Abstract: To detect and prognosticate the occurrences of post-surgery infections has now become an important requirement in the field of medical sciences. It helps in making the strategies for management of the infections thereby reducing the time of hospital stay and patient morbidity. Classification of patients into high and low risk has effectively aided in leading a number of publication, researches as well as progress in the bioinformatics and biomedical field and for the study of various methods for timely identification of infection, application of Machine Learning techniques and neural networks. Among the collections of these techniques, including thresholding algorithms, Artificial Neural Networks (ANNs),machine learning algorithms usages of new technology are been used in research programs as it helps in developing predictive models with great resulting accuracy in decision making process. Being able to accurately calibrated surgical site infections (SSI) risk in medical field would be useful for two key reasons. First, it helps in determining the likelihood that a particular patient get the particular signs of surgical site infection which can be similar to the divided groups and useful in deciding the method of prevention. Second, an accuracy model/system will ease and forward the significant similarity and also the comparison of (SSI) that is surgical site infection rates within health care providers and the facilities. In the current paper, we have done a literature review of the emerging methods involved in the prediction of infection and detection of the same. These models are based on numerous unconfirmed and supervised techniques like neural networks, algorithms, thermal techniques, devices and machine learning (ML) techniques. As an emerging application of machine learning methods and thermal devices, we here describe the most up-to-date techniques used, researches made and publications referring post-operative infection models as the aim of their work which use these techniques.