Classification of postural profiles among mouth-breathing children by learning vector quantization

A Bayesian network for estimating hypertension risk due to occupational aluminum exposure

Background

The correlation between metals and hypertension, such as sodium, zinc, potassium, and magnesium, has been confirmed, while the relationship between aluminum and hypertension is not very clear. This study aimed to evaluate the correlation between plasma aluminum and hypertension in electrolytic aluminum workers by the Bayesian networks (BN).

Methods

In 2019, 476 male workers in an aluminum factory were investigated. The plasma aluminum concentration of workers was measured by inductively coupled plasma mass spectrometry. The influencing factors on the prevalence of hypertension were analyzed by the BN.

Results

The prevalence of hypertension was 23.9% in 476 male workers. The risk of hypertension from plasma aluminum in the Q2, Q3, and Q4 groups was 5.20 (1.90-14.25), 6.92 (2.51-19.08), and 7.33 (2.69-20.01), respectively, compared with that in the Q1 group. The risk of hypertension from the duration of exposure to aluminum of >10 years was 2.23 (1.09-4.57), compared without aluminum exposure. Area under the curve was 0.80 of plasma aluminum and the duration of exposure to aluminum was based on covariates, indicating that aluminum exposure had important predictive value in the prevalence of hypertension in the occupational population. The results of the study using the BN model showed that if the plasma aluminum of all participants was higher than Q4 (≥47.86 µg/L) and the participants were drinking, smoking, diabetes, central obesity, dyslipidemia, and aged >50 years, the proportion of hypertension was 71.2%.

Conclusions

The prevalence of hypertension increased significantly with the increase of plasma aluminum level.

Prevalence and influencing factors of hyperuricemia in middle-aged and older adults in the Yao minority area of China: a cross-sectional study

Hyperuricemia (HUA) endangers human health, and its prevalence has increased rapidly in recent decades. The current study investigated HUA's prevalence and influencing factors in Gongcheng, southern China. A cross-sectional investigation was conducted; 2128 participants aged 30-93 years were included from 2018 to 2019. Univariate and multivariate logistic regression models were used to screen HUA variables. A Bayesian network model was constructed using the PC algorithm to evaluate the association between influencing factors and HUA. The prevalence of HUA was 15.6% (23.2% in men, 10.7% in women). After screening the variables using a logistic regression analysis model, fatty liver disease (FLD), dyslipidemia, abdominal obesity, creatinine (CREA), somatotype, bone mass, drinking, and physical activity level at work were included in the Bayesian network model. The model results showed that dyslipidemia, somatotype, CREA, and drinking were directly related to HUA. Bone mass and FLD were indirectly associated with HUA by affecting the somatotype. The prevalence of HUA in Gongcheng was high in China. The prevalence of HUA was related to somatotype, drinking, bone mass, physical activity level at work, and other metabolic diseases. A good diet and moderate exercise are recommended to maintain a healthy somatotype and reduce the prevalence rate of HUA.

Using Bayesian networks with Tabu-search algorithm to explore risk factors for hyperhomocysteinemia

Hyperhomocysteinemia (HHcy) is a condition closely associated with cardiovascular and cerebrovascular diseases. Detecting its risk factors and taking some relevant interventions still represent the top priority to lower its prevalence. Yet, in discussing risk factors, Logistic regression model is usually adopted but accompanied by some defects. In this study, a Tabu Search-based BNs was first constructed for HHcy and its risk factors, and the conditional probability between nodes was calculated using Maximum Likelihood Estimation. Besides, we tried to compare its performance with Hill Climbing-based BNs and Logistic regression model in risk factor detection and discuss its prospect in clinical practice. Our study found that Age, sex, α1-microgloblobumin to creatinine ratio, fasting plasma glucose, diet and systolic blood pressure represent direct risk factors for HHcy, and smoking, glycosylated hemoglobin and BMI constitute indirect risk factors for HHcy. Besides, the performance of Tabu Search-based BNs is better than Hill Climbing-based BNs. Accordingly, BNs with Tabu Search algorithm could be a supplement for Logistic regression, allowing for exploring the complex network relationship and the overall linkage between HHcy and its risk factors. Besides, Bayesian reasoning allows for risk prediction of HHcy, which is more reasonable in clinical practice and thus should be promoted.

Application of a novel hybrid algorithm of Bayesian network in the study of hyperlipidemia related factors: a cross-sectional study

Background

This article aims to understand the prevalence of hyperlipidemia and its related factors in Shanxi Province. On the basis of multivariate Logistic regression analysis to find out the influencing factors closely related to hyperlipidemia, the complex network connection between various variables was presented through Bayesian networks(BNs).

Methods

Logistic regression was used to screen for hyperlipidemia-related variables, and then the complex network connection between various variables was presented through BNs. Since some drawbacks stand out in the Max-Min Hill-Climbing (MMHC) hybrid algorithm, extra hybrid algorithms are proposed to construct the BN structure: MMPC-Tabu, Fast.iamb-Tabu and Inter.iamb-Tabu. To assess their performance, we made a comparison between these three hybrid algorithms with the widely used MMHC hybrid algorithm on randomly generated datasets. Afterwards, the optimized BN was determined to explore to study related factors for hyperlipidemia. We also make a comparison between the BN model with logistic regression model.

Results

The BN constructed by Inter.iamb-Tabu hybrid algorithm had the best fitting degree to the benchmark networks, and was used to construct the BN model of hyperlipidemia. Multivariate logistic regression analysis suggested that gender, smoking, central obesity, daily average salt intake, daily average oil intake, diabetes mellitus, hypertension and physical activity were associated with hyperlipidemia. BNs model of hyperlipidemia further showed that gender, BMI, and physical activity were directly related to the occurrence of hyperlipidemia, hyperlipidemia was directly related to the occurrence of diabetes mellitus and hypertension; the average daily salt intake, daily average oil consumption, smoking, and central obesity were indirectly related to hyperlipidemia.

Conclusions

The BN of hyperlipidemia constructed by the Inter.iamb-Tabu hybrid algorithm is more reasonable, and allows for the overall linking effect between factors and diseases, revealing the direct and indirect factors associated with hyperlipidemia and correlation between related variables, which can provide a new approach to the study of chronic diseases and their associated factors.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12889-021-11412-5.

Application of a Tabu search-based Bayesian network in identifying factors related to hypertension

The study aimed to study the related factors of hypertension using multivariate logistic regression analysis and tabu search-based Bayesian Networks (BNs). A cluster random sampling method was adopted to obtain samples of the general population aged 15 years or above. Multivariate logistic regression analysis indicated that gender, age, cultural level, body mass index (BMI), central obesity, drinking, diabetes mellitus, Myocardial infarction, Coronary heart disease, Stroke are associated with hypertension. While BNs found connections between those related factors and hypertension were established by complex network structure, age, smoking, occupation, cultural level, BMI, central obesity, drinking, diabetes mellitus, myocardial infarction, coronary heart disease, nephropathy, stroke were direct connection with hypertension, gender was indirectly linked to hypertension through drinking. The results showed that BNs can not only find out the correlative factors of hypertension but also analyze how these factors affect hypertension and their interrelationships, which is consistent with practical theory better than logistic regression and has a better application prospects.

Prevalence of hyperlipidemia in Shanxi Province, China and application of Bayesian networks to analyse its related factors

This study aimed to obtain the prevalence of hyperlipidemia and its related factors in Shanxi Province, China using multivariate logistic regression analysis and tabu search-based Bayesian networks (BNs). A multi-stage stratified random sampling method was adopted to obtain samples among the general population aged 18 years or above. The prevalence of hyperlipidemia in Shanxi Province was 42.6%. Multivariate logistic regression analysis indicated that gender, age, region, occupation, vegetable intake level, physical activity, body mass index, central obesity, hypertension, and diabetes mellitus are associated with hyperlipidemia. BNs were used to find connections between those related factors and hyperlipidemia, which were established by a complex network structure. The results showed that BNs can not only be used to find out the correlative factors of hyperlipidemia but also to analyse how these factors affect hyperlipidemia and their interrelationships, which is consistent with practical theory, is superior to logistic regression and has better application prospects.

A Systems Science Approach to Understanding Polytrauma and Blast-Related Injury: Bayesian Network Model of Data From a Survey of the Florida National Guard

We sought to further define the epidemiology of the complex, multiple injuries collectively known as polytrauma/blast-related injury (PT/BRI). Using a systems science approach, we performed Bayesian network modeling to find the most accurate representation of the complex system of PT/BRI and identify key variables for understanding the subsequent effects of blast exposure in a sample of Florida National Guard members (1,443 deployed to Operation Enduring Freedom/Operation Iraqi Freedom and 1,655 not deployed) who completed an online survey during the period from 2009 to 2010. We found that postdeployment symptoms reported as present at the time of the survey were largely independent of deployment per se. Blast exposure, not mild traumatic brain injury (TBI), acted as the primary military deployment-related driver of PT/BRI symptoms. Blast exposure was indirectly linked to mild TBI via other deployment-related traumas and was a significant risk for a high level of posttraumatic stress disorder (PTSD) arousal symptoms. PTSD arousal symptoms and tinnitus were directly dependent upon blast exposure, with both acting as bridge symptoms to other postdeployment mental health and physical symptoms, respectively. Neurobehavioral or postconcussion-like symptoms had no significant dependence relationship with mild TBI, but they were synergistic with blast exposure in influencing PTSD arousal symptoms. A replication of this analysis using a larger PT/BRI database is warranted.

Probabilistic modeling of short survivability in patients with brain metastasis from lung cancer

The prediction of substantially short survivability in patients is extremely risky. In this study, we proposed a probabilistic model using Bayesian network (BN) to predict the short survivability of patients with brain metastasis from lung cancer. A nationwide cancer patient database from 1996 to 2010 in Taiwan was used. The cohort consisted of 438 patients with brain metastasis from lung cancer. We utilized synthetic minority over-sampling technique (SMOTE) to solve the imbalanced property embedded in the problem. The proposed BN was compared with three competitive models, namely, naive Bayes (NB), logistic regression (LR), and support vector machine (SVM). Statistical analysis showed that performances of BN, LR, NB, and SVM were statistically the same in terms of all indices with low sensitivity when these models were applied on an imbalanced data set. Results also showed that SMOTE can improve the performance of the four models in terms of sensitivity, while keeping high accuracy and specificity. Further, the proposed BN is more effective as compared with NB, LR, and SVM from two perspectives: the transparency and ability to show the relation of factors affecting brain metastasis from lung cancer; it allows decision makers to find the probability despite incomplete evidence and information; and the sensitivity of the proposed BN is the highest among all standard machine learning methods.

Modeling and predicting the occurrence of brain metastasis from lung cancer by Bayesian network: a case study of Taiwan

The Bayesian network (BN) is a promising method for modeling cancer metastasis under uncertainty. BN is graphically represented using bioinformatics variables and can be used to support an informative medical decision/observation by using probabilistic reasoning. In this study, we propose such a BN to describe and predict the occurrence of brain metastasis from lung cancer. A nationwide database containing more than 50,000 cases of cancer patients from 1996 to 2010 in Taiwan was used in this study. The BN topology for studying brain metastasis from lung cancer was rigorously examined by domain experts/doctors. We used three statistical measures, namely, the accuracy, sensitivity, and specificity, to evaluate the performances of the proposed BN model and to compare it with three competitive approaches, namely, naive Bayes (NB), logistic regression (LR) and support vector machine (SVM). Experimental results show that no significant differences are observed in accuracy or specificity among the four models, while the proposed BN outperforms the others in terms of sampled average sensitivity. Moreover the proposed BN has advantages compared with the other approaches in interpreting how brain metastasis develops from lung cancer. It is shown to be easily understood by physicians, to be efficient in modeling non-linear situations, capable of solving stochastic medical problems, and handling situations wherein information are missing in the context of the occurrence of brain metastasis from lung cancer.

Decision support at home (DS@HOME)--system architectures and requirements

Background

Demographic change with its consequences of an aging society and an increase in the demand for care in the home environment has triggered intensive research activities in sensor devices and smart home technologies. While many advanced technologies are already available, there is still a lack of decision support systems (DSS) for the interpretation of data generated in home environments. The aim of the research for this paper is to present the state-of-the-art in DSS for these data, to define characteristic properties of such systems, and to define the requirements for successful home care DSS implementations.

Methods

A literature review was performed along with the analysis of cross-references. Characteristic properties are proposed and requirements are derived from the available body of literature.

Results

79 papers were identified and analyzed, of which 20 describe implementations of decision components. Most authors mention server-based decision support components, but only few papers provide details about the system architecture or the knowledge base. A list of requirements derived from the analysis is presented. Among the primary drawbacks of current systems are the missing integration of DSS in current health information system architectures including interfaces, the missing agreement among developers with regard to the formalization and customization of medical knowledge and a lack of intelligent algorithms to interpret data from multiple sources including clinical application systems.

Conclusions

Future research needs to address these issues in order to provide useful information – and not only large amounts of data – for both the patient and the caregiver. Furthermore, there is a need for outcome studies allowing for identifying successful implementation concepts.

Sensors vs. experts - a performance comparison of sensor-based fall risk assessment vs. conventional assessment in a sample of geriatric patients

Background

Fall events contribute significantly to mortality, morbidity and costs in our ageing population. In order to identify persons at risk and to target preventive measures, many scores and assessment tools have been developed. These often require expertise and are costly to implement. Recent research investigates the use of wearable inertial sensors to provide objective data on motion features which can be used to assess individual fall risk automatically. So far it is unknown how well this new method performs in comparison with conventional fall risk assessment tools. The aim of our research is to compare the predictive performance of our new sensor-based method with conventional and established methods, based on prospective data.

Methods

In a first study phase, 119 inpatients of a geriatric clinic took part in motion measurements using a wireless triaxial accelerometer during a Timed Up&Go (TUG) test and a 20 m walk. Furthermore, the St. Thomas Risk Assessment Tool in Falling Elderly Inpatients (STRATIFY) was performed, and the multidisciplinary geriatric care team estimated the patients' fall risk. In a second follow-up phase of the study, 46 of the participants were interviewed after one year, including a fall and activity assessment. The predictive performances of the TUG, the STRATIFY and team scores are compared. Furthermore, two automatically induced logistic regression models based on conventional clinical and assessment data (CONV) as well as sensor data (SENSOR) are matched.

Results

Among the risk assessment scores, the geriatric team score (sensitivity 56%, specificity 80%) outperforms STRATIFY and TUG. The induced logistic regression models CONV and SENSOR achieve similar performance values (sensitivity 68%/58%, specificity 74%/78%, AUC 0.74/0.72, +LR 2.64/2.61). Both models are able to identify more persons at risk than the simple scores.

Conclusions

Sensor-based objective measurements of motion parameters in geriatric patients can be used to assess individual fall risk, and our prediction model's performance matches that of a model based on conventional clinical and assessment data. Sensor-based measurements using a small wearable device may contribute significant information to conventional methods and are feasible in an unsupervised setting. More prospective research is needed to assess the cost-benefit relation of our approach.