A Study on the Artificial Intelligence Model of White Blood Cell Counts Prediction Using Gan

In this paper, an artificial intelligence model for predicting white blood cell counts that required conventional blood tests were studied using deep learning. White blood cell counts are crucial human information for knowing inflammatory levels in the body and septic shock. However, white blood cell counts require a blood test, and two hours of medical waiting time is required to confirm the test results. Therefore, emergency patients may find it difficult to receive a sufficient medical response while waiting for blood test results that can reliably confirm white blood cell counts. As a process to solve this problem, medical responses are performed based on other bio-signals and information in the medical field. However, responses differ from responses according to quantitatively provided white blood cell counts. Therefore, in this study, we conducted a study on an artificial intelligence model that predicts white blood cell counts by receiving patient bio-signals and information based on Generative Adversarial Networks (GAN) of artificial intelligence. The artificial intelligence model of this study learns non-missing data and quantitatively predicts when the data with missing white blood cell counts act as input. The verification of the model consisted of the performance when input into the artificial intelligence model by mixing the original data and missing data. The verification results showed that the mixed data group, including white blood cell counts generated through the white blood cell prediction model, had better detection performance for sepsis patients than the original data group.