Prashant Shah

https://doi.org/10.1038/s42256-023-00652-2
Part of ISSN: 2522-5839
CONTRIBUTORS: Alexandros Karargyris; Renato Umeton; Micah Sheller; Alejandro Aristizabal; Johnu George; Anna Wuest; Sarthak Pati; Hasan Kassem; Maximilian Zenk; Ujjwal Baid et al.

Medical artificial intelligence (AI) has tremendous potential to advance healthcare by supporting and contributing to the evidence-based practice of medicine, personalizing patient treatment, reducing costs, and improving both healthcare… Show more

https://doi.org/10.1038/s42256-023-00652-2
Part of ISSN: 2522-5839
CONTRIBUTORS: Alexandros Karargyris; Renato Umeton; Micah Sheller; Alejandro Aristizabal; Johnu George; Anna Wuest; Sarthak Pati; Hasan Kassem; Maximilian Zenk; Ujjwal Baid et al.

Medical artificial intelligence (AI) has tremendous potential to advance healthcare by supporting and contributing to the evidence-based practice of medicine, personalizing patient treatment, reducing costs, and improving both healthcare provider and patient experience. Unlocking this potential requires systematic, quantitative evaluation of the performance of medical AI models on large-scale, heterogeneous data capturing diverse patient populations. Here, to meet this need, we introduce MedPerf, an open platform for benchmarking AI models in the medical domain. MedPerf focuses on enabling federated evaluation of AI models, by securely distributing them to different facilities, such as healthcare organizations. This process of bringing the model to the data empowers each facility to assess and verify the performance of AI models in an efficient and human-supervised process, while prioritizing privacy. We describe the current challenges healthcare and AI communities face, the need for an open platform, the design philosophy of MedPerf, its current implementation status and real-world deployment, our roadmap and, importantly, the use of MedPerf with multiple international institutions within cloud-based technology and on-premises scenarios. Finally, we welcome new contributions by researchers and organizations to further strengthen MedPerf as an open benchmarking platform. Show less

Although machine learning (ML) has shown promise across disciplines, out-of-sample generalizability is concerning. This is currently addressed by sharing multi-site data, but such centralization is challenging/infeasible to scale due to various limitations. Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates. Here we present the largest FL study to-date, involving data from 71 sites across 6 continents, to generate an… Show more

Although machine learning (ML) has shown promise across disciplines, out-of-sample generalizability is concerning. This is currently addressed by sharing multi-site data, but such centralization is challenging/infeasible to scale due to various limitations. Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates. Here we present the largest FL study to-date, involving data from 71 sites across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, reporting the largest such dataset in the literature (n = 6, 314). We demonstrate a 33% delineation improvement for the surgically targetable tumor, and 23% for the complete tumor extent, over a publicly trained model. We anticipate our study to: 1) enable more healthcare studies informed by large diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further analyses for glioblastoma by releasing our consensus model, and 3) demonstrate the FL effectiveness at such scale and task-complexity as a paradigm shift for multi-site collaborations, alleviating the need for data-sharing. Show less

De-centralized data analysis becomes an increasingly preferred option in the healthcare domain, as it alleviates the need for sharing primary patient data across collaborating institutions. This highlights the need for consistent harmonized data curation, pre-processing, and identification of regions of interest based on uniform criteria. Approach. Towards this end, this manuscript describes the Federated Tumor Segmentation (FeTS) tool, in terms of software architecture and functionality. Main… Show more

De-centralized data analysis becomes an increasingly preferred option in the healthcare domain, as it alleviates the need for sharing primary patient data across collaborating institutions. This highlights the need for consistent harmonized data curation, pre-processing, and identification of regions of interest based on uniform criteria. Approach. Towards this end, this manuscript describes the Federated Tumor Segmentation (FeTS) tool, in terms of software architecture and functionality. Main results. The primary aim of the FeTS tool is to facilitate this harmonized processing and the generation of gold standard reference labels for tumor sub-compartments on brain magnetic resonance imaging, and further enable federated training of a tumor sub-compartment delineation model across numerous sites distributed across the globe, without the need to share patient data. Significance. Building upon existing open-source tools such as the Insight Toolkit and Qt, the FeTS tool is designed to enable training deep learning models targeting tumor delineation in either centralized or federated settings. The target audience of the FeTS tool is primarily the computational researcher interested in developing federated learning models, and interested in joining a global federation towards this effort. The tool is open sourced at https://github.com/FETS-AI/Front-End. Show less

Federated learning (FL) is a computational paradigm that enables organizations to
collaborate on machine learning (ML) and deep learning (DL) projects without sharing sensitive data, such as patient records, financial data, or classified secrets. Approach. Open federated learning (OpenFL) framework is an open-source python-based tool for training ML/DL algorithms using the data-private collaborative learning paradigm of FL, irrespective of the use case. OpenFL works with training pipelines… Show more

Federated learning (FL) is a computational paradigm that enables organizations to
collaborate on machine learning (ML) and deep learning (DL) projects without sharing sensitive data, such as patient records, financial data, or classified secrets. Approach. Open federated learning (OpenFL) framework is an open-source python-based tool for training ML/DL algorithms using the data-private collaborative learning paradigm of FL, irrespective of the use case. OpenFL works with training pipelines built with both TensorFlow and PyTorch, and can be easily extended to other ML and DL frameworks. Main results. In this manuscript, we present OpenFL and summarize its motivation and development characteristics, with the intention of facilitating its application to existing ML/DL model training in a production environment. We further provide recommendations to secure a federation using trusted execution environments to ensure explicit model security and integrity, as well as maintain data confidentiality. Finally, we describe the first real-world healthcare federations that use the OpenFL library, and highlight how it can be applied to other non-healthcare use cases.
Significance. The OpenFL library is designed for real world scalability, trusted execution, and also prioritizes easy migration of centralized ML models into a federated training pipeline. Although OpenFL’s initial use case was in healthcare, it is applicable beyond this domain and is now reaching wider adoption both in research and production settings. The tool is open-sourced at github.com/intel/openfl. Show less

Brain extraction is an indispensable step in neuro-imaging with a direct impact on downstream analyses. Most such methods have been developed for non-pathologically affected brains, and hence tend to suffer in performance when applied on brains with pathologies, e.g., gliomas, multiple sclerosis, traumatic brain injuries. Deep Learning (DL) methodologies for healthcare have shown promising results, but their clinical translation has been limited, primarily due to these methods suffering from i)… Show more

Brain extraction is an indispensable step in neuro-imaging with a direct impact on downstream analyses. Most such methods have been developed for non-pathologically affected brains, and hence tend to suffer in performance when applied on brains with pathologies, e.g., gliomas, multiple sclerosis, traumatic brain injuries. Deep Learning (DL) methodologies for healthcare have shown promising results, but their clinical translation has been limited, primarily due to these methods suffering from i) high computational cost, and ii) specific hardware requirements, e.g., DL acceleration cards. In this study, we explore the potential of mathematical optimizations, towards making DL methods amenable to application in low resource environments. We focus on both the qualitative and quantitative evaluation of such optimizations on an existing DL brain extraction method, designed for pathologically-affected brains and agnostic to the input modality. We conduct direct optimizations and quantization of the trained model (i.e., prior to inference on new data). Our results yield substantial gains, in terms of speedup, latency, throughput, and reduction in memory usage, while the segmentation performance of the initial and the optimized models remains stable, i.e., as quantified by both the Dice Similarity Coefficient and the Hausdorff Distance. These findings support post-training optimizations as a promising approach for enabling the execution of advanced DL methodologies on plain commercial-grade CPUs, and hence contributing to their translation in limited- and low- resource clinical environments. Show less

The enormous amount of data collected in cancer screening and the need to analyze it quickly create significant challenges. To address these issues, some companies collaborate with computation experts.

In China, Ningbo Konfoong Bioinformation Tech (KFBio), a digital pathology company, set up a collaboration with Intel, a technology company based in Santa Clara, California, to screen for cervical cancer. Instead of using blood samples, KFBio uses slides of liquid-based cytology specimens… Show more

The enormous amount of data collected in cancer screening and the need to analyze it quickly create significant challenges. To address these issues, some companies collaborate with computation experts.

In China, Ningbo Konfoong Bioinformation Tech (KFBio), a digital pathology company, set up a collaboration with Intel, a technology company based in Santa Clara, California, to screen for cervical cancer. Instead of using blood samples, KFBio uses slides of liquid-based cytology specimens obtained from Pap smears into images. Intel is helping with the image analysis. These slides are scanned at 40,000 by 40,000 pixels, and the resulting 1.6 gigapixels include lots of information, says Prashant Shah—global head of artificial intelligence for health and life sciences at Intel, and an advisor on AI for the U.S. National Institutes of Health.

The objective is to analyze the slides as quickly and accurately as possible. Using Intel's technology and expertise, the company increased the speed of analysis 8.4 times. In addition to being speedy, the AI-based model must run on various computers. Running the model that analyzes the slides takes hundreds of gigabytes of computer memory. "Using our Xeon-based servers and optimizing neural-network algorithms using OpenVINO, we created a solution that can run efficiently on small- and large-footprint hardware," Shah says. That's necessary for the screening tool to be used around the world. Show less

Frustrated by their inability to bend their healthcare cost curves, large employers are directly collaborating with provider systems to design new benefit programs.

Document can be accessed here:
https://app.box.com/files/0/f/0/1/f_60175018973

Interoperability—the fluid and secure sharing of electronic health record (EHR) data and other health information among all members of a patient’s healthcare team—is essential to achieving the Institute for Healthcare Improvement (IHI) Triple Aim. Yet despite attention from EHR vendors and policymakers alike, smooth cross-vendor sharing of actionable EHR data has remained limited and cumbersome. The results are detrimental to patients, providers, and payers alike.

Intel addressed these… Show more

Interoperability—the fluid and secure sharing of electronic health record (EHR) data and other health information among all members of a patient’s healthcare team—is essential to achieving the Institute for Healthcare Improvement (IHI) Triple Aim. Yet despite attention from EHR vendors and policymakers alike, smooth cross-vendor sharing of actionable EHR data has remained limited and cumbersome. The results are detrimental to patients, providers, and payers alike.

Intel addressed these limitations as the company scaled its Connected Care employee health program to Oregon , where healthcare partner organizations used Greenway Prime and multiple versions of Epic EHR. Using industry standards and supported by both Epic and Greenway, Intel and its collaborators—Kaiser Permanente Northwest, Providence Health and Services in Oregon, Premise Health, and The Portland Clinic (TPC)—needed just eight months to implement coordinated workflows with push and pull connectivity across the diverse EHRs. The delivery system partners (DSPs) are using these interoperability improvements to help provide Intel employees and their dependents with more coordinated care and a better patient experience while improving efficiency and gaining more complete data for with which to manage population health including accurate medications, allergies, problem lists and other key clinical data. We expect this interoperability foundation to help us improve our population’s health outcomes, support a shared-risk compensation model, and scale the program to other areas where Intel has a large employee base.

The Connected Care experience shows that standards-based, cross-vendor interoperability, while not perfect, is achievable today. It also highlights areas where further refinement of healthcare industry standards can advance collaboration and deliver bigger payoffs .
Show less

Intel is working with Intermountain's Transformation Lab to understand and develop tools that integrate genetic data and accelerate its use through a new patient data-centric model that delivers meaningful and easy-to-understand information, and accelerates its use at the point of care

Coordinated Care Organizations in Oregon for the medicaid population