On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,982 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “ischemic”

Automated Computer Evaluation of Acute Ischemic Stroke and Large Vessel Occlusioneess.IV

Paper develops a model to identify LVO in stroke patients.

problem Early identification of LVO in stroke patients to prevent severe outcomes.

method Used demographic, clinical, and CT scan data to build three hierarchical models.

result Level-3 model with clinical and imaging features achieved best performance.

stroke ischemic LVO deep learning CT scans

2019-06-18abs ↗pdf ↗

Semi-Supervised Natural Language Approach for Fine-Grained Classification of Medical Reportscs.LG

Model uses unsupervised learning to classify medical reports with less labeled data.

problem Lack of labeled data for fine-grained disease classification in medical reports.

method Developed a pipeline combining an unsupervised encoder-language model and a supervised classifier model.

result Improved classification accuracy with less labeled data compared to previous methods.

natural language processing unsupervised learning medical report classification deep learning machine learning

2019-10-29abs ↗pdf ↗

Predicting Clinical Outcome of Stroke Patients with Tractographic Featureeess.IV

Paper introduces tractographic feature to predict stroke outcomes.

problem Predicting stroke outcomes using lesion volume alone is limited.

method Tractographic feature combining lesion and connectome data.

result Tractographic feature outperforms stroke volume in predicting mRS grades.

stroke neuroimaging connectome predictive modeling mRS

2019-07-22abs ↗pdf ↗

Optimization of Ensemble Supervised Learning Algorithms for Increased Sensitivity, Specificity, and AUC of Population-Based Colorectal Cancer Screeningsstat.ML

Over 150,000 new people in the United States are diagnosed with colorectal cancer each year. Nearly a third die from it (American Cancer Society). The only approved noninvasive diagnosis tools currently involve fecal blood count tests (FOBTs) or stool DNA tests. Fecal blood count tests take only five minutes and are av…

2017-08-13abs ↗pdf ↗

Integrating uncertainty in deep neural networks for MRI based stroke analysiseess.IV

Bayesian CNN improves MRI stroke diagnosis accuracy and uncertainty quantification.

problem Uncertainty quantification in automated image analysis for medical decision-making.

method Bayesian Convolutional Neural Network (CNN) with aggregation methods for patient-level diagnoses.

result Bayesian CNN achieved 95.33% accuracy on 511 patients, 2% higher than non-Bayesian.

Bayesian deep learning MRI stroke diagnosis uncertainty quantification aggregation methods patient-level accuracy

2020-08-13abs ↗pdf ↗