Background and Purpose— The prediction of long-term outcomes in ischemic stroke patients may be useful in treatment decisions. Machine learning techniques are being increasingly adapted for use in the medical field because of their high accuracy. This study investigated the applicability of machine learning techniques to predict long-term outcomes in ischemic stroke patients. Methods— This was a retrospective study using a prospective cohort that enrolled patients with acute ischemic stroke. Favorable outcome was defined as modified Rankin Scale score 0, 1, or 2 at 3 months. We developed 3 machine learning models (deep neural network, random forest, and logistic regression) and compared their predictability. To evaluate the accuracy of the machine learning models, we also compared them to the Acute Stroke Registry and Analysis of Lausanne (ASTRAL) score. Results— A total of 2604 patients were included in this study, and 2043 (78%) of them had favorable outcomes. The area under the curve for the deep neural network model was significantly higher than that of the ASTRAL score (0.888 versus 0.839; P <0.001), while the areas under the curves of the random forest (0.857; P =0.136) and logistic regression (0.849; P =0.413) models were not significantly higher than that of the ASTRAL score. Using only the 6 variables that are used for the ASTRAL score, the performance of the machine learning models did not significantly differ from that of the ASTRAL score. Conclusions— Machine learning algorithms, particularly the deep neural network, can improve the prediction of long-term outcomes in ischemic stroke patients.

Background and Aims Biliary tract cancer (BTC) exhibits diverse molecular characteristics. However, reliable biomarkers that predict therapeutic responses are yet to be discovered. We aimed to identify the molecular features of treatment responses to chemotherapy and immunotherapy in BTCs. Approach and Results We enrolled 121 advanced BTC patients (68 cholangiocarcinomas [33 intrahepatic, 35 extrahepatic], 41 gallbladder cancers, and 12 Ampulla of Vater cancers) whose specimens were analyzed by clinical sequencing platforms. All patients received first‐line palliative chemotherapy; 48 patients underwent programmed death 1 (PD‐1)/programmed death‐ligand 1 (PD‐L1) blockade therapy after failed chemotherapy. Molecular and histopathological characterization was performed using targeted sequencing and immunohistochemical staining to investigate treatment response‐associated biomarkers. Genomic analysis revealed a broad spectrum of mutational profiles according to anatomical location. Favorable responses to chemotherapy were observed in the small‐duct type compared with the large‐duct type intrahepatic cholangiocarcinoma, with frequent mutations in BRCA1‐associated protein‐1/isocitrate dehydrogenase 1/2 and KRAS proto‐oncogene, GTPase/SMAD family member 4 genes, respectively. The molecular features were further analyzed in BTCs, and transforming growth factor beta and DNA damage response pathway‐altered tumors exhibited poor and favorable chemotherapy responses, respectively. In PD‐1/PD‐L1 blockade‐treated patients, KRAS alteration and chromosomal instability tumors were associated with resistance to immunotherapy. The majority of patients (95.0%) with these resistance factors show no clinical benefit to PD‐1/PD‐L1 blockade and low tumor mutational burdens. Low tumor‐infiltrating lymphocyte (TIL) density in tumors with these resistance factors indicated immune‐suppressive tumor microenvironments, whereas high intratumoral TIL density was associated with a favorable immunotherapy response. Conclusions This study proposes predictive molecular features of chemotherapy and immunotherapy responses in advanced BTCs using clinical sequencing platforms. Our result provides an intuitive framework to guide the treatment of advanced BTCs benefiting from therapeutic agents based on the tumors’ molecular features.

PurposeThe genus Aeromonas is a pathogen that is well known to cause severe clinical illnesses, ranging from gastroenteritis to sepsis. Accurate identification of A. hydrophila, A. caviae, and A. veronii is important for the care of patients. However, species identification remains difficult using conventional methods. The aim of this study was to compare the accuracy of different methods of identifying Aeromonas at the species level: a biochemical method, matrix-assisted laser desorption ionization mass spectrometry-time of flight (MALDI-TOF MS), 16S rRNA sequencing, and housekeeping gene sequencing (gyrB, rpoB).Materials and MethodsWe analyzed 65 Aeromonas isolates recovered from patients at a university hospital in Korea between 1996 and 2012. The isolates were recovered from frozen states and tested using the following four methods: a conventional biochemical method, 16S rRNA sequencing, housekeeping gene sequencing with phylogenetic analysis, and MALDI-TOF MS.ResultsThe conventional biochemical method and 16S rRNA sequencing identified Aeromonas at the genus level very accurately, although species level identification was unsatisfactory. MALDI-TOF MS system correctly identified 60 (92.3%) isolates at the species level and an additional four (6.2%) at the genus level. Overall, housekeeping gene sequencing with phylogenetic analysis was found to be the most accurate in identifying Aeromonas at the species level.ConclusionThe most accurate method of identification of Aeromonas to species level is by housekeeping gene sequencing, although high cost and technical difficulty hinder its usage in clinical settings. An easy-to-use identification method is needed for clinical laboratories, for which MALDI-TOF MS could be a strong candidate.

Backgraoud & AimsAberrant epithelial bicarbonate (HCO3−) secretion caused by mutations in the cystic fibrosis transmembrane conductance regulator (CFTR) gene is associated with several diseases including cystic fibrosis and pancreatitis. Dynamically regulated ion channel activity and anion selectivity of CFTR by kinases sensitive to intracellular chloride concentration ([Cl−]i) play an important role in epithelial HCO3− secretion. However, the molecular mechanisms of how [Cl−]i-dependent mechanisms regulate CFTR are unknown.MethodsWe examined the mechanisms of the CFTR HCO3− channel regulation by [Cl−]i-sensitive kinases using an integrated electrophysiological, molecular, and computational approach including whole-cell, outside-out, and inside-out patch clamp recordings and molecular dissection of WNK1 and CFTR proteins. In addition, we analyzed the effects of pancreatitis-causing CFTR mutations on the WNK1-mediated regulation of CFTR.ResultsAmong the WNK1, SPAK, and OSR1 kinases that constitute a [Cl−]i-sensitive kinase cascade, the expression of WNK1 alone was sufficient to increase the CFTR bicarbonate permeability (PHCO3/PCl) and conductance (GHCO3) in patch clamp recordings. Molecular dissection of the WNK1 domains revealed that the WNK1 kinase domain is responsible for CFTR PHCO3/PCl regulation by direct association with CFTR, while the surrounding N-terminal regions mediate the [Cl−]i-sensitivity of WNK1. Furthermore, the pancreatitis-causing R74Q and R75Q mutations in the elbow helix 1 of CFTR hampered WNK1-CFTR physical associations and reduced WNK1-mediated CFTR PHCO3/PCl regulation.ConclusionThe CFTR HCO3− channel activity is regulated by [Cl−]i and a WNK1-dependent mechanism. Our results provide new insights into the regulation of the ion selectivity of CFTR and the pathogenesis of CFTR-related disorders.

PurposeCircular stapled hemorrhoidopexy (CSH) is widely used to treat patients with grades III–IV hemorrhoids because of less pain and short hospital stay. However, this procedure is associated with some complications, such as urge to defecate, anal stenosis, staple line dehiscence, abscess and sepsis. To avoid these complications, surgeons perform a partial stapled hemorrhoidopexy (PSH). The aim of this study is to present our early experience with the PSH.MethodsWe retrospectively reviewed the medical records of 58 patients with hemorrhoids who were treated with a PSH at Busan Hang-Un Hospital from January 2016 to June 2016. A specially designed tri-window anoscope was used, and a purse string suture was made at the mucosae of the protruding hemorrhoids through the window of the anoscope. The hemorrhoidopexy was done by using a circular stapler.ResultsOf the 58 patients included in this study, 34 were male and 24 were female patients (mean age, 50.4 years). The mean operation time was 12.4 minutes, and the mean postoperative hospital stay was 3.8 days. Three patients experienced bleeding (5.1%) 5 urinary retention (8.6%) and 5 skin tags (8.6%). Urge to defecate, tenesmus, abscess, rectovaginal fistula, anal stricture, incontinence, and recurrence did not occur.ConclusionPSH is a minimally invasive, feasible, and safe technique for treating patients with grades III–IV hemorrhoids. A PSH, instead of a CSH, can be used to treat certain patients with hemorrhoids.