harm of secondhand smoke should be promoted. For high-risk population who smoke, the “mask protection” effect during the COVID-19 pandemic should be fully utilized to encourage smoking cessation.