487-P: AI Prediction of Chronic Kidney Disease Stage Progression Combinations for Type 2 Diabetes Mellitus

Abstract

Chronic Kidney Disease (CKD) for type 2 diabetes mellitus (T2DM) is an increasingly serious issue worldwide. CKD stage is known to progress in stages where 1 is normal and 5 is the worst case of hemodialysis. We have previously reported on the accuracy of AI technology to target CKD stage 1 patients and predict the progression to stages 2 and above. Such prediction is targeted to help identify patients who require intensive care. Such study showed maximum 0.75 AUC score. In this study, we have extended our study to investigate all other stage combinations. For example, we can set our goal to answer questions such as: "Can AI technology accurately predict stage 2 patients progressing into stage 5 (hemodialysis)?" We have investigated the EMR (Electronic Medical Record) of 64,059 type-2 diabetes patients who have visited the hospital. We have extracted 36 features, where 12 sources (e.g., Urine protein, albuminuria and eGFR) were selectively chosen by extraction from known literature and 3 types of values (mean, latest, SD) were calculated for each source. Period of 180 days range was scanned within 20% range (i.e., 180 days * 0.2 = 36 days). We balanced the label transition of each stage evenly by the number of data for each good label (no progress from current target stage) and bad label (progress from target to worse stage). We created a new prediction model for each combination (i.e., 1 to 2, 1 to 3, 1 to 4, 1 to 5, etc.) and performed cross validation by Logistic Regression to calculate the accuracy, F-Score and AUC. All the combinations showed relatively good results. The range and average of each measurements were: Accuracy 0.653 through 0.753 Average: 0.708. F-Score 0.673 through 0.754 Average:0.719. AUC 0.705 through 0.826 Average 0.770. We applied AI techniques to create new predictive model which can detect the progression for all combinations of type-2 diabetes CKD stage progression. This model may contribute by a more effective and accurate intervention to reduce hemodialysis and cardiovascular events. Disclosure K. Miyamoto: None. A. Koseki: Employee; Self; IBM. M. Kudo: Employee; Self; IBM. M. Makino: None. A. Suzuki: Research Support; Self; Chugai Pharmaceutical Co., Ltd., Kowa Company, Ltd., Ono Pharmaceutical Co., Ltd., Taisho Pharmaceutical Co., Ltd., Takeda Pharmaceutical Company Limited.