Exploring risk factors and their differences on suicidal ideation and suicide attempts among depressed adolescents based on decision tree model

BACKGROUND

Suicide has been recognized as a major global public health issue. Depressed adolescents are more prone to experiencing it. We explore risk factors and their differences on suicidal ideation and suicide attempts to further enhance our understanding of suicidal behavior.

METHODS

2343 depressed adolescents aged 12-18 from 9 provinces/cities in China participated in this cross-sectional study. We utilized decision tree model, incorporating 32 factors encompassing participants' suicidal behavior. The feature importance of each factor was measured using Gini coefficients.

RESULTS

The decision tree model demonstrated a good fit with high accuracy (SI = 0.86, SA = 0.85 and F-Score (SI = 0.85, SA = 0.83). The predictive importance of each factor varied between groups with suicidal ideation and with suicide attempts. The most significant risk factor in both groups was depression (SI = 16.7 %, SA = 19.8 %). However, factors such as academic stress (SI = 7.2 %, SA = 1.6 %), hopelessness (SI = 9.1 %, SA = 5.0 %), and age (SI = 7.1 %, SA = 3.2 %) were more closely associated with suicidal ideation than suicide attempts. Factors related to the schooling status (SI = 3.5 %, SA = 10.1 %), total years of education (SI = 2.6 %, SA = 8.6 %), and loneliness (SI = 2.3 %, SA = 7.4 %) were relatively more important in the suicide attempt stage compared to suicidal ideation.

LIMITATIONS

The cross-sectional design limited the ability to capture changes in suicidal behavior among depressed adolescents over time. Possible bias may exist in the measurement of suicidal ideation.

CONCLUSION

The relative importance of each risk factor for suicidal ideation and attempted suicide varies. These findings provide further empirical evidence for understanding suicide behavior. Targeted treatment measures should be taken for different stages of suicide in clinical interventions.

Metric evaluation of the anterior nasal spine to estimate sex and population group in South African individuals

INTRODUCTION

The anterior nasal spine is a pointed, midline projection of the maxilla. This bony structure dictates the overlying soft tissues providing the phenotypic features of the nose and upper lip and determines the differences in the mid-face morphology. Little data is available on the metric features of the Anterior nasal spine (ANS). This study aimed to perform metric evaluations of the ANS of white and black South African males and females to ascertain if morphological variations exist and if the differences are viable for the use in sex and population identification.

MATERIALS AND METHODS

The sample included 100 CBCT images for each population and sex group. Linear and angular measurements of the ANS were recorded in both the sagittal and axial planes.

RESULTS

Classification decision trees (pruned) were fitted to ascertain the relationship between population group, sex and the ANS measurements including and excluding age. For population group, all the ANS measurements were statistically significant for females but in males, all the ANS measurements were significant when performed individually. However, when fitted to the classification tree, Sagittal 2 did not show any statistical significance. When considering sex, only 2 of the ANS measurements (Sagittal 2 and Axial 1) were found to be significant. The results did not differ significantly when comparing the decision trees including and excluding age.

CONCLUSIONS

White South African individuals presented with a longer ANS that produced a more acute angle whereas black South African individuals presented with a shorter ANS and a more obtuse angle. Additionally, males presented with a longer ANS compared to females. ANS measurements were found to be more relevant for population discernment than for sex.

Leveraging machine learning for prediction of antibiotic resistance genes post thermal hydrolysis-anaerobic digestion in dairy waste

Anaerobic digestion holds promise as a method for removing antibiotic resistance genes (ARGs) from dairy waste. However, accurately predicting the efficiency of ARG removal remains a challenge. This study introduces a novel appproach utilizing machine learning to forecast changes in ARG abundances following thermal hydrolysis-anaerobic digestion (TH-AD) treatment. Through network analysis and redundancy analyses, key determinants of affect ARG fluctuations were identified, facilitating the development of machine learning models capable of accurately predicting ARG changes during TH-AD processes. The decision tree model demonstrated impressive predictive power, achieving an impessive R2 value of 87% against validation data. Feature analysis revealed that the genes intI2 and intI1 had a critical impact on the absolute abundance of ARGs. The predictive model developed in this study offers valuable insights for improving operational and managerial practices in dairy waste treatment facilities, with the ultimate goal of mitigating the spread of antibiotic resistance.

Demographic and clinical characteristics associated with advanced stage colorectal cancer: a registry-based cohort study in Saudi Arabia

BACKGROUND

In Saudi Arabia, approximately one-third of colorectal cancer (CRC) patients are diagnosed at an advanced stage. Late diagnosis is often associated with a worse prognosis. Understanding the risk factors for late-stage presentation of CRC is crucial for developing targeted interventions enabling earlier detection and improved patient outcomes.

METHODS

We conducted a retrospective cohort study on 17,541 CRC patients from the Saudi Cancer Registry (1997-2017). We defined distant CRCs as late-stage and localized and regional CRCs as early-stage. To assess risk factors for late-stage CRC, we first used multivariable logistic regression, then developed a decision tree to segment regions by late-stage CRC risk, and finally used stratified logistic regression models to examine geographical and sex variations in risk factors.

RESULTS

Of all cases, 29% had a late-stage diagnosis, and 71% had early-stage CRC. Young (< 50 years) and unmarried women had an increased risk of late-stage CRC, overall and in some regions. Regional risk variations by sex were observed. Sex-related differences in late-stage rectosigmoid cancer risk were observed in specific regions but not in the overall population. Patients diagnosed after 2001 had increased risks of late-stage presentation.

CONCLUSION

Our study identified risk factors for late-stage CRC that can guide targeted early detection efforts. Further research is warranted to fully understand these relationships and develop and evaluate effective prevention strategies.

Diet and lifestyle behaviours simultaneously act on frailty: it is time to move the threshold of frailty prevention and control forward

BACKGROUND

To analyse the association among the simultaneous effects of dietary intake, daily life behavioural factors, and frailty outcomes in older Chinese women, we predicted the probability of maintaining physical robustness under a combination of different variables.

METHODS

The Fried frailty criterion was used to determine the three groups of "frailty", "pre-frailty", and "robust", and a national epidemiological survey was performed. The three-classification decision tree model was fitted, and the comprehensive performance of the model was evaluated to predict the probability of occurrence of different outcomes.

RESULTS

Among the 1,044 participants, 15.9% were frailty and 50.29% were pre-frailty; the overall prevalence first increased and then decreased with age, reaching a peak at 70-74 years of age. Through univariate analysis, filtering, and embedded screening, eight significant variables were identified: staple food, spices, exercise (frequency, intensity, and time), work frequency, self-feeling, and family emotions. In the three-classification decision tree, the values of each evaluation index of Model 3 were relatively average; the accuracy, recall, specificity, precision, and F1 score range were between 75% and 84%, and the AUC was also greater than 0.800, indicating excellent performance and the best interpretability of the results. Model 3 takes exercise time as the root node and contains 6 variables and 10 types, suggesting the impact of the comprehensive effect of these variables on robust and non-robust populations (the predicted probability range is 6.67-93.33%).

CONCLUSION

The combined effect of these factors (no exercise or less than 0.5 h of exercise per day, occasional exercise, exercise at low intensity, feeling more tired at work, and eating too many staple foods (> 450 g per day) are more detrimental to maintaining robustness.

High-throughput phenotyping using VIS/NIR spectroscopy in the classification of soybean genotypes for grain yield and industrial traits

Employing visible and near infrared sensors in high-throughput phenotyping provides insight into the relationship between the spectral characteristics of the leaf and the content of grain properties, helping soybean breeders to direct their program towards improving grain traits according to researchers' interests. Our research hypothesis is that the leaf reflectance of soybean genotypes can be directly related to industrial grain traits such as protein and fiber contents. Thus, the objectives of the study were: (i) to classify soybean genotypes according to the grain yield and industrial traits; (ii) to identify the algorithm(s) with the highest accuracy for classifying genotypes using leaf reflectance as model input; (iii) to identify the best input data for the algorithms to improve their performance. A field experiment was carried out in randomized block design with three replications and 32 soybean genotypes. At 60 days after emergence, spectral analysis was carried out on three leaf samples from each plot. A hyperspectral sensor was used to capture reflectance between the wavelengths from 450 to 824 nm. Representative spectral bands were selected and grouped into means. After harvest, grain yield was assessed and laboratory analyses of industrial traits were carried out. Spectral, industrial traits and yield data were subjected to statistical analysis. Data were analyzed by the following machine learning algorithms: J48 (J48) and REPTree (DT) decision trees, Random Forest (RF), Artificial Neural Networks (ANN), Support Vector Machine (SVM), and conventional Logistic Regression (LR) analysis. The clusters formed were used as the output of the models, while two groups of input data were used for the input of the models: the spectral variables (WL) noise-free obtained by the sensor (450-828 nm) and the spectral means of the selected bands (SB) (450.0-720.6 nm). Soybean genotypes were grouped according to their grain yield and industrial traits, in which the SVM and J48 algorithms performed better at classifying them. Using the spectral bands selected in the study improved the classification accuracy of the algorithms.

Kidney scoring surveillance: predictive machine learning models for clear cell renal cell carcinoma growth using MRI

INTRODUCTION

Classification of clear cell renal cell carcinoma (ccRCC) growth rates in patients with Von Hippel-Lindau (VHL) syndrome has several ramifications for tumor monitoring and surgical planning. Using two separate machine-learning algorithms, we sought to produce models to predict ccRCC growth rate classes based on qualitative MRI-derived characteristics.

MATERIAL AND METHODS

We used a prospectively maintained database of patients with VHL who underwent surgical resection for ccRCC between January 2015 and June 2022. We employed a threshold growth rate of 0.5 cm per year to categorize ccRCC tumors into two distinct groups-'slow-growing' and 'fast-growing'. Utilizing a questionnaire of qualitative imaging features, two radiologists assessed each lesion on different MRI sequences. Two machine-learning models, a stacked ensemble technique and a decision tree algorithm, were used to predict the tumor growth rate classes. Positive predictive value (PPV), sensitivity, and F1-score were used to evaluate the performance of the models.

RESULTS

This study comprises 55 patients with VHL with 128 ccRCC tumors. Patients' median age was 48 years, and 28 patients were males. Each patient had an average of two tumors, with a median size of 2.1 cm and a median growth rate of 0.35 cm/year. The overall performance of the stacked and DT model had 0.77 ± 0.05 and 0.71 ± 0.06 accuracies, respectively. The best stacked model achieved a PPV of 0.92, a sensitivity of 0.91, and an F1-score of 0.90.

CONCLUSION

This study provides valuable insight into the potential of machine-learning analysis for the determination of renal tumor growth rate in patients with VHL. This finding could be utilized as an assistive tool for the individualized screening and follow-up of this population.

Advanced direct torque control based on neural tree controllers for induction motor drives

This paper introduces a novel direct torque control approach based on the decision tree (T-DTC), employing artificial neural networks that are effectively trained to enhance accuracy and robustness. The main objective of T-DTC is the substantial reduction of flux and torque ripples inherent in the conventional DTC, ensuring effective control of the induction motor. The conventional hysteresis controllers for stator flux and electromagnetic torque are replaced by two advanced controllers named M5 Prime model trees. Additionally, the traditional switching table is substituted with a novel decision tree table utilizing the classifier algorithm 4.5. The effectiveness of the proposed T-DTC strategy is demonstrated through simulation in MATLAB/Simulink and validated in real-time using an HIL platform based on OPAL-RT OP 5600 and Virtex 6 FPGA ML605. The results obtained demonstrate a notable improvement compared to existing techniques in the literature.

Coastal Flood risk assessment using ensemble multi-criteria decision-making with machine learning approaches

Coastal areas are at a higher risk of flooding, and novel changes in the climate are induced to raise the sea level. Flood acceleration and frequency have increased recently because of unplanned infrastructural conveniences and anthropogenic activities. Therefore, the assessment of flood susceptibility mapping is considered the most significant flood management model. In this paper, flood susceptibility identification is performed by applying the innovative Multi-criteria decision-making model (MCDM) called Analytical Hierarchy Process (AHP) by ensembles with Support vector machine (AHP-SVM) and Decision Tree (AHP-DT). This model combines two Representation concentration pathway (RCP) scenarios such as RCP 2.6 & RCP 8.5. The factors influencing the coastal flooding in Bandar Abbas, Iran, identified through Flood susceptibility mapping. Multi-criteria decision-making (MCDM) has been applied to evaluate the Coastal flood conditioning factors, and ensemble machine learning (ML) approaches are employed for Coastal risk factor (CRF) prediction and classification. The statistical variances are measured through Friedman and Wilcoxon signed rank tests and statistical metrics such as Accuracy, sensitivity, and specificity. Among the models, AHP-DT obtained an improved AUC value of ROC as 0.95. After applying the ML models, the northern and western park of Raidak Basin River recognises very low and low flood susceptibility because of their topographic characteristics. The eastern part of the middle section fell very high and high CFSM. Observed from this result analysis, the people living nearer to the coastline are distributed by the low to medium exposure in the region of the west and middle of the considered study area. The results of this study can help decision-makers take necessary risk reduction approaches in the high-risk flooding zones of the coastal system.

Laryngeal cancer diagnosis via miRNA-based decision tree model

PURPOSE

Laryngeal cancer (LC) is the most common head and neck cancer, which often goes undiagnosed due to the inaccessible nature of current diagnosis methods in some parts of the world. Many recent studies have shown that microRNAs (miRNAs) are crucial biomarkers for a variety of cancers.

METHODS

In this study, we create a decision tree model for the diagnosis of laryngeal cancer using a created series of miRNA attributes, such as sequence-based characteristics, predicted miRNA target genes, and gene pathways. This series of attributes is extracted from both differentially expressed blood-based miRNAs in laryngeal cancer and random, non-associated with cancer miRNAs.

RESULTS

Several machine-learning (ML) algorithms were tested in the ML model, and the Hoeffding Tree classifier yields the highest accuracy (86.8%) in miRNAs-based recognition of laryngeal cancer. Furthermore, our model is validated with the independent laryngeal cancer datasets and can accurately diagnose laryngeal cancer with 86% accuracy. We also explored the biological relationships of the attributes used in our model to understand their relationship with cancer proliferation or suppression pathways.

CONCLUSION

Our study demonstrates that the proposed model and an inexpensive miRNA testing strategy have the potential to serve as an additional method for diagnosing laryngeal cancer.

Sensitivity Evaluation of Enveloped and Non-enveloped Viruses to Ethanol Using Machine Learning: A Systematic Review

Viral diseases are a severe public health issue worldwide. During the coronavirus pandemic, the use of alcohol-based sanitizers was recommended by WHO. Enveloped viruses are sensitive to ethanol, whereas non-enveloped viruses are considerably less sensitive. However, no quantitative analysis has been conducted to determine virus ethanol sensitivity and the important variables influencing the inactivation of viruses to ethanol. This study aimed to determine viruses' sensitivity to ethanol and the most important variables influencing the inactivation of viruses exposed to ethanol based on machine learning. We examined 37 peer-reviewed articles through a systematic search. Quantitative analysis was employed using a decision tree and random forest algorithms. Based on the decision tree, enveloped viruses required around ≥ 35% ethanol with an average contact time of at least 1 min, which reduced the average viral load by 4 log10. In non-enveloped viruses with and without organic matter, ≥ 77.50% and ≥ 65% ethanol with an extended contact time of ≥ 2 min were required for a 4 log10 viral reduction, respectively. Important variables were assessed using a random forest based on the percentage increases in mean square error (%IncMSE) and node purity (%IncNodePurity). Ethanol concentration was a more important variable with a higher %IncMSE and %IncNodePurity than contact time for the inactivation of enveloped and non-enveloped viruses with the available organic matter. Because specific guidelines for virus inactivation by ethanol are lacking, data analysis using machine learning is essential to gain insight from certain datasets. We provide new knowledge for determining guideline values related to the selection of ethanol concentration and contact time that effectively inactivate viruses.

A supervised machine learning approach for the prediction of antioxidant activities of Amaranthus viridis seed

This research aimed at modelling and predicting the antioxidant activities of Amaranthus viridis seed extract using four (4) data-driven models. Artificial Neural Network (ANN), Support Vector Machine (SVM), k-nearest Neighbour (k-NN), and Decision Tree (DT) were used as modelling algorithms for the construction of a non-linear empirical model to predict the antioxidant properties of Amaranthus viridis seed extract. Datasets for the modelling operation were obtained from a Box Behnken design while the hyperparameters of the ANN, SVM, k-NN and DT were determined using a 10-fold cross-validation technique. Among the Machine Learning algorithms, DT was observed to exhibit excellent performance and outperformed other Machine Learning algorithms in predicting the antioxidant activities of the seed extract, with a sensitivity of 0.867, precision of 0.928, area under the curve of 0.979, root mean square error of 0.184 and correlation coefficient of 0.9878. It was closely followed by ANN which was used to analyze and explain in detail the effect of the independent variables on the antioxidant activities of the seed extracts. This result affirmed the suitability of DT in predicting the antioxidant activities of Amaranthus viridis.

Construction and optimization of vending machine decision support system based on improved C4.5 decision tree

The intensification of market competition makes refined operation management become the focus of attention of major manufacturers. As an important branch of artificial intelligence (AI), machine learning (ML) plays a key role in it, and has its application prospect in various systems. Based on this situation, this paper takes vending machines as the research object. On the one hand, the product classification model of vending machine is constructed based on decision tree algorithm. On the other hand, based on neural network (NN), the sales forecast model of vending machines is built. Finally, based on the above research, the theoretical framework of decision support system (DSS) for vending machines is constructed. The research shows that: (1) The accuracy of C4.5 algorithm can reach 87 % at the highest and 68 % at the lowest. The accuracy of the improved C4.5 algorithm can reach 87 % at the highest and 67 % at the lowest, with little difference between them. (2) The maximum running time of the improved C4.5 algorithm is about 5500 ms, and the minimum is close to 1 ms. In addition, the running time of all seven datasets is better than that of the unmodified algorithm. (3) When the back propagation neural network (BPNN) is used to forecast the sales of vending machines, the curve of the predicted data basically coincides with the curve of the actual data, which shows that its accuracy is high. This paper aims to build a convenient and secure DSS by taking vending machines as an example. In addition, this paper also uses reinforcement learning to optimize the research methods of this paper. It can further optimize the performance and efficiency of vending machines and provide better service experience for customers. Meanwhile, the use of reinforcement learning can make the whole system more intelligent and adaptive to better cope with the changing market environment.

Mapping of soil suitability for medicinal plants using machine learning methods

Inadequate conservation of medicinal plants can affect their productivity. Traditional assessments and strategies are often time-consuming and linked with errors. Utilizing herbs has been an integral part of the traditional system of medicine for centuries. However, its sustainability and conservation are critical due to climate change, over-harvesting and habitat loss. The study reveals how machine learning algorithms, geographic information systems (GIS) being a powerful tool for mapping and spatial analysis, and soil information can contribute to a swift decision-making approach for actual forethought and intensify the productivity of vulnerable curative plants of specific regions to promote drug discovery. The data analysis based on machine learning and data mining techniques over the soil, medicinal plants and GIS information can predict quick and effective results on a map to nurture the growth of the herbs. The work incorporates the construction of a novel dataset by using the quantum geographic information system tool and recommends the vulnerable herbs by implementing different supervised algorithms such as extra tree classifier (EXTC), random forest, bagging classifier, extreme gradient boosting and k nearest neighbor. Two unique approaches suggested for the user by using EXTC, firstly, for a given subregion type, its suitable soil classes and secondly, for soil type from the user, its respective subregion labels are revealed, finally, potential medicinal herbs and their conservation status are visualised using the choropleth map for classified soil/subregion. The research concludes on EXTC as it showcases outstanding performance for both soil and subregion classifications compared to other models, with an accuracy rate of 99.01% and 98.76%, respectively. The approach focuses on serving as a comprehensive and swift reference for the general public, bioscience researchers, and conservationists interested in conserving medicinal herbs based on soil availability or specific regions through maps.

Ensemble methods of rank-based trees for single sample classification with gene expression profiles

Building Single Sample Predictors (SSPs) from gene expression profiles presents challenges, notably due to the lack of calibration across diverse gene expression measurement technologies. However, recent research indicates the viability of classifying phenotypes based on the order of expression of multiple genes. Existing SSP methods often rely on Top Scoring Pairs (TSP), which are platform-independent and easy to interpret through the concept of "relative expression reversals". Nevertheless, TSP methods face limitations in classifying complex patterns involving comparisons of more than two gene expressions. To overcome these constraints, we introduce a novel approach that extends TSP rules by constructing rank-based trees capable of encompassing extensive gene-gene comparisons. This method is bolstered by incorporating two ensemble strategies, boosting and random forest, to mitigate the risk of overfitting. Our implementation of ensemble rank-based trees employs boosting with LogitBoost cost and random forests, addressing both binary and multi-class classification problems. In a comparative analysis across 12 cancer gene expression datasets, our proposed methods demonstrate superior performance over both the k-TSP classifier and nearest template prediction methods. We have further refined our approach to facilitate variable selection and the generation of clear, precise decision rules from rank-based trees, enhancing interpretability. The cumulative evidence from our research underscores the significant potential of ensemble rank-based trees in advancing disease classification via gene expression data, offering a robust, interpretable, and scalable solution. Our software is available at https://CRAN.R-project.org/package=ranktreeEnsemble .

White blood cell and platelet distribution widths are associated with hypertension: data mining approaches

In this paper, we are going to investigate the association between Hypertension (HTN) and routine hematologic indices in a cohort of Iranian adults. The data were obtained from a total population of 9704 who were aged 35-65 years, a prospective study was designed. The association between hematologic factors and HTN was assessed using logistic regression (LR) analysis and a decision tree (DT) algorithm. A total of 9704 complete datasets were analyzed in this cohort study (N = 3070 with HTN [female 62.47% and male 37.52%], N = 6634 without HTN [female 58.90% and male 41.09%]). Several variables were significantly different between the two groups, including age, smoking status, BMI, diabetes millitus, high sensitivity C-reactive protein (hs-CRP), uric acid, FBS, total cholesterol, HGB, LYM, WBC, PDW, RDW, RBC, sex, PLT, MCV, SBP, DBP, BUN, and HCT (P < 0.05). For unit odds ratio (OR) interpretation, females are more likely to have HTN (OR = 1.837, 95% CI = (1.620, 2.081)). Among the analyzed variables, age and WBC had the most significant associations with HTN OR = 1.087, 95% CI = (1.081, 1.094) and OR = 1.096, 95% CI = (1.061, 1.133), respectively (P-value < 0.05). In the DT model, age, followed by WBC, sex, and PDW, has the most significant impact on the HTN risk. Ninety-eight percent of patients had HTN in the subgroup with older age (≥58), high PDW (≥17.3), and low RDW (<46). Finally, we found that elevated WBC and PDW are the most associated factor with the severity of HTN in the Mashhad general population as well as female gender and older age.

EOS - Environment & Oil Spill Response. An analytic tool for environmental assessments to support oil spill response planning: Framework, principles, and proof-of-concept by an Arctic example

The Environment & Oil Spill Response tool (EOS), supports oil spill response planning and decision making. This tool is developed on a research basis, and is an index based, generic and open-source analytic tool, which environmentally can optimise the choice of oil spill response methods for a given spill situation and for a given sea area with respect to environment and nature. The tool is not linked to a particular oil spill simulation model, although it is recommended using oil spill simulation models to have detailed data available for the analysis. The EOS tool consists of an Excel workbook with formulas for calculations and scores followed by screening through decision trees. As case for the EOS tool proof-of-concept, the area of Store Hellefiskebanke, West Greenland, is used. The tool can be downloaded from the Aarhus University home page as a free-of-charge application and is accompanied by a handbook for guidance.

Predicting the 10-year incidence of dyslipidemia based on novel anthropometric indices, using data mining

BACKGROUND

The aim was to establish a 10-year dyslipidemia incidence model, investigating novel anthropometric indices using exploratory regression and data mining.

METHODS

This data mining study was conducted on people who were diagnosed with dyslipidemia in phase 2 (n = 1097) of the Mashhad Stroke and Heart Atherosclerotic Disorder (MASHAD) study, who were compared with healthy people in this phase (n = 679). The association of dyslipidemia with several novel anthropometric indices including Conicity Index (C-Index), Body Roundness Index (BRI), Visceral Adiposity Index (VAI), Lipid Accumulation Product (LAP), Abdominal Volume Index (AVI), Weight-Adjusted-Waist Index (WWI), A Body Shape Index (ABSI), Body Mass Index (BMI), Body Adiposity Index (BAI) and Body Surface Area (BSA) was evaluated. Logistic Regression (LR) and Decision Tree (DT) analysis were utilized to evaluate the association. The accuracy, sensitivity, and specificity of DT were assessed through the performance of a Receiver Operating Characteristic (ROC) curve using R software.

RESULTS

A total of 1776 subjects without dyslipidemia during phase 1 were followed up in phase 2 and enrolled into the current study. The AUC of models A and B were 0.69 and 0.63 among subjects with dyslipidemia, respectively. VAI has been identified as a significant predictor of dyslipidemias (OR: 2.81, (95% CI: 2.07, 3.81)) in all models. Moreover, the DT showed that VAI followed by BMI and LAP were the most critical variables in predicting dyslipidemia incidence.

CONCLUSIONS

Based on the results, model A had an acceptable performance for predicting 10 years of dyslipidemia incidence. Furthermore, the VAI, BMI, and LAP were the principal anthropometric factors for predicting dyslipidemia incidence by LR and DT models.

Flood susceptibility assessment of the Agartala Urban Watershed, India, using Machine Learning Algorithm

Frequent floods are a severe threat to the well-being of people the world over. This is particularly severe in developing countries like India where tropical monsoon climate prevails. Recently, flood hazard susceptibility mapping has become a popular tool to mitigate the effects of this threat. Therefore, the present study utilized four distinctive Machine Learning algorithms i.e., K-Nearest Neighbor, Decision Tree, Naive Bayes, and Random Forest to estimate flood susceptibility zones in the Agartala Urban Watershed of Tripura, India. The latter experiences debilitating floods during the monsoon season. A multicollinearity test was conducted to examine the collinearity of the chosen flood conditioning factors, and it was seen that none of the factors were compromised by multicollinearity. Results showed that around three-fourths of the AUW area was classified as moderate to very high flood-prone zones, while over 20 percent was between low and very low flood-prone zones. The models applied performed well with ROC-AUC scores greater than 70 percent and MAE, MSE, and RMSE scores less than 30 percent. DT and RF algorithms were suggested for places with similar physical characteristics based on their outstanding performance and the training datasets. The study provides valuable insights to policymakers, administrative authorities, and local stakeholders to cope with floods and enhance flood prevention measures as a climate change adaptation strategy in the AUW.

A multi-center diagnostic system for intrahepatic mass-forming cholangiocarcinoma based on preoperative MRI and clinical features

OBJECTIVES

To establish a non-invasive diagnostic system for intrahepatic mass-forming cholangiocarcinoma (IMCC) via decision tree analysis.

METHODS

Totally 1008 patients with 504 pathologically confirmed IMCCs and proportional hepatocellular carcinomas (HCC) and combined hepatocellular cholangiocarcinomas (cHCC-CC) from multi-centers were retrospectively included (internal cohort n = 700, external cohort n = 308). Univariate and multivariate logistic regression analyses were applied to evaluate the independent clinical and MRI predictors for IMCC, and the selected features were used to develop a decision tree-based diagnostic system. Diagnostic efficacy of the established system was calculated by the receiver operating characteristic curve analysis in the internal training-testing and external validation cohorts, and also in small lesions  ≤ 3 cm.

RESULTS

Multivariate analysis revealed that female, no chronic liver disease or cirrhosis, elevated carbohydrate antigen 19-9 (CA19-9) level, normal alpha-fetoprotein (AFP) level, lobulated tumor shape, progressive or persistent enhancement pattern, no enhancing tumor capsule, targetoid appearance, and liver surface retraction were independent characteristics favoring the diagnosis of IMCC over HCC or cHCC-CC (odds ratio = 3.273-25.00, p < 0.001 to p = 0.021). Among which enhancement pattern had the highest weight of 0.816. The diagnostic system incorporating significant characteristics above showed excellent performance in the internal training (area under the curve (AUC) 0.971), internal testing (AUC 0.956), and external validation (AUC 0.945) cohorts, as well as in small lesions  ≤ 3 cm (AUC 0.956).

CONCLUSIONS

In consideration of the great generalizability and clinical efficacy in multi-centers, the proposed diagnostic system may serve as a non-invasive, reliable, and easy-to-operate tool in IMCC diagnosis, providing an efficient approach to discriminate IMCC from other HCC-containing primary liver cancers.

CLINICAL RELEVANCE STATEMENT

This study established a non-invasive, easy-to-operate, and explainable decision tree-based diagnostic system for intrahepatic mass-forming cholangiocarcinoma, which may provide essential information for clinical decision-making.

KEY POINTS

• Distinguishing intrahepatic mass-forming cholangiocarcinoma (IMCC) from other primary liver cancers is important for both treatment planning and outcome prediction. • The MRI-based diagnostic system showed great performance with satisfying generalization ability in the diagnosis and discrimination of IMCC. • The diagnostic system may serve as a non-invasive, easy-to-operate, and explainable tool in the diagnosis and risk stratification for IMCC.

Psychrometry in the thermal comfort diagnosis of production animals: a combination of the systematic review and methodological proposal

Animal welfare and productive performance are compromised when animals are housed in environments which place them outside their thermal comfort zone. However, the identification of thermal stress, when based on air properties, suggests the use of outdated and generic indices. The objective of this work was to develop and validate a methodology for classifying and diagnosing heat stress in production animals based on psychrometric air relations. The model was created for broilers, pigs, dairy cattle, and laying birds, categorized into a total of 21 breeding phases. For each phase, a bibliographic search was carried out for the psychrometric parameters of the air-dry bulb temperature (AT) and relative humidity (RH)-that satisfied the animals' critical and ideal thermoneutral zones. Adding the local atmospheric pressure (AP), the parameters were used to calculate the enthalpy (h), resulting in five comfort ranges. Based on this, a decision tree was elaborated, consisting of three attributes (AT, RH, and h) and seven diagnostic classes, based on the psychrometric principles of air. The proposed methodology was used in a case study, with a database extracted from an individual shelter for calves. For the evaluation of the decision tree, two induction algorithms, ID3 and c4.5, were compared, both of which presented high accuracy and proposed simpler tree models than the one theoretically developed for the methodology. In conclusion, the methodology represents a great potential to characterize the thermal comfort of the animals, diagnose the causes of stress, and recommend possible corrective actions. The study revealed that decision trees can be adapted and simplified for each creation phase.

Using convolutional neural networks to support examiners in duct tape physical fit comparisons

This paper describes the construction and use of a machine-learning model to provide objective support for a physical fit examination of duct tapes. We present the ForensicFit package that can preprocess and database raw tape images. Using the processed tape image, we trained a convolutional neural network to compare tape edges and predict membership scores (i.e., fit or non-fit category). A dataset of nearly 2000 tapes and 4000 images was evaluated, including various quality grades: low, medium, and high, as well as two separation methods, scissor-cut and hand-torn. The model predicts medium-quality and high-quality scissor-cut tape more accurately than hand-torn, whereas for low-quality tape predicts the hand-torn tapes more accurately. These results are consistent with previous studies performed on the same datasets by analyst examinations. A method of pixel importance was also implemented to show which pixels are used to make the decision. This method can confirm some fit features that correspond with analyst-identified features, like edge morphology and backing pattern. This pilot study demonstrates the feasibility of computational algorithms to build physical fit databases and automated comparisons using deep neural networks, which can be used as a model for other materials.

Artificial intelligence models for predicting calcium and magnesium removal by polyfunctional ketone using ensemble machine learners

Calcium (Ca2+) and magnesium (Mg2+) are the major scaling ions of reverse osmosis concentrate in zero-liquid discharge systems, causing performance decline. In this study, we predicted the removal of Ca2+ and Mg2+ from simulated reverse osmosis concentrate by functional polyketones (FPKs). Four amines, including 1,2-diaminopropane (DAP), 1-(2-aminoethyl) piperazine (AEP), 1-(3-aminopropyl) imidazole (API), and butyl amine (BA) used to synthesize FPKs. The effects of various factors such as the amount of adsorbent, feed water concentration, and pH were investigated for process optimization. In this study, ensemble learner artificial intelligence models, decision tree (DT), extreme gradient boost (XGB), and random forest (RF) were used to predict Ca2+ and Mg2+ removal by the FPKs. Datasets were collected experimentally using FPKs to remove Ca2+ and Mg2+ from the simulated reverse osmosis concentrate. The predictions were made by XGB, DT, and RF models for the first chosen amine for Ca2+ and then for Mg2+, subsequently, this process was repeated with each amine. The developed DT, RF, and XGB models demonstrated higher coefficients of determination for predicting Mg2+ removal by AEP and DAP (R2 = 0.841-0.935) than by API and BA (R2 = 0.774-0.801) except in the RF and XGB model results (R2 = 0.801-0.846). Overall, the XGB model displayed good results for both Ca2+ and Mg2+ removal but slight changes were observed in the AEP and BA predictions by DT and RF. Therefore, artificial intelligence models may be a viable alternative for further insight in predicting Ca2+ and Mg2+ removal by FPKs from simulated reverse osmosis concentrate.

Identification of circulating miRNA as early diagnostic molecular markers in malignant glioblastoma base on decision tree joint scoring algorithm

PURPOSE

The lack of clinical markers prevents early diagnosis of glioblastoma (GBM). Many studies have found that circulating microRNAs (miRNAs) can be used as early diagnostic markers of malignant tumours. Therefore, the identification of novel circulating miRNA biomolecular markers could be beneficial to clinicians in the early diagnosis of GBM.

METHODS

We developed a decision tree joint scoring algorithm (DTSA), systematically integrating significance analysis of microarray (SAM), Pearson hierarchical clustering, T test, Decision tree and Entropy weight score algorithm, to screen out circulating miRNA molecular markers with high sensitivity and accuracy for early diagnosis of GBM.

RESULTS

DTSA was developed and applied for GBM datasets and three circulating miRNA molecular markers were identified, namely, hsa-miR-2278, hsa-miR-555 and hsa-miR-892b. We have found that hsa-miR-2278 and hsa-miR-892b regulate the GBM pathway through target genes, promoting the development of GBM and affecting the survival of patients. DTSA has better classification effect in all data sets than other classification algorithms, and identified miRNAs are better than existing markers of GBM.

CONCLUSION

These results suggest that DTSA can effectively identify circulating miRNA, thus contributing to the early diagnosis and personalised treatment of GBM.

Decision trees and labeling of low noise pavements as support for noise action plans

Low noise pavements (LNPs) are a market driven trend to mitigate the high road traffic noise exposure levels. Their improvement towards acoustic efficiency and durability over time is a challenge since these factors can conflict with road primary functions, such as safety. LNPs are not always the most cost-effective solution in health effects prevention. Whilst Green Public Procurement (GPP) highlighted the importance of reducing rolling noise emissions by introducing new regulations for new-layed LNPs, the fixed minimum requirements are not exhaustive. Generally, limits are set following the Close ProXimity method, which is only source oriented. This method does not consider real traffic flows and it is not aimed at evaluating citizens' disturbance. This work presents strategy tools that could assist policymakers in choosing LNPs, when truly effective, over other mitigations. The approach includes a variety of indicators that would allow for comparing different facets of noise assessment. The proposed methodology does not require additional efforts from stakeholders because the measurements required for the estimation of the indicators must already be carried out for both verification of legal limits and GPP. The strategy tools are a decisional tree to support the evaluation of the applicability of a LNP before its approval, and an evaluation flowchart applicable after its laying to evaluate its efficiency. Finally, a first LNP labeling approach, based on the same set of indicators, is proposed. As a case study, these tools are applied to measurements performed before and after the laying of twelve LNPs part of the LIFE NEREiDE project.

An efficient data-driven desalination approach for the element-scale forward osmosis (FO)-reverse osmosis (RO) hybrid systems

Freshwater shortages are a consequence of the rapid increase in population, and desalination of saltwater has gained popularity as an alternative water treatment method in recent years. To date, the forward osmosis-reverse osmosis (FO-RO) hybrid technology has been proposed as a low-energy and environmentally friendly next-generation seawater desalination process. Scaling up the FO-RO hybrid system significantly affects the success of a commercial-scale process. However, neither the ideal structure nor the membrane components for plate-and-frame FO (PFFO) and spiral-wound FO (SWFO) are known. This study aims to explore and optimize the performance of SWFO-RO and PFFO-RO hybrid element-scale systems in the desalination of seawater. The results showed that both hybrid systems could yield high water recovery under optimal operating conditions. The prediction of the system performance (water flux and reverse salt flux) by artificial intelligence was considerably better (R > 0.99, root mean square error <5%) than that of conventional mass balance models. A Markov-based decision tree successfully classified the water flux level in hybrid systems. An optimal set of operational conditions for each membrane system was proposed. For example, in RO, a combination of the feed solution (FS) flow rate (≥17.5 L/min), FS concentration (<17,500 ppm), and operation pressure (<35 bar) would result in high water permeability (>40 LMH). In addition, five SWFO elements and four PFFO elements should be the optimal numbers of FO membranes in the hybrid FO-RO system for effective seawater desalination, especially for long-term operation.

Identifying relapse predictors in individual participant data with decision trees

BACKGROUND

Depression is a highly common and recurrent condition. Predicting who is at most risk of relapse or recurrence can inform clinical practice. Applying machine-learning methods to Individual Participant Data (IPD) can be promising to improve the accuracy of risk predictions.

METHODS

Individual data of four Randomized Controlled Trials (RCTs) evaluating antidepressant treatment compared to psychological interventions with tapering ([Formula: see text]) were used to identify predictors of relapse and/or recurrence. Ten baseline predictors were assessed. Decision trees with and without gradient boosting were applied. To study the robustness of decision-tree classifications, we also performed a complementary logistic regression analysis.

RESULTS

The combination of age, age of onset of depression, and depression severity significantly enhances the prediction of relapse risk when compared to classifiers solely based on depression severity. The studied decision trees can (i) identify relapse patients at intake with an accuracy, specificity, and sensitivity of about 55% (without gradient boosting) and 58% (with gradient boosting), and (ii) slightly outperform classifiers that are based on logistic regression.

CONCLUSIONS

Decision tree classifiers based on multiple-rather than single-risk indicators may be useful for developing treatment stratification strategies. These classification models have the potential to contribute to the development of methods aimed at effectively prioritizing treatment for those individuals who require it the most. Our results also underline the existing gaps in understanding how to accurately predict depressive relapse.

Ensemble model for predicting chronic non-communicable diseases using Latin square extraction and fuzzy-artificial neural networks from 2013 to 2019

Background

The presented study tracks the increase or decrease in the prevalence of seventeen different chronic non-communicable diseases in Serbia. This analysis considers factors such as region, age, and gender and is based on data from two national cross-sectional studies conducted in 2013 and 2019. The research aims to accurately identify the regions with the highest percentage of affected individuals, as well as their respective age and gender groups. The ultimate goal is to facilitate organized, free preventive screenings for these population categories within a very short time-frame in the future.

Materials and methods

The study analyzed two cross-sectional studies conducted between 2013 and 2019, using data obtained from the Institute of Public Health of Serbia. Both studies involved a total of 27801 participants. The study compared the performance of Decision Tree and Support Vector Regressor models with artificial neural network (ANN) models that employed two encoding functions. The new methodology for the ANN-L36 model was based on artificial neural networks constructed using a Latin square (L36) design, incorporating Taguchi's robust design optimization.

Results

The results of the analysis from three different models have shown that cardiovascular diseases are the most prevalent illnesses among the population in Serbia, with hypertension as the leading condition in all regions, particularly among individuals aged 64 to 75 years, and more prevalent among females. In 2019, there was a decrease in the percentage of the leading disease, hypertension, compared to 2013, with a decrease from 34.0% to 32.2%. The ANN-L36 model with Fuzzy encoding function demonstrated the highest precision, achieving the smallest relative error of 0.1%.

Conclusion

To date, no studies have been conducted at the national level in Serbia to comprehensively track and identify chronic diseases in the manner proposed by this study. The model presented in this research will be implemented in practice and is set to significantly contribute to the future healthcare framework in Serbia, shaping and advancing the approach towards addressing these conditions. Furthermore, experimental evidence has shown that Taguchi's optimization approach yields the best results for identifying various chronic non-communicable diseases.

Predicting the formation of mixed pattern hemorrhages in ruptured middle cerebral artery aneurysms based on a decision tree model: A multicenter study

OBJECTIVE

Mixed-pattern hemorrhages (MPH) commonly occur in ruptured middle cerebral artery (MCA) aneurysms and are associated with poor clinical outcomes. This study aimed to predict the formation of MPH in a multicenter database of MCA aneurysms using a decision tree model.

METHODS

We retrospectively reviewed patients with ruptured MCA aneurysms between January 2009 and June 2020. The MPH was defined as subarachnoid hemorrhages with intracranial hematomas and/or intraventricular hemorrhages and/or subdural hematomas. Univariate and multivariate logistic regression analyses were used to explore the prediction factors of the formation of MPH. Based on these prediction factors, a decision tree model was developed to predict the formation of MPH. Additional independent datasets were used for external validation.

RESULTS

We enrolled 436 patients with ruptured MCA aneurysms detected by computed tomography angiography; 285 patients had MPH (65.4%). A multivariate logistic regression analysis showed that age, aneurysm size, multiple aneurysms, and the presence of a daughter dome were the independent prediction factors of the formation of MPH. The areas under receiver operating characteristic curves of the decision tree model in the training, internal, and external validation cohorts were 0.951, 0.927, and 0.901, respectively.

CONCLUSION

Age, aneurysm size, the presence of a daughter dome, and multiple aneurysms were the independent prediction factors of the formation of MPH. The decision tree model is a useful visual triage tool to predict the formation of MPH that could facilitate the management of unruptured aneurysms in routine clinical work.

Investigating the association of acute kidney injury (AKI) with COVID-19 mortality using data-mining scheme

COVID-19 has caused significant challenges in kidney research and disease management. Data mining techniques such as logistic regression (LR) and decision tree (DT) were used to model data. All analyses were performed using SPSS 25 and Python 3. The incidence of acute kidney injury (AKI) was 14.1% and the overall mortality risk was 13% among COVID-19 patients. The mortality was associated with, AKI, age, marital status, smoking status, heart failure, chronic obstructive pulmonary disease, malignancy, and SPO2 level using LR. The accuracy, sensitivity, specificity, and area under the curve of the DT (and LR) classifier were 70% (85%), 73% (75%), 78% (79%), and 77% (81%), respectively. Based on the DT model, the variable most significantly associated with COVID-19 mortality was AKI followed by age, high WBC count, BMI, and lymphocyte count. It was concluded that the incidence of AKI was high, and AKI was identified as one of the important factors that played an effective role in mortality due to COVID-19.

Establishment and application of three predictive models of anastomotic leakage after rectal cancer sphincter-preserving surgery

BACKGROUND

Anastomotic leakage (AL) occurs frequently after sphincter-preserving surgery for rectal cancer and has a significant mortality rate. There are many factors that influence the incidence of AL, and each patient's unique circumstances add to this diversity. The early identification and prediction of AL after sphincter-preserving surgery are of great significance for the application of clinically targeted preventive measures. Developing an AL predictive model coincides with the aim of personalised healthcare, enhances clinical management techniques, and advances the medical industry along a more precise and intelligent path.

AIM

To develop nomogram, decision tree, and random forest prediction models for AL following sphincter-preserving surgery for rectal cancer and to evaluate the predictive efficacy of the three models.

METHODS

The clinical information of 497 patients with rectal cancer who underwent sphincter-preserving surgery at Jincheng People's Hospital of Shanxi Province between January 2017 and September 2022 was analyzed in this study. Patients were divided into two groups: AL and no AL. Using univariate and multivariate analyses, we identified factors influencing postoperative AL. These factors were used to establish nomogram, decision tree, and random forest models. The sensitivity, specificity, recall, accuracy, and area under the receiver operating characteristic curve (AUC) were compared between the three models.

RESULTS

AL occurred in 10.26% of the 497 patients with rectal cancer. The nomogram model had an AUC of 0.922, sensitivity of 0.745, specificity of 0.966, accuracy of 0.936, recall of 0.987, and accuracy of 0.946. The above indices in the decision tree model were 0.919, 0.833, 0.862, 0.951, 0.994, and 0.955, respectively and in the random forest model were 1.000, 1.000, 1.000, 0.951, 0.994, and 0.955, respectively. The DeLong test revealed that the AUC value of the decision-tree model was lower than that of the random forest model (P < 0.05).

CONCLUSION

The random forest model may be used to identify patients at high risk of AL after sphincter-preserving surgery for rectal cancer owing to its strong predictive effect and stability.

A comparative study of machine learning algorithms for predicting domestic violence vulnerability in Liberian women

Domestic violence against women is a prevalent in Liberia, with nearly half of women reporting physical violence. However, research on the biosocial factors contributing to this issue remains limited. This study aims to predict women's vulnerability to domestic violence using a machine learning approach, leveraging data from the Liberian Demographic and Health Survey (LDHS) conducted in 2019-2020. We employed seven machine learning algorithms to achieve this goal, including ANN, KNN, RF, DT, XGBoost, LightGBM, and CatBoost. Our analysis revealed that the LightGBM and RF models achieved the highest accuracy in predicting women's vulnerability to domestic violence in Liberia, with 81% and 82% accuracy rates, respectively. One of the key features identified across multiple algorithms was the number of people who had experienced emotional violence. These findings offer important insights into the underlying characteristics and risk factors associated with domestic violence against women in Liberia. By utilizing machine learning techniques, we can better predict and understand this complex issue, ultimately contributing to the development of more effective prevention and intervention strategies.

An Optimal Model Combining SqueezeNet and Machine Learning Methods for Lung Disease Diagnosis

BACKGROUND

Artificial intelligence (AI) is rapidly evolving in healthcare, with transformative potential. AI revolutionizes medical imaging by enabling online self-diagnosis for patients and improving diagnostic accuracy for healthcare professionals. While valuable datasets aid machine learning in disease detection, challenges persist in diagnosing similar lung conditions from chest X-rays. Integrating AI into healthcare holds promise for enhanced outcomes and efficiency.

OBJECTIVE

In this article, we aim to present a new AI model that solves this challenge by allowing the differentiation, diagnosis and classification of three distinct diseases, whose symptoms are very similar. The fundamental contribution is to reduce the number of parameters used while maintaining the same level of precision for use in embedded systems.

METHODS

Our proposed model combines the power of the neural network using the SqueezeNet architecture with a set of machine learning algorithms as classifiers, including logistic regression, support vector machine (SVM), k-nearest neighbors (KNN), decision tree, and naive Bayes. The chest Xray dataset used in the proposed model consists of CXR images that are classified into four categories: pneumonia, tuberculosis, COVID-19, and normal cases.

RESULTS

Our proposed model demonstrated remarkable accuracy (97,32%), precision (97,33), F1 score (97,31%), recall (97,30%), and AUC (99,40), which is close to the best model. Whereas, the number of parameters used by our model (4,6 M) is very small compared to the best model in the literature (47M).

CONCLUSION

The model demonstrated good classification accuracy. In addition, the proposed model has the ability to use fewer parameters, which means it requires less internal memory and computing resources.

.

Features characterising cardiac autonomic neuropathy in diabetes using ensembled classification

OBJECTIVE

Using supervised machine learning to classify the severity of cardiovascular autonomic neuropathy (CAN). The aims were 1) to investigate which features contribute to characterising CAN 2) to generate an ensembled set of features that best describes the variation in CAN classification.

METHODS

Eighty-two features from demographic, beat-to-beat, biochemical, and inflammation were obtained from 204 people with diabetes and used in three machine-learning-classifiers, these are: support vector machine, decision tree, and random forest. All data were ensembled using a weighted mean of the features from each classifier.

RESULTS

The 10 most important features derived from the domains: Beat-to-beat, inflammation markers, disease-duration, and age.

CONCLUSIONS

Beat-to-beat measures associate with CAN as diagnosis is mainly based on cardiac reflex responses, disease-duration and age are also related to CAN development throughout disease progression. The inflammation markers may reflect the underlying disease process, and therefore, new treatment modalities targeting systemic low-grade inflammation should potentially be tested to prevent the development of CAN.

SIGNIFICANCE

Cardiac reflex responses should be monitored closely to diagnose and classify severity levels of CAN accurately. Standard clinical biochemical analytes, such as glycaemic level, lipidic level, or kidney function were not included in the ten most important features. Beat-to-beat measures accounted for approximately 60% of the features in the ensembled data.

Construction of a multi-classified decision tree model for identifying malignant pleural effusion and tuberculous pleural effusion

OBJECTIVE

Pleural effusion (PE) is a common clinical complication associated with various disorders. We aimed to utilize laboratory variables and their corresponding ratios in serum and PE for the differential diagnosis of multiple types of PE based on a decision tree (DT) algorithm.

METHODS

A total of 1435 untreated patients with PE admitted to The First Affiliated Hospital of Ningbo University were enrolled. The demographic and laboratory variables were collected and compared. The receiver operating characteristic curve was used to select important variables for diagnosing malignant pleural effusion (MPE) or tuberculous pleural effusion (TPE) and included in the DT model. The data were divided into the training set and the test set at a ratio of 7:3. The training data was used to develop the DT model, and the test data was for evaluating the model. Independent data was collected as external validation.

RESULTS

Three PE indicators (carcinoembryonic antigen, adenosine deaminase [ADA], and total protein), two serum indicators (neuron-specific enolase and cytokeratin 19 fragments), and two ratios [high-sensitivity C-reactive protein (hsCRP)/ PE lymphocyte and hsCRP/PE ADA] were used to construct the DT model. The area under the curve (AUC), sensitivity, and specificity for diagnosing MPE were 0.963, 84.0%, 91.6% in the training set, 0.976, 84.1%, 88.6% in the test set, and 0.955,83.3%, 86.7% in the external validation set. The AUC, sensitivity, and specificity of diagnosing TPE were 0.898, 86.8%, 92.3% in the training set, 0.888, 88.8%, 92.7% in the test set, and 0.778, 84.8%, 94.3% in the external validation set.

CONCLUSION

The DT model showed good diagnostic efficacy and could be applied for the differential diagnosis of MPE and TPE in clinical settings.

Cost-effectiveness of cytomegalovirus vaccination for females in China: A decision-analytical Markov study

BACKGROUND

The global burden of disease caused by congenital cytomegalovirus (CMV) infection is high. Previous modeling studies have suggested that CMV vaccination may be cost-effective in developed countries. Congenital CMV infection is more likely driven by maternal non-primary infection in China. We aimed to measure the effectiveness and cost-effectiveness of population-level CMV vaccination in Chinese females.

METHODS

A decision tree Markov model was developed to simulate potential CMV vaccination strategies in a multi-cohort setting, with a population size of 1,000,000 each for the infant, adolescent (10-year-old) and young adult (20-year-old) cohorts. The hypothetical vaccines were assumed to have 50% efficacy, 20 years of protection, 70% coverage, at a price of US$120/dose for base-case analysis. Costs and disability-adjusted life years (DALYs) were discounted by 3% per year and the vaccination would be considered cost-effective if an incremental cost-effectiveness ratio (ICER) was lower than 2021 Chinese per capita GDP (US$12,500).

FINDINGS

For the pre-infection (PRI) vaccine efficacy type, the adolescent strategy was the most cost-effective, with an ICER of US$12,213 (12,134 to 12,291) pre DALY averted, compared with the next best strategy (young adult strategy). For pre- and post-infection (P&PI) efficacy type, the young adult strategy was the most cost-effective as it was cost-saving. In one-way analysis varying the PRI vaccine price, the infant strategy, adolescent strategy and the young adult strategy would be a dominant strategy over others if the vaccine cost ≤US$60, US$61-121 and US$122-251 per dose respectively. In contrast, the young adult strategy continued to be the preferred strategy until the P&PI vaccine price exceeded US$226/dose. Our main results were robust under a wide variety of sensitivity analyses and scenario analyses.

INTERPRETATION

CMV vaccination for females would be cost-effective and even cost-saving in China. Our findings had public health implications for control of CMV diseases.

Prediction of diabetes disease using an ensemble of machine learning multi-classifier models

BACKGROUND AND OBJECTIVE

Diabetes is a life-threatening chronic disease with a growing global prevalence, necessitating early diagnosis and treatment to prevent severe complications. Machine learning has emerged as a promising approach for diabetes diagnosis, but challenges such as limited labeled data, frequent missing values, and dataset imbalance hinder the development of accurate prediction models. Therefore, a novel framework is required to address these challenges and improve performance.

METHODS

In this study, we propose an innovative pipeline-based multi-classification framework to predict diabetes in three classes: diabetic, non-diabetic, and prediabetes, using the imbalanced Iraqi Patient Dataset of Diabetes. Our framework incorporates various pre-processing techniques, including duplicate sample removal, attribute conversion, missing value imputation, data normalization and standardization, feature selection, and k-fold cross-validation. Furthermore, we implement multiple machine learning models, such as k-NN, SVM, DT, RF, AdaBoost, and GNB, and introduce a weighted ensemble approach based on the Area Under the Receiver Operating Characteristic Curve (AUC) to address dataset imbalance. Performance optimization is achieved through grid search and Bayesian optimization for hyper-parameter tuning.

RESULTS

Our proposed model outperforms other machine learning models, including k-NN, SVM, DT, RF, AdaBoost, and GNB, in predicting diabetes. The model achieves high average accuracy, precision, recall, F1-score, and AUC values of 0.9887, 0.9861, 0.9792, 0.9851, and 0.999, respectively.

CONCLUSION

Our pipeline-based multi-classification framework demonstrates promising results in accurately predicting diabetes using an imbalanced dataset of Iraqi diabetic patients. The proposed framework addresses the challenges associated with limited labeled data, missing values, and dataset imbalance, leading to improved prediction performance. This study highlights the potential of machine learning techniques in diabetes diagnosis and management, and the proposed framework can serve as a valuable tool for accurate prediction and improved patient care. Further research can build upon our work to refine and optimize the framework and explore its applicability in diverse datasets and populations.

Advancing the use of new approach methodologies for assessing teratogenicity: Building a tiered approach

Many New Approach Methodologies (NAMs) have been developed for the safety assessment of new ingredients. Research into reproductive toxicity and teratogenicity is a particularly high priority, especially given their mechanistic complexity. Forty-six non-teratogenic and 39 teratogenic chemicals were screened for teratogenic potential using the in silico DART model from the OECD QSAR Toolbox; the devTox quickPredict™ (devTox assay) test and the Zebrafish Embryotoxicity Test (ZET). The sensitivity and specificity were 94.7% and 84.1%, respectively, for the DART tree (83 chemicals), 86.1% and 35.6% for the devTox (81 chemicals) and 77.8% and 76.7% for the ZET (57 chemicals). Fifty-three chemicals were tested in all three assays and when results were combined and based on a "2 out of 3 rule", the sensitivity and specificity were 96.0% and 71.4%, respectively. The specificity of the devTox assay for a sub-set of 43 chemicals was increased from 26.1% to 82.6% by incorporating human plasma concentrations into the assay interpretation. When all 85 chemicals were assessed in a decision tree approach, there was an excellent predictivity and assay robustness of 90%. In conclusion, all three models exhibited a good sensitivity and specificity, especially when outcomes from all three were combined or used in "2 out of 3" or a tiered decision tree approach. The latter is an interesting predictive approach for evaluating the teratogenic potential of new chemicals. Future investigations will extend the number of chemicals tested, as well as explore ways to refine the results and obtain a robust Integrated Testing Strategy to evaluate teratogenic potential.

A diagnostic model based on color vision examination for dysthyroid optic neuropathy using Hardy-Rand-Rittler color plates

PURPOSE

To investigate color vision deficiency and the value of Hardy-Rand-Rittler (HRR) color plates in monitoring dysthyroid optic neuropathy (DON) to improve the diagnosis of DON.

METHODS

The participants were divided into DON and non-DON (mild and moderate-to-severe) groups. All the subjects underwent HRR color examination and comprehensive ophthalmic examinations. The random forest and decision tree models based on the HRR score were constructed by R software. The ROC curve and accuracy of different models in diagnosing DON were calculated and compared.

RESULTS

Thirty DON patients (57 eyes) and sixty non-DON patients (120 eyes) were enrolled. The HRR score was lower in DON patients than in non-DON patients (12.1 ± 6.2 versus 18.7 ± 1.8, p < 0.001). The major color deficiency was red-green deficiency in DON using HRR test. The HRR score, CAS, RNFL, and AP100 were found to be important factors in predicting DON from random forest and selected by decision tree to construct the multifactor model. The sensitivity, specificity, and the area under the curve (AUC) of the HRR score were 86%, 72%, and 0.87, respectively. The HRR score decision tree had a sensitivity, specificity, and AUC of 93%, 57%, and 0.75, respectively, with an accuracy of 82%. The data of the multifactor decision tree were 90%, 89%, and 0.93 for sensitivity, specificity, and AUC, respectively, with an accuracy of 91%.

CONCLUSION

The HRR test was valid as screening method for DON. The multifactor decision tree based on the HRR test improved the diagnostic efficacy for DON. An HRR score of less than 12 and red-green deficiency may be characteristic of DON.

EDST: a decision stump based ensemble algorithm for synergistic drug combination prediction

INTRODUCTION

There are countless possibilities for drug combinations, which makes it expensive and time-consuming to rely solely on clinical trials to determine the effects of each possible drug combination. In order to screen out the most effective drug combinations more quickly, scholars began to apply machine learning to drug combination prediction. However, most of them are of low interpretability. Consequently, even though they can sometimes produce high prediction accuracy, experts in the medical and biological fields can still not fully rely on their judgments because of the lack of knowledge about the decision-making process.

RELATED WORK

Decision trees and their ensemble algorithms are considered to be suitable methods for pharmaceutical applications due to their excellent performance and good interpretability. We review existing decision trees or decision tree ensemble algorithms in the medical field and point out their shortcomings.

METHOD

This study proposes a decision stump (DS)-based solution to extract interpretable knowledge from data sets. In this method, a set of DSs is first generated to selectively form a decision tree (DST). Different from the traditional decision tree, our algorithm not only enables a partial exchange of information between base classifiers by introducing a stump exchange method but also uses a modified Gini index to evaluate stump performance so that the generation of each node is evaluated by a global view to maintain high generalization ability. Furthermore, these trees are combined to construct an ensemble of DST (EDST).

EXPERIMENT

The two-drug combination data sets are collected from two cell lines with three classes (additive, antagonistic and synergistic effects) to test our method. Experimental results show that both our DST and EDST perform better than other methods. Besides, the rules generated by our methods are more compact and more accurate than other rule-based algorithms. Finally, we also analyze the extracted knowledge by the model in the field of bioinformatics.

CONCLUSION

The novel decision tree ensemble model can effectively predict the effect of drug combination datasets and easily obtain the decision-making process.

Identification for the species of aquatic higher plants in the Taihu Lake basin based on hyperspectral remote sensing

Aquatic plants are crucial for aquatic ecosystems and their species and distribution reflect aquatic ecosystem health. Remote sensing technology has been used to monitor plant distributions over large scales. However, the fine identification of the species of aquatic higher plants is challenging due to large temporal-spatial changes in optical water body properties and small spectral differences among plant species. Here, an aquatic plant identification method was developed by constructing a decision tree file in the C4.5 algorithm based on the canopy spectra of eight plants in the Changguangxi Wetland water area from hyperspectral remote sensing technology. The method was used to monitor the distribution of different plants in the Changguangxi Wetland area and two other water areas. The results showed that the spectral characteristics of plants were enhanced by calculating their spectral index, thereby improving the comparability among different species. The total recognition accuracy of the constructed decision tree file for eight types of plants was 85.02%. Nymphaea tetragona, Pontederia cordata, and Nymphoides peltatum had the highest recognition accuracy and Eichhornia crassipes was the lowest. The specific species and distributions of aquatic plants were consistent with the water quality in the area. The results can provide a reference for the accurate identification of aquatic plants in the same type of water area.

A decision tree model for accurate prediction of sand erosion in elbow geometry

Erosion of piping components, e.g., elbows, is a hazardous phenomenon that frequently occurs due to sand flow with fluids during petroleum production. Early prediction of the sand's erosion rate (ER) is essential for ensuring a safe flow process and material integrity. Some models have been applied to determine the ER of the sand in the literature. However, these models have been created based on specific data to require a model for application to wide-range data. Moreover, the previous models have not studied relationships between independent and dependent variables. Thus, this research aims to use machine learning techniques, namely linear regression and decision tree (DT), to predict the ER robustly. The optimum model, the DT model, was evaluated using various trend analysis and statistical error analyses (SEA) techniques, namely the correlation coefficient (R). The evaluation results proved proper physical behavior for all independent variables, along with high accuracy and the DT model robustness. The proposed DT method can accurately predict the ER with R of 0.9975, 0.9911, 0.9761, and 0.9908, AAPRE of 5.0%, 6.27%, 6.26%, and 5.5%, RMSE of 2.492E-05, 6.189E-05, 9.310E-05, and 5.339E-05, and STD of 13.44, 6.66, 8.01, and 11.44 for the training, validation, testing, and whole datasets, respectively. Hence, this study delivers an effective, robust, accurate, and fast prediction tool for ER determination, significantly saving the petroleum industry's cost and time.

A prediction model for moderate to severe cancer-related fatigue in colorectal cancer after chemotherapy: a prospective case‒control study

AIMS

The study aims to develop a model to predict the risk of moderate to severe cancer-related fatigue (CRF) in colorectal cancer patients after chemotherapy.

METHODS

The study population was colorectal cancer patients who received chemotherapy from September 2021 to June 2022 in a grade 3 and first-class hospital. Demographic, clinical, physiological, psychological, and socioeconomic factors were collected 1 to 2 days before the start of chemotherapy. Patients were followed up for 1 to 2 days after the end of chemotherapy to assess fatigue using the Piper Fatigue Scale. A random sampling method was used to select 181 patients with moderate to severe CRF as the case group. The risk set sampling method was used to select 181 patients with mild or no CRF as the control group. Logistic regression, back-propagation artificial neural network (BP-ANN), and decision tree models were constructed and compared.

RESULTS

A total of 362 patients consisting of 241 derivation samples and 121 validation samples were enrolled. Comparing the three models, the prediction effect of BP-ANN was the best, with a receiver operating characteristic (ROC) curve of 0.83. Internal and external verification indicated that the accuracy of prediction was 70.4% and 80.8%, respectively. Significant predictors identified were surgery, complications, hypokalaemia, albumin, neutrophil percentage, pain (VAS score), Activities of Daily Living (ADL) score, sleep quality (PSQI score), anxiety (HAD-A score), depression (HAD-D score), and nutrition (PG-SGA score).

CONCLUSIONS

BP-ANN was the best model, offering theoretical guidance for clinicians to formulate a tool to identify patients at high risk of moderate to severe CRF.

Derivation of riding risk precursors using 100 delivery motor scooter naturalistic riding study

The rapid growth of the delivery service market in Korea due to the impact of COVID-19 has resulted in an increase in crashes associated with delivery motor scooters. In particular, required minimum delivery time, which is an important factor for food delivery service, can lead to hazardous riding situations leading to traffic crashes. Although the food delivery service industry is continuously increasing, effective measures to improve the traffic safety of delivery motor scooters are insufficient. This study derived precursors in order to detect risky riding events using real-world naturalistic riding study data. It is essential to understand the riding characteristics of food delivery motor scooters to conduct the riding safety monitoring in more scientific and automated manners. Various candidate precursors were derived from riding characteristics data collected from GPS sensors and inertial measurement unit sensors. A decision tree model was then adopted to classify unsafe and normal riding events in order to determine the priority of precursors. A classification accuracy of 95.7% was obtained using three salient riding risk precursors including the norm of the angular velocity, which represents composite vector quantity of 3-axis measurements, acceleration, and X-axis angular velocity. The results of this study are expected to be used as a fundamental data to prepare for riding safety management systems that contribute to enhancing the safety of food delivery motor scooters.

Unraveling preference heterogeneity in willingness-to-pay for enhanced road safety: A hybrid approach of machine learning and quantile regression

Investing in road safety enhancement programs highly depends on the economic valuation of road traffic accidents and their outcomes. Such evaluation underpins road safety interventions in cost-benefit analysis. To this end, understanding and modeling public willingness-to-pay for enhanced road safety have received significant attention in the past few decades. However, despite considerable modeling efforts, some issues still persist in earlier studies, namely, (i) using standard regression approaches that assume a homogeneous impact of explanatory variables on willingness-to-pay, not accounting for heterogeneity, and depends on a priori distribution of the dependent variable, and (ii) the absence of higher-order interactions from models, leading to omitted variable bias and erroneous model inferences. To overcome this critical research gap, our study proposes a new modeling framework, integrating a machine learning technique (decision tree) to identify a priori relationships for higher-order interactions and a quantile regression model to account for heterogeneity along the entire range of willingness-to-pay. The proposed framework examines the determinants of willingness-to-pay for enhanced road safety using a sample of car drivers from Peshawar, Pakistan. Modeling results indicate that variables not significant in a linear model become significant at specific quantiles of the willingness-to-pay distribution. Further, including higher-order interactions among the explanatory variables provides additional insights into the complex relationship between willingness-to-pay and its determinants. In addition, willingness-to-pay for fatal and severe injury risk reductions is estimated at different quartiles and used to calculate the values of corresponding risk reductions. Overall, the proposed framework provides a better understanding of public sensitivities to willingness-to-pay for enhanced road safety.

Diagnosis of Epstein-Barr and cytomegalovirus infections using decision trees: an effective way to avoid antibiotic overuse in paediatric tonsillopharyngitis

BACKGROUND

The incidence of tonsillopharyngitis is especially prevalent in children. Despite the fact that viruses cause the majority of infections, antibiotics are frequently used as a treatment, contrary to international guidelines. This is not only an inappropriate method of treatment for viral infections, but it also significantly contributes to the emergence of antibiotic-resistant strains. In this study, EBV and CMV-related tonsillopharyngitis were distinguished from other pathogens by using machine learning techniques to construct a classification tree based on clinical characteristics.

MATERIALS AND METHODS

In 2016 and 2017, we assessed information regarding 242 children with tonsillopharyngitis. Patients were categorized according to whether acute cytomegalovirus or Epstein-Barr virus infections were confirmed (n = 91) or not (n = 151). Based on symptoms and blood test parameters, we constructed decision trees to discriminate the two groups. The classification efficiency of the model was characterized by its sensitivity, specificity, positive predictive value, and negative predictive value. Fisher's exact and Welch's tests were used to perform univariable statistical analyses.

RESULTS

The best decision tree distinguished EBV/CMV infection from non-EBV/CMV group with 83.33% positive predictive value, 88.90% sensitivity and 90.30% specificity. GPT (U/l) was found to be the most discriminatory variable (p < 0.0001). Using the model, unnecessary antibiotic treatment could be reduced by 66.66% (p = 0.0002).

DISCUSSION

Our classification model can be used as a diagnostic decision support tool to distinguish EBC/CMV infection from non EBV/CMV tonsillopharyngitis, thereby significantly reducing the overuse of antibiotics. It is hoped that the model may become a tool worth considering in routine clinical practice and may be developed to differentiate between viral and bacterial infections.

Adoption of machine learning algorithm for predicting the length of stay of patients (construction workers) during COVID pandemic

The construction sector in a rapidly developing country like India is a very unorganized sector. A large number of workers were affected and hospitalized during the pandemic. This situation is costing the sector heavily in several respects. This research study was conducted as part of using machine learning algorithms to improve construction company health and safety policies. LOS (length of stay) is used to predict how long a patient will stay in a hospital. Predicting LOS is very useful not only for hospitals, but also for construction companies to measure resources and reduce costs. Predicting LOS has become an important step in most hospitals before admitting patients. In this post, we used the Medical Information Mart for Intensive Care(MIMIC III) dataset and applied four different machine learning algorithms: decision tree classifier, random forest, Artificial Neural Network (ANN), and logistic regression. First, I performed data pre-processing to clean up the dataset. In the next step, we performed function selection using the Select Best algorithm with an evaluation function of chi2 to perform hot coding. We then performed a split between training and testing and applied a machine learning algorithm. The metric used for comparison was accuracy. After implementing the algorithms, the accuracy was compared. Random forest was found to perform best at 89%. Afterwards, we performed hyperparameter tuning using a grid search algorithm on a random forest to obtain higher accuracy. The final accuracy is 90%. This kind of research can help improve health security policies by introducing modern computational techniques, and can also help optimize resources.

A cross-sectional analysis of the impact of health insurance on the use of health care in Rwanda

Although the policy in Rwanda aims at ensuring quality healthcare, a portion of the Rwandan population still does not have access to it due to the lack of health insurance. This study investigates the impact of health insurance on healthcare utilization in all 30 administrative districts of Rwanda, using secondary data from the 5th Integrated Household Living Conditions Survey (EICV 5) in Rwanda, with a total of 14,580 households. A logistic regression model was used to evaluate the effects of health insurance on healthcare utilization, and a decision tree model was adopted to categorize districts based on the use of health services. This study has made a novel contribution to the existing research by classifying districts based on similarities in the use of health care services, regarding households with or without health insurance. The results showed a significant age effect on the use of health care services for household heads with an age range of 56-65, a significant increase was observed with an adjusted odds ratio of AO = 1.308, (95% CI: 1.044-1.639). It was the same for the household heads whose age range is 66-75 with an adjusted odds ratio of A0 = 1.589 with (95% CI: 1.244-2.028) and those aged 76 and older with an adjusted odds ratio of AO = 1.524, with (95% CI: 1.170-1.985). Households with health insurance interacted with districts (A0 = 2.76) increased health service use threefold compared to households without health insurance, female-headed households increased health service use (AO = 1.423, 95% CI:1.293-1.566) 1.4-fold compared to male-headed households, while households in the third quintile (AO = 1.198, 95% CI: 1.035-1.385) used health services 1.2 times compared to those in the first quintile; households in the fourth quintile (AO = 1.307, 95% CI: 1.134-1.506) and in the fifth quintile (AO = 1.307, 95% CI: 1.136 1.504) used health services 1.3 times compared to those in the first quintile. Similarly, for the households located in the main district group 4 variable had an odds ratio of 1.386 with (95% CI: 1.242-1.547), indicating that the households located in the main district group 4 use the health care services 1.4 times higher compared to those located in Ruhango district. Households in Rwanda who lack health insurance do not utilize health services to their full capacity, which has a negative influence on the wellbeing of the country's population. The researchers recommend that future policies target households in rural areas with an elderly head of household and those without health insurance that have a low usage of health care services in Rwanda. They also recommend that health insurance fees are reduced in order to increase health coverage rate as recommended by the World Health Organization.

Cost-Effectiveness of Fractional Exhaled Nitric Oxide Suppression Testing as an Adherence Screening Tool Among Patients With Difficult-to-Control Asthma

BACKGROUND

Approximately 50% of adults on long-term asthma medication are nonadherent. Current methods to detect nonadherence have had limited effect. Fractional exhaled nitric oxide suppression testing (FeNOSuppT) has demonstrated clinical effectiveness as an adherence screening tool to detect poor adherence to inhaled corticosteroids in difficult-to-control asthma prior to initiation of expensive biologic therapy.

OBJECTIVE

Estimate the cost effectiveness and budget impact of FeNOSuppT as a screen prior to the initiation of biologic therapy among U.S. adults with difficult-to-control asthma and high fractional exhaled nitric oxide (≥45 ppb).

METHODS

A decision tree simulated the progression of a cohort of patients over a 1-year time horizon into 1 of 3 states ([1] discharged from or [2] remain in specialist care; or [3] progress to biologics). Two strategies, with and without FeNOSuppT, were examined and the incremental net monetary benefit estimated using a discount rate of 3% and a willingness-to-pay threshold of $100,000 per quality-adjusted life year (QALY). Sensitivity analysis and a budget impact analysis were also undertaken.

RESULTS

In the baseline scenario, FeNOSuppT prior to the initiation of biologic therapy was associated with lower costs ($4,435/patient) and fewer QALYs (0.0023 QALY/patient) compared with no FeNOSuppT over 1 year and was considered cost effective (incremental net monetary benefit = $4,207). The FeNOSuppT was consistently found to be cost effective across a range of scenarios and in deterministic and probabilistic sensitivity analyses. Assuming differential levels of FeNOSuppT uptake (20%-100%), this was associated with budget savings ranging from USD $5 million to $27 million.

CONCLUSIONS

The FeNOSuppT is likely to be cost effective as a protocol-driven, objective, biomarker-based tool for identifying nonadherence in difficult-to-control asthma. This cost effectiveness is driven by cost savings from patients not progressing to expensive biologic therapy.