Researchers from MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) have developed a machine learning system that can either make a prediction about a task, or defer the decision to an expert. Most importantly, it can adapt when and how often it defers to its human collaborator, based on factors such as its teammate’s availability and level of experience.  The team trained the system on multiple tasks, including looking at chest X-rays to diagnose specific conditions such as atelectasis (lung collapse) and cardiomegaly (an enlarged heart). In the case of cardiomegaly, they found that their human-AI hybrid model performed 8 percent better than either could on their own (based on AU-ROC scores).  Researchers have not yet tested the system with human experts, but instead developed a series of “synthetic experts” so that they could tweak parameters such as experience and availability.  In future work, the team plans to test their approach with real human experts, such as radiologists for X-ray diagnosis. They will also explore how to develop systems that can learn from biased expert data, as well as systems that can work with — and defer to — several experts at once.

Infervision received U.S. Food and Drug Administration (FDA) 510(K) clearance of the InferRead Lung CTAI product, which uses artificial intelligence and deep learning technology, to automatically perform lung segmentation, along with accurately identifying and labeling nodules of different types. InferRead Lung CTAI is designed to support concurrent reading and is designed to aid radiologists in pulmonary nodule detection during the review of chest computed tomography (CT) scans, increasing accuracy and efficiency.  InferRead Lung CTAI is currently in use at over 380 hospitals and imaging centers globally. More than 55,000 cases daily are being processed by the system, and over 19 million patients have already benefited from this advanced AI technology. “Fast, workflow friendly, and accurate are the three key areas we have emphasized during product development. We’re excited to be able to make our InferRead Lung CTAI solution available to the North American market. Our clients tell us it has great potential to help provide improved outcomes for providers and patients alike,” said Matt Deng, Ph.D., director of Infervision North America.

Recent Headlines

Infervision Receives FDA Clearance For The InferRead Lung CT.AI Product | August 4 2020
Ping An AskBob Doctor's Deep Learning Model Improves Diagnosis Of Kidney Disease | August 4 2020
X-Ray Firm Nanox Files For $125m U.S. Offering | August 2 2020

An Automated Health Care System That Understands When To Step In | July 31 2020
FDA, Syapse Real-World Study Reveal Higher Risk Of Hospitalization And Death Among Cancer Patients With COVID-19, Underscore Health Disparities | July 31 2020
Veracyte Announces Data Published In AJRCCM Showing That The Envisia Genomic Classifier Improves Physicians’ Ability To Diagnose IPF Without Surgery | July 30 2020
Artificial Intelligence Software May Prevent Unneeded Cancer Surgeries | July 29 2020
Study Results From The UCSF Ci2 Suggest Deep Learning Methods Can Help Grade ACL Injuries | July 29 2020
Artificial Intelligence Can Speed Up And Improve Alzheimer’s Diagnosis, Says Study | July 29 2020