Design and Development of Auxiliary Diagnosis and Prognosis Prediction Software for Hemorrhagic Stroke Based on Deep Learning

This paper mainly studies the expansion of hematoma, edema progression and prognosis prediction in hemorrhagic stroke patients, and develops an auxiliary diagnosis and prognosis prediction software based on hemorrhagic stroke. We analyzed 160 clinical data, including personal history, disease history, imaging information features, treatment-related features, location information and gray distribution of hematoma and edema, and divided them into 104 features. Firstly, the random forest algorithm was used to predict the hematoma expansion events within 48 hours. After that, BP neural network was used to predict the mRS Rating of patients after 90 days. Finally, one-way ANOVA was used to analyze the influence of different treatment methods on the trend of hematoma expansion and edema progression. Based on the above research analysis, this software is designed to assist diagnosis and prognosis prediction, which can update patient data training, predict mRS Rating of patients, hematoma expansion and edema progression and other related information, in order to give suggestions to doctors and patients, which has certain practical significance in clinical assistant diagnosis.