Table 1.

Statistical methods for predicting diabetic foot

Author	Statistical methods	Purpose	Prediction Result Methods
Iztok Štotl, (2020)[10]	Logistic Regression	It is used to analyze the relationship between multiple independent variables (such as age, gender, duration of illness, blood glucose level, etc.) and the dependent variable (whether diabetic foot occurs), in order to identify the independent risk factors for diabetic foot	Age, duration of diabetes, and blood glucose levels are important risk factors for the occurrence of diabetic foot. Gender indirectly affects the risk of diabetic foot by influencing susceptibility to complications
Peta Ellen Tehan, (2022) [11]	Correlation coefficient	It can clarify the risk of developing diabetic foot and its underlying causes, improving the prediction accuracy and reliability of the model	There is a positive correlation between the risk of diabetic foot and factors such as age, duration of diabetes, blood glucose levels, history of foot ulcers, and history of foot amputations
Fan Hu, (2021) [12]	ROC Curve Analysis	By depicting the relationship between different classification thresholds, it can comprehensively demonstrate the performance of the prediction model and determine the optimal diagnostic threshold for diabetic foot	More accurately distinguishing between patients with diabetic foot and those without diabetic foot
Jun Ho Lee, (2020) [13]	Chi-Square Test	Research has found a correlation between different foot care habits and the occurrence of diabetic foot	There is a strong correlation between poor foot care habits and the occurrence of diabetic foot
Qusai Aljarrah, (2022) [14]	T-test	Study the differences in glycated hemoglo- Aljarrah (2022) [14] bin levels between patients with diabetic foot and those without diabetic foot	There is a significant difference in the mean glycated hemoglobin levels between patients with diabetic foot and those without diabetic "foot".
Lihong Chen, (2023) [15]	Kaplan–Chen Meier Curve	Perform survival analysis on the occurrence time or progression of diabetic foot to describe the survival probabilities of patients in different risk groups	The faster the speed and the greater the magnitude of the decline in the curve, the higher the risk of developing diabetic foot
Zahraa Mansoor, (2022) [16]	Mean and Standard Deviation	It can describe the central tendency of the dataset, reflect the degree of data dispersion, determine weight allocation, and assess the stability of diabetic foot prediction models	variable with a smaller standard deviation implies that the data is more concentrated, and the prediction model is more likely to capture this trend
Flora Mbela Lusendi, (2022) Regression [17]	Cox Proportional Hazards Regression Model	Analyze the relationship between the risk of diabetic foot occurrence and time, while considering the influence of other covariates	A long disease duration is a risk factor for the occurrence of diabetic foot