News | Artificial Intelligence | November 07, 2018

Artificial Intelligence May Fall Short Analyzing Data Across Multiple Health Systems

Study shows deep learning models must be carefully tested across multiple environments before being put into clinical practice

November 7, 2018 — Artificial intelligence (AI) tools trained to detect pneumonia on chest X-rays suffered significant decreases in performance when tested on data from outside health systems, according to a new study. The study, conducted at the Icahn School of Medicine at Mount Sinai, was published in a special issue of PLOS Medicine on machine learning and healthcare.1 These findings suggest that artificial intelligence in the medical space must be carefully tested for performance across a wide range of populations; otherwise, the deep learning models may not perform as accurately as expected.  

As interest in the use of computer system frameworks called convolutional neural networks (CNN) to analyze medical imaging and provide a computer-aided diagnosis grows, recent studies have suggested that AI image classification may not generalize to new data as well as commonly portrayed.

Researchers at the Icahn School of Medicine at Mount Sinai assessed how AI models identified pneumonia in 158,000 chest X-rays across three medical institutions: the National Institutes of Health; The Mount Sinai Hospital; and Indiana University Hospital. Researchers chose to study the diagnosis of pneumonia on chest X-rays for its common occurrence, clinical significance and prevalence in the research community.

In three out of five comparisons, CNNs’ performance in diagnosing diseases on X-rays from hospitals outside of its own network was significantly lower than on X-rays from the original health system. However, CNNs were able to detect the hospital system where an X-ray was acquired with a high-degree of accuracy, and cheated at their predictive task based on the prevalence of pneumonia at the training institution. Researchers found that the difficulty of using deep learning models in medicine is that they use a massive number of parameters, making it challenging to identify specific variables driving predictions, such as the types of computed tomography (CT) scanners used at a hospital and the resolution quality of imaging.

“Our findings should give pause to those considering rapid deployment of artificial intelligence platforms without rigorously assessing their performance in real-world clinical settings reflective of where they are being deployed,” said senior author Eric Oermann, M.D., instructor in neurosurgery at the Icahn School of Medicine at Mount Sinai. “Deep learning models trained to perform medical diagnosis can generalize well, but this cannot be taken for granted since patient populations and imaging techniques differ significantly across institutions.”

“If CNN systems are to be used for medical diagnosis, they must be tailored to carefully consider clinical questions, tested for a variety of real-world scenarios and carefully assessed to determine how they impact accurate diagnosis,” said first author John Zech, a medical student at the Icahn School of Medicine at Mount Sinai.

This research builds on papers published earlier this year in the journals Radiology and Nature Medicine, which laid the framework for applying computer vision and deep learning techniques, including natural language processing algorithms, for identifying clinical concepts in radiology reports for CT scans.

Listen to the PODCAST: Radiologists Must Understand AI To Know If It Is Wrong

For more information: www.journals.plos.org/plosmedicine

Reference

1. Zech J.R., Badgeley M.A., Liu M., et al. Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study. PLOS Medicine, Nov. 6, 2018. https://doi.org/10.1371/journal.pmed.1002683

Related Content

IBM Watson Health Announces New AI Collaborations With Leading Medical Centers
News | Artificial Intelligence | February 14, 2019
IBM Watson Health announced plans to make a 10-year, $50 million investment in research collaborations with two...
Medivis Launches SurgicalAR Augmented Reality Platform
Technology | Advanced Visualization | February 14, 2019
Medical imaging and visualization company Medivis officially unveiled SurgicalAR, its augmented reality (AR) technology...
Densitas Enters Partnership Agreement With TeleMammography Specialists
News | Breast Density | February 14, 2019
Breast imaging analytics company Densitas Inc. announced a new collaboration partnership with TeleMammography...
Office of the National Coordinator Releases Proposed Rule on Healthcare Data Interoperability
News | Information Technology | February 14, 2019
The U.S. Department of Health and Human Services (HHS) has proposed a new rule to support seamless and secure access,...
Sponsored Content | Webinar | Artificial Intelligence | February 14, 2019
This Nuance-sponsored ITN webinar will be held at 1 p.m. Eastern time, Tuesday, Feb. 26, 2019.
Siemens Healthineers Demonstrates Artificial Intelligence, Healthcare Digitalization at HIMSS19
News | Artificial Intelligence | February 13, 2019
February 13, 2019 — At the 2019 Healthcare Information and Management Systems Society (HIMSS) global conference and e
PaxeraHealth Launching Universal Image Sharing Platform at ECR 2019
News | PACS Accessories | February 13, 2019
PaxeraHealth will launch the PaxeraShare image sharing platform at the 2019 European Congress of Radiology (ECR) annual...
NVIDIA Explores Role of AI, Analytics and Virtualization in Healthcare at HIMSS19
News | Artificial Intelligence | February 13, 2019
Digital technology company NVIDIA will highlight its newest partnerships to advance the digital transformation of...
Patients and surgeons at Hoag Memorial Hospital are looking at virtual reality reconstructions (right) over conventional 2D images

Slice v 3D: Patients and surgeons at Hoag Memorial Hospital are looking at virtual reality reconstructions (right) over conventional 2D images. Images courtesy of Hoag Memorial Hospital

Feature | Information Technology | February 13, 2019 | By Greg Freiherr
The same virtual reality (VR) reconstructions that surgeons use to plan and rehearse brain surgeries at Hoag Memorial
Philips Launches Latest Iteration of IntelliSpace Cardiovascular at HIMSS 2019
Technology | Cardiac PACS | February 13, 2019
Philips announced the launch of IntelliSpace Cardiovascular 4.1, its next-generation cardiovascular image and...