Effect of Artificial Intelligence-based Health Education Accurately Linking System (AI-HEALS) for Type 2 diabetes self-management: protocol for a mixed-methods study.

BACKGROUND: Patients with type 2 diabetes (T2DM) have an increasing need for personalized and Precise management as medical technology advances. Artificial intelligence (AI) technologies on mobile devices are being developed gradually in a variety of healthcare fields. As an AI field, knowledge graph (KG) is being developed to extract and store structured knowledge from massive data sets. It has great prospects for T2DM medical information retrieval, clinical decision-making, and individual intelligent question and answering (QA), but has yet to be thoroughly researched in T2DM intervention. Therefore, we designed an artificial intelligence-based health education accurately linking system (AI-HEALS) to evaluate if the AI-HEALS-based intervention could help patients with T2DM improve their self-management abilities and blood glucose control in primary healthcare. METHODS: This is a nested mixed-method study that includes a community-based cluster-randomized control trial and personal in-depth interviews. Individuals with T2DM between the ages of 18 and 75 will be recruited from 40-45 community health centers in Beijing, China. Participants will either receive standard diabetes primary care (SDPC) (control, 3 months) or SDPC plus AI-HEALS online health education program (intervention, 3 months). The AI-HEALS runs in the WeChat service platform, which includes a KBQA, a system of physiological indicators and lifestyle recording and monitoring, medication and blood glucose monitoring reminders, and automated, personalized message sending. Data on sociodemography, medical examination, blood glucose, and self-management behavior will be collected at baseline, as well as 1,3,6,12, and 18 months later. The primary outcome is to reduce HbA1c levels. Secondary outcomes include changes in self-management behavior, social cognition, psychology, T2DM skills, and health literacy. Furthermore, the cost-effectiveness of the AI-HEALS-based intervention will be evaluated. DISCUSSION: KBQA system is an innovative and cost-effective technology for health education and promotion for T2DM patients, but it is not yet widely used in the T2DM interventions. This trial will provide evidence on the efficacy of AI and mHealth-based personalized interventions in primary care for improving T2DM outcomes and self-management behaviors. TRIAL REGISTRATION: Biomedical Ethics Committee of Peking University: IRB00001052-22,058, 2022/06/06; Clinical Trials: ChiCTR2300068952, 02/03/2023.

Organochlorine pesticides and polycyclic aromatic hydrocarbons in serum of Beijing population: Exposure and health risk assessment.

Organochlorine pesticides (OCPs) and polycyclic aromatic hydrocarbons (PAHs) are widespread environmental contaminants, but large-scale human biomonitoring and health risk assessment data on these contaminants remain limited. In this study, concentrations of 6 OCPs and 5 PAHs were determined by GC-MS/MS in 1268 human serum samples which were collected from the participants in 2017 Beijing Chronic Disease and Risk Factor Surveillance. The detection frequencies of OCPs and PAHs ranged from 64.7 % to 96.5 % and 89.4 % to 99.6 %, respectively. The most abundant contaminants in OCPs and PAHs were pentachlorophenol (PCP) and pyrene (Pyr) with median concentrations reaching up to 3.13 and 8.48 µg/L, respectively. Nonparametric tests were employed to assess the correlations among contaminants levels, demographic characteristics (age, gender, body mass index, residence) and serum biochemical indexes. Significantly higher serum levels of all PAHs were observed in suburb residents than that in urban residents (P < 0.001). Binary logistic regression analysis demonstrated that exposure to benzo(a)pyrene (OR 2.17 [1.29, 3.63]), phenanthrene (OR 1.06 [1.02, 1.11]), fluoranthene (OR 1.04 [1.02, 1.07]) and Pyr (OR 1.02 [1.01, 1.03]) might increase the occurrence of hyperglycemia, and exposure to hexachlorobenzene (HCB) (OR 1.53 [1.05, 2.22]) and pentachlorobenzene (OR 1.14 [1.02, 1.27]) were positively associated with hyperlipidemia. Furthermore, the hazard quotients (HQs) for serum HCB, PCP and p,p'-dichlorodiphenyldichloroethylene were calculated based on health-based guidance values to predict health risks. 0.2 % and 4.3 % of serum samples showed HQ values exceeding 1 for HCB and PCP, respectively, in case of the non-carcinogenic risk, while 23.1 % of HQs for HCB were above 1 in case of the carcinogenic risk for a risk level 10-5. Our study reveals that the body burden of the Beijing general population relative to OCPs and PAHs was nonnegligible. The past exposure of HCB and PCP might adversely affect the health status of the Beijing population.

Prevalence and Related Factors of Metabolic Syndrome in Beijing, China (Year 2017).

OBJECTIVE: Metabolic syndrome (MetS) is one of the major public health problems worldwide. The aim of this study was to investigate the prevalence and associated risk factors of MetS in Beijing to formulate targeted policies. METHODS: Data from the 2017 Beijing Chronic Disease and Risk Factors Surveillance were used in this study, in which multistage stratified cluster sampling was adopted to collect a representative sample of 12,597 Beijing residents aged from 18 to 79 years. According to the definition of the International Diabetes Federation, the weighted prevalence of MetS and clustering of MetS components were estimated. The Rao-Scott adjusted χ2 test was used to test differences in MetS and components rates, and complex sampling unconditional logistic regression was used to explore influencing factors of MetS. RESULTS: The prevalence of MetS was 25.59% (95% CI 23.77-27.41), and the proportion of men and women was 30.53% (95% CI 28.32-32.75) and 20.44% (95% CI 18.29-22.58), respectively. The proportion of central obesity, high fasting plasma glucose, high triglyceride, low high-density lipoprotein cholesterol, and high blood pressure (BP) was 42.02, 27.96, 32.87, 27.25, and 43.06%, respectively. A total of 29.60% (95% CI 27.55-31.74) participants presented at least three components of MetS. The results from complex sampling unconditional logistic regression revealed that the risk factors for having MetS included being 45-59 years old, being 60-79 years old, being male, living in a rural area, education with junior middle school level, education with primary school or below level, harmful use of alcohol, inappropriate sleep time, and having an unhealthy waist-to-height ratio (WHtR); the OR values were 1.55 (95% CI 1.32-1.81), 1.94 (95% CI 1.62-2.31), 1.51 (95% CI 1.34-1.70), 1.27 (95% CI 1.06-1.52), 1.38 (95% CI 1.13-1.68), 1.44 (95% CI 1.13-1.84), 1.50 (95% CI 1.14-1.99), 1.23 (95% CI 1.10-1.37), and 238.20 (95% CI 92.54-613.12), respectively. CONCLUSIONS: The prevalence of MetS is still in a rising trend in Beijing. Strategies aimed at prevention and control of high BP should be prioritized to reduce the occurrence of MetS. WHtR is more important to evaluate MetS. Health education and personalized lifestyle intervention should be promoted to keep a healthy WHtR and waist circumference. An appropriate sleep time should be kept, and harmful alcohol drinkers should limit or abstain from alcohol.

Weight underestimation for adults in Beijing and its association with chronic disease awareness and weight management.

BACKGROUND: Obesity is known to be a risk factor to a variety of chronic diseases. Weight misperception has an impact on weight-loss attitude and behavior. We aimed to investigate factors associated with weight underestimation, and to assess the effect of hypertension, diabetes and dyslipidemia awareness on weight underestimation and weight management for overweight and obese adults. METHODS: Data was obtained from the 2011 Beijing Non-communicable disease and risk factors Surveillance (BJNCDRS). A total of 19,932 participants with measures of weight and height were included in the analysis. Self-perception of weight was obtained by asking, "How do you describe your weight?", and the question for weight management was "Are you taking any actions to control your body weight?". Multiple logistic regression was used to investigate factors related to weight underestimation. RESULTS: For the underweight, normal weight, and overweight/obese categories, more than half of the participants perceived their weight accurately (63.6, 53.8, 66.2%, respectively). For overweight and obese adults, older age, male, rural residence, lower level of education, lower level of income, absence of hypertension, presence of diabetes and absence of dyslipidemia positively associated with weight underestimation, and awareness of having hypertension and dyslipidemia were negatively associated with weight underestimation (Adjusted OR(95%CI) were 0.70(0.61~ 0.79) and 0.71(0.62~ 0.80), respectively). Awareness of having hypertension and dyslipidemia were significantly associated with weight management (Adjusted OR (95%CI) were 1.42(1.25~ 1.62) and 1.53(1.36~ 1.72), respectively). There was no significant association between awareness of diabetes and weight underestimation(P > 0.05) or weight management(P > 0.05). CONCLUSIONS: More than half of the participants perceived their weight accurately. For overweight/obese population, awareness of having hypertension and dyslipidemia could improve weight perception and weight management, whereas awareness of having diabetes might not.

[Effect of intervention program on stroke regarding blood pressure control among Beijing community population at high-risk].

OBJECTIVE: To evaluate the effect of blood pressure intervention program on stroke among high risk population aged 45-79 at the community level, in Beijing. METHODS: 7604 subjects were followed and given specific advice according to the situation of each individual, every month. Data regarding average blood pressure, number of hypertension control and the incidence of stroke among people in the community, were recorded and analyzed. RESULTS: Prior to the follow-up program, the hypertension prevalence was 64.1% but both the systolic and diastolic blood pressure showed a reduction of 2.9 and 1.5 mm Hg, respectively after the intervention program was implemented,with t value as -20.987, -15.494, respectively, and P values were both 0.000. Decrease of BP at the first four follow-up experiences was more obvious. Decrease of systolic blood pressure appeared more in elderly (F value was 14.287, and P value was 0.000), in males (t value was -2.885, P value was 0.004), people living in suburban areas (t value was 5.314, P value was 0.000) and with poorer education (t value was -6.943, P value was 0.000). However, decrease of diastolic blood pressure was seen more in younger age population (F value was 22.864, P value was 0.000), in males (t value was -2.259, P value was 0.024) and those having received better education (t value was 2.428, P value was 0.015). Rate regarding hypertension control increased from 67.7% to 87.9% after the intervention program was implemented (chi2 value was 324.595, P value was 0.000). Incidence of stroke was 2.7 per thousand and seen higher in suburban area (chi2 value was 5.293, P value was 0.021). CONCLUSION: Community intervention program on hypertension could both reduce the blood pressure and the incidence rate of stroke among high-risk population. The earlier the blood pressure intervention program started, the better the effect would be seen. Reduction of blood pressure in males seemed more obvious. In order to prevent or delay the occurrence of stroke, knowledge on hypertension prevention should be improved among populations at high risk. Individualized and comprehensive follow-up management programs should be strengthened among the community health care takers.

[Prevalence rates and risk factors on stroke among 50 - 79 years-olds in Beijing, 2011].

OBJECTIVE: To investigate the prevalence and risk factors of stroke among population aged 50 - 79 in Beijing, 2011. METHODS: 38 532 subjects were randomly selected with cluster sampling method, under the proportion to the population size (PPS). Each participant was invited to receive face to face standardized questionnaire interview, physical examination and neck ultrasonography. RESULTS: The standardized prevalence of stroke was 9.3%, with 11.5% and 8.1% for males and females respectively. The prevalence rate increased with age and was higher in males, in suburb areas and people with poor education. Ischemic stroke accounted for 80.8% of all the stroke cases, with 16.6% of the patients had one recur. The standardized prevalence rates of hypertension, dyslipidemia, obesity, diabetes mellitus were 80.7%, 29.6%, 22.9%, 16.9%, respectively. The prevalence rates of hypertension, dyslipidemia, obesity, diabetes mellitus, migraine, heart disease, carotid stenosis, sleep apnea, peripheral cascular disease, ischemic eye disease, high homocysteine level (HHE) and sickle cell anemia among stroke patients were 89.3%, 39.7%, 25.4%, 25.4%, 21.4%, 23.7%, 13.2%, 6.4%, 6.5%, 5.9%, 0.3%, 0.3%, respectively, all higher than those without the disease. 47.9 percent of the stroke patients had 3 or more chronic diseases with more risk factors. CONCLUSION: People who were 50 to 79 years old and living in Beijing had both higher prevalence and recurrence rate of stroke, with the main type as ischemic stroke. Compared with urban area, the situation in suburb was more serious. Stroke patients had more risk factors. The top four relevant chronic diseases of stroke patients were hypertension, dyslipidemia, obesity and diabetes mellitus. In order to reduce or delay the occurrence or recurrence of stroke, lifestyle intervention programs should be adopted to control related chronic diseases at their early stages.