Kadiyala et al. analyzed the negative effects of long-distance running among college teachers and the ways in which an intelligent injury prevention and healthcare intervention model can decrease the amount of common running injuries. The researchers specifically chose college teachers with recent data showing the mental and emotional impact of teaching on teachers; running is a helpful remedy to these problems. Therefore, Kadiyala et al. sought to design an intelligent machine learning based prevention and healthcare intervention model (ML-PHIM). The ML-PHIM included the usage of a wireless sensor network (WSN), which allowed the researchers to collect physiological gait data from the runners and detect abnormalities in stride. A principal component analysis (PCA) was also used to extract specific features of the images produced by the WSN; the PCA specifically highlighted patterns and reduced noise. The support vector machine (SVM) was utilized for injury classification, specifically detecting running form abnormalities to denote the severity and type of injury prone to occur given a model. When Kadiyala et al. tested ML-PHIM in MATLAB with gait and injury monitoring dataset, ML-PHIM was able to achieve 94% accuracy, 97% precision, and 98% recall, which outclassed previous methods to determine safety of gait and running form. The researchers intended for the model to promote faster recovery and support long term health goals with detection of form abnormalities with college teachers, and the model was quite successful in determining this.