Hybrid novice-AI system achieves expert-level performance in intraoperative ischemia detection
Murali, N.; Mina, A. I.; Anderson, J. W.; Raka, Y.; Amiri, H. K.; Thirumala, P. D.; Batmanghelich, K.; Visweswaran, S.
Show abstract
Carotid endarterectomy carries the risk of intraoperative cerebral ischemia, which is monitored by expert neurophysiologists through continuous electroencephalography (cEEG). Because expert availability is limited, we developed a hybrid novice-artificial intelligence (AI) system that detects ischemia using novice monitors with limited cEEG training. The hybrid system dynamically weights novice and AI inputs to arrive at a final output. Using four novices, we compared hybrid systems against experts alone, novices alone, and AI alone. Hybrid systems were statistically non-inferior to experts in sensitivity and false-positive rate (FPR), whereas novices alone were not. At 80% sensitivity, hybrid systems reduced FPR by half compared with the AI-only system, with similar benefits at 90% sensitivity. Further, the area under the precision-recall curve improved from 0.546 to 0.610-0.726, the area under the receiver operating characteristic curve improved from 0.957 to 0.967-0.971, and calibration improved compared with AI alone. These results highlight the potential of a hybrid system to monitor intraoperative cerebral ischemia.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Indexing Cerebrovascular Health Using Near-infrared Spectroscopy 93%
- Segmentation of Pancreatic Ductal Adenocarcinoma (PDAC) and surrounding vessels in CT images using deep convolutional neural networks and Texture Descriptors 92%
- Detection and categorization of severe cardiac disorders based solely on pulse interval measurements 92%
Similar papers in this journal
- Predicting critical state after COVID-19 diagnosis: Model development using a large US electronic health record dataset 91%
- A Deep Learning Based Smartphone Application for Early Detection of Nasopharyngeal Carcinoma Using Endoscopic Images 91%
- Artificial Intelligence for Surgical Scene Understanding: A Systematic Review and Reporting Quality Meta-Analysis 91%
Similar papers in this journal
- Spiking neural networks provide accurate, efficient and robust models for whisker stimulus classification and allow for inter-individual generalization 91%
- Artificial cerebellum on FPGA: Realistic real-time cerebellar spiking neural network model capable of real-world adaptive motor control 91%
- Quantitative evaluation of normal cerebrospinal fluid flow in the Sylvian aqueduct and perivascular spaces of the middle cerebral artery and circle of Willis via 2D phase-contrast MR imaging 91%
Similar papers in this journal
- Opening the Black Box of Artificial Intelligence for Clinical Decision Support: A Study Predicting Stroke Outcome 94%
- Leveraging Machine Learning for Enhanced and Interpretable Risk Prediction of Venous Thromboembolism in Acute Ischemic Stroke Care 94%
- Estimating pulse wave velocity from the radial pressure wave using machine learning algorithms 93%
Similar papers in this journal
- Objective Assessment of Beat Quality in Transcranial Doppler Measurement of Blood Flow Velocity in Cerebral Arteries 95%
- Personalizing the Pressure Reactivity Index for Neurocritical Care Decision Support 94%
- Surgical Planning and Optimization of Patient-Specific Fontan Grafts With Uncertain Post-Operative Boundary Conditions and Anastomosis Displacement 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.