Application of artificial intelligence using a novel EUS-based convolutional neural network model to identify and distinguish benign and malignant hepatic masses

1. Download : Download high-res image (151KB)
2. Download : Download full-size image

     

Functional evaluation of out-of-the-box text-mining tools for data-mining tasks

Objective The trade-off between the speed and simplicity of dictionary-based term recognition and the richer linguistic information provided by more advanced natural language processing (NLP) is an area of active discussion in clinical informatics. In this paper, we quantify this trade-off among text processing systems that make different trade-offs between speed and linguistic understanding. We tested both types of systems in three clinical research tasks: phase IV safety profiling of a drug, learning adverse drug–drug interactions, and learning used-to-treat relationships between drugs and indications.Materials We first benchmarked the accuracy of the NCBO Annotator and REVEAL in a manually annotated, publically available dataset from the 2008 i2b2 Obesity Challenge. We then applied the NCBO Annotator and REVEAL to 9 million clinical notes from the Stanford Translational Research Integrated Database Environment (STRIDE) and used the resulting data for three research tasks.Results There is no significant difference between using the NCBO Annotator and REVEAL in the results of the three research tasks when using large datasets. In one subtask, REVEAL achieved higher sensitivity with smaller datasets.Conclusions For a variety of tasks, employing simple term recognition methods instead of advanced NLP methods results in little or no impact on accuracy when using large datasets. Simpler dictionary-based methods have the advantage of scaling well to very large datasets. Promoting the use of simple, dictionary-based methods for population level analyses can advance adoption of NLP in practice.     

Post-ischemic treatment with a lazaroid (U74389G) prevents transient global ischemic damage in rat hippocampus

Abstract

The ability of an experimental lazaroid, U74389G, to prevent damage to hippocampal CA 1 cytoarchitecture due to transient global ischemia was studied by light and electron microscopy. Post-ischemic rats were given a single i.p. dose of lazaroid (6 or 18 mg kg-¹) at 5 min after revival by cardiopulmonary resuscitation (CPR). Without lazaroid treatment the number of normal-appearing neurons in the CA1 region declined from a normal value of 75.49± 2.21 to 8.40± 10.08 per 100 μ,m² on day 7 after the ischemic episode, and there was extensive damage visible in the cytoarchitecture of this region. In lazaroid treated rats, the normal cytoarchitecture was retained and the number of normal-appearing cells was maintained at 15.1O± 2.22 per 100 ¼,m²? Ultrastructure studies indicated that pyknotic pyramidal cells laden with Pysosomal aggregates were common in untreated post-ischemic rats but rare in lazaroid-treated rats. These results indicate that U74389G maintained the structural integrity of this region of the brain after transient global ischemia and suggest that this lazaroid may be an effective neuroprotectant. [Neural Res 1997; 19: 431-434]     

The Impact of Hot Melt Extrusion and Spray Drying on Mechanical Properties and Tableting Indices of Materials Used in Pharmaceutical Development

The impact of melt extrusion (HME) and spray drying (SD) on mechanical properties of hypromellose acetate succinate (HPMCAS), copovidone, and their formulated blends was studied and compared with that of reference excipients. Tensile strength (TS), compression pressure (CP), elastic modulus (E), and dynamic hardness (H_d) were determined along with Hiestand indices using compacts prepared at a solid fraction of ～0.85. HPMCAS and copovidone exhibited lower H_d, lower CP, and lower E than the reference excipients and moderate TS. HPMCAS was found to be highly brittle based on brittle fracture index values. The CP was 24% and 61% higher for HPMCAS after SD and HME, respectively, than for unprocessed material along with a higher H_d. Furthermore, the TS of HPMCAS and copovidone decreased upon HME. Upon blending melt-extruded HPMCAS with plastic materials such as microcrystalline cellulose, the TS increased. These results suggest that SD and HME could impact reworkability by reducing deformation of materials and in case of HME, likely by increasing density due to heating and shear stress in a screw extruder. A somewhat similar effect was observed for the dynamic binding index (BI_d) of the excipients and formulated blends. Such data can be used to quantitate the impact of processing on mechanical properties of materials during tablet formulation development.