An Efficacy Predictive Method for Diabetic Ulcers Based on Higher-Order Markov Chain-Set Pair Analysis

Area of Science:

• Biomedical Engineering
• Computational Medicine
• Traditional Chinese Medicine

Background:

• Diabetic ulcer management requires both curative effect evaluation and prediction.
• Few studies have focused on predicting diabetic ulcer outcomes.
• Accurate prediction is crucial for effective clinical decision-making.

Purpose of the Study:

• To develop and validate a novel predictive model for diabetic ulcers.
• To compare the accuracy of a higher-order Markov chain-Set Pair Analysis (SPA) model against traditional methods.
• To enhance clinical decision-making in diabetic ulcer treatment.

Main Methods:

• Set Pair Analysis (SPA) was employed for curative effect evaluation, using connection degree (CD).
• A higher-order Markov chain-SPA model was developed for predicting future curative effects.
• The predictive accuracy of the higher-order model was compared with a first-order Markov-SPA model using patient data.

Main Results:

• SPA indicated improving curative effects in diabetic ulcer patients treated with Traditional Chinese Medicine (TCM).
• The higher-order Markov chain-SPA model demonstrated reduced relative errors in predictions compared to the first-order model.
• Connection degree analysis showed trends in treatment effectiveness over time.

Conclusions:

• The combination of SPA and higher-order Markov chains provides an effective method for predicting diabetic ulcer outcomes.
• This novel approach offers higher accuracy than traditional first-order prediction models.
• The proposed method is suitable for clinical application in diabetic ulcer management.