1
|
Lin L, Liu K, Feng H, Li J, Chen H, Zhang T, Xue B, Si J. Glucose trajectory prediction by deep learning for personal home care of type 2 diabetes mellitus: modelling and applying. MATHEMATICAL BIOSCIENCES AND ENGINEERING : MBE 2022; 19:10096-10107. [PMID: 36031985 DOI: 10.3934/mbe.2022472] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Glucose management for people with type 2 diabetes mellitus is essential but challenging due to the multi-factored and chronic disease nature of diabetes. To control glucose levels in a safe range and lessen abnormal glucose variability efficiently and economically, an intelligent prediction of glucose is demanding. A glucose trajectory prediction system based on subcutaneous interstitial continuous glucose monitoring data and deep learning models for ensuing glucose trajectory was constructed, followed by the application of personalised prediction models on one participant with type 2 diabetes in a community. The predictive accuracy was then assessed by RMSE (root mean square error) using blood glucose data. Changes in glycaemic parameters of the participant before and after model intervention were also compared to examine the efficacy of this intelligence-aided health care. Individual Recurrent Neural Network model was developed on glucose data, with an average daily RMSE of 1.59 mmol/L in the application segment. In terms of the glucose variation, the mean glucose decreased by 0.66 mmol/L, and HBGI dropped from 12.99 × 102 to 9.17 × 102. However, the participant also had increased stress, especially in eating and social support. Our research presented a personalised care system for people with diabetes based on deep learning. The intelligence-aided health management system is promising to enhance the outcome of diabetic patients, but further research is also necessary to decrease stress in the intelligence-aided health management and investigate the stress impacts on diabetic patients.
Collapse
Affiliation(s)
- Lingmin Lin
- School of Basic Medical Sciences, Tianjin Medical University, Tianjin, China
- School of Brain Science and Brain Medicine, Zhejiang University, Hangzhou, China
| | - Kailai Liu
- College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, China
| | - Huan Feng
- School of Medical Humanities, Tianjin Medical University, Tianjin, China
| | - Jing Li
- NHC Key Laboratory of Hormones and Development, Tianjin Key Laboratory of Metabolic Diseases, Chu Hsien-I Memorial Hospital & Tianjin Institute of Endocrinology, Tianjin Medical University, Tianjin 300134, China
| | - Hengle Chen
- School of Basic Medical Sciences, Tianjin Medical University, Tianjin, China
| | - Tao Zhang
- School of Biomedical Engineering and Technology, Tianjin Medical University, Tianjin, China
| | - Boyun Xue
- School of Biomedical Engineering and Technology, Tianjin Medical University, Tianjin, China
| | - Jiarui Si
- School of Basic Medical Sciences, Tianjin Medical University, Tianjin, China
| |
Collapse
|
2
|
O'Connor EA, Evans CV, Rushkin MC, Redmond N, Lin JS. Behavioral Counseling to Promote a Healthy Diet and Physical Activity for Cardiovascular Disease Prevention in Adults With Cardiovascular Risk Factors: Updated Evidence Report and Systematic Review for the US Preventive Services Task Force. JAMA 2020; 324:2076-2094. [PMID: 33231669 DOI: 10.1001/jama.2020.17108] [Citation(s) in RCA: 72] [Impact Index Per Article: 18.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/19/2022]
Abstract
IMPORTANCE Cardiovascular disease is the leading cause of death in the US, and poor diet and lack of physical activity are major factors contributing to cardiovascular morbidity and mortality. OBJECTIVE To review the benefits and harms of behavioral counseling interventions to improve diet and physical activity in adults with cardiovascular risk factors. DATA SOURCES MEDLINE, PubMed, PsycINFO, and the Cochrane Central Register of Controlled Trials through September 2019; literature surveillance through July 24, 2020. STUDY SELECTION English-language randomized clinical trials (RCTs) of behavioral counseling interventions to help people with elevated blood pressure or lipid levels improve their diet and increase physical activity. DATA EXTRACTION AND SYNTHESIS Data were extracted from studies by one reviewer and checked by a second. Random-effects meta-analysis and qualitative synthesis were used. MAIN OUTCOMES AND MEASURES Cardiovascular events, mortality, subjective well-being, cardiovascular risk factors, diet and physical activity measures (eg, minutes of physical activity, meeting physical activity recommendations), and harms. Interventions were categorized according to estimated contact time as low (≤30 minutes), medium (31-360 minutes), and high (>360 minutes). RESULTS Ninety-four RCTs were included (N = 52 174). Behavioral counseling interventions involved a median of 6 contact hours and 12 sessions over the course of 12 months and varied in format and dietary recommendations; only 5% addressed physical activity alone. Interventions were associated with a lower risk of cardiovascular events (pooled relative risk, 0.80 [95% CI, 0.73-0.87]; 9 RCTs [n = 12 551]; I2 = 0%). Event rates were variable; in the largest trial (Prevención con Dieta Mediterránea [PREDIMED]), 3.6% in the intervention groups experienced a cardiovascular event, compared with 4.4% in the control group. Behavioral counseling interventions were associated with small, statistically significant reductions in continuous measures of blood pressure, low-density lipoprotein cholesterol levels, fasting glucose levels, and adiposity at 12 to 24 months' follow-up. Measurement of diet and physical activity was heterogeneous, and evidence suggested small improvements in diet consistent with the intervention recommendation targets but mixed findings and a more limited evidence base for physical activity. Adverse events were rare, with generally no group differences in serious adverse events, any adverse events, hospitalizations, musculoskeletal injuries, or withdrawals due to adverse events. CONCLUSIONS AND RELEVANCE Medium- and high-contact multisession behavioral counseling interventions to improve diet and increase physical activity for people with elevated blood pressure and lipid levels were effective in reducing cardiovascular events, blood pressure, low-density lipoproteins, and adiposity-related outcomes, with little to no risk of serious harm.
Collapse
Affiliation(s)
- Elizabeth A O'Connor
- Kaiser Permanente Evidence-based Practice Center, Center for Health Research, Kaiser Permanente, Portland, Oregon
| | - Corinne V Evans
- Kaiser Permanente Evidence-based Practice Center, Center for Health Research, Kaiser Permanente, Portland, Oregon
| | - Megan C Rushkin
- Kaiser Permanente Evidence-based Practice Center, Center for Health Research, Kaiser Permanente, Portland, Oregon
| | - Nadia Redmond
- Kaiser Permanente Evidence-based Practice Center, Center for Health Research, Kaiser Permanente, Portland, Oregon
| | - Jennifer S Lin
- Kaiser Permanente Evidence-based Practice Center, Center for Health Research, Kaiser Permanente, Portland, Oregon
| |
Collapse
|
3
|
Zhang YB, Pan XF, Chen J, Cao A, Xia L, Zhang Y, Wang J, Li H, Liu G, Pan A. Combined lifestyle factors, all-cause mortality and cardiovascular disease: a systematic review and meta-analysis of prospective cohort studies. J Epidemiol Community Health 2020; 75:92-99. [PMID: 32892156 DOI: 10.1136/jech-2020-214050] [Citation(s) in RCA: 59] [Impact Index Per Article: 14.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/05/2020] [Revised: 07/19/2020] [Accepted: 08/24/2020] [Indexed: 12/14/2022]
Abstract
INTRODUCTION Unhealthy lifestyles caused a huge disease burden. Adopting healthy lifestyles is the most cost-effective strategy for preventing non-communicable diseases. The aim was to perform a systematic review and meta-analysis to quantify the relationship of combined lifestyle factors (eg, cigarette smoking, alcohol consumption, physical activity, diet and overweight/obesity) with the risk of all-cause mortality, cardiovascular mortality and incident cardiovascular disease (CVD). METHODS PubMed and EMBASE were searched from inception to April 2019. Cohort studies investigating the association between the combination of at least three lifestyle factors and all-cause mortality, cardiovascular mortality or incidence of CVD were filtered by consensus among reviewers. Pairs of reviewers independently extracted data and evaluated study quality. Random-effects models were used to pool HRs. Heterogeneity and publication bias were tested. RESULTS In total, 142 studies were included. Compared with the participants with the least-healthy lifestyles, those with the healthiest lifestyles had lower risks of all-cause mortality (HR=0.45, 95% CI 0.41 to 0.48, 74 studies with 2 584 766 participants), cardiovascular mortality (HR=0.42, 95% CI 0.37 to 0.46, 41 studies with 1 743 530 participants), incident CVD (HR=0.38, 95% CI 0.29 to 0.51, 22 studies with 754 894 participants) and multiple subtypes of CVDs (HRs ranging from 0.29 to 0.45). The associations were largely significant and consistent among individuals from different continents, racial groups and socioeconomic backgrounds. CONCLUSIONS Given the great health benefits, comprehensively tackling multiple lifestyle risk factors should be the cornerstone for reducing the global disease burden.
Collapse
Affiliation(s)
- Yan-Bo Zhang
- Department of Epidemiology and Biostatistics, Key Laboratory of Environment and Health, Ministry of Education & Ministry of Environmental Protection, State Key Laboratory of Environmental Health (Incubating), School of Public Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Xiong-Fei Pan
- Department of Epidemiology and Biostatistics, Key Laboratory of Environment and Health, Ministry of Education & Ministry of Environmental Protection, State Key Laboratory of Environmental Health (Incubating), School of Public Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.,Division of Epidemiology, Department of Medicine, Vanderbilt University Medical Center, Nashville, Tennessee, USA
| | - Junxiang Chen
- Department of Epidemiology and Biostatistics, Key Laboratory of Environment and Health, Ministry of Education & Ministry of Environmental Protection, State Key Laboratory of Environmental Health (Incubating), School of Public Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Anlan Cao
- Department of Epidemiology and Biostatistics, Key Laboratory of Environment and Health, Ministry of Education & Ministry of Environmental Protection, State Key Laboratory of Environmental Health (Incubating), School of Public Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Lu Xia
- Department of Epidemiology and Biostatistics, Key Laboratory of Environment and Health, Ministry of Education & Ministry of Environmental Protection, State Key Laboratory of Environmental Health (Incubating), School of Public Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Yuge Zhang
- Department of Epidemiology and Biostatistics, Key Laboratory of Environment and Health, Ministry of Education & Ministry of Environmental Protection, State Key Laboratory of Environmental Health (Incubating), School of Public Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Jing Wang
- Department of Forensic Medicine, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Huiqi Li
- Department of Epidemiology and Biostatistics, Key Laboratory of Environment and Health, Ministry of Education & Ministry of Environmental Protection, State Key Laboratory of Environmental Health (Incubating), School of Public Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Gang Liu
- Department of Nutrition and Food Hygiene, Hubei Key Laboratory of Food Nutrition and Safety, Ministry of Education Key Lab of Environment and Health, School of Public Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - An Pan
- Department of Epidemiology and Biostatistics, Key Laboratory of Environment and Health, Ministry of Education & Ministry of Environmental Protection, State Key Laboratory of Environmental Health (Incubating), School of Public Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| |
Collapse
|