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

The RIS market is expected to reach $979.1 M by 2025

Image courtesy of Agfa

News | Information Technology | December 13, 2019
December 13, 2019 — According to a new study released by Rese...
Schematic diagram of the proposed multichannel deep neural network model analyzing multiscale functional brain connectome for a classification task. rsfMRI = resting-state functional MRI.

Schematic diagram of the proposed multichannel deep neural network model analyzing multiscale functional brain connectome for a classification task. rsfMRI = resting-state functional MRI. Graphic courtesy of the Radiological Society of North America.

News | Artificial Intelligence | December 11, 2019
December 11, 2019 — Deep learning, a type of arti...
EMR patient portal on a smartphone
News | Electronic Medical Records (EMR) | December 11, 2019
December 11, 2019 — Despite the numerous benefits associated with patients accessing their medical records, a new stu
Damage from concussion alters the way information is transmitted between the two halves of the brain, according to a new study presented today at the annual meeting of the Radiological Society of North America (RSNA).

Image courtesy of RSNA

News | Clinical Trials | December 10, 2019
December 10, 2019 — Damage from...
After receiving acupuncture treatment three days a week during the course of radiation treatment, head and neck cancer patients experienced less dry mouth, according to study results from researchers at The University of Texas MD Anderson Cancer Center

Image by Rudolf Langer from Pixabay 

News | Clinical Trials | December 06, 2019
December 6, 2019 — After receiving acupuncture treatment three days a week during the course of...
Timothy Whelan is a professor of oncology at McMaster University and a radiation oncologist at the Juravinski Cancer Centre of Hamilton Health Sciences. He holds a Canada Research Chair in Breast Cancer Research. Photo courtesy McMaster University

Timothy Whelan is a professor of oncology at McMaster University and a radiation oncologist at the Juravinski Cancer Centre of Hamilton Health Sciences. He holds a Canada Research Chair in Breast Cancer Research. Photo courtesy McMaster University. Photo courtesy of McMaster University

News | Breast Imaging | December 06, 2019
December 6, 2019 — A shorter course of higher-dose radiation treatment to part of the breast is showing promise in wo
MRI Exablate neuro helmet from INSIGHTEC

MRI Exablate neuro helmet from INSIGHTEC. Image courtesy of Ali Rezai, M.D., and RSNA.

News | Clinical Trials | December 03, 2019
December 3, 2019 — Focused ultrasound is a safe and effective way to target and open areas of the blood-brain barrier
#RSNA19 A sophisticated type of artificial intelligence (AI) can detect clinically meaningful chest X-ray findings as effectively as experienced radiologists, according to a study published in the journal Radiology.

Image courtesy of GE Healthcare

News | Artificial Intelligence | December 03, 2019
December 3, 2019 — A sophisticated type of...