HIV-1-infected T-cells dynamics and prognosis
HIV disease has all components of an evolutionary process, including replication, mutation, and selection.In this study we propose a novel spatial game theoretical model for evolution of HIV-1-Infected CD4+T-cells and invasion of immune system.The ...
Comparative approaches for classification of diabetes mellitus data
- Md. Maniruzzaman,
- Nishith Kumar,
- Md. Menhazul Abedin,
- Md. Shaykhul Islam,
- Harman S. Suri,
- Ayman S. El-Baz,
- Jasjit S. Suri
Introduce Gaussian process classification (GPC) technique for diabetes classification in machine learning framework.GPC uses three kernels types, namely: linear, polynomial and radial basis kernel.Comparison of GPC with existing classification ...
Enhancing performance of P300-Speller under mental workload by incorporating dual-task data during classifier training
- Yuqian Chen,
- Yufeng Ke,
- Guifang Meng,
- Jin Jiang,
- Hongzhi Qi,
- Xuejun Jiao,
- Minpeng Xu,
- Peng Zhou,
- Feng He,
- Dong Ming
Performance of P300-Speller always impaired once applied in practical situations due to the effect of mental workload. We aimed to mitigate this effect and enhance its performance.We propose a new method of incorporating dual-task data during classifier ...
Development and validation of various phenotyping algorithms for Diabetes Mellitus using data from electronic health records
- Santiago Esteban,
- Manuel Rodrguez Tablado,
- Francisco E. Peper,
- Yamila S. Mahumud,
- Ricardo I. Ricci,
- Karin S. Kopitowski,
- Sergio A. Terrasa
Performance comparison of different electronic phenotyping algorithms using real data extracted from EHRs from Argentina.Stacked generalization showed to be the best performing strategy in the validation set.These algorithms can facilitate the ...
Evaluation of robotic surgery skills using dynamic time warping
A new algorithm for the evaluation of surgeons according to their skills.Analysis of surgical performance based on motion information with dynamic time warping algorithm.Definition of an evaluating indicator to outstand critical information in surgical ...
Using anchors from free text in electronic health records to diagnose postoperative delirium
- Karl yvind Mikalsen,
- Cristina Soguero-Ruiz,
- Kasper Jensen,
- Kristian Hindberg,
- Mads Gran,
- Arthur Revhaug,
- Rolv-Ole Lindsetmo,
- Stein Olav Skrvseth,
- Fred Godtliebsen,
- Robert Jenssen
The anchor framework is introduced as a diagnosis tool for postoperative delirium.A procedure based on clustering and data visualization is used to specify anchors.We increase the AUC-PR from 0.51 to 0.96 compared to baselines. ObjectivesPostoperative ...
A segmentation method based on HMRF for the aided diagnosis of acute myeloid leukemia
Background and objectivesThe diagnosis of acute myeloid leukemia (AML) is purely dependent on counting the percentages of blasts (>20%) in the peripheral blood or bone marrow. Manual microscopic examination of peripheral blood or bone marrow aspirate ...
Methodology on quantification of sonication duration for safe application of MR guided focused ultrasound for liver tumour ablation
- Senay Mihcin,
- Ioannis Karakitsios,
- Nhan Le,
- Jan Strehlow,
- Daniel Demedts,
- Michael Schwenke,
- Sabrina Haase,
- Tobias Preusser,
- Andreas Melzer
Translational research requires evidence before clinical trials. The described methodology enables a systematic automated quality assurance (QA) tool for use in clinics.The designed protocols measure the sonication duration and, the delay after the ...
Binary classification of multichannel-EEG records based on the -complexity of continuous vector functions
A new model-free methodology for binary classification of multichannel EEG records is proposed.This methodology is based on our theory of the -complexity of continuous functions.In this paper the theory of the -complexity was extended into the case of ...
ECG based Myocardial Infarction detection using Hybrid Firefly Algorithm
Hybrid optimization technique for Myocardial Infarction classification.A comparison of three classifiers demonstrates the validity of the proposed method.The proposed technique could be applied to any image and research field.This is a novel approach to ...
Predicting CD4 count changes among patients on antiretroviral treatment
Predicted CD4 count changes using J48, Neural Network and Random Forest data mining algorithms.Compared the predictive performance of three data mining algorithms.Identified variables important for prediction of CD4 count changes. Background and ...
Theoretical prediction of pullout strengths for dental and orthopaedic screws with conical profile and buttress threads
The dental, trauma, and spinal screw groups were used to evaluate the accuracy of the calculated pullout strengths using different formulae.The experimental tests were conducted to compare the measured and calculated pullout strengths.The buttress ...
Drug-target interaction prediction
Proposing BRDTI method for per-drug ranking of DTIs.Performed comparative evaluation of BRDTI w.r.t. AUC and per-drug nDCG.BRDTI achieved best average results on predicting new targets for existing drugs. Background and objectiveIn silico prediction of ...
Edge enhancement algorithm for low-dose X-ray fluoroscopic imaging
Existing edge enhancement methods have overshoot problems and noise artifacts.Proposed enhancement algorithm combines region adaptive high-pass filter with transient improvement and artifacts and noise reduction.X-ray fluoroscopy images are sharpened ...
nmsBuilder
nmsBuilder 2.0: freely available software to create subject-specific musculoskeletal models for OpenSim from 3D geometries.Data processing to create supporting objects, and creation of OpenSim objects.Case study: creation of a MRI-based musculoskeletal ...
Using artificial neural networks to select the parameters for the prognostic of mild cognitive impairment and dementia in elderly individuals
We present a paper proposing a computational model based on artificial neural network to classify data patterns of elderly people in terms of dementia and Mild Cognitive Impairment.We used real-world data from Brazilian hospital.The proposal takes into ...
