牧野 真樹

Chronic kidney disease (CKD) and heart failure (HF) are the first and most frequent comorbidities associated with mortality risks in early-stage type 2 diabetes mellitus (T2DM). However, efficient screening and risk assessment strategies for identifying T2DM patients at high risk of developing CKD and/or HF (CKD/HF) remains to be established. This study aimed to generate a novel machine learning (ML) model to predict the risk of developing CKD/HF in early-stage T2DM patients. The models were derived from a retrospective cohort of 217,054 T2DM patients without a history of cardiovascular and renal diseases extracted from a Japanese claims database. Among algorithms used for the ML, extreme gradient boosting exhibited the best performance for CKD/HF diagnosis and hospitalization after internal validation and was further validated using another dataset including 16,822 patients. In the external validation, 5-years prediction area under the receiver operating characteristic curves for CKD/HF diagnosis and hospitalization were 0.718 and 0.837, respectively. In Kaplan-Meier curves analysis, patients predicted to be at high risk showed significant increase in CKD/HF diagnosis and hospitalization compared with those at low risk. Thus, the developed model predicted the risk of developing CKD/HF in T2DM patients with reasonable probability in the external validation cohort. Clinical approach identifying T2DM at high risk of developing CKD/HF using ML models may contribute to improved prognosis by promoting early diagnosis and intervention.

We propose mini-batch top-n k-medoids to sequential pattern mining to improve CGM interpretation. Mecical workers can treat specific patient groups better by understanding the time series variation of blood glucose results. For 10 years, continuous glucose monitoring (CGM) has provided time-series data of blood glucose thanks to the invention of devices with low measurement errors. We conducted two experiments. In the first experiment, we evaluated the proposed method with a manually created dataset and confirmed that the method provides more accurate patterns than other clustering methods. In the second experiment, we applied the proposed method to a CGM dataset consisting of real data from 163 patients. We created two labels based on blood glucose (BG) statistics and found patterns that correlated with a specific label in each case.

In this paper, we propose feature extraction method for prediction model for at the early stage of diabetic kidney disease (DKD) progression. DKD needs continuous treatment; however, a hospital visit interval of a patient at the early stage of DKD is normally from one month to three months, and this is not a short time period. Therefore it makes difficult to apply sophisticated approaches such as using convolutional neural networks because of the data limitation. The propose method uses with hierarchical clustering that can estimate a suitable interval for grouping inputted sequences. We evaluate the proposed method with a real-EMR dataset that consists of 30,810 patient records and conclude that the proposed method outperforms the baseline methods derived from related work.

OBJECTIVE: Immunoglobulin G4 (IgG4)-related disease (IgG4-RD) is an immune-mediated condition that can affect almost any organ. We investigated the association between IgG4-RD and the main characteristics of Graves' disease (GD) at the time of diagnosis. Additionally, we evaluated whether serum IgG4 levels change during treatment. DESIGN AND PATIENTS: Twenty-eight patients with newly diagnosed GD were enrolled into this longitudinal follow-up study. Serum IgG4 levels and thyroid function were measured in all the participants at the time of diagnosis. Further, the serum IgG4 levels of nine of 28 patients with untreated GD were measured after the achievement of euthyroid state (through the use of methimazole). RESULTS: Two (7.1%) of 28 patients with untreated GD had elevated serum IgG4 levels of >135 mg/dL. There was no significant difference in the average IgG4 levels before and after the achievement of euthyroid state (66.2±74.0 mg/dL vs. 50.5±47.3 mg/dL). In two patients, the elevated serum IgG4 levels returned to normal after treatment. However, one patient had an elevated serum IgG4 level of 136.6 mg/dL after treatment. CONCLUSIONS: This study showed that serum IgG4 levels varied with treatment in patients with GD, independent of thyroid function, suggesting that IgG4 might be indirectly related to GD.

AIMS: The aim of this study is to investigate the effects of a low-carbohydrate staple food (i.e., low-carbohydrate bread) on glucose and lipid metabolism and pancreatic and enteroendocrine hormone secretion in comparison with meals containing normal-carbohydrate bread, without consideration of the carbohydrate content of the side dishes. METHODS: T2DM patients (n = 41) were provided meals containing low-carbohydrate bread (LB) together with side dishes or normal-carbohydrate bread (NB) together with side dishes every other day as a breakfast. Blood glucose levels were evaluated by using a continuous glucose monitoring system; blood samples were collected before and 1 and 2 h after the breakfast. RESULTS: Postprandial blood glucose levels, plasma insulin, plasma glucose-dependent insulinotropic polypeptide (GIP) and plasma triglyceride were significantly lower and plasma glucagon levels were significantly higher in LB compared with those in NB. Plasma glucagon-like peptide-1 (GLP-1) levels did not differ in the LB and NB groups. CONCLUSIONS: These results indicate that changing only the carbohydrate content of the staple food has benefits on glucose and lipid metabolism in T2DM patients concomitant with the decrease of insulin and GIP secretion, which ameliorate body weight gain and insulin resistance.

Artificial intelligence (AI) is expected to support clinical judgement in medicine. We constructed a new predictive model for diabetic kidney diseases (DKD) using AI, processing natural language and longitudinal data with big data machine learning, based on the electronic medical records (EMR) of 64,059 diabetes patients. AI extracted raw features from the previous 6 months as the reference period and selected 24 factors to find time series patterns relating to 6-month DKD aggravation, using a convolutional autoencoder. AI constructed the predictive model with 3,073 features, including time series data using logistic regression analysis. AI could predict DKD aggravation with 71% accuracy. Furthermore, the group with DKD aggravation had a significantly higher incidence of hemodialysis than the non-aggravation group, over 10 years (N = 2,900). The new predictive model by AI could detect progression of DKD and may contribute to more effective and accurate intervention to reduce hemodialysis.

This paper describes a technology for predicting the aggravation of diabetic nephropathy from electronic health record (EHR). For the prediction, we used features extracted from event sequence of lab tests in EHR with a stacked convolutional autoencoder which can extract both local and global temporal information. The extracted features can be interpreted as similarities to a small number of typical sequences of lab tests, that may help us to understand the disease courses and to provide detailed health guidance. In our experiments on real-world EHRs, we confirmed that our approach performed better than baseline methods and that the extracted features were promising for understanding the disease.

<p>  A 34-year-old woman with type 1 diabetes on hemodialysis was admitted to our hospital for simultaneous pancreas kidney transplantation received from her father. She had suffered from type 1 diabetes mellitus since age 13, and had complained of serious atonic gastroenteropathy and orthostatic hypotension. After the transplantation, she became free from hemodialysis and insulin injection. At the same time, her gastrointestinal symptoms disappeared. However, she still had orthostatic hypotension, which was improved by taking fludrocortisone. Two months after the transplantation, orthostatic hypotension with marked polyuria became obvious. By hypertonic saline challenge test, she was diagnosed as partial central diabetes insipidus. Although treatment with desmopressin was necessary for 5 months, she became free from medication afterwards. Diabetes insipidus seems to be a rare but could be an important complication after simultaneous pancreas kidney transplantation and/or or kidney transplantation.</p>