Idiopathic thrombocytopenic purpura (ITP) is a common bloody disease with a high incidence in children, but its diagnostic method is exclusive diagnosis, and the existing detection techniques are mostly invasive, which may cause secondary injury to patients and also may increase the risk of disease. In order to make up for the lack of the detection method, this study made a preliminary exploration on the diagnosis of children's ITP from the perspective of infrared thermography. In this study, a total of 11 healthy children and 22 ITP children's frontal infrared thermal images were collected, and the pattern characteristic (PFD), average temperature (Troi) and maximum temperature (MAX) characteristics of 7 target areas were extracted. The weighted PFD parameters were correlated with the platelet count commonly used in clinical diagnosis, and the sensitivity and specificity of the weighted PFD parameters for children's ITP were calculated through the receiver operating characteristic curve (ROC). The final results showed that the difference of the weighted PFD parameters between healthy children and ITP children was statistically significant, and the parameters negatively correlated with platelet count. Under the ROC curve, the area under the curve (AUC) of this parameter is as high as 92.1%. Based on the research results of this paper, infrared thermography can clearly show the difference between ITP children and healthy children. It is hoped that the methods proposed in this paper can non-invasively and objectively describe the characteristics of ITP infrared thermal imaging of children, and provide a new ideas for ITP diagnosis.
Area Under Curve ; Child ; Humans ; Platelet Count ; Purpura, Thrombocytopenic, Idiopathic ; Thermography