BioMed research international
-
The plethora of biomedical relations which are embedded in medical logs (records) demands researchers' attention. Previous theoretical and practical focuses were restricted on traditional machine learning techniques. However, these methods are susceptible to the issues of "vocabulary gap" and data sparseness and the unattainable automation process in feature extraction. ⋯ We evaluated our model on two biomedical relation extraction tasks: drug-drug interaction (DDI) extraction and protein-protein interaction (PPI) extraction. For DDI task, our system achieved an overall f-score of 70.2% compared to the standard linear SVM based system (e.g., 67.0%) on DDIExtraction 2013 challenge dataset. And for PPI task, we evaluated our system on Aimed and BioInfer PPI corpus; our system exceeded the state-of-art ensemble SVM system by 2.7% and 5.6% on f-scores.
-
The use of robotic technology in the surgical treatment of brain tumour promises increased precision and accuracy in the performance of surgery. Robotic manipulators may allow superior access to narrow surgical corridors compared to freehand or conventional neurosurgery. This paper reports values and ranges of tool-tissue interaction forces during the performance of glioma surgery using an MR compatible, image-guided neurosurgical robot called neuroArm. ⋯ Mean values of the peak forces varied in range of 1.27 N (anaplastic astrocytoma, WHO grade III) to 1.89 N (glioblastoma with oligodendroglial component, WHO grade IV). In some cases, ANOVA test failed to reject the null hypothesis of equality in means of the peak forces measured. However, we could not find a relationship between forces exerted to the pathological tissue and its size, type, or location.
-
The state-of-the-art methods for protein-protein interaction (PPI) extraction are primarily based on kernel methods, and their performances strongly depend on the handcraft features. In this paper, we tackle PPI extraction by using convolutional neural networks (CNN) and propose a shortest dependency path based CNN (sdpCNN) model. ⋯ We performed experiments on standard Aimed and BioInfer datasets, and the experimental results demonstrated that our approach outperformed state-of-the-art kernel based methods. In particular, by tracking the sdpCNN model, we find that sdpCNN could extract key features automatically and it is verified that pretrained word embedding is crucial in PPI task.
-
Observational Study
The Effects of Hemodynamic Changes on Pulse Wave Velocity in Cardiothoracic Surgical Patients.
The effect of blood pressure on pulse wave velocity (PWV) is well established. However, PWV variability with acute hemodynamic changes has not been examined in the clinical setting. The aim of the present study is to investigate the effect of hemodynamic changes on PWV in patients who undergo cardiothoracic surgery. ⋯ Increases in BP, HR, and SVR were associated with higher values for PWV. In contrast increases in SV were associated with decreases in PWV. Changes in CO were not significantly associated with PWV.
-
Background. Lung recruitment maneuver (LRM) during thoracic surgery can reduce systemic venous return and resulting drop in systemic blood pressure depends on the patient's fluid status. We hypothesized that changes in systemic blood pressure during the transition in LRM from one-lung ventilation (OLV) to two-lung ventilation (TLV) may provide an index to predict fluid responsiveness. ⋯ Areas under the curve for change in MAP, CVP, and SVV were 0.852, 0.759, and 0.820, respectively; the optimal threshold values for distinguishment of responders were 9.5 mmHg, 0.5 mmHg, and 3.5%, respectively. Conclusions. The change in the MAP associated with LRM at the OLV to TLV conversion appears to be a useful indicator of fluid responsiveness after thoracic surgery.