Regression Tree Analysis Research Articles

Risk subgroups and intervention effects among infants at high risk for peanut allergy: A model for clinical decision making.

The Learning Early About Peanut Allergy (LEAP) trial showed that early dietary introduction of peanut reduced the risk of developing peanut allergy by age 60 months in infants at high risk for peanut allergy. In this secondary analysis of LEAP data, we aimed to determine risk subgroups within these infants and estimate their respective intervention effects of early peanut introduction. LEAP raw data were retrieved from ITNTrialShare.org. Conditional random forest was applied to participants in the peanut avoidance arm to select statistically important features for the classification and regression tree (CART) analysis to group infants based on their risk of peanut allergy at 60 months of age. Intervention effects were estimated for each derived risk subgroup using data from both arms. Our main model was generated based on baseline data when the participants were 4-11 months old. Specific IgE measurements were truncated to account for the limit of detection commonly used by laboratories in clinical practice. The model found infants with higher predicted probability of peanut allergy at 60 months of age had a similar relative risk reduction, but a greater absolute risk reduction in peanut allergy with early introduction of peanut, than those with lower probability. The intervention effects were significant across all risk subgroups. Participants with baseline peanut sIgE ≥0.22 kU/L (n = 78) had an absolute risk reduction of 40.4% (95% CI 27.3, 51.9) whereas participants with baseline peanut sIgE<0.22 kU/L and baseline Ara h 2 sIgE <0.10 kU/L (n = 226) had an absolute risk reduction of 6.5% (95% CI 2.6, 11.0). These findings were consistent in sensitivity analyses using alternative models. In this study, risk subgroups were determined among infants from the LEAP trial based on the probability of developing peanut allergy and the intervention effects of early peanut introduction were estimated. This may be relevant for further risk assessment and personalized clinical decision-making.

Gafftopsail Catfish in Texas estuaries: Population trends and ecosystem implications

AbstractObjectiveGiven the limited information on population dynamics of Gafftopsail Catfish Bagre marinus in the western Gulf of Mexico, the objectives of this study were to determine the status of this species in Texas estuaries by assessing trends in relative abundance, length, and habitat preferences from fishery‐independent trawl (juvenile) and gill‐net (adult) data, as well as angler harvest trends from fishery‐dependent creel surveys collected in all Texas estuaries.MethodsFishery‐independent and ‐dependent monitoring data were collected by the Texas Parks and Wildlife Department in all major bay systems of the Texas coast from 1983 to 2022. Linear trend analysis was used to assess trends across the full time series and all major bay systems for both juvenile and adult specimens and for total recreational harvest. Boosted regression tree analysis was used to assess habitat preference for both juveniles and adults.ResultBoth juvenile and adult catch rates consistently increased in most Texas estuaries, with the most extreme increases occurring in central Texas coast estuaries beginning in the early 2000s. During the same time frame, mean lengths of adult specimens significantly decreased in many of the same estuaries. Habitat suitability analysis suggested that Gafftopsail Catfish were primarily influenced by salinity, though they still exist across a very broad range of salinity conditions. Angler catch rates showed some localized patterns of increasing or decreasing trends, though they generally did not follow fishery‐independent trends for most estuaries.ConclusionThese trends interpreted in the context of the known trophic role of Gafftopsail Catfish imply the potential for larger ecosystem‐level effects on both prey organisms and competitors. A more thorough awareness of these trends and potential interactions should help fisheries managers operate in an ecosystem‐based context when investigating population dynamics and recommending management strategies.

Denitrification regulates spatiotemporal pattern of N2O emission in an interconnected urban river-lake network

Urban rivers are hotspots of N2O production and emission. Interconnected river-lake networks are constructed to improve the water quality and hydrodynamic conditions of urban rivers in many cities of China. However, the impact of the river-lake connectivity project on N2O production and emission remains unclear. This study investigated dissolved N2O and emission of the river-lake network in Wuhan City, China from March 2021 to December 2021. The results showed that river-lake connection greatly decreased riverine Nitrogen (N) concentration and increased dissolved oxygen (DO) concentration compare to traditional urban rivers. N2O emissions from the urban river interconnected with lakes (LUR: 67.3 ± 92.6 μmol/m2/d) were much lower than those from the traditional urban rivers (UR: 467.3 ± 1075.7 μmol/m2/d) and agricultural rivers (AR: 20.4 ± 15.3μmol/m2/d). Regression tree analysis suggested that the N2O concentrations were extremely high when hypoxia exists (DO < 1.6 mg/L), and TDN was the primary factor regulating N2O concentrations when hypoxia does not occur. Thus, we ascribe the low N2O emission in the LUR and AR to the lower N contents and higher DO concentrations. The microbial process of N2O production and consumption were quantitatively estimated by isotopic models. The mean proportion of denitrification derived N2O (fbD) was 63.5 %, 55.6 %, 42.3 % and 42.7 % in the UR, LUR, lakes and AR, suggested denitrification dominated N2O production in the urban rivers, but nitrification dominated N2O production in the lakes and AR. The positive correlation between logN2O and fbD suggested that denitrification is the key process to regulate the N2O production and emission. The abundance of denitrification genes (nirS and nirK) was much higher than that of nitrification genes (amoA and amoB), also evidenced that denitrification was the main N2O source. Therefore, river-lake interconnected projects changed the nutrients level and hypoxic condition, leading to the inhibition of denitrification and nitrification, and ultimately resulting in a decrease of N2O production and emission. These results advance the knowledge on the microbial processes that regulate N2O emissions in inland waters and illustrate the integrated management of water quality and N2O emission.

Multiple risk factors for unplanned readmissions within 1 month of hospital discharge in acute care hospitals in Japan.

The aim of this study is to analyse the risk factors for unplanned readmissions within 1 month after hospital discharge to develop a seamless support system from discharge to home care. With shorter hospital stay lengths, understanding the characteristics of patients with multiple risk factors is important to prevent rehospitalization. This is a single-centre retrospective descriptive study. Logistic regression and decision tree analyses were performed using eight items from the records of 3117 patients discharged from a university hospital between April-September 2017 as risk factors. Unplanned readmission risk was significantly associated with emergency hospitalization (odds ratio [OR]: 3.12, 95% confidence interval [CI]: 2.04-4.77), malignancy (OR: 2.16, 95% CI: 1.44-3.24), non-surgical admission (OR: 1.76, 95% CI: 1.07-2.88), hospital stay of ≥ 15 days (OR: 1.66, 95% CI: 1.14-2.43) and decline in activities of daily living owing to hospitalization (OR: 1.68, 95% CI: 1.06-2.64). The highest risk combinations for rehospitalization were as follows: emergency hospitalization and malignancy; emergency admission, non-malignancy and a hospital stay of ≥15 days; and scheduled hospitalization, no surgery and a hospital stay of ≥15 days. Patients with multiple risks for unplanned readmission should be accurately screened and provided with optimal home care.

Identifying the highest risk vascular patients: Insights from the XATOA registry

AimsPatients with coronary and peripheral artery disease (PAD) have a residual risk of major adverse cardiovascular and limb events despite standards of care. Among patients with coronary artery disease (CAD) and/or PAD selected for low dose rivaroxaban (2.5 mg BID) and aspirin, we sought to determine the highest risk vascular patients. MethodsXATOA is a single-arm registry of CAD and/or PAD patients. All participants were initiated on low dose rivaroxaban (2.5 mg BID) and aspirin. We report the incidence risk of MACE or MALE and major bleeding. A classification and regression tree analysis (CART) determined independent subgroups. ResultsBetween November 2018 and May 2020, 5,808 participants were enrolled in XATOA; 5,532 were included in the full analysis. The median follow-up (interquartile range) was 462 (371-577) days. The incidence risk per 100 pt-years of major adverse cardiovascular events (MACE) or major adverse limb events (MALE) was highest among participants with polyvascular disease (2 or more vascular beds affected, n=2889). The incidence risk was 9.16 versus 2.48 per 100 patient-years in polyvascular and non-polyvascular patients respectively. Other subgroups of high-risk patients included participants 75 years or older, with a history of diabetes, heart failure, or chronic renal insufficiency (CRI). Rates of major bleeding were low overall. A CART analysis showed that polyvascular disease was the most dominant factor separating higher from lower risk participants, and this was heightened with CRI or diabetes. ConclusionPatients with polyvascular disease represent a substantial subset of patients in clinical practice and should be prioritized to receive maximal medical therapy including low dose rivaroxaban (2.5 mg BID) and aspirin. Lay summaryPatients with coronary and peripheral artery disease have a residual risk of major adverse cardiovascular and limb events despite standards of care. In the XATOA registry, we determine the highest risk vascular patients and report the incidence risk of major adverse cardiovascular events, major adverse limb events, and major bleeding.Rates of major bleeding were low overall. Polyvascular disease was the most dominant factor and was heightened with CRI or diabetes.Patients with polyvascular disease should be prioritized to receive maximal medical therapy including low dose rivaroxaban (2.5 mg BID) and aspirin.

Interactions of genetic variations in FAS, GJB2 and PTPRN2 are associated with noise-induced hearing loss: a case-control study in China

BackgroundThis study aimed to screen and validate noise-induced hearing loss (NIHL) associated single nucleotide polymorphisms (SNPs), construct genetic risk prediction models, and evaluate higher-order gene-gene, gene-environment interactions for NIHL in Chinese population.MethodsFirst, 83 cases and 83 controls were recruited and 60 candidate SNPs were genotyped. Then SNPs with promising results were validated in another case-control study (153 cases and 252 controls). NIHL-associated SNPs were identified by logistic regression analysis, and a genetic risk model was constructed based on the genetic risk score (GRS), and classification and regression tree (CART) analysis was used to evaluate interactions among gene-gene and gene-environment.ResultsSix SNPs in five genes were significantly associated with NIHL risk (p < 0.05). A positive dose-response relationship was found between GRS values and NIHL risk. CART analysis indicated that strongest interaction was among subjects with age ≥ 45 years and cumulative noise exposure ≥ 95 [dB(A)·years], without personal protective equipment, and carried GJB2 rs3751385 (AA/AB) and FAS rs1468063 (AA/AB) (OR = 10.038, 95% CI = 2.770, 47.792), compared with the referent group. CDH23, FAS, GJB2, PTPRN2 and SIK3 may be NIHL susceptibility genes.ConclusionGRS values may be utilized in the evaluation of the cumulative effect of genetic risk for NIHL based on NIHL-associated SNPs. Gene-gene, gene-environment interaction patterns play an important role in the incidence of NIHL.

Predictors for the Knee Extension Strength at 2 Yrs After Total Knee Arthroplasty Using Regression Tree Analysis.

The aim of the study is to clarify the interactive combinations of clinical factors associated with knee extension strength 2 yrs after total knee arthroplasty. A retrospective cohort study was conducted on 264 patients who underwent total knee arthroplasty. Knee extension strength was assessed preoperatively, 3 wks, and 2 yrs after total knee arthroplasty. Physical functions were measured with 10-m walking test, Timed Up and Go test, one-leg standing time, isometric knee flexion strength, knee joint stability, knee pain, femora-tibial angle, and passive knee extension and flexion angle before surgery as a baseline and 3 wks after total knee arthroplasty as acute phase. Regression tree analysis was conducted to clarify the interactive combinations that accurately predict the knee extension strength 2 yrs after total knee arthroplasty. Operational side knee extension strength (>1.00 Nm/kg) at acute phase was the primal predictor for the highest knee extension strength at 2 yrs after total knee arthroplasty. Acute phase Timed Up and Go test (≤10.13 secs) and baseline 10-m walking test (≤11.72 secs) was the second predictor. Acute phase nonoperative side knee extension strength (>0.90 Nm/kg) was also selected as the predictor. This study demonstrated that knee extension strength or Timed Up and Go test in the acute phase and 10-m walking test before total knee arthroplasty are useful for estimating the knee extension strength after total knee arthroplasty. The results will help determine specific postoperative rehabilitation goals and training options.

Using morphometrics to distinguish the restinga and cerrado ecotypes of wild Anacardium occidentale (Anacardiaceae): a preliminary study in northeastern Brazil

The cashew tree Anacardium occidentale is a globally important food species and in Brazil is a natural component of cerrado and restinga vegetation and has an important role in local economies as a food and medicinal plant. Nevertheless, diversity studies of wild populations—the most important reservoir of natural variation—of this naturally widespread species are urgently needed for conservation strategies because of human impact on tropical American ecosystems where it occurs. Here, we sought to differentiate the previously recognized restinga and cerrado ecotypes using multivariate morphometrics of wild populations in a limited area of northeast Brazil (northern Piauí and northeastern Maranhão states). Thirty individuals were sampled for 47 vegetative and reproductive descriptors from six wild populations (three of each ecotype). Data analysis included principal component analysis and three classification methods (linear discriminant analysis, k-nearest neighbour analysis and classification and regression tree analysis); cross-validation tests were applied to classification results. Univariate statistics obtained for each population and ecotype were found to be consistent with the previously proposed distinction between the two ecotypes. Although principal component analysis showed extensive variation and overlap between populations, cross-validations of classification analyses showed strong differentiation between ecotypes and between most populations; vegetative and reproductive variables were equally important for discrimination. Cerrado populations were more variable and somewhat less distinct than restinga ones. New molecular genetic investigations of wild populations are needed to provide genetic support for the morphological differentiation of the ecotypes reported here.

Predicting personal PAH exposure using high dimensional questionnaire and wristband data.

Polycyclic aromatic hydrocarbons (PAHs) are a class of pervasive environmental pollutants with a variety of known health effects. While significant work has been completed to estimate personal exposure to PAHs, less has been done to identify sources of these exposures. Comprehensive characterization of reported sources of personal PAH exposure is a critical step to more easily identify individuals at risk of high levels of exposure and for developing targeted interventions based on source of exposure. In this study, we leverage data from a New York (NY)-based birth cohort to identify personal characteristics or behaviors associated with personal PAH exposure and develop models for the prediction of PAH exposure. We quantified 61 PAHs measured using silicone wristband samplers in association with 75 questionnaire variables from 177 pregnant individuals. We evaluated univariate associations between each compound and questionnaire variable, conducted regression tree analysis for each PAH compound and completed a principal component analysis of for each participant's entire PAH exposure profile to determine the predictors of PAH levels. Regression tree analyses of individual compounds and exposure mixture identified income, time spent outdoors, maternal age, country of birth, transportation type, and season as the variables most frequently predictive of exposure.

Investigation of the evolved pyrolytic products and energy potential of Bagasse: experimental, kinetic, thermodynamic and boosted regression trees analysis

This study explored bagasse's energy potential grown using treated industrial wastewater through various analyses, experimental, kinetic, thermodynamic, and machine learning boosted regression tree methods. Thermogravimetry was employed to determine thermal degradation characteristics, varying the heating rate from 10 to 30 °C/min. The primary pyrolysis products from bagasse are H2, CH4, H2O, CO2, and hydrocarbons. Kinetic parameters were estimated using three model-free methods, yielding activation energies of approximately 245.98 kJ mol−1, 247.58 kJ mol−1, and 244.69 kJ mol−1. Thermodynamic parameters demonstrated the feasibility and reactivity of pyrolysis with ΔH ≈ 240.72 kJ mol−1, ΔG ≈ 162.87 kJ mol−1, and ΔS ≈ 165.35 J mol−1 K-1. The distribution of activation energy was analyzed using the multiple distributed activation energy model. Lastly, boosted regression trees predicted thermal degradation successfully, with an R2 of 0.9943. Therefore, bagasse's potential as an eco-friendly alternative to fossil fuels promotes waste utilization and carbon footprint reduction.

Markerless Kinematic Data in the Frontal Plane Contributions to Movement Quality in the Single-Leg Squat Test: A Comparison and Decision Tree Approach.

The aim of this study is to compare kinematic data of the frontal trunk, pelvis, knee, and summated angles (trunk plus knee) among categorized grades using the single-leg squat (SLS) test, to classify the SLS grade, and to investigate the association between the SLS grade and the frontal angles using smartphone-based markerless motion capture. Ninety-one participants were categorized into 3 grades (good, reduced, and poor) based on the quality of the SLS test. An automated pose estimation algorithm was employed to assess the frontal joint angles during SLS, which were captured by a single smartphone camera. Analysis of variance and a decision tree model using classification and regression tree analysis were utilized to investigate intergroup differences, classify the SLS grades, and identify associations between the SLS grade and frontal angles, respectively. In the poor group, each frontal trunk, knee, and summated angle was significantly larger than in the good group. Classification and regression tree analysis showed that frontal knee and summated angles could classify the SLS grades with a 76.9% accuracy. Additionally, the classification and regression tree analysis established cutoff points for each frontal knee (11.34°) and summated angles (28.4°), which could be used in clinical practice to identify individuals who have a reduced or poor grade in the SLS test. The quality of SLS was found to be associated with interactions among frontal knee and summated angles. With an automated pose estimation algorithm, a single smartphone computer vision method can be utilized to compare and distinguish the quality of SLS movement for remote clinical and sports assessments.

Relationships Between Speech, Spatial and Qualities of Hearing Short Form SSQ12 Item Scores and their Use in Guiding Rehabilitation for Cochlear Implant Recipients.

Cochlear implantation successfully improves hearing in most adult recipients. However, in rare cases, post-implant rehabilitation is required to maximize benefit. The primary aim of this investigation was to test if self-reports by cochlear implant users indicate the need for post-implant rehabilitation. Listening performance was assessed with the Speech, Spatial and Qualities short-form SSQ12, which was self-administered via a web-based survey. Subjects included over 2000 adult bilateral or unilateral cochlear implant users with at least one year of experience. A novel application of regression tree analysis identified core SSQ12 items that serve as first steps in establishing a plan for further rehabilitation: items 1, 8, and 11 dealing with single-talker situations, loudness perception, and clarity, respectively. Further regression and classification tree analyses revealed that SSQ12 item scores were weakly related to age, degree of tinnitus, and use of bilateral versus unilateral implants. Conversely, SSQ12 scores were strongly associated with self-rated satisfaction and confidence in using their cochlear implant. The SSQ12 total scores did not vary significantly over 1-9 or more years' experience. These findings suggest that the SSQ12 may be a useful tool to guide rehabilitation at any time after cochlear implantation. Identification of poor performance may have implications for timely management to improve the outcomes, through various techniques such as device fitting adjustments, counseling, active sound exposure, and training spatial hearing.

Can predictive factors determine the time to treatment initiation for oral and oropharyngeal cancer? A classification and regression tree analysis.

This ecological study aimed to identify the factors with the greatest power to discriminate the proportion of oral and oropharyngeal cancer (OOC) records with time to treatment initiation (TTI) within 30 days of diagnosis in Brazilian municipalities. A descriptive analysis was performed on the variables grouped into five dimensions related to patient characteristics, access to health services, support for cancer diagnosis, human resources, and socioeconomic characteristics of 3,218 Brazilian municipalities that registered at least one case of OOC in 2019. The Classification and Regression Trees (CART) technique was adopted to identify the explanatory variables with greater discriminatory power for the TTI response variable. There was a higher median percentage of records in the age group of 60 years or older. The median percentage of records with stage III and IV of the disease was 46.97%, and of records with chemotherapy, radiation, or both as the first treatment was 50%. The median percentage of people with private dental and health insurance was low. Up to 75% had no cancer diagnostic support services, and up to 50% of the municipalities had no specialist dentists. Most municipalities (49.4%) started treatment after more than 30 days. In the CART analysis, treatment with chemotherapy, radiotherapy, or both explained the highest TTI in all municipalities, and it was the most relevant for predicting TTI. The final model also included anatomical sites in the oral cavity and oropharynx and the number of computed tomography services per 100,000. There is a need to expand the availability of oncology services and human resources specialized in diagnosing and treating OOC in Brazilian municipalities for a timely TTI of OOC.

Predicting Complete versus Incomplete Long-Term Functional Independence after Acute AIS Grade D Spinal Cord Injury: A Prospective Cohort Study.

The proportion of patients with American Spinal Injury Association Impairment Scale (AIS) grade D traumatic spinal cord injuries (tSCI) is increasing. Although initial motor deficits can be relatively mild, some individuals fail to recover functional independence. This study aims to identify factors associated with failure to reach complete functional independence after AIS grade D tSCI. An observational prospective cohort study was conducted at a level 1 trauma center specialized in SCI care. A prospective cohort of 121 individuals with an AIS-D tSCI was considered. The baseline characteristics, length of acute stay, need for inpatient rehabilitation, and 12-month functional status were assessed. Univariate and classification and regression tree (CART) analyses were performed to identify factors associated with reaching complete versus incomplete functional independence (defined as perfect total SCIM III score at 12-month follow-up). There were 69.3%, 83.3%, and 61.4% individuals reaching complete independence in self-care, respiration/sphincter management, and mobility, respectively. A total of 64 individuals (52%) reached complete functional independence in all three domains. In the CART analysis, we found that patients are more likely to achieve complete functional independence when they have a baseline motor score ≥83 (65% individuals) and if they present fewer medical comorbidities (70% individuals if Charlson Comorbidity Index [CCI] ≤4). About half of individuals with AIS grade D tSCI can expect complete long-term functional independence. It is important to recognize early during acute care individuals with baseline motor score <83 or a high burden of comorbidities (CCI ≥5) to optimize their rehabilitation plan.

Pro/antioxidant status and selenium, zinc and arsenic concentration in patients with bipolar disorder treated with lithium and valproic acid.

Disturbances in pro/antioxidant balance emerge as a crucial element in bipolar disorder (BD). Some studies suggest that treatment effects on trace element concentration in BD. This study aimed to identify (a) the changes related to oxidative stress in BD and their relationship with trace elements engaged in pro/antioxidant homeostasis; (b) BD biomarkers using machine learning algorithm classification and regression tree (C&RT) analysis. 62 individuals with BD and 40 healthy individuals (HC) were included in the study. The concentration of pro/antioxidant state and concentration of selenium, zinc, arsenic in blood were assessed. We found a higher concentration of total antioxidant capacity, catalase, advanced oxidation protein products and a lower concentration of 4-hydroxynonenal (4-HNE), glutathione, glutathione peroxidase (GPx) in BD compared to HC. All examined trace elements were lower in the BD group compared to HC. A combination of two variables, 4-HNE (cut-off: ≤ 0.004 uM/mg protein) and GPx (cut-off: ≤ 0.485 U/mg protein), was the most promising markers for separating the BD from the HC. The area under the receiver operating characteristic curve values for C&RT was 90.5%. Disturbances in the pro/antioxidant state and concentration of trace elements of patients with BD may be a target for new therapeutic or diagnostic opportunity of BD biomarkers.

Alzheimer’s disease susceptibility in African American elders: a classification and regression tree (CART) analysis approach

Alzheimer's disease (AD) is increasingly prevalent, especially among African American older adults. Despite its widespread nature, accurate and timely diagnosis of AD remains challenging. Addressing the research gap in sociodemographic and cardiovascular risk factor research associated with AD in African American older adults, this study aimed to identify and analyze distinct subgroups within this population that are particularly vulnerable to AD, thereby contributing to the development of targeted interventions and healthcare strategies. This study employs a rigorous methodology utilizing classification and regression tree (CART) analysis to examine data from the 2017 Uniform Data Set (UDS). This approach enables a nuanced analysis of AD susceptibility among African American older adults. The CART analysis revealed significant associations between the studied sociodemographic and cardiovascular risk factors and AD susceptibility among African American older adults. The results indicate the presence of specific subgroups with increased vulnerability to AD, shaped by varying levels of education [relative importance (RI): 100%], antidepressant usage (RI: 83.1%), BMI (RI: 71.2%), use of antipsychotic agents (RI: 35.5%), and age of smoking cessation (RI: 21.5%). These findings underscore the importance of culturally specific research and interventions for addressing AD among African Americans. This study's findings, revealing significant associations between sociodemographic and cardiovascular risk factors and AD susceptibility among African American older adults, underscore the necessity of developing healthcare policies and interventions specifically tailored to address these risks.

회귀나무 분석을 이용한 외국인비율, 집단위협인식, 집합효율성 관계에 관한 탐색적 연구

In order to empirically verify the integrative hypothesis of the Social Integration Model-Group Threat Theory, this paper examines the relationship between the proportion of foreigners in residential areas and Koreans' perception of group threat and collective efficiency. This analysis is conducted at the exploratory level using regression tree analysis. The case of 800 Korean residents was utilized as secondary data in the “Research on Measures for Strengthening the Efficacy of Criminal Policy for Guaranteeing Public Safety (IV): A Study on the Safety Condition and Policy Issues in Foreign Population Concentrated Areas” conducted by the Korean Institute of Criminology and Justice. As a result of the main analysis, it was found that the integrated hypothesis of the Social Integration Model-Group Threat Theory, which has been discussed in Western society, was partially supported. However, the factor of perceived group threat had a significant effect only in multi-ethnic communities with more than 50% of foreigners in predicting collective efficiency. Through the derived results, the study suggests the necessity of implementing a control policy to mitigate the spread of anti-multicultural emotions resulting from the increasing ethnic diversity. Finally, the study also presents its limitations.

New insight in massive cerebral infarction predictions after anterior circulation occlusion

To predict massive cerebral infarction (MCI) occurrence after anterior circulation occlusion (ACO) by cASPECTS-CTA-CS (combined ASPECTS and CTA-CS). Of 185 cerebral infarction patients with the ACO, their collateral circulation scores from CT angiography (CTA) images in two groups (MCI and non-MCI) were evaluated using Alberta Stroke Program Early CT Score (ASPECTS) and CT angiography collateral score (CTA-CS) approaches. The cASPECTS-CTA-CS was validated internally using the bootstrap sampling method with 1000 bootstrap repetitions and compared to CTA-CS. Receiver-operating characteristic curve (ROC), clinical impact curve (CIC), and decision curve analysis (DCA) strategies were used to assess the clinical practicality and predictability of both approaches (cASPECTS-CTA-CS and CTA-CS). Using net reclassification improvement (NRI) and integrated discrimination improvement (IDI) analyses, discrimination levels of the cASPECTS-CTA-CS were compared with CTA-CS. Classification and regression tree (CART) analyses was conducted to identify the best predictive values and identify subgroup of MCI. The discrimination ability of collateral circulation evaluation score using the cASPECTS-CTA-CS [AUC: 0.918, 95% confidence interval (CI): 0.869–0.967, P < 0.01; NRI: 0.200, 95% CI: −0.104 to 0.505, P = 0.197; and IDI: 0.107, 95% CI: 0.035–0.178, P = 0.004] was better than CTA-CS alone (AUC: 0.885, 95% CI: 0.833–0.937, P < 0.01). DCA indicated the net benefits of the cASPECTS-CTA-CS approach was higher than CTA-CS alone when the threshold probability range over 20%. CIC analyses showed that the number of high risks and true positives were in agreement when the threshold probability > 80%. Less than 23 of cASPECTS-CTA-CS by CART was important factor in determining MCI occurrence, and ASPECTS < 7 was followed factor. The cASPECTS-CTA-CS approach cumulatively predicted MCI after ACO.

Machine-learning prediction of treatment response to stereotactic body radiation therapy in oligometastatic gynecological cancer: A multi-institutional study

Background and purposeWe aimed to develop and validate different machine-learning (ML) prediction models for the complete response of oligometastatic gynecological cancer after SBRT. Material and methodsOne hundred fifty-seven patients with 272 lesions from 14 different institutions and treated with SBRT with radical intent were included. Thirteen datasets including 222 lesions were combined for model training and internal validation purposes, with an 80:20 ratio. The external testing dataset was selected as the fourteenth Institution with 50 lesions. Lesions that achieved complete response (CR) were defined as responders. Prognostic clinical and dosimetric variables were selected using the LASSO algorithm. Six supervised ML models, including logistic regression (LR), classification and regression tree analysis (CART) and support vector machine (SVM) using four different kernels, were trained and tested to predict the complete response of uterine lesions after SBRT. The performance of models was assessed by receiver operating characteristic curves (ROC), area under the curve (AUC) and calibration curves. An explainable approach based on SHapley Additive exPlanations (SHAP) method was deployed to generate individual explanations of the model's decisions. Results63.6% of lesions had a complete response and were used as ground truth for the supervised models. LASSO strongly associated complete response with three variables, namely the lesion volume (PTV), the type of lesions (lymph-nodal versus parenchymal), and the biological effective dose (BED10), that were used as input for ML modeling. In the training set, the AUCs for complete response were 0.751 (95% CI: 0.716–0.786), 0.766 (95% CI: 0.729–0.802) and 0.800 (95% CI: 0.742–0.857) for the LR, CART and SVM with a radial basis function kernel, respectively. These models achieve AUC values of 0.727 (95% CI: 0.669–0.795), 0.734 (95% CI: 0.649–0.815) and 0.771 (95% CI: 0.717–0.824) in the external testing set, demonstrating excellent generalizability. ConclusionML models enable a reliable prediction of the treatment response of oligometastatic lesions receiving SBRT. This approach may assist radiation oncologists to tailor more individualized treatment plans for oligometastatic patients.

Geriatric Nutritional Risk Index predicts bleeding event in patients with heart failure.

We aimed to elucidate the association between malnutrition and the occurrence of bleeding events in patients with heart failure. We evaluated the nutritional status of patients with heart failure [n=2044, median (inter-quartile range) age 69.0 (59.0-78.0) years, 1209 (59.1%) males] using the Geriatric Nutritional Risk Index (GNRI). The primary endpoint was a composite of bleeding events such as haemorrhagic stroke or gastrointestinal bleeding. According to the survival classification and regression tree analysis, the accurate cut-off point of GNRI for predicting the primary endpoint was 106.2. We divided the patients into two groups based on GNRI levels: high GNRI group (GNRI≥106.2, n=606, 29.6%) and low GNRI group (GNRI<106.2, n=1438, 70.4%). We compared the patients' characteristics and prognosis between the two groups. The low GNRI group was older [72.0 (63.0-79.0) vs. 63.0 (53.0-73.0) years, P<0.001] and had a lower prevalence of male sex (56.9% vs. 64.5%, P=0.001). There were no differences in the use of antiplatelet agents and anticoagulants between the two groups. Levels of B-type natriuretic peptide were higher [321.1 (123.3-667.4) vs. 111.6 (42.6-235.4) pg/mL, P<0.001] and levels of haemoglobin were lower [12.4 (10.8-13.7) vs. 14.2 (12.9-15.4) g/dL, P<0.001] in the low GNRI group. The Kaplan-Meier analysis demonstrated that bleeding event rates were higher in the low GNRI group (log-rank P<0.001). The multivariable Cox proportional hazard analysis revealed that low GNRI (hazard ratio 1.952, 95% confidence interval 1.002-3.805, P=0.049) was associated with bleeding events. Heart failure patients with poor nutritional status, determined by GNRI under 106.2, experienced high bleeding event rates. Comprehensive management is required to avoid bleeding event in those populations.