BACKGROUND AND OBJECTIVE:Artificial intelligence (AI) is widely applied in medical decision support systems. AI also plays an essential role in snakebite identification (SI). To date, no review has been conducted on AI-based SI. This work aims to identify, compare, and summarize the state-of-the-art AI methods in SI. Another objective is to analyze these methods and propose solutions for future directions. METHODS:Searches were performed in PubMed, Web of Science, Engineering Village, and IEEE Xplore to identify the SI studies. The datasets, preprocessing, feature extraction, and classification algorithms of these studies were systematically reviewed. Then, their merits and defects were also analyzed and compared. Next, the quality of these studies was assessed by using the ChAIMAI checklist. Finally, solutions were proposed based on the limitations of current studies. RESULTS:Twenty-six articles were included in the review. Traditional machine learning (ML) and deep learning (DL) algorithms were applied for the classification of snake images (Acc = 72 %∼98 %), wound images (Acc = 80 %∼100 %), and other modalities of information (Acc = 71.67 %∼97.6 %). According to the research quality assessment, one of the studies was considered to be of high quality. Most studies were flawed in data preparation, data understanding, validation, and deployment dimensions. In addition, we propose an active perception-based system framework for collecting images and bite forces and constructing a multi-modal dataset named "Digital Snake" to address the lack of high-quality datasets for DL algorithms to improve recognition accuracy and robustness. A Snakebite Identification, Treatment, and Management Assistive Platform architecture is also proposed as a decision support system for patients and doctors. CONCLUSIONS:AI-based methods can quickly and accurately decide the snake species and classify venomous and non-venomous snakes. Current studies still have limitations in SI. Future studies based on AI methods should focus on constructing high-quality datasets and decision support systems for snakebite treatment.

Automated snake image identification is important from different points of view, most importantly, snake bite management. Auto-identification of snake images might help the avoidance of venomous snakes and also providing better treatment for patients. In this study, for the first time, it's been attempted to compare the accuracy of a series of state-of-the-art machine learning methods, ranging from the holistic to neural network algorithms. The study is performed on six snake species in Lar National Park, Tehran Province, Iran. In this research, the holistic methods [k-nearest neighbors (kNN), support vector machine (SVM) and logistic regression (LR)] are used in combination with a dimension reduction approach [principle component analysis (PCA) and linear discriminant analysis (LDA)] as the feature extractor. In holistic methods (kNN, SVM, LR), the classifier in combination with PCA does not yield an accuracy of more than 50%, But the use of LDA to extract the important features significantly improves the performance of the classifier. A combination of LDA and SVM (kernel = 'rbf') is achieved to a test accuracy of 84%. Compared to holistic methods, convolutional neural networks show similar to better performance, and accuracy reaches 93.16% using MobileNetV2. Visualizing intermediate activation layers in VGG model reveals that just in deep activation layers, the color pattern and the shape of the snake contribute to the discrimination of snake species. This study presents MobileNetV2 as a powerful deep convolutional neural network algorithm for snake image classification that could be used even on mobile devices. This finding pave the road for generating mobile applications for snake image identification.