Detection of fibrosing interstitial lung disease-suspected chest radiographs using a deep learning-based computer-aided detection system: a retrospective, observational study.

OBJECTIVES: To investigate the effectiveness of BMAX, a deep learning-based computer-aided detection system for detecting fibrosing interstitial lung disease (ILD) on chest radiographs among non-expert and expert physicians in the real-world clinical setting. DESIGN: Retrospective, observational study. SETTING: This study used chest radiograph images consecutively taken in three medical facilities with various degrees of referral. Three expert ILD physicians interpreted each image and determined whether it was a fibrosing ILD-suspected image (fibrosing ILD positive) or not (fibrosing ILD negative). Interpreters, including non-experts and experts, classified each of 120 images extracted from the pooled data for the reading test into positive or negative for fibrosing ILD without and with the assistance of BMAX. PARTICIPANTS: Chest radiographs of patients aged 20 years or older with two or more visits that were taken during consecutive periods were accumulated. 1251 chest radiograph images were collected, from which 120 images (24 positive and 96 negative images) were randomly extracted for the reading test. The interpreters for the reading test were 20 non-expert physicians and 5 expert physicians (3 pulmonologists and 2 radiologists). PRIMARY AND SECONDARY OUTCOME MEASURES: The primary outcome was the comparison of area under the receiver-operating characteristic curve (ROC-AUC) for identifying fibrosing ILD-positive images by non-experts without versus with BMAX. The secondary outcome was the comparison of sensitivity, specificity and accuracy by non-experts and experts without versus with BMAX. RESULTS: The mean ROC-AUC of non-expert interpreters was 0.795 (95% CI; 0.765 to 0.825) without BMAX and 0.825 (95% CI; 0.799 to 0.850) with BMAX (p=0.005). After using BMAX, sensitivity was improved from 0.744 (95% CI; 0.697 to 0.791) to 0.802 (95% CI; 0.754 to 0.850) among non-experts (p=0.003), but not among experts (p=0.285). Specificity and accuracy were not changed after using BMAX among either non-expert or expert interpreters. CONCLUSION: BMAX was useful for detecting fibrosing ILD-suspected chest radiographs for non-expert physicians. TRIAL REGISTRATION NUMBER: jRCT1032220090.

Continuous regional arterial infusion versus intravenous administration of the protease inhibitor nafamostat mesilate for predicted severe acute pancreatitis: a multicenter, randomized, open-label, phase 2 trial.

BACKGROUND: Continuous regional arterial infusion (CRAI) of protease inhibitor nafamostat mesilate (NM) is used in the context of predicted severe acute pancreatitis (SAP) to prevent the development of pancreatic necrosis. Although this therapy is well known in Japan, its efficacy and safety remain unclear. METHODS: This investigator-initiated and -driven, multicenter, open-label, randomized, controlled trial (UMIN000020868) enrolled 39 patients with predicted SAP and low enhancement of the pancreatic parenchyma on computed tomography (CT). Twenty patients were assigned to the CRAI group, while 19 served as controls and were administered NM at the same dose intravenously (IV group). The primary endpoint was the development of pancreatic necrosis as determined by CT on Day 14, judged by blinded central review. RESULTS: There was no difference between the CRAI and IV groups regarding the percentages of participants who developed pancreatic necrosis (more than 1/3 of the pancreas: 25.0%, range 8.7-49.1% vs. 15.8%, range 3.4-39.6%, respectively, P = 0.694; more than 2/3 of the pancreas: 20%, range 5.7-43.7% vs. 5.3%, range 0.1-26.0%, respectively, P = 0.341). The early analgesic effect was evaluated based on 24-h cumulative fentanyl consumption and additional administration by intravenous patient-controlled analgesia. The results showed that the CRAI group used significantly less analgesic. There were two adverse events related to CRAI, namely bleeding and splenic infarction. CONCLUSIONS: CRAI with NM did not inhibit the development of pancreatic necrosis although early analgesic effect of CRAI was superior to that of IV. Less-invasive IV therapy can be considered a viable alternative to CRAI therapy.

Effects of the duration and inorganic nitrogen composition of a nutrient-rich patch on soil exploration by the roots of Lolium perenne in a heterogeneous environment.

We investigated the growth of and soil exploration by Lolium perenne under a heterogeneous environment before its roots reached a nutrient-rich patch. Temporal changes in the distribution of inorganic nitrogen, i.e., NO(3)(-)-N and NH(4)(+)-N, in the heterogeneous environment during the experimental period were also examined. The results showed that roots randomly explored soil, irrespective of the patchy distribution of inorganic nitrogen and differences in the chemical composition of inorganic nitrogen distribution between heterogeneous and homogeneous environments. We have also elucidated the potential effects of patch duration and inorganic nitrogen distribution on soil exploration by roots and thus on plant growth.

Root growth and plant biomass in Lolium perenne exploring a nutrient-rich patch in soil.

We investigated soil exploration by roots and plant growth in a heterogeneous environment to determine whether roots can selectively explore a nutrient-rich patch, and how nutrient heterogeneity affects biomass allocation and total biomass before a patch is reached. Lolium perenne L. plants were grown in a factorial experiment with combinations of fertilization (heterogeneous and homogeneous) and day of harvest (14, 28, 42, or 56 days after transplanting). The plant in the heterogeneous treatment was smaller in its mean total biomass, and allocated more biomass to roots. The distributions of root length and root biomass in the heterogeneous treatment did not favor the nutrient-rich patch, and did not correspond to the patchy distribution of inorganic nitrogen. Specific root length (length/biomass) was higher and root elongation was more extensive both laterally and vertically in the heterogeneous treatment. These characteristics may enable plants to acquire nutrients efficiently and increase the probability of encountering nutrient-rich patches in a heterogeneous soil. However, heterogeneity of soil nutrients would hold back plant growth before a patch was reached. Therefore, although no significant selective root placement in the nutrient-rich patch was observed, plant growth before reaching nutrient-rich patches differed between heterogeneous and homogeneous environments.