Predicting the incidence risk of ischemic stroke in a hospital population of southern China: A classification tree analysis

Isolation forest-voting fusion-multioutput: A stroke risk classification method based on the multidimensional output of abnormal sample detection

BACKGROUND AND OBJECTIVE

Stroke has become a major disease threatening the health of people around the world. It has the characteristics of high incidence, high fatality, and a high recurrence rate. At this stage, problems such as poor recognition accuracy of stroke screening based on electronic medical records and insufficient recognition of stroke risk levels exist. These problems occur because of the systematic errors of medical equipment and the characteristics of the collectors during the process of electronic medical record collection. Errors can also occur due to misreporting or underreporting by the collection personnel and the strong subjectivity of the evaluation indicators.

METHODS

This paper proposes an isolation forest-voting fusion-multioutput algorithm model. First, the screening data are collected for numerical processing and normalization. The composite feature score index of this paper is used to analyze the importance of risk factors, and then, the isolation forest is used. The algorithm detects abnormal samples, uses the voting fusion algorithm proposed in this article to perform decision fusion prediction classification, and outputs multidimensional (risk factor importance score, abnormal sample label, risk level classification, and stroke prediction) results that can be used as auxiliary decision information by doctors and medical staff.

RESULTS

The isolation forest-voting fusion-multioutput algorithm proposed in this article has five categories (zero risk, low risk, high risk, ischemic stroke (TIA), and hemorrhagic stroke (HE)). The average accuracy rate of stroke prediction reached 79.59 %.

CONCLUSIONS

The isolation forest-voting fusion-multioutput algorithm model proposed in this paper can not only accurately identify the various categories of stroke risk levels and stroke prediction but can also output multidimensional auxiliary decision-making information to help medical staff make decisions, thereby greatly improving the screening efficiency.

Risk Assessment Score and Chi-Square Automatic Interaction Detection Algorithm for Hypertension Among Africans: Models From the SIREN Study

BACKGROUND

This study aimed to develop a risk-scoring model for hypertension among Africans.

METHODS

In this study, 4413 stroke-free controls were used to develop the risk-scoring model for hypertension. Logistic regression models were applied to 13 risk factors. We randomly split the dataset into training and testing data at a ratio of 80:20. Constant and standardized weights were assigned to factors significantly associated with hypertension in the regression model to develop a probability risk score on a scale of 0 to 1 using a logistic regression model. The model accuracy was assessed to estimate the cutoff score for discriminating hypertensives.

RESULTS

Mean age was 59.9±13.3 years, 56.0% were hypertensives, and 8 factors, including diabetes, age ≥65 years, higher waist circumference, (BMI) ≥30 kg/m2, lack of formal education, living in urban residence, family history of cardiovascular diseases, and dyslipidemia use were associated with hypertension. Cohen κ was maximal at ≥0.28, and a total probability risk score of ≥0.60 was adopted for both statistical weighting for risk quantification of hypertension in both datasets. The probability risk score presented a good performance-receiver operating characteristic: 64% (95% CI, 61.0-68.0), a sensitivity of 55.1%, specificity of 71.5%, positive predicted value of 70.9%, and negative predicted value of 55.8%, in the test dataset. Similarly, decision tree had a predictive accuracy of 67.7% (95% CI, 66.1-69.3) for the training set and 64.6% (95% CI, 61.0-68.0) for the testing dataset.

CONCLUSIONS

The novel risk-scoring model discriminated hypertensives with good accuracy and will be helpful in the early identification of community-based Africans vulnerable to hypertension for its primary prevention.

Development of a predictive risk stratification tool to identify the population over age 45 at risk for new-onset stroke within 7 years

Background and purpose

With the acceleration of the aging process of society, stroke has become a major health problem in the middle-aged and elderly population. A number of new stroke risk factors have been recently found. It is necessary to develop a predictive risk stratification tool using multidimensional risk factors to identify people at high risk for stroke.

Methods

The study included 5,844 people (age ≥ 45 years) who participated in the China Health and Retirement Longitudinal Study in 2011 and its follow-up up to 2018. The population samples were divided into training set and validation set according to 1:1. A LASSO Cox screening was performed to identify the predictors of new-onset stroke. A nomogram was developed, and the population was stratified according to the score calculated through the X-tile program. Internal and external verifications of the nomogram were performed by ROC and calibration curves, and the Kaplan-Meier method was applied to identify the performance of the risk stratification system.

Results

The LASSO Cox regression screened out 13 candidate predictors from 50 risk factors. Finally, nine predictors, including low physical performance and the triglyceride-glucose index, were included in the nomogram. The nomogram's overall performance was good in both internal and external validations (AUCs at 3-, 5-, and 7-year periods were 0.71, 0.71, and 0.71 in the training set and 0.67, 0.65, and 0.66 in the validation set, respectively). The nomogram was proven to excellently discriminate between the low-, moderate-, and high-risk groups, with a prevalence of 7-year new-onset stroke of 3.36, 8.32, and 20.13%, respectively (P < 0.001).

Conclusion

This research developed a clinical predictive risk stratification tool that can effectively identify the different risks of new-onset stroke in 7 years in the middle-aged and elderly Chinese population.

Green tea consumption and the risk of stroke: A systematic review and meta-analysis of cohort studies

OBJECTIVES

Epidemiologic studies are inconsistent regarding the association between green tea consumption and the risk of stroke. We performed a meta-analysis to determine whether an association exists between them in cohort studies.

METHODS

We searched the PubMed and Embase databases for studies conducted from 1966 through September 2022. Prospective cohort studies that provided relative risk (RR) estimates with 95% confidence interval (CI)s for the association were included. Study-specific risk estimates were combined by using a random-effects model.

RESULTS

A total of five studies, with 11 421 stroke cases among 645 393 participants, were included in the meta-analysis. The summary RR indicated a significant association between highest green tea consumption and reduced risk of stroke (summary RR: 0.74; 95% CI, 0.66-0.83). In the dose-response analysis, we observed a nonlinear association between green tea consumption and the risk of stroke (P for nonlinearity = 0.0000). Compared with non-consumers, the RRs (95% CI) of stroke across levels of green tea consumption were 0.91 (0.89-0.94) for 150 mL/d, 0.84 (0.80-0.89) for 300 mL/d, 0.79 (0.74-0.84) for 500 mL/d, 0.77 (0.72-0.82) for 900 mL/d, and 0.84 (0.77-0.91) for 1500 mL/d.

CONCLUSIONS

This meta-analysis suggests that green tea consumption is inversely associated with the risk of stroke, especially among those with moderate consumption. Our results support recommendations for green tea consumption to the primary prevention of stroke.

Prognostic factors in diabetes: Comparison of Chi-square automatic interaction detector (CHAID) decision tree technology and logistic regression

This study aimed to develop a diabetes prediction model. The model performance was compared with logistic regression, and the decision tree Chi-square automatic interaction detection (CHAID) was used to predict diabetes. In total, 3233 patients were included in the analysis. Of these, 589 patients with diabetes and 2644 patients without diabetes were included after analyzing the study sample from the Korean Genome and Epidemiology Study (KoGES)-8 data. In this study, Diabetes Mellitus (DM) diagnosis prediction was compared with logistic regression and prediction through machine learning (ML) using the CHAID decision classification tree. We performed statistical analysis using the CHAID method with International Business Machine (IBM) statistical program SPSS®. We performed logistic regression analysis to predict the classification of diabetes accurately, and the total classification accuracy of the analysis was 81.7%, and the CHAID decision tree classification accuracy was 81.8%. A diabetes diagnosis decision tree was created, which included seven terminal nodes and three depth levels. This analysis showed that a blood pressure problem and hospital visits were the most decisive variables at the time of classification, and two risk levels were created for diabetes diagnosis. The suggested method is a valuable tool for predicting diabetes. Patients who visit the hospital because of blood pressure problems are more likely to develop diabetes than under-treating hyperlipidemia. The diabetes prediction model can help doctors make decisions by detecting the possibility of diabetes early; however, it is impossible to diagnose diabetes using only the model without the doctor's opinion.

Education, Socioeconomic Status, and Intelligence in Childhood and Stroke Risk in Later Life: A Meta-analysis

BACKGROUND

Stroke is the second most common cause of death, and a common cause of dependency and dementia. Adult vascular risk factors and socioeconomic status (SES) are associated with increased risk, but less is known about early life risk factors, such as education, childhood SES, or intelligence (IQ).

METHODS

We comprehensively searched Medline, PsycINFO, and EMBASE from inception to November 2015. We included all studies reporting data on >50 strokes examining childhood/premorbid IQ, SES, and education. Two reviewers independently screened full texts and extracted and cross-checked data, including available risk factor adjustments. We meta-analyzed stroke risk using hazard ratios (HR), odds ratios (OR), and mean differences (MD). We tested effects of study and participant characteristics in sensitivity analyses and meta-regression, and assessed heterogeneity and publication bias.

RESULTS

We identified 90 studies examining stroke risk and education (79), SES (10), or IQ (nine) including approximately 164,683 stroke and over 5 million stroke-free participants. Stroke risk increased with lower education (OR = 1.35, 95% CI = 1.24, 1.48), SES (OR = 1.28, 95% CI = 1.12, 1.46), and IQ (HR = 1.17, 95% CI = 1.00, 1.37) in studies reporting point estimates, with similar associations for MD. We found minimal publication bias. Between-study heterogeneity was partly explained by participant age and case ascertainment method.

CONCLUSIONS

Education, childhood SES, and intelligence have modest but important associations with lifetime stroke, and hence dementia, risks. Future studies distinguishing between the individual and combined effects of education, childhood SES and intelligence are needed to determine the independent contribution of each factor to stroke risk. See video abstract at, http://links.lww.com/EDE/B210.

Identification of Risk Factors of Multidrug-Resistant Tuberculosis by using Classification Tree Method

Multidrug-resistant tuberculosis (MDR-TB) has become a major public health problem. We tried to apply the classification tree model in building and evaluating a risk prediction model for MDR-TB. In this case-control study, 74 newly diagnosed MDR-TB patients served as the case group, and 95 patients without TB from the same medical institution served as the control group. The classification tree model was built using Chi-square Automatic Interaction Detectormethod and evaluated by income diagram, index map, risk statistic, and the area under receiver operating characteristic (ROC) curve. Four explanatory variables (history of exposure to TB patients, family with financial difficulties, history of other chronic respiratory diseases, and history of smoking) were included in the prediction model. The risk statistic of misclassification probability of the model was 0.160, and the area under ROC curve was 0.838 (P < 0.01). These suggest that the classification tree model works well for predicting MDR-TB. Classification tree model can not only predict the risk of MDR-TB effectively but also can reveal the interactions among variables.

Stroke screening and health-related physical fitness testing in medical staff members in Urumqi, China

Objective

Stroke is the leading cause of death and disability, and is closely related to a lack of exercise. Currently, most Chinese medical staff members lack exercise and may be at risk for stroke. We sought to determine the risk factors for stroke and study the significance of health-related physical fitness testing in stroke prevention among Chinese medical staff members.

Methods

A total of 627 subjects from Urumqi, Xinjiang, China, were included in the study and a survey was conducted from 1st January 2016 to 1st February 2016. Stroke screening and health-related physical fitness testing were completed according to the standard protocol, and the related data were analyzed.

Results

Based on the screening, 27.6% (n = 173) of the subjects were at high risk for stroke. The top risk factors for stroke in these subjects were dyslipidemia, lack of exercise or mild physical activity, being overweight or obese, and high blood pressure. Body weight, body mass index, body fat, visceral fat area, body fat percentage, and basal metabolic rate were significantly higher (P < 0.01) in subjects at high risk for stroke than in subjects who were not at high risk. Lung capacity, step index, grip test, vertical jump, and sit-up/push-up index were significantly lower (P < 0.01) in subjects at high risk for stroke than in subjects who were not at high risk.

Conclusions

A large proportion of China's on-the-job medical personnel is at high risk for stroke. This may be related to the nature of the profession and warrants more attention from the society. The health-related physical fitness measurement parameters in subjects at high risk for stroke were significantly different from those in subjects who were not at high risk. Screening and health-related physical fitness testing in medical staff members may contribute to stroke prevention. More rigorous controlled clinical trials will be needed in the future.

The effect of additional training on motor outcomes at discharge from recovery phase rehabilitation wards: a survey from multi-center stroke data bank in Japan

Objectives

The purpose of the present study was to examine the potential benefits of additional training in patients admitted to recovery phase rehabilitation ward using the data bank of post-stroke patient registry.

Subjects and Methods

Subjects were 2507 inpatients admitted to recovery phase rehabilitation wards between November 2004 and November 2010. Participants were retrospectively divided into four groups based upon chart review; patients who received no additional rehabilitation, patients who were added with self-initiated off hours training, patients who were added with off hours training by ward staff, patients who received both self-initiated training and training by ward staff. Parameters for assessing outcomes included length of stay, motor/cognitive subscales of functional independent measures (FIM) and motor benefit of FIM calculated by subtracting the score at admission from that at discharge.

Results

Participants were stratified into three groups depending on the motor FIM at admission (≦28, 29∼56, 57≦) for comparison. Regarding outcome variables, significant inter-group differences were observed in all items examined within the subgroup who scored 28 or less and between 29 and 56. Meanwhile no such trends were observed in the group who scored 57 or more compared with those who scored less. In a decision tree created based upon Exhaustive Chi-squared Automatic Interaction Detection method, variables chosen were the motor FIM at admission (the first node) additional training (the second node), the cognitive FIM at admission(the third node).

Conclusions

Overall the results suggest that additional training can compensate for the shortage of regular rehabilitation implemented in recovery phase rehabilitation ward, thus may contribute to improved outcomes assessed by motor FIM at discharge.

Association of Sterol Regulatory Element-Binding Transcription Factor Gene Polymorphisms with Ischaemic Stroke

OBJECTIVE: To explore the association between polymorphisms of the sterol regulatory element-binding transcription factor ( SREBF) gene and ischaemic stroke. METHODS: The SREBF1c 54G>C and SREBPF2 1784G>C genotypes were assessed using restriction fragment length polymorphism analysis in 446 Han Chinese ischaemic stroke patients and 355 Han Chinese control subjects without cerebrovascular disease. RESULTS: The frequencies of the SREBF2 1784G>C CC genotype and the C allele were significantly higher in the ischaemic stroke group than in controls. Patients with ischaemic stroke who had the SREBF2 1784G>C CC genotype had significantly lower high-density lipoprotein (HDL) levels, compared with ischaemic stroke patients and control subjects with the GC or GG genotypes. Multivariate logistic regression analysis revealed a significant positive association between SREBF2 1784G>C and ischaemic stroke; an inverse association was observed between HDL level and risk of ischaemic stroke. CONCLUSIONS: The CC genotype of the SREBF2 1784G>C polymorphism was associated with an increased risk of ischaemic stroke, possibly through decreasing the HDL level, which was inversely associated with the risk of ischaemic stroke.