Infrared thermography (IRT) combined with advanced artificial intelligence (AI) algorithms has emerged as a promising non-invasive tool for assessing and managing diseases. Herpes zoster (HZ) and postherpetic neuralgia (PHN), a chronic neuropathic pain is condition that often follows HZ infection. This scoping review synthesizes current knowledge on the integration of IRT and AI in understanding the pathophysiology, predicting the development, and guiding the treatment of PHN. A comprehensive literature search was conducted in multiple databases from inception to May 20, 2024. Studies investigating the use of infrared thermography in herpes zoster and postherpetic neuralgia were included, with focus on recent advancements in AI applications. The review encompassed 1177 participants across various studies. We analyzed research utilizing machine learning techniques, including support vector machines, logistic regression, random forests, and deep learning models, to address the limitations identified in current HZ/PHN management practices. The review adhered to PRISMA-ScR guidelines. Findings suggest that patients with PHN exhibit distinct thermal patterns, with asymmetry between affected and unaffected dermatomes correlating more with disease duration than pain intensity. Temperature differences greater than 0.5 ℃ between affected and unaffected dermatomes were associated with a significantly increased risk of PHN development. IRT has shown promise as a predictor of PHN development in acute HZ patients and for assessing treatment response. This review introduces innovative AI approaches to standardize thermal imaging in HZ and PHN management. Novel biomarkers - Thermal Asymmetry Index (TAI), Persistent Thermal Asymmetry Index (PTAI), and Thermal Normalization Index (TNI) - are proposed, along with an Adjusted Risk Index (ARI) incorporating Age and Pain Adjustment Factors. These elements are integrated into the AI THERMO-Z protocol for standardized assessment. While requiring further validation, this framework aims to enhance the scientific rigor of thermal imaging in HZ and PHN management. IRT shows promise as a biomarker for predicting PHN in acute HZ. The proposed AI THERMO-Z protocol, integrating novel biomarkers and risk indices, aims to standardize thermal imaging assessment. Large-scale studies are needed to validate its clinical utility in HZ and PHN management. By leveraging AI, particularly machine learning models, the accuracy of IRT in detecting subtle thermal anomalies can be enhanced, providing clinicians with more precise predictive analytics and personalized treatment strategies.