Tree Model Research Articles

Enhancing Heart Disease Prediction through Machine Learning: A Comparative Analysis of Algorithm Generalization across Datasets with Various Distributions

Heart disease, due to its high prevalence and mortality, remains a key area of global research. Although traditional diagnostic methods are effective, they are often invasive and time-consuming, highlighting the need for non-invasive, AI-based approaches. A significant challenge in real-world applications is ensuring model generalization across different datasets, particularly when the datasets are small. In this study, the performance of machine learning models, including Decision Tree, Random Forest, Support Vector Machine (SVM), and Multi-Layer Perceptron (MLP), was evaluated on two distinct heart disease datasets with different distributions and relatively small sizes. Two datasets with varying distributions were used for training and testing, with the primary focus on assessing model generalization in crossdataset applications. It is shown in the results that, while the Decision Tree model performed best after hyperparameter tuning, the improvements in Random Forest and MLP were limited, and SVM exhibited a decline in performance after tuning in the cross-dataset task. It was found that grid search tuning has limitations in cross-dataset scenarios, especially with small datasets, where complex models are prone to overfitting. The study demonstrates that, with smaller datasets, simpler models like Decision Trees often adapt better to different datasets. Furthermore, transfer learning and domain adaptation techniques are suggested as crucial for improving model generalization. Future research should focus on employing these techniques to enhance the robustness and accuracy of heart disease prediction models across diverse datasets.

Built Environment’s Non-Linear Impact on Subway Passenger Flow Through Improved Interpretable Machine Learning

Understanding the complex correlation between the built environment and subway passenger flow can provide unique insights for the development of transportation operations and urban coordination policies. Few studies have systematically analyzed the rationality of selecting built environment variables and further explored the non-linear relationships. In this study, we integrated various sources of built environmental factors and developed an interpretable machine learning analysis framework using backward elimination extreme gradient boosting and SHapley Additive exPlanations (SHAP) values analysis (BE-XGBoost-SHAP). The framework was validated by analyzing passenger flows during the morning peak, non-peak, and evening peak periods at the station level. The research results indicate that there are significant differences between built environment factors and the time-varying passenger flow. Land use characteristics significantly dominate across all three temporal periods. The importance of other variable types in relation to passenger flows varies significantly across the three time periods. It is worth noting that the relationships between all variables and passenger flow at different time periods are non-linear, with the majority displaying threshold effects. Compared with the gradient boosting decision tree (GBDT) and ordinary least squares (OLS) models, the proposed interpretive framework performs better as regards R-square, root mean square error (RMSE), and mean absolute error (MAE) metrics. This study offers valuable insights, elucidating the pivotal land use attributes that notably affect passenger flow, the significance of varied built environment factors across distinct time spans, and the acknowledgment of non-linearities and threshold effects within these relationships. These findings are imperative for urban planning and the enhancement of station area design.

Screening for congenital Chagas disease in a non-endemic area: a cost-effectiveness analysis

Abstract Background Due to climate changes, immigration, and globalization, Chagas Disease (CD) also afflicts nations without vector transmission. In Europe, congenital CD (cCD) is a significant public health issue, perpetuating the disease: it is crucial to perform CD screening in pregnant women at risk, as the treatment of infants is effective in eradicating the infection. Only a few European regions have a definite algorithm for diagnosing cCD, but no official guidance has been published at the national or European level. To support policymakers, this study aims to outline a cost-effectiveness analysis of CD screening in non-endemic areas, such as Italy, in pregnant women born or arriving from endemic countries and in their newborns. Methods To measure the economic impact of cCD screening, a decision tree model will be used to compare the test option (screening, diagnosis, treatment, follow-up) with no test option (no screening, progression of disease). Model parameters will be taken from relevant scientific literature. The primary outcome will be the Incremental Cost-Effectiveness Ratio (ICER) between the two options. Sensitivity analyses will be conducted to determine how changes in prevalence, transmission rate, screening adherence, and treatment adherence may affect the ICER. Results We expect the ‘test’ option to be cost-effective even with significant reductions in prevalence, transmission rate, adherence to screening or treatment. Threshold levels of these variables will allow to critically extend the results to areas with reduced immigration, patchy distribution of migrants at risk, health logistical limitations, and limited access to care for immigrants. Conclusions Our findings can help policymakers implement official screening programs and diagnostic algorithms for cCD in Italy and other non-endemic countries. This contributes to SDG 3 by combating the spread and burden of neglected tropical diseases and contributing to maternal, child, and migrant health. Key messages • Screening for congenital Chagas Disease in a non-endemic area may be cost-effective and cost-saving. • Study findings could provide useful information for health policymakers to combat Chagas Disease in Europe.

Thyroglobulin measurement is the most powerful outcome predictor in differentiated thyroid cancer: a decision tree analysis in a European multicenter series.

An accurate prognostic assessment is pivotal to adequately inform and individualize follow-up and management of patients with differentiated thyroid cancer (DTC). We aimed to develop a predictive model for recurrent disease in DTC patients treated by surgery and 131I by adopting a decision tree model. Age, sex, histology, T stage, N stage, risk classes, remnant estimation, thyroid-stimulating hormone (TSH), thyroglobulin (Tg), administered 131I activities and post-therapy whole body scintigraphy (PT-WBS) were identified as potential predictors and put into regression algorithm (conditional inference tree, c-tree) to develop a risk stratification model for predicting persistent/recurrent disease over time. The PT-WBS pattern identified a partition of the population into two subgroups (PT-WBS positive or negative for distant metastases). Patients with distant metastases exhibited lower disease-free survival (either structural, DFS-SD, and biochemical, DFS-BD, disease) compared to those without metastases. Meanwhile, the latter were further stratified into three risk subgroups based on their Tg values. Notably, Tg values >63.1 ng/mL predicted a shorter survival time, with increased DFS-SD for Tg values <63.1 and <8.9 ng/mL, respectively. A comparable model was generated for biochemical disease (BD), albeit different DFS were predicted by slightly different Tg cutoff values (41.2 and 8.8 ng/mL) compared to DFS-SD. We developed a simple, accurate and reproducible decision tree model able to provide reliable information on the probability of structurally and/or biochemically persistent/relapsed DTC after a TTA. In turn, the provided information is highly relevant to refine the initial risk stratification, identify patients at higher risk of reduced structural and biochemical DFS, and modulate additional therapies and the relative follow-up.

Physical Frailty Prediction Using Cane Usage Characteristics during Walking

This study aimed to determine the characteristics of accelerations and angular velocities obtained by an inertial measurement unit (IMU) attached to a cane between older people with and without physical frailty. Community-dwelling older people walked at a comfortable speed using a cane with a built-in IMU. Physical frailty was assessed using exercise-related items extracted from the Kihon Check List. The efficacy of five machine learning models in distinguishing older people with physical frailty was investigated. This study included 48 older people, of which 24 were frail and 24 were not. Compared with the non-frail participants, the older people with physical frailty had a small root mean square value in the vertical and anteroposterior directions and angular velocity in the anteroposterior direction (p &lt; 0.001, r = 0.36; p &lt; 0.001, r = 0.29; p &lt; 0.001, r = 0.30, respectively) and a large mean power frequency value in the vertical direction (p = 0.042, r = 0.18). The decision tree model could most effectively classify physical frailty, with an accuracy, F1 score, and area under the curve of 78.6%, 91.8%, and 0.81, respectively. The characteristics of IMU-attached cane usage by older adults with physical frailty can be utilized to effectively evaluate and determine physical frailty in their usual environments.

Cost-effectiveness analysis of implementing the Nagasaki Acute Myocardial Infarction (AMI) secondary prevention clinical pathway

Abstract Background/Introduction Because of the poor prognosis associated with acute coronary syndromes (ACS), intensive low-density lipoprotein cholesterol (LDL-C) management therapy is recommended as early as possible after the onset of ACS, with the goal of lowering plasma LDL-C to &amp;lt;70 mg/dL. In Nagasaki City, a council was formed comprising all hospitals performing percutaneous coronary intervention along with general physicians, and an initiative to manage LDL-C using a region-wide LDL-C management clinical pathway (Figure 1) was launched in July 2022. The rate of intensive statin therapy at discharge increased from 34.5% to 79.8%, and the rate of patients achieving LDL-C &amp;lt;70 mg/dL at discharge increased from 37.2% to 54.6% following the implementation of the clinical pathway. However, the cost-effectiveness of implementing the clinical pathway remains to be determined. Purpose: The purpose of this study was to evaluate the cost-effectiveness of implementing the Nagasaki AMI Secondary Prevention Clinical Pathway. Methods: To evaluate the cost-effectiveness of implementing the clinical pathway compared with no implementation, a lifetime simulation was performed using mathematical models. The models consisted of a decision tree model to model the flow of the clinical pathway (Figure 2) and a Markov model to consider the risks of developing cardiovascular disease (CVD) events. The quality-adjusted life year (QALY) was used as the outcome. Drug costs and treatment costs for each CVD event were included. Drug costs were calculated from actual prescriptions. Treatment costs and utility scores for each event were based on the literature. The risk of each CVD event was calculated using baseline risks estimated using commercial claims data (DeSC Healthcare, Inc.) and patients' LDL-C levels at discharge and 1 month after discharge. LDL-C levels at each time point were set separately for the groups that achieved or did not achieve a discharge LDL-C &amp;lt; 70 mg/dL, for patients with and without implementing the clinical pathway. Results: Implementing the clinical pathway was evaluated as dominant, with an incremental gain of 0.079 QALYs per person and expected cost savings of JPY 103,124 per person. Implementing the clinical pathway was shown to not only provide additional health benefits by preventing CVD, but also to reduce future health care costs. In the analysis with a 10-year time horizon, the result remained dominant, and the same level of cost savings was expected. Conclusions: Implementing the Nagasaki AMI Secondary Prevention Clinical Pathway can be expected to reduce costs, in addition to increasing QALYs by preventing CVD. Further clinical and economic evaluation of long-term follow-up with a collaborative pathway to the general physician after discharge from the hospital is expected.

Heart rate variability to predict 1-day atrial fibrillation episode onset using machine learning

Abstract Background Studies using AI assessment of 10-second 12-lead ECG suggest that it provides incremental identification of AF risk compared with clinical scores. However, it is not clear what preventive treatment should be given as the exact time of AF onset remains unknown. The use of machine learning (ML) with 2-lead Holter ECG allows the development of predictive models for paroxysmal AF within a short time window, potentially allowing an optimised pill-in-the-pocket (PITP)-like strategy. Aim To identify patients who are still in sinus rhythm but will develop an episode of AF in the next few hours using 24-hour Holter recordings and ML. Materials and methods We created a new database of 95871 Holter recordings that were manually analysed. We identified 1319 paroxysmal AF episodes from 872 patients. A total of 835 AF episodes from 506 recordings had more than 60 minutes of normal sinus rhythm (NSR) before AF onset and more than 10 minutes of AF after onset, and a total of 964 AF episodes had 30 minutes or more of NSR before AF onset. Patients were divided into five groups: all patients, patients younger than 60 years, 60-70 years, 70-80 years, and older than 80 years. A total of 365 recordings from 347 patients without rhythm abnormalities were identified and classified in our database, from which we took two ECG windows. We used a gradient-boosted decision tree model with heart rate variability (HRV) parameters as input. Results The most significant results were obtained from recordings with more than 5 minutes of AF with an AUROC of 0.919 (95% CI: 0.879-0.958) and an AUPRC of 0.919 (0.879-0.958) 15H08 ± 13H05 hours before the onset of AF (Figures 1 - 2). Using a threshold of 0.5, the accuracy was 84.5% (81.2-87.8), the sensitivity was 83.0% (79.5-86.4), the specificity was 86.6% (79.3-93.9), the PPV was 90.2% (85.5-94.9), the NPV was 78.4% (74.7-82.1) and the F1 score was 86.2% (83.5-89.0) for all patients. Conclusion These results suggest that the most important information for short-term prediction of AF onset is contained in HRV, allowing a preventive strategy. This could be exploited by wearables in mHealth allowing the use of a PITP-like preventive strategy to reduce the burden of AF. Prospective studies are needed to confirm the encouraging potential of these findings.AUROC of the XGBoost modelPrecision-recall curves

Nonlinear relationships of commuting and built environments surrounding residences and workplaces with obesity

Obesity is a prominent risk contributor to health. However, few studies have explored the nonlinear relationships between commuting and built environments, particularly around workplaces, with obesity. Based on a sample of 1080 respondents in Shanghai, China, we used the gradient-boosting decision trees model to investigate the relative contributions and nonlinear relationships of commuting and built environments surrounding residences and workplaces with body mass index (BMI). Results showed that the built environment made greater contributions to BMI than sociodemographics and behavioral attributes. The built environment around workplaces was more important than that around residences, and commuting behavior rather than exercise or food intake contributed more. Gender and age were the most important predictors among all predictors. Moreover, most predictors were nonlinearly related to BMI. Car and bus commuters had higher BMI. Commuting distance (<20 km) was positively related to BMI and the duration of active modes (<20 min) was negatively associated with BMI. Around workplaces, green space (<0.28 km2) and population density (10,000–28,000 people/km2) had negative associations with BMI. Land use diversity around workplaces (>0.5) had a U-shaped relationship with BMI and the threshold was 0.78, but it around residences (0.82–0.85) had a positive effect. A longer distance to the subway station from residences (<1500 m) was associated with lower BMI. Men had higher BMI and age (24–47 years) was positively correlated with BMI. Beyond the thresholds, these predictors had limited contributions to BMI. We concluded that prioritizing interventions in the built environment around workplaces and commuting behavior to reach effective thresholds is important to reduce obesity.

A Hybrid Machine Learning‐Based Data‐Centric Cybersecurity Detection in the 5G‐Enabled IoT

ABSTRACTBy increasing smart objects as high‐potential computing devices and 5G technology, the Internet of Things (IoT) has emerging technology to provide a data‐centric infrastructure for detecting safe device‐to‐device communications by supporting security and privacy issues. As a 5G‐enabled communication technology, vehicle‐to‐vehicle (V2V) communication provides a wireless exchange information connection between smart vehicles, intelligent devices, and a cloud‐edge computing environment. This connection should be established with a safe and secured run‐time protection system to avoid many critical anomalies and misbehavior problems. Detecting run‐time malicious transformations with data‐centric misbehaving reactions is a main challenge for autonomous vehicle communications with 5G‐enabled communication technology. This paper provides a hybrid genetic algorithm‐based ensemble bagged trees (GA‐EBT) algorithm for a data‐centric misbehavior detection approach to support the V2V communications against malicious and misbehavior transactions. In this hybrid algorithm, GA provides a beneficial performance on the training accuracy factor based on a single‐objective fitness function and EBT supports a high‐degree prediction and training process using multiple decision tree models with bootstrapped samples of the training data. For the evaluation of the proposed algorithm, four real test cases are applied for messaging injection attacks in the V2V environments in comparison to the state‐of‐the‐art machine learning algorithms. The experimental results show that the proposed hybrid approach can achieve an optimal high rate accuracy factor of 99.999, precision and recall factors of 100%, and an F1‐Score factor of 100% to detect unexpected cyber‐attacks for the V2V communications in the IoT environment.

A budget impact analysis of exclusive human milk diet in very low birth weight infants in United Arab Emirates

Introduction Very low birth weight (VLBW) infants have the highest rate of neonatal intensive care unit (NICU) admissions owing to the higher comorbidities associated with premature birth and long hospital stays. VLBW infants fed a bovine (BOV)-based diet have higher mortality rates, necrotizing enterocolitis (NEC), late-onset sepsis (LOS), and other comorbidities than those fed 100% human milk-based products. This study aims to evaluate the budgetary impact of adopting an exclusive human milk diet (EHMD) instead of a BOV-based diet in VLBW infants from Al-Ain Hospital, Sheikh Shakhbout Medical City, and Dubai Health Authority (DHA) in the United Arab Emirates (UAE). Methods We use a decision tree model to estimate the budget impact of adopting EHMD versus the current local practice (BOV) over five years. Patients enter the tree model and have a probability of transitioning to one of the following mutually exclusive health states: NEC, which may be treated medically or surgically; LOS, NEC, and LOS; or neither NEC nor LOS. Depending on the feeding strategy, infants in the aforementioned health states are likely to develop any of the following complications: retinopathy of prematurity, bronchopulmonary dysplasia, or short bowel syndrome. The model accounts for the costs associated with diet, management of health states and complications, and the follow-up period. Results Al-Ain Hospital saved United Arab Emirates Dirham (AED) 3.3 million ($1.4million) in the first year of the EHMD feeding arm and AED 16.6 million ($7.1million) over the course of five years. In comparison to Sheikh Shabout Medical City and DHA, AED 36.7 million ($15.8million) and AED 24 million ($10.3million) were saved over five years, respectively, with AED 7.3 million ($3.1million) and 4.8 million ($2million) saved in the first year. The estimated pooled results across the three institutions were AED 5.1 million ($2.2million) and AED 25.7 million ($11million) savings in the first year and over five years, respectively. Conclusion Implementing the EHMD feeding scheme in VLBWs that has significant clinical benefits has resulted in substantial budget savings from the payer’s perspective in the UAE owing to fewer comorbidities associated with premature birth and shorter hospital stays. It is highly recommended for the Emirati health care settings to evaluate the real-world neonatal complication rates.

Deciphering house prices by integrating street perceptions with a machine-learning algorithm: A case study of Xi'an, China

A comprehensive understanding of house prices and their factors provide insights into the demand for housing while helping policymakers implement measures to manage the housing market. Traditional studies either focus more on linear relationships and ignore complex, non-linear influences or consider neighborhood amenities but lose sight of the streetscape. This study aims to enrich the literature by integrating street-perception characteristics with an interpretable machine-learning technique for modeling house prices. Specifically, street-view images were semantically segmented to quantify street-perception characteristics from five perspectives: greenness, openness, enclosure, walkability, and imageability. By combining the determinants of community attributes and living convenience, 17 explanatory variables were fed into a gradient-boosting decision tree (GBDT) model to estimate housing prices. The results reveal that the model significantly outperforms the linear model (R2 increased by 47.87 %). Additionally, an improvement of 26.15 % (R2) was observed when street-perception characteristics were incorporated. Moreover, complicated non-linear relationships and interaction effects are discussed by visualizing partial dependence plots (PDPs). These findings offer nuanced guidance for improving the neighborhood environment to promote urban equity and develop a sustainable housing market.

Reliability assessment method of wind power DC collection system based on MLFTA-SMC

Wind power DC collection system, as a crucial component of wind farms, plays a vital role in ensuring the safe and stable operation of the entire wind farm. This paper proposes a reliability assessment method for wind power DC collection systems based on MLFTA-SMC. Firstly, it analyzes the topology and key equipment of wind power DC collection systems. Secondly, based on the topology of different wind power DC collection systems, it constructs multi-level fault tree models to calculate the comprehensive importance of different events, thus providing data support for subsequent reliability assessment. Then, it utilizes the MLFTA-SMC method to assess and analyze the reliability of different wind power DC collection system topologies. Finally, taking a 100 MW wind farm in Northwest China as an example, the proposed reliability assessment method is verified through simulation. The results indicate that this method exhibits good effectiveness and superiority.

From microplastics to pixels: testing the robustness of two machine learning approaches for automated, Nile red-based marine microplastic identification.

Despite the urgent need for accurate and robust observations of microplastics in the marine environment to assess current and future environmental risks, existing procedures remain labour-intensive, especially for smaller-sized microplastics. In addition to this, microplastic analysis faces challenges due to environmental weathering, impacting the reliability of research relying on pristine plastics. This study addresses these knowledge gaps by testing the robustness of two automated analysis techniques which combine machine learning algorithms with fluorescent colouration of Nile red (NR)-stained particles. Heterogeneously shaped uncoloured microplastics of various polymers-polyethylene (PE), polyethylene terephthalate (PET), polypropylene (PP), polystyrene (PS), and polyvinyl chloride (PVC)-ranging from 100 to 1000µm in size and weathered under semi-controlled surface and deep-sea conditions, were stained with NR and imaged using fluorescence stereomicroscopy. This study assessed and compared the accuracy of decision tree (DT) and random forest (RF) models in detecting and identifying these weathered plastics. Additionally, their analysis time and model complexity were evaluated, as well as the lower size limit (2-4µm) and the interoperability of the approach. Decision tree and RF models were comparably accurate in detecting and identifying pristine plastic polymers (both > 90%). For the detection of weathered microplastics, both yielded sufficiently high accuracies (> 77%), although only RF models were reliable for polymer identification (> 70%), except for PET particles. The RF models showed an accuracy > 90% for particle predictions based on 12-30 pixels, which translated to microplastics sized < 10µm. Although the RF classifier did not produce consistent results across different labs, the inherent flexibility of the method allows for its swift adaptation and optimisation, ensuring the possibility to fine-tune the method to specific research goals through customised datasets, thereby strengthening its robustness. The developed method is particularly relevant due to its ability to accurately analyse microplasticsweathered under various marine conditions, as well as ecotoxicologically relevant microplastic sizes, making it highly applicable to real-world environmental samples.

Investigating the Mechanisms Impacting Soil Ca, Mg, and Na in Wastewater Land Application Systems Using Machine Learning Models

ABSTRACTWastewater land application is a widely accepted solution for addressing global water crisis, particularly in arid and semiarid regions, but it may cause soil Ca, Mg, and Na accumulation and result in soil degradation. The objective of this study was to investigate the underlying mechanisms impacting soil Ca, Mg, and Na in wastewater land application systems using tree‐based machine learning models. Using data collected from previous field studies, decision tree (DT), random forest (RF), and extreme gradient boosting decision trees (XGBoost) models were developed to predict soil Ca, Mg, and Na in wastewater land application systems. XGBoost models showed the best performance, with R2 and RMSE values of 0.999 and 18.9 mg/kg, 0.999 and 3.2 mg/kg, and 0.912 and 104 mg/kg on the training data and 0.989 and 345 mg/kg, 0.925 and 56.1 mg/kg, and 0.908 and 112 mg/kg on the test data for soil Ca, Mg, and Na prediction, respectively. Permutation importance analysis reveals that initial soil Ca and electrical conductivity (EC) and total irrigation amount, initial soil Mg, total precipitation and initial soil EC, and initial soil Na, total irrigation amount and wastewater Na were the top three predictive variables for soil Ca, Mg, and Na, respectively. Partial dependence analysis demonstrates how soil Ca, Mg, and Na changed with the predictive variables, and indicates that wastewater irrigation caused soil Ca, Mg, and Na accumulation. This study highlights the need for sustainable wastewater land application management to control soil sodium adsorption ratio and mitigate the risks of land degradation.

Möbius Invariant Y-systems (Cluster Structures) for Miquel Dynamics

Abstract Miquel dynamics is a discrete time dynamics for circle patterns, which relies on Miquel’s six circle theorem. Previous work shows that the evolution of the circle centers satisfy the dSKP equation on the octahedral lattice $A_{3}$. As a consequence, Miquel dynamics is a discrete integrable system. Moreover, Miquel dynamics give rise to a real-valued cluster structure. The evolution of the cluster variables under Miquel dynamics is also called a Y-system in the discrete integrable systems community. If the Y-system is real positive-valued then the circle pattern is accompanied by an invariant dimer model, an exactly solvable model studied in statistical physics. However, while circle patterns are Möbius invariant, the circle centers and the Y-system are not Möbius invariant, which violates the so called transformation group principle. In this article we show that half the intersection points satisfy the dSKP equation as well, and we introduce two new real-valued Y-systems for Miquel dynamics that involve only the intersection points. Therefore, the new Y-systems are Möbius invariant, and thus satisfy the transformation group principle. We also show that the circle centers and intersection points combined satisfy the dSKP equation on the 4-dimensional octahedral lattice $A_{4}$. In addition, we present two more complex-valued Y-systems for Miquel dynamics, which are real-valued in and only in the case of integrable circle patterns. We also investigate the special cases of harmonic embeddings and s-embeddings, which relate to the spanning tree and Ising model, respectively.

Identification of drought-salinity combined stress in tomato plants by vegetation indices

A major issue in several farming areas of the Mediterranean basin consists of drought and salinity stress. This stress is mainly due to a steady exposition of warm daily temperature and heatwaves, moreover with inevitable irrigation with saline water. Therefore, detecting the stress is essential to minimise significant yield loss and preserve agricultural sustainability. In this context, remote and proximal sensing can play a crucial role in allowing fast, not destructive, extensive, and reliable assessment of crop status. In this work, the effectiveness of several multispectral indices in detecting salinity and water stress in tomato plants, grown under controlled green-house conditions, was investigated. Three different classifiers (fine tree model, linear discriminant model, and linear support vector machines model) were used to verify whether, and the extent to which, the adopted multispectral indices can be adopted to identify a stress condition of the tomato plants. In the experimental campaign, the stress occurrence on tomato plants was assessed on the base of a set of ecophysiological measurements, such as transpiration, stomatal conductance, and photosynthesis rate. Obtained results showed that a classification model based on linear support vector machines, exploiting the combination of Photochemical Reflectance Index and the Chlorophyl Index, can detect drought and salinity stress in tomato plants with an accuracy higher than 94%.

Predictive value of the systemic immune-inflammation index for periprocedural complications in flow diverter treatment for patients with intracranial aneurysms.

Flow-diverter devices (FDs) are effective in treating intracranial aneurysms (IAs) but carry substantial periprocedural risks, particularly ischemic complications. This study aimed to determine if elevated Systemic Immune-Inflammation Index (SII) can independently predict these risks and assess the impact of age and dual antiplatelet therapy on this association. We conducted a retrospective analysis of patients treated with FDs between February 2016 and August 2023, using blood samples taken within six days before surgery to calculate SII. Logistic regression and decision tree analyses assessed the link between SII and periprocedural complications, with subgroups exploring influencing factors. Multivariable analysis identified high SII as an independent predictor of periprocedural complications (OR = 5.306, 95% CI: 1.367-18.455; P = 0.009). The decision tree model confirmed SII > 0.437 as a critical threshold. Subgroup analysis showed a pronounced association of SII with periprocedural complications in patients ≥ 65 years (OR = 36.979, 95% CI: 2.103-650.134; P = 0.014) and in those on clopidogrel plus aspirin therapy (OR = 16.921, 95% CI: 2.733-104.746; P = 0.002). An elevated Systemic Immune-Inflammation Index (SII) > 0.437 significantly correlates with increased periprocedural complications (6.5% vs. 1.8%, P = 0.017). Although not statistically significant, higher SII is associated with a greater rate of ischemic events (3.9% vs. 0.9%). Elevated preoperative SII independently predicts periprocedural complications, particularly ischemic events, in patients undergoing FDs treatment for intracranial aneurysms. This association is particularly pronounced in older patients (> 65 years) and those receiving dual therapy with clopidogrel plus aspirin. Trial Registration: ClinicalTrials.gov (NCT06446778). Registered on May 22, 2024.

Risk stratification of thymic epithelial tumors based on peritumor CT radiomics and semantic features.

To develop and validate nomograms combining radiomics and semantic features to identify the invasiveness and histopathological risk stratification of thymic epithelial tumors (TET) using contrast-enhanced CT. This retrospective multi-center study included 224 consecutive cases. For each case, 6764 intratumor and peritumor radiomics features and 31 semantic features were collected. Multi-feature selections and decision tree models were performed on radiomics features and semantic features separately to select the most important features for Masaoka-Koga staging and WHO classification. The selected features were then combined to create nomograms for the two systems. The performance of the radiomics model, semantic model, and combined model was evaluated using the area under the receiver operating characteristic curves (AUCs). One hundred eighty-seven cases (56.5 years ± 12.3, 101 men) were included, with 62 cases as the external test set. For Masaoka-Koga staging, the combined model, which incorporated five peritumor radiomics features and four semantic features, showed an AUC of 0.958 (95% CI: 0.912-1.000) in distinguishing between early-stage (stage I/II) and advanced-stage (III/IV) TET in the external test set. For WHO classification, the combined model incorporating five peritumor radiomics features and two semantic features showed an AUC of 0.857 (0.760-0.955) in differentiating low-risk (type A/AB/B1) and high-risk (B2/B3/C) TET. The combined models showed the most effective predictive performance, while the semantic models exhibited comparable performance to the radiomics models in both systems (p > 0.05). The nomograms combining peritumor radiomics features and semantic features could help in increasing the accuracy of grading invasiveness and risk stratification of TET. Peripheral invasion and histopathological type are major determinants of treatment and prognosis of TET. The integration of peritumoral radiomics features and semantic features into nomograms may enhance the accuracy of grading invasiveness and risk stratification of TET. Peritumor region of TET may suggest histopathological and invasive risk. Peritumor radiomic and semantic features allow classification by Masaoka-Koga staging (AUC: 0.958). Peritumor radiomic and semantic features enable the classification of histopathological risk (AUC: 0.857).

Development of gross motor skills in children under the age of 3 years: a decision tree approach

BackgroundThe early years of life are critical for gross motor development (GMD). This study utilized decision tree modeling to examine the influences on gross motor development in children under the age of 3 years and to rank the key factors affecting their development.MethodsBased on randomized stratified sampling, 9,507 children aged 0–3 years in Shenzhen were included in this study. The Ages and Stages Questionnaires (ASQ) were utilized for the assessment of gross motor development. The chi-square test was used to compare groups, and variables were screened using univariable and multivariable regression analyses. Decision tree modeling was employed to rank the importance of statistically significant variables.ResultsThe research found a prevalence of gross motor developmental delay of 1.41% among the respondents. The accuracy of the decision tree model is 70.96%. The results demonstrated a strong correlation between seven variables affecting the gross motor development of children, which were ranked based on importance: age, whether to provide supplementary food, average time spent interacting with children, family type, feeding method, mode of delivery, and birth order.ConclusionThe risk of gross motor developmental delay increases with age. Furthermore, supplementary food and interacting with other children are critical factors in improving children’s GMD delay. It is therefore imperative to enhance the monitoring of children’s gross motor skills through regular developmental assessments that detect potential GMD delays. Moreover, family type, feeding method, mode of delivery, and birth order were also predictive factors of GMD delay.

Multiple Machine Learning Models, Molecular Subtyping and Singlecell Analysis Identify PANoptosis-related Core Genes and their Association with Subtypes in Crohn's Disease.

PANoptosis plays an important role in many inflammatory diseases. However, there are no reports on the association between PANoptosis and CD. This study used five machine learning algorithms - least absolute shrinkage and selection operator, support vector machine, random forest, decision tree and Gaussian mixture models - to construct CD's PANoptosis signature. Unsupervised hierarchical clustering analysis was used to identify PANoptosis-associated subgroups of CD. Gene Ontology (GO) enrichment analysis, Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis, Gene Set Enrichment Analysis (GSEA) and Gene Set Variation Analysis (GSVA) were conducted to compare the PANoptosis-associated subgroups of CD among the potential biological mechanisms. Single sample GSEA was used to assess immune microenvironmental differences among the subgroups. The potential role of PANoptosis in CD was further explored using single-cell RNA-Seq (scRNA-Seq) for PANoptosis scoring, differential analysis, pseudotime analysis, cellular communication analysis and weighted gene co-expression network analysis (WGCNA) analysis. CD's PANoptosis signature consisted of seven genes: CEACAM6, CHP2, PIK3R1, CASP10, PSMB1, PSMB8 and UBC. The PANoptosis signature in multiple cohorts had a strong ability to recognise CD. The levels of immune cell infiltration and the vigour of the immune responses significantly varied between the two subpopulations of CD associated with PANoptosis. Multiple lines of evidence from the GO, KEGG, GSEA, GSVA, scRNA-Seq and WGCNA analyses suggested that I-kappaB kinase/NF- kappaB signalling, mitogen-activated protein kinase (MAPK), leukocyte activation and leukocyte migration were mechanisms closely associated with PANoptosis in CD. This study is the first to construct a PANoptosis signature with excellent efficacy in recognising CD. PANoptosis may mediate the process of CD through inflammatory and immune mechanisms, such as NF- kappaB, MAPK and leukocyte migration.