Risk factor analysis and clinical decision tree model construction for diabetic retinopathy in Western China

Zhou, Yuanyuan; Zhou, Taicheng; Chen, Nan; Zhou, Guozhong; Zhou, Hongjian; Li, Xingdong; Wang, Jinrui; Bai, Chao-Fang; Liang, Rong; Xiong, Yu-Xin; Yang, Ying

doi:10.4239/wjd.v13.i11.986

Cited by 5 publications

(1 citation statement)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, as the interpretation and understanding of logistic regression model are more difficult than that of decision tree model, especially for those without experience with this particular model type, decision tree model is more recommended in clinical practice (Fu et al., 2022 ). In the diabetic population, few studies to date have used the decision tree models to predict diabetic comorbidities or complications (Kasbekar et al., 2017 ; Rinkel et al., 2020 ; Zhou et al., 2022 ), and to our knowledge, there is no study on prediction of MCI in patients with T2DM using the decision tree model. Given the growing utilization of decision trees in prediction of health‐related outcomes and the negative effects of MCI on the prognosis of T2DM patients, this study aimed to identify MCI in T2DM patients using the decision tree approach to help better identify MCI.…”

Section: Introductionmentioning

confidence: 99%

Predictive model for identifying mild cognitive impairment in patients with type 2 diabetes mellitus: A CHAID decision tree analysis

Maimaitituerxun,

Chen,

Xiang

et al. 2024

Brain and Behavior

View full text Add to dashboard Cite

BackgroundAs the population ages, mild cognitive impairment (MCI) and type 2 diabetes mellitus (T2DM) become common conditions that often coexist. Evidence has shown that MCI could lead to reduced treatment compliance, medication management, and self‐care ability in T2DM patients. Therefore, early identification of those with increased risk of MCI is crucial from a preventive perspective. Given the growing utilization of decision trees in prediction of health‐related outcomes, this study aimed to identify MCI in T2DM patients using the decision tree approach.MethodsThis hospital‐based case–control study was performed in the Endocrinology Department of Xiangya Hospital affiliated to Central South University between March 2021 and December 2022. MCI was defined based on the Petersen criteria. Demographic characteristics, lifestyle factors, and T2DM‐related information were collected. The study sample was randomly divided into the training and validation sets in a 7:3 ratio. Univariate and multivariate analyses were performed, and a decision tree model was established using the chi‐square automatic interaction detection (CHAID) algorithm to identify key predictor variables associated with MCI. The area under the curve (AUC) value was used to evaluate the performance of the established decision tree model, and the performance of multivariate regression model was also evaluated for comparison.ResultsA total of 1001 participants (705 in the training set and 296 in the validation set) were included in this study. The mean age of participants in the training and validation sets was 60.2 ± 10.3 and 60.4 ± 9.5 years, respectively. There were no significant differences in the characteristics between the training and validation sets (p > .05). The CHAID decision tree analysis identified six key predictor variables associated with MCI, including age, educational level, household income, regular physical activity, diabetic nephropathy, and diabetic retinopathy. The established decision tree model had 15 nodes composed of 4 layers, and age is the most significant predictor variable. It performed well (AUC = .75 [95% confidence interval (CI): .71–.78] and .67 [95% CI: .61–.74] in the training and validation sets, respectively), was internally validated, and had comparable predictive value compared to the multivariate logistic regression model (AUC = .76 [95% CI: .72–.80] and .69 [95% CI: .62–.75] in the training and validation sets, respectively).ConclusionThe established decision tree model based on age, educational level, household income, regular physical activity, diabetic nephropathy, and diabetic retinopathy performed well with comparable predictive value compared to the multivariate logistic regression model and was internally validated. Due to its superior classification accuracy and simple presentation as well as interpretation of collected data, the decision tree model is more recommended for the prediction of MCI in T2DM patients in clinical practice.

show abstract

Section: Introductionmentioning

confidence: 99%

Predictive model for identifying mild cognitive impairment in patients with type 2 diabetes mellitus: A CHAID decision tree analysis

Maimaitituerxun,

Chen,

Xiang

et al. 2024

Brain and Behavior

View full text Add to dashboard Cite

show abstract

Application of a Decision Tree Model for Predicting Diabetic Retinopathy

Pan,

Chen

2024

2024 IEEE 6th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)

View full text Add to dashboard Cite

Effectiveness of Internet + E-Coach chronic disease management on blood glucose, lipid levels, liver function, and quality of life in patients with chronic diabetic retinopathy: a comparative study

Yao,

Cao,

Yan

et al. 2024

BMC Ophthalmol

View full text Add to dashboard Cite

Objective This study aims to explore the effect of Internet + E-Coach chronic disease system intervention on fasting blood glucose (FPG), 2-hour postprandial blood glucose(2hPG), fasting serum insulin (FINS), triglyceride (TG), alanine transaminase (ALT) and quality of life in patients with chronic diabetic retinopathy. Methods 208 patients with chronic diabetic retinopathy who were treated in the hospital from March 2021 to March 2023 are chosen and separated into two groups by random number Table 104 patients in the control group received routine continuous intervention, and the research group received Internet + E-Coach chronic disease system intervention. The cognition of disease related knowledge, blood related indicators inflammatory factor levels and improvement of life quality between the two groups before intervention, 6 and 12 months after intervention were compared. Results Before the intervention, the comparison between the two groups in disease related knowledge scores, blood glucose, blood lipid, liver function indicators, inflammatory factor, and low vision quality of life scale (CLVQOL) scores was with P > 0.05. After 6 and 12 months of intervention, the research group had significantly higher scores for basic blood glucose intervention, healthy diet, reasonable exercise, and correct medication use compared to the control group ( P < 0.05). FPG, 2hPG, TG and ALT in the research group were lower than those in the control group. FINS were higher in the control group, with P < 0.05. Interleukin-6 (IL-6), tumor necrosis factor (TNF-α), and hypersensitive C-reactive protein (Hs-CRP) in the research group were obviously lower than those in the control group ( P < 0.05). The scores of far vision, movement and light perception, adjustment ability, reading and fine work, and daily living ability in the research group were higher than those in the control group, with P < 0.05. Conclusion The intervention of Internet + E-Coach chronic disease system can improve the knowledge of chronic diabetic retinopathy patients about their own condition, stabilize the levels of blood sugar, blood lipid and liver function indicators, reduce the inflammatory reaction of the body, and improve the quality of life.

show abstract

Risk factor analysis and clinical decision tree model construction for diabetic retinopathy in Western China

Cited by 5 publications

References 66 publications

Predictive model for identifying mild cognitive impairment in patients with type 2 diabetes mellitus: A CHAID decision tree analysis

Predictive model for identifying mild cognitive impairment in patients with type 2 diabetes mellitus: A CHAID decision tree analysis

Application of a Decision Tree Model for Predicting Diabetic Retinopathy

Effectiveness of Internet + E-Coach chronic disease management on blood glucose, lipid levels, liver function, and quality of life in patients with chronic diabetic retinopathy: a comparative study

Contact Info

Product

Resources

About