Leiomyosarcoma of the transverse colon with lymph node metastasis and malignant transformation: a case report.

Background: The concept of GIST was established in 1998, clearly differentiating between gastrointestinal leiomyosarcoma and GISTs among gastrointestinal mesenchymal tumors. Lymph node metastasis is extremely rare in true gastrointestinal leiomyosarcoma, and there are no reports of malignant transformation from leiomyoma.

Case Presentation: The patient was an old woman who had undergone endoscopic mucosal resection for an Is polyp on the left side of the transverse colon at the age of 73.

Artificial intelligence predicts the progression of diabetic kidney disease using big data machine learning.

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.

Number of positive lymph nodes and lymphatic invasion are significant prognostic factors after pancreaticoduodenectomy for distal cholangiocarcinoma.

Early recurrence of distal cholangiocarcinoma (DCC) may result in a poorer prognosis. This study aimed to evaluate the clinicopathological factors that predict survival and recurrence in patients with DCC. Fifty-five patients with DCC who underwent pancreaticoduodenectomy between 2005 and 2015 were studied retrospectively.

Risk Prediction of Diabetic Nephropathy via Interpretable Feature Extraction from EHR Using Convolutional Autoencoder.

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.

Photocurrent attenuation by a single polar-to-nonpolar point mutation of channelrhodopsin-2.

Channelrhodopsin-2 (ChR2), one of the algal light-gated cation channel rhodopsins, contains five peculiar glutamic acid residues in the N-terminal region corresponding to the second to third transmembrane helices. Here we made systematic mutations of these polar amino acid residues of ChR2 into nonpolar alanine, and evaluated their photocurrent properties. Amongst them, the photocurrent generated by the E97A mutation, ChR2(E97A), was much smaller than expected from its expression.