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

Life Image and Mendel.ai Bringing Artificial Intelligence to Clinical Trial Development
News | Artificial Intelligence | November 15, 2018
Life Image and Mendel.ai announced a new strategic partnership that will facilitate the adoption and enhancement of...
News | Enterprise Imaging | November 14, 2018
Konica Minolta Healthcare Americas Inc. will showcase new features and tools for the Exa Enterprise Imaging platform at...
Artificial Intelligence Predicts Alzheimer's Years Before Diagnosis
News | Neuro Imaging | November 14, 2018
Artificial intelligence (AI) technology improves the ability of brain imaging to predict Alzheimer’s disease, according...
Researchers Awarded 2018 Canon Medical Systems USA/RSNA Research Grants
News | Radiology Imaging | November 13, 2018
The Radiological Society of North America (RSNA) Research & Education (R&E) Foundation recently announced the...
MDW Unveils First Radiology Blockchain Platform at RSNA 2018
News | Radiology Business | November 13, 2018
Medical Diagnostic Web (MDW) will debut the first radiology blockchain platform designed to connect all players in the...
Subtle Medical Showcases Artificial Intelligence for PET, MRI Scans at RSNA 2018
News | Artificial Intelligence | November 13, 2018
At the 2018 Radiological Society of North America annual meeting (RSNA 2018), Nov. 25-30 in Chicago, Subtle Medical...
ContextVision Introduces AI-Powered Image Enhancement for Digital Radiography
Technology | Artificial Intelligence | November 09, 2018
With the integration of deep learning technology, ContextVision takes digital radiography to new levels with its latest...
Ambra Health Launches Mobile App for Instant Medical Image Access
Technology | Mobile Devices | November 09, 2018
Ambra Health announced the launch of its first iOS mobile app for healthcare providers and patient access. Designed...
Figure 1

Figure 1

Feature | Information Technology | November 09, 2018 | By Jef Williams and Laurie Lafleur
Every year in late November tens of thousands of diagnostic imaging professionals from all over the globe descend upon...
Sponsored Content | Videos | Information Technology | November 08, 2018
Deployed on Microsoft Azure, GE Healthcare’s iCenter is a secure, cloud-based tool that provides visibility to asset