Machine Learning

Inspur Information Improve Patient Outcomes Using AI & ML

AI report analysis ensures that lung patients receive necessary follow-up care after medical diagnostic imaging

At NVIDIA GTC, Inspur Information announced the results of its partnership with the Feinberg School of Medicine at Northwestern University in leveraging artificial intelligence (AI) to advance medical research and healthcare. Northwestern researchers have developed a custom AI workflow using Inspur AI servers with NVIDIA GPUs to accelerate the processing of radiology reports and provide crucial patient follow-up.

Medical diagnostic imaging from modalities such as X-rays, CTs and MRIs are reviewed, and findings are summarized in a radiology report which can contain recommendations for follow-up actions, such as further tests and evaluations. Due to the length and intricacy of these types of reports, up to 33% of follow-up recommendations are delayed or unintentionally overlooked, which can lead to poor patient outcomes. To solve this problem, Mozziyar Etemadi, MD, PhD, and his team at Northwestern developed an initiative to ensure reliable follow-ups of radiographic findings to prevent diagnostic and treatment delays and improve outcomes. The team developed an AI workflow based on recurrent neural networks and natural language processing (NLP) to examine and identify radiology reports with findings that require additional medical follow-up.

“We used AI and the tools at our disposal, including the Inspur NF5488M5-D GPU server featuring the NVIDIA A100 Tensor Core GPU,” said Dr. Etemadi. “We built our own custom AI workflow that reads nearly every single radiology report and, through deep integration with our medical record system, provides alerts and notifications to the primary care doctor, patient, and dedicated follow-up team, to ensure that important details do not fall through the cracks.”

In a study published in the New England Journal of Medicine Catalyst, Northwestern reported that its custom AI workflow screened over 570,000 imaging studies in 13 months and found 29,000—5.1% of the total—to contain lung-related follow-up recommendations, at an average rate of 70 findings flagged per day. Results demonstrated 77.1% sensitivity, 99.5% specificity, and 90.3% accuracy for follow-up on lung findings. Nearly 5,000 interactions with physicians were generated, and over 2,400 follow-ups were completed. The article concludes that AI and machine learning processes improve reliability of medical imaging findings, which can lead to effective reduction and prevention of high-risk diseases. The researchers have also released their open-source code with a tutorial at this link.

This custom AI program is just one result of Northwestern’s AI initiative that has been supported by Inspur Information since 2019. The partnership first began when Northwestern was pilot testing high-performance data pipelines to enable deep learning directly on health system enterprise data. The AI development teams at Northwestern had been limited by constraints of the legacy enterprise systems where the data is stored, requiring separate and costly copies of data to be created when conducting deep learning projects. Inspur Information provided the NF5488M5-D AI training platform, integrated with custom middleware and high-speed network connections, which Dr. Etemadi’s team used to build in-house, custom PyTorch and TensorFlow dataloaders that allowed for seamless data access on their legacy environment, vastly improving AI training.

Results found that the NF5488M5-D provided compute performance that delivered significant improvements not just in model training but in overall project delivery. With manifold improvements in training speed and data prep, Inspur’s solution enabled rapid prototyping, iteration, and deployment of deep learning models directly into the healthcare environment.

Rhonda Liao, VP of Strategic Alliance at Inspur Systems, remarked on the collaboration, “It is amazing to work with Dr. Etemadi, to see how he brings new technology to AI-based research at Northwestern and converts it into real improvements in healthcare. Inspur is proud to be part of this journey, and we appreciate NVIDIA’s great collaboration and support on this endeavor.”

“Inspur AI servers are some of the most robust and performance optimized multi-GPU server solutions on the market, backed by our deep capabilities in AI innovation that span MLPerf-winning servers to AI frameworks to large model development,” said Liu Jun, Vice President of Inspur Information and General Manager of AI and HPC. “I want to congratulate Dr. Etemadi’s work and applaud Northwestern Feinberg School of Medicine’s leadership in AI innovation.”

“AI enables medical researchers to bring much-needed tools into the clinic, delivering results for doctors and patients alike,” said Dr. Mona Flores, Global Head of Medical AI at NVIDIA. “By optimizing workflows using AI, backlogs can be alleviated, and clinicians can prioritize follow-ups with patients who need it the most.”

Dr. Etemadi concluded, “Working with Inspur and utilizing cutting-edge technologies, we’re able to build customized AI tools to serve our patients, doctors, nurses, and front-line staff. We’re excited for the future of healthcare, artificial intelligence, and all the ways that we can continue to help our patients.”

For more such updates and perspectives around Digital Innovation, IoT, Data Infrastructure, AI & Cybersecurity, go to AI-Techpark.com.

Related posts

Black Crow AI Raises $25 Mn to Make Machine Learning Available to All

PR Newswire

GLOBALFOUNDRIES and Cadence Add ML Capabilities to DFM Signoff

Business Wire

InterSystems & AFG to develop data management solution

Business Wire