A machine learning algorithm for the identification elevated Lp(a) in patients with, or high-risk of having, coronary heart disease.

BACKGROUND: Decision tree algorithms, obtained by machine learning, provide clusters of patients with similar clinical patterns by the identification of variables that best merge with a given dependent variable. METHODS: We performed a multicenter registry, with 7 hospitals form Spain, of patients with, or high-risk of having, coronary heart disease (CHD). Elevated Lp(a) was defined as >50 mg/dl. Machine learning based decision trees were obtained by Chi-square automatic interaction detection. RESULTS: We analyzed 2301 patients. Median Lp(a) was 26.7 (9.3-79.9) mg/dl and 887 (38.6 %) patients had Lp(a) >50 mg/dl. The machine learning algorithm identified 6 clusters based on LDLc, CHD, FH of premature CHD and age (Fig. 1). Clusters 1 (LDLc <100 mg/dl, no CHD and, no FH of CHD) and 3 (LDLc <100 mg/dl, CHD and, no FH and, age < 50 yo) had the lowest Lp(a) values (Fig. 2); patients classified in cluster 5 (LDLc >100 mg/dl, CHD and, FH of CHD) and 6 (LDLc >100 mg/dl) had the highest values. We collapsed clusters in 3 groups: group 1 with clusters 1 and 3; group 2 with clusters 2 and 4; group 3 with clusters 5 and 6. The 3 groups have significantly different (p < 0.001) and progressively higher Lp(a) values. The prevalence of Lp(a) >50 mg/dl was 15.4 % in group 1, 29.2 % in group 2 and 91.1 % in group 3; similarly, the prevalence of Lp(a) >180 mg/dl was 1.0 %, 3.0 % and 7.6 % respectively. CONCLUSIONS: A decision tree algorithm, performed by machine learning, identified patients with, or at high risk of having, CHD have higher probabilities of having elevated Lp(a).

How should climate actions be planned? Model lessons from published action plans.

To effectively protect against the increasingly pervasive effects of climate change, countries and cities around the world are tasked with formulating and implementing climate actions that effectively respond to the challenges ahead. However, choosing the optimal climate actions is complex, since it is necessary to consider many external impacts as early on as the planning phase. Our novel methodology uncovers and integrates into first-of-its-kind decision support framework the identified climate actions of 443 European cities (from 32 countries) and the city structure-related features that influence the basic success of strategy creation into a first-of-its-kind decision support framework. Depending on their budget, population density, development and energy consumption portfolio, the results highlight that the analyzed European cities need to adopt a different way of thinking. The research results lay the foundation for the decision support of evidence-based climate action planning and contribute towards strengthening the role of cities worldwide in the fight against climate change in the future.

Heterogeneity in the association between social support and mental distress in old-age retirees - a computational approach using longitudinal cohort data.

BACKGROUND: Mental distress among retirees and older people is a severe public health challenge, and information on new risk groups is needed. This study aims to identify subgroups of old-age retirees with varying associations between low social support and mental distress by applying model-based recursive partitioning (MOB). METHODS: We used the Helsinki Health Study follow-up survey data of old-age retired former municipal sector employees of the City of Helsinki, Finland. Phase 1 data were collected in 2000-2002, when all participants were employed, Phase 2 in 2007, Phase 3 in 2012, Phase 4 in 2017, and Phase 5 in 2022 (n = 4,466, 81% women). Social support and covariates were measured at each Phase 1-5 and the outcome, mental distress (Depression Anxiety Stress Scales [DASS-21]) was measured at a single occasion, during Phase 5. The three subscales and the common factor of general distress were analysed separately. An approach rooted in computational statistics was used to investigate risk factor heterogeneity in the association of low social support and mental distress. MOB combines decision trees with regression analysis to identify subgroups with the most significant heterogeneity among risk factors. RESULTS: Median (IQR) general distress score from DASS-21 was 5.7 (3.0, 9.0), while Social Support Questionnaire number-score (SSQN) was 1.5 (1.15, 2.05). The primary effect modifier for the association between social support and general distress was education (p < 0.001). Those with high education had a different association of low social support and general distress than those with low or medium education. Additionally, the subgroup with low and medium education had a significant effect modification for age (p = 0.01). For the association between low social support and depressive symptoms, the moderating effect of education was dependent on gender, as men with medium-high education had the weakest association, while for women with medium-high education the association was strongest. CONCLUSIONS: Our results suggest that stratification by sociodemographic variables is justifiable when investigating risk factors of mental distress in old-age retirees. The incongruent association of low social support and depressive symptoms in men with medium-high education compared to women with medium-high education is a promising target for confirmatory research.

Comparison between statistical and machine learning methods to detect the hematological indices with the greatest influence on elevated serum levels of low-density lipoprotein cholesterol.

INTRODUCTION: Elevated levels of low-density lipoprotein-cholesterol (LDL-C) is a significant risk factor for the development of cardiovascular diseases (CVD)s. Furthermore, studies have revealed an association between indices of the complete blood count (CBC) and dyslipidemia. We aimed to investigate the relationship between CBC parameters and serum levels of LDL. METHOD: In a prospective study involving 9704 participants aged 35-65 years, comprehensive screening was conducted to estimate LDL-C levels and CBC indicators. The association between these biomarkers and high LDL-C (LDL-C≥130 mg/dL (3.25 mmol/L)) was investigated using various analytical methods, including Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Neural Network (NN), and Support Vector Machine (SVM) methodologies. RESULT: The present study found that age, hemoglobin (HGB), hematocrit (HCT), platelet count (PLT), lymphocyte (LYM), PLT-LYM ratio (PLR), PLT-High-Density Lipoprotein (HDL) ratio (PHR), HGB-LYM ratio (HLR), red blood cell count (RBC), Neutrophil-HDL ratio (NHR), and PLT-RBC ratio (PRR) were all statistically significant between the two groups (p<0.05). Another important finding was that red cell distribution width (RDW) was a significant predictor for higher LDL levels in women. Furthermore, in men, RDW-PLT ratio (RPR) and PHR were the most important indicators for assessing the elevated LDL levels. CONCLUSION: The study found that sex increases LDL-C odds in females by 52.9 %, while age and HCT increase it by 4.1 % and 5.5 %, respectively. RPR and PHR were the most influential variables for both genders. Elevated RPR and PHR were negatively correlated with increased LDL levels in men, and RDW levels was a statistically significant factor for women. Moreover, RDW was a significant factor in women for high levels of HDL-C. The study revealed that females have higher LDL-C levels (16 % compared to 14 % of males), with significant differences across variables like age, HGB, HCT, PLT, RLR, PHR, RBC, LYM, NHR, RPR, and key factors like RDW and SII.

A global model-agnostic rule-based XAI method based on Parameterized Event Primitives for time series classifiers.

Time series classification is a challenging research area where machine learning and deep learning techniques have shown remarkable performance. However, often, these are seen as black boxes due to their minimal interpretability. On the one hand, there is a plethora of eXplainable AI (XAI) methods designed to elucidate the functioning of models trained on image and tabular data. On the other hand, adapting these methods to explain deep learning-based time series classifiers may not be straightforward due to the temporal nature of time series data. This research proposes a novel global post-hoc explainable method for unearthing the key time steps behind the inferences made by deep learning-based time series classifiers. This novel approach generates a decision tree graph, a specific set of rules, that can be seen as explanations, potentially enhancing interpretability. The methodology involves two major phases: (1) training and evaluating deep-learning-based time series classification models, and (2) extracting parameterized primitive events, such as increasing, decreasing, local max and local min, from each instance of the evaluation set and clustering such events to extract prototypical ones. These prototypical primitive events are then used as input to a decision-tree classifier trained to fit the model predictions of the test set rather than the ground truth data. Experiments were conducted on diverse real-world datasets sourced from the UCR archive, employing metrics such as accuracy, fidelity, robustness, number of nodes, and depth of the extracted rules. The findings indicate that this global post-hoc method can improve the global interpretability of complex time series classification models.

Classification of mindfulness experiences from gamma-band effective connectivity: Application of machine-learning algorithms on resting, breathing, and body scan.

BACKGROUND AND OBJECTIVE: Practicing mindfulness is a mental process toward interoceptive awareness, achieving stress reduction and emotion regulation through brain-function alteration. Literature has shown that electroencephalography (EEG)-derived connectivity possesses the potential to differentiate brain functions between mindfulness naïve and mindfulness experienced, where such quantitative differentiation could benefit telediagnosis for mental health. However, there is no prior guidance in model selection targeting on the mindfulness-experience prediction. Here we hypothesized that the EEG effective connectivity could reach a good prediction performance in mindfulness experiences with brain interpretability. METHODS: We aimed at probing direct Directed Transfer Function (dDTF) to classify the participants' history of mindfulness-based stress reduction (MBSR), and aimed at optimizing the prediction accuracy by comparing multiple machine learning (ML) algorithms. Targeting the gamma-band effective connectivity, we evaluated the EEG-based prediction of the mindfulness experiences across 7 machine learning (ML) algorithms and 3 sessions (i.e., resting, focus-breathing, and body-scan). RESULTS: The support vector machine and naïve Bayes classifiers exhibited significant accuracies above the chance level across all three sessions, and the decision tree algorithm reached the highest prediction accuracy of 91.7 % with the resting state, compared to the classification accuracies with the other two mindful states. We further conducted the analysis on essential EEG channels to preserve the classification accuracy, revealing that preserving just four channels (F7, F8, T7, and P7) out of 19 yielded the accuracy of 83.3 %. Delving into the contribution of connectivity features, specific connectivity features predominantly located in the frontal lobe contributed more to classifier construction, which aligned well with the existing mindfulness literature. CONCLUSION: In the present study, we initiated a milestone of developing an EEG-based classifier to detect a person's mindfulness experience objectively. The prediction accuracy of the decision tree was optimal to differentiate the mindfulness experiences using the local resting-state EEG data. The suggested algorithm and key channels on the mindfulness-experience prediction may provide guidance for predicting mindfulness experiences using the EEG-based classification embedded in future wearable neurofeedback systems or plausible digital therapeutics.

Understanding parental preference for childcare: a cross-sectional study in Chongqing, China.

This study analyzed the factors influencing childcare preference and the relationship between childcare preference and childcare service demand scale, using data collected from a questionnaire survey of 3,921 parents of infants and toddlers in Chongqing, China. The results indicate that parents with higher incomes, higher education levels, older ages, multiple infants, and dual-career living in urban areas have a stronger preference for childcare. In the shared or grandparent care model, the childcare preference is not obvious. Parents of infants tend to choose childcare institutions that provide reception services, early education, and convenience services. Higher quality environmental facilities tend to reduce the preference of parents for childcare.

Data-Driven Clinical Pharmacy Research: Utilizing Machine Learning and Medical Big Data.

To conduct clinical pharmacy research, we often face the limitations of conventional statistical methods and single-center observational study. To overcome these issues, we have conducted data-driven research using machine learning methods and medical big data. Decision tree analysis, one of the typical machine learning methods, has a flowchart-like structure that allows users to easily and quantitatively evaluate the occurrence percentage of events due to the combination of multiple factors by answering related questions with Yes or No. Using this feature, we first developed a risk prediction model for acute kidney injury caused by vancomycin, a condition we frequently encounter in clinical practice. Additionally, by replacing the prediction target from a binary variable (i.e., presence or absence of adverse drug reactions) to a continuous variable (i.e., drug dosage), we built a model to estimate the initial dose of vancomycin required to reach the optimal blood level recommended by guidelines. We found its accuracy to be better than that of conventional dose-setting algorithms. Moreover, employing Japanese medical big data such as the claims database helped us overcome the major limitations of conventional clinical pharmacy research such as institutional bias caused by single-center studies. We demonstrated that the combined use of machine learning and medical big data could generate high-quality evidence leveraging the strengths of each approach. Data-driven clinical pharmacy research using machine learning and medical big data has enabled researchers to surpass the limitations of conventional research and produce clinically valuable findings.

A machine learning classifier-based approach for diabetes mellitus risk prediction.

Currently, Diabetes Mellitus (DM) can be life-threatening due to the dietary habits and lifestyle choices of individuals. Diabetes is characterised by elevated levels of glucose in the blood and an excess of protein in the blood. Poor eating habits and lifestyles are largely responsible for the rise in overweight, obesity, and various related conditions. This study investigated many diabetes-related risk forecasting techniques and algorithms. The eight machine learning (ML) algorithms used the diabetes dataset to test various prediction techniques, including a Support Vector Classifier, gradient-boosting, multilayer perceptron, random forest, K-nearest neighbors, logistic regression, extreme gradient boosting, and decision tree. To enhance the diabetic prediction ability of the model, we suggested using Feature Engineering (FE) and feature scaling. For our investigation, we utilized the Mendeley dataset on diabetes to assess the capacity of the model to predict diabetes. We developed a model by using Python programming and eight classification techniques. The Random Forest with 99.21%, Gradient Boosting with 99.61%, Extreme Gradient Boosting, and Decision Tree achieved the highest F1 score (99.81%), accuracy rate (99.80%), precision (99.81%), and recall (99.81%) of all classification approaches.

Decision tree learning for predicting chronic postpartum depression in the Japan Environment and Children's Study.

BACKGROUND: Many studies have used machine learning techniques to construct predictive models of postpartum depression, but few such models are simple enough to use in community maternal health settings with pen and paper. Here, we use a decision tree to construct a prediction model for chronic postpartum depression. METHODS: Participants were 84,091 mothers. Chronic postpartum depression was identified as an Edinburgh Postnatal Depression Scale score of ≥9 at both 1 and 6 months postpartum. The training dataset included 84 diverse variables measured during pregnancy, including health status and biomarkers. In learning, the branching depth was constrained to 3, the number of branches per branch to 4, and the minimum number of n in a branch was 100. The training to validation data ratio was set to 7:3. RESULTS: A decision tree with 35 branches and an area under the receiver operating characteristic of 0.84 was created. Ten of 84 variables were extracted, and the most effective in classification was "feeling worthless." At training (n = 58,635), the most and least prevalent branches were 73.2 % and 0.84 % (mean = 6.29 %), respectively; at validation (n = 25,456), they were 60.4 % and 0.72 % (mean = 6.52 %), respectively. LIMITATIONS: Chronic postpartum depression was identified using self-administered questionnaires. CONCLUSIONS: This study created a simple and relatively high-performing prediction model. Because the model can be easily understood and used without expertise in machine learning, it is expected to be useful in maternal health settings, including grassroots community health.

Multi-Elemental Analysis and Geographical Discrimination of Greek "Gigantes Elefantes" Beans Utilizing Inductively Coupled Plasma Mass Spectrometry and Machine Learning Models.

Greek giant beans, also known as "Gigantes Elefantes" (elephant beans, Phaseolus vulgaris L.,) are a traditional and highly cherished culinary delight in Greek cuisine, contributing significantly to the economic prosperity of local producers. However, the issue of food fraud associated with these products poses substantial risks to both consumer safety and economic stability. In the present study, multi-elemental analysis combined with decision tree learning algorithms were investigated for their potential to determine the multi-elemental profile and discriminate the origin of beans collected from the two geographical areas. Ensuring the authenticity of agricultural products is increasingly crucial in the global food industry, particularly in the fight against food fraud, which poses significant risks to consumer safety and economic stability. To ascertain this, an extensive multi-elemental analysis (Ag, Al, As, B, Ba, Be, Ca, Cd, Co, Cr, Cs, Cu, Fe, Ga, Ge, K, Li, Mg, Mn, Mo, Na, Nb, Ni, P, Pb, Rb, Re, Se, Sr, Ta, Ti, Tl, U, V, W, Zn, and Zr) was performed using Inductively Coupled Plasma Mass Spectrometry (ICP-MS). Bean samples originating from Kastoria and Prespes (products with Protected Geographical Indication (PGI) status) were studied, focusing on the determination of elemental profiles or fingerprints, which are directly related to the geographical origin of the growing area. In this study, we employed a decision tree algorithm to classify Greek "Gigantes Elefantes" beans based on their multi-elemental composition, achieving high performance metrics, including an accuracy of 92.86%, sensitivity of 87.50%, and specificity of 96.88%. These results demonstrate the model's effectiveness in accurately distinguishing beans from different geographical regions based on their elemental profiles. The trained model accomplished the discrimination of Greek "Gigantes Elefantes" beans from Kastoria and Prespes, with remarkable accuracy, based on their multi-elemental composition.

Factors Predicting Treatment Adherence in Outpatients with Cancer-Related Edema: Decision Tree Analysis.

Purpose: This study aimed to determine the combination of factors associated with continuity of care in outpatients with cancer-related edema six months after the initial visit. Patients and Methods: A total of 101 outpatients were divided into two groups: continuation (n=65) and non-continuation (n=36) groups. Details regarding age, body mass index, sex, affected extremities (upper or lower), site of edema (unilateral or bilateral), International Society of Lymphology (ISL) classification, presence of distant metastasis, and overall score on the lymphedema quality of life questionnaire (LYMQOL) were obtained before initial lymphedema care. In this study, we performed a decision tree analysis using a classification and regression tree (CART) to detect the combination of factors associated with the continuity of edema care for cancer-related edema. Results: Significant differences were observed in the site of edema (unilateral or bilateral) and distant metastasis between the two groups. In the decision tree using CART analysis, the factors selected to influence the possibility of continuation were the side of edema as the first layer, and body mass index of 23.0 and distant metastasis (with/without) as the second layer. Outpatients with unilateral edema and a body mass index higher than 23.0 were most likely to be able to continue care. In contrast, outpatients with bilateral edema and distant metastasis had greater difficulty in continuing care. Conclusion: In this study, factors that were suggested to influence the continuity of cancer-related edema care were the side with edema, body mass index higher than 23.0, and distant metastasis. This information may be helpful for developing care strategies and improving patient adherence.

The BCPM method: decoding breast cancer with machine learning.

Breast cancer prediction and diagnosis are critical for timely and effective treatment, significantly impacting patient outcomes. Machine learning algorithms have become powerful tools for improving the prediction and diagnosis of breast cancer. The Breast Cancer Prediction and Diagnosis Model (BCPM), which utilises machine learning techniques to improve the precision and efficiency of breast cancer diagnosis and prediction, is presented in this paper. BCPM collects comprehensive and high-quality data from diverse sources, including electronic medical records, clinical trials, and public datasets. Through rigorous pre-processing, the data is cleaned, inconsistencies are addressed, and missing values are handled. Feature scaling techniques are applied to normalize the data, ensuring fair comparison and equal importance among different features. Furthermore, feature-selection algorithms are utilized to identify the most relevant features that contribute to breast cancer projection and diagnosis, optimizing the model's efficiency. The BCPM employs numerous machine learning methods, such as logistic regression, random forests, decision trees, support vector machines, and neural networks, to generate accurate models. Area under the curve (AUC), sensitivity, specificity, and accuracy are only some of the metrics used to assess a model's performance once it has been trained on a subset of data. The BCPM holds promise in improving breast cancer prediction and diagnosis, aiding in personalized treatment planning, and ultimately taming patient results. By leveraging machine learning algorithms, the BCPM contributes to ongoing efforts in combating breast cancer and saving lives.

Factors and prediction model associated with resumption of social outings in stroke survivors 6 months after onset: a multicenter prospective study.

OBJECTIVES: To identify factors associated with the resumption of social outings 6 months after stroke onset and develop a simple clinically practical prediction model. MATERIALS AND METHODS: Participants were recruited from first-ever stroke survivors admitted to three rehabilitation wards, and resumption of social outings 6 months after stroke onset was assessed using the Japanese version of the Frenchay Activities Index. The association of physical and cognitive functions with activities of daily living at admission to the rehabilitation ward and resumption of social outings 6 months after stroke onset was examined using logistic regression and decision trees. RESULTS: Notably, 63.2% of the 57 stroke survivors who participated in this study had lower Frenchay Activities Index scores for social outings 6 months after stroke onset than before. Logistic regression analysis revealed that attention deficit and grooming on the Functional Independence Measure (FIMTM) were significantly associated with decreased social outing scores 6 months after stroke onset. A decision tree model was created to predict the resumption of social outings using the presence or absence of attention disorders and FIMTM grooming score (>2 or ≤ 2). CONCLUSIONS: The results of this study suggest that attention deficit and beyond a certain level of independence in grooming (FIMTM >2) at admission to the rehabilitation ward are associated with recovery to the pre-stroke level of social outings 6 months after stroke onset. The decision tree created in this study holds promise as a simple model to predict the resumption of social outings among stroke survivors.

Development of a decision tree model for predicting the malignancy of localized gingival enlargements based on clinical characteristics.

The present study aimed to determine the prevalence of localized gingival enlargements (LGEs) and their clinical characteristics in a group of Thai patients, as well as utilize this information to develop a clinical diagnostic guide for predicting malignant LGEs. All LGE cases were retrospectively reviewed during a 20-year period. Clinical diagnoses, pathological diagnoses, patient demographic data, and clinical information were analyzed. The prevalence of LGEs was determined and categorized based on their nature, and concordance rates between clinical and pathological diagnoses among the groups were evaluated. Finally, a diagnostic guide was developed using clinical information through a decision tree model. Of 14,487 biopsied cases, 946 cases (6.53%) were identified as LGEs. The majority of LGEs were reactive lesions (72.62%), while a small subset was malignant tumors (7.51%). Diagnostic concordance rates were lower in malignant LGEs (54.93%) compared to non-malignant LGEs (80.69%). Size, consistency, color, duration, and patient age were identified as pivotal factors to formulate a clinical diagnostic guide for distinguishing between malignant and non-malignant LGEs. Using a decision tree model, we propose a novel diagnostic guide to assist clinicians in enhancing the accuracy of clinical differentiation between malignant and non-malignant LGEs.

Towards an automated classification phase in the software maintenance process using decision tree.

The software maintenance process is costly, accounting for up to 70% of the total cost in the software development life cycle (SDLC). The difficulty of maintaining software increases with its size and complexity, requiring significant time and effort. One way to alleviate these costs is to automate parts of the maintenance process. This research focuses on the automation of the classification phase using decision trees (DT) to sort, rank, and accept/reject maintenance requests (MRs) for mobile applications. Our dataset consisted of 1,656 MRs. We found that DTs could automate sorting and accepting/rejecting MRs with accuracies of 71.08% and 64.15%, respectively, though ranking accuracy was lower at 50%. While DTs can reduce costs, effort, and time, human verification is still necessary.

Development of predictive model for post-stroke depression at discharge based on decision tree algorithm: A multi-center hospital-based cohort study.

OBJECTIVE: Post-stroke depression (PSD) is one of the most common and severe neuropsychological sequelae after stroke. Using a prediction model composed of multiple predictors may be more beneficial than verifying the predictive performance of any single predictor. The primary objective of this study was to construct practical prediction tools for PSD at discharge utilizing a decision tree (DT) algorithm. METHODS: A multi-center prospective cohort study was conducted from May 2018 to October 2019 and stroke patients within seven days of onset were consecutively recruited. The independent predictors of PSD at discharge were identified through multivariate logistic regression with backward elimination. Classification and regression tree (CART) algorithm was employed as the DT model's splitting method. RESULTS: A total of 876 stroke patients who were discharged from the neurology departments of three large general Class A tertiary hospitals in Wuhan were eligible for analysis. Firstly, we divided these 876 patients into PSD and non-PSD groups, history of coronary heart disease (OR = 1.835; 95 % CI, 1.106-3.046; P = 0.019), length of hospital stay (OR = 1.040; 95 % CI, 1.013-1.069; P = 0.001), NIHSS score (OR = 1.124; 95 % CI, 1.052-1.201; P = 0.001), and Mini mental state examination (MMSE) score (OR = 0.935; 95 % CI, 0.893-0.978; P = 0.004) were significant predictors. The subgroup analysis results have shown that hemorrhagic stroke, history of hypertension and higher modified Rankin Scale score (mRS) score were associated with PSD at discharge in the young adult stroke patients. CONCLUSIONS: Several predictors of PSD at discharge were identified and convenient DT models were constructed to facilitate clinical decision-making.

Identification of early predictive biomarkers for severe cytokine release syndrome in pediatric patients with chimeric antigen receptor T-cell therapy.

CAR-T cell therapy is a revolutionary new treatment for hematological malignancies, but it can also result in significant adverse effects, with cytokine release syndrome (CRS) being the most common and potentially life-threatening. The identification of biomarkers to predict the severity of CRS is crucial to ensure the safety and efficacy of CAR-T therapy. To achieve this goal, we characterized the expression profiles of seven cytokines, four conventional biochemical markers, and five hematological markers prior to and following CAR-T cell infusion. Our results revealed that IL-2, IFN-γ, IL-6, and IL-10 are the key cytokines for predicting severe CRS (sCRS). Notably, IL-2 levels rise at an earlier stage of sCRS and have the potential to serve as the most effective cytokine for promptly detecting the condition's onset. Furthermore, combining these cytokine biomarkers with hematological factors such as lymphocyte counts can further enhance their predictive performance. Finally, a predictive tree model including lymphocyte counts, IL-2, and IL-6 achieved an accuracy of 85.11% (95% CI = 0.763-0.916) for early prediction of sCRS. The model was validated in an independent cohort and achieved an accuracy of 74.47% (95% CI = 0.597-0.861). This new prediction model has the potential to become an effective tool for assessing the risk of CRS in clinical practice.

A Dynamic Trust evaluation and update model using advance decision tree for underwater Wireless Sensor Networks.

Underwater wireless sensor networks (UWSNs) are an emerging research area that is rapidly gaining popularity. However, it has several challenges, including security, node mobility, limited bandwidth, and high error rates. Traditional trust models fail to adapt to the dynamic underwater environment. Thus, to address these issues, we propose a dynamic trust evaluation and update model using a modified decision tree algorithm. Unlike baseline methods, which often rely on static and generalized trust evaluation approaches, our model introduces several innovations tailored specifically for UWSNs. These include energy-aware decision-making, real-time adaptation to environmental changes, and the integration of multiple underwater-specific factors such as water currents and acoustic signal properties. Our model enhances trust accuracy, reduces energy consumption, and lowers data overhead, achieving a 96% accuracy rate with a 2% false positive rate. Additionally, it outperforms baseline models by improving energy efficiency by 50 mW and reducing response time to 20 ms per packet. These innovations demonstrate the proposed model's effectiveness in addressing the unique challenges of UWSNs, ensuring both security and operational efficiency goals. The proposed model effectively enhances the trust evaluation process in UWSNs, providing both security and operational benefits. These key findings validate the potential of integrating modified decision tree algorithms to improve the performance and sustainability of UWSNs.

Development of decision tree classification algorithms in predicting mortality of COVID-19 patients.

INTRODUCTION: The accurate prediction of COVID-19 mortality risk, considering influencing factors, is crucial in guiding effective public policies to alleviate the strain on the healthcare system. As such, this study aimed to assess the efficacy of decision tree algorithms (CART, C5.0, and CHAID) in predicting COVID-19 mortality risk and compare their performance with that of the logistic model. METHODS: This retrospective cohort study examined 5080 cases of COVID-19 in Babol, a city in northern Iran, who tested positive for the virus via PCR from March 2020 to March 2022. In order to check the validity of the findings, the data was randomly divided into an 80% training set and a 20% testing set. The prediction models, such as Logistic regression models and decision tree algorithms, were trained on the 80% training data and tested on the 20% testing data. The accuracy of these methods for the test samples was assessed using measures like ROC curve, sensitivity, specificity, and AUC. RESULTS: The findings revealed that the mortality rate for COVID-19 patients who were admitted to hospitals was 7.7%. Through cross validation, it was determined that the CHAID algorithm outperformed other decision tree and logistic regression algorithms in specificity, and precision but not sensitivity in predicting the risk of COVID-19 mortality. The CHAID algorithm demonstrated a specificity, precision, accuracy, and F-score of 0.98, 0.70, 0.95, and 0.52 respectively. All models indicated that factors such as ICU hospitalization, intubation, age, kidney disease, BUN, CRP, WBC, NLR, O2 sat, and hemoglobin were among the factors that influenced the mortality rate of COVID-19 patients. CONCLUSIONS: The CART and C5.0 models had outperformed in sensitivity but CHAID demonstrates a better performance compared to other decision tree algorithms in specificity, precision, accuracy and shows a slight improvement over the logistic regression method in predicting the risk of COVID-19 mortality in the population under study.