Categoriearchief: eHealth Network

Diagnose prostaatkanker door kunstmatige intelligentie

Onderzoekers van het Radboudumc (aangesloten bij DUOS) hebben een ‘deep learning’ systeem ontwikkeld dat, op basis van een stukje weefsel, de agressiviteit van prostaatkanker beter kan bepalen dan de meeste pathologen. Het AI-systeem leerde zelf om prostaatkanker te herkennen, op basis van data van meer dan 1200 patiënten. Het team van het Radboud heeft de intentie om samen met onderzoekers van het Karolinska Instituut uit Zweden en Kaggle, een dochterbedrijf van Google, deze methoden verder ontwikkelen in een grote internationale wedstrijd. Het Nijmeegse onderzoek, van onder meer Wouter Bulten en Geert Litjens, is beschreven in The Lancet Oncology.

Consistent computersysteem

De onderzoekers van Radboudumc ontwikkelden het AI-systeem zo, dat het net zo naar die biopten kijkt als een patholoog. Het systeem bepaalt ook de Gleason score, en vervolgens kan het systeem een biopt indelen volgens de Gleason Grade Groups. Middels ‘deep learning’ leerde het systeem aan de hand van duizenden foto’s van biopten te herkennen wat een gezonde prostaat is, en hoe meer of minder agressief prostaatkankerweefsel eruitziet. Onderzoeker Wouter Bulten: “Het is nu getraind met 5759 biopten van ruim 1200 patiënten. Toen we de prestaties van het algoritme vergeleken met die van vijftien pathologen uit verschillende landen en met uiteenlopende ervaring, was ons systeem beter dan tien van hen en vergelijkbaar met zeer ervaren pathologen.” Een bijkomend voordeel van zo’n computersysteem is dat het consistent is en overal ingezet kan worden; de behandeling van de patiënt hangt dan niet meer af van welke patholoog naar het weefsel kijkt.

Internationale competitie

Omdat wereldwijd 1,2 miljoen mensen per jaar de diagnose prostaatkanker krijgen, was het ontwikkelen van een AI-systeem voor de diagnose interessant voor veel onderzoeksgroepen en bedrijven. “Het is een meerwaarde dat we een academisch ziekenhuis zijn,” zegt Bulten. “We zitten dicht bij de patiënt en de zorgverlener, en hebben onze eigen database van biopten.” Als vervolgstap wil het team van het Radboudumc nu samen met onderzoekers van het Karolinska Instituut in Zweden en Kaggle, een dochterbedrijf van Google gespecialiseerd in data science competities, een internationale wedstrijd organiseren waarin deelnemers gaan proberen het algoritme van het Radboudumc te verslaan. De inzichten uit zo’n wedstrijd worden dan gebruikt om de algoritmes verder te verbeteren.

Lees het complete artikel in de Zorgkrant

Philips launches AI platform for healthcare

Philips HealthSuite Insights delivers healthcare-specific tools and technologies to address the full process of building, maintaining, deploying and scaling AI solutions
Industry-first online marketplace offers curated, readily available AI assets for license

Amsterdam, the Netherlands – Royal Philips (NYSE: PHG, AEX: PHIA), a global leader in health technology, today announced the launch of HealthSuite Insights, including the Insights Marketplace, to support the advancing adoption of analytics and artificial intelligence (AI) in key healthcare domains. Making their debut at the 2018 HIMSS Conference & Exhibition (HIMSS18), HealthSuite Insights gives data scientists, software developers, clinicians and healthcare providers access to advanced analytic capabilities to curate and analyze healthcare data and offers them tools and technologies to build, maintain, deploy and scale AI-based solutions. Insights Marketplace will provide the healthcare industry’s first ecosystem where curated Artificial Intelligence assets from Philips and others are readily available for license.

AI-based solutions have great potential to improve patient outcomes and care efficiency. However, developing and deploying AI solutions for healthcare use cases can be time consuming, resource intensive and expensive. HealthSuite Insights eases the logistical challenges of deploying AI solutions in research and clinical environments. It accelerates the development of analytics solutions, and reduces development and total cost of AI solutions.

“The quality of your AI is only as good as the quality of the data you feed into it,” said Jeroen Tas, Chief Innovation & Strategy Officer Philips. “We have designed HealthSuite Insights to be used by the people who work with patient data on a daily basis and have the contextual understanding; including doctors, clinicians and hospital managers. With the HealthSuite Insights platform, we give them the ability to bring all the relevant patient information together, curate the data and use the power of AI to support precision diagnosis, personalized therapy, early intervention and greater hospital efficiency.”

We have designed HealthSuite Insights to be used by the people who work with patient data on a daily basis and have the contextual understanding; including doctors, clinicians and hospital managers.
Jeroen Tas

Chief Innovation & Strategy Officer Philips

Proven tools and technologies
The tools and technologies available through HealthSuite Insights already enable the machine learning and deep learning applications in Philips’ diagnostic imaging solutions, patient monitoring solutions, and oncology and genomics offerings. Enabled by the platform, Philips leverages AI across these innovations, by combining it with other technologies and a deep understanding of the clinical, operational and personal context to augment care professionals and patients/consumers.

Insights Marketplace for reusable AI assets
Philips’ Insights Marketplace initially offers assets supplied by Philips – including assets developed by leading scientists at Philips Research. Medically validated Philips assets will be added later this year. In late 2018, the Insights Marketplace will be further expanded to include assets submitted by third parties.

AI assets built using the Insights Platform are designed to be secure regardless of the execution environment, with sophisticated Identity and Access Management, integrated Blockchain services, and data collection and management services built in. The Insights platform can be deployed on a healthcare cloud infrastructure such as the Philips HealthSuite Digital Platform, or on premise at a provider site.

For more information on HealthSuite Insights and Philips’ full suite of integrated solutions for driving operational efficiency and improving clinical excellence, visit booth #3812 at the 2018 Annual HIMSS Conference & Exhibition taking place March 5 – 9 at the Sands Expo in Las Vegas, NV. For updates on Philips’ presence at HIMSS, follow @PhilipsLiveFrom and visit www.philips.com/himss.

Microsoft’s focus on transforming healthcare: Intelligent health through AI and the cloud

Healthcare is an industry that touches all of us, given the most basic of human goals: we all want to lead healthy lives. Last year we embarked on Healthcare NExT, a Microsoft initiative which aims to accelerate healthcare innovation through artificial intelligence and cloud computing. By working side-by-side with the healthcare industry’s most pioneering players, we are bringing Microsoft’s capabilities in groundbreaking research and product development to help healthcare providers, biotech companies and organizations around the world use artificial intelligence (AI) and the cloud to innovate.
It’s exciting work with unique challenges, and in the lead-up to next week’s Healthcare Information and Management Systems Society (HIMSS) conference, we’re announcing a number of solutions, projects and AI accelerators that we believe will help make intelligent health possible, with more details below:
Microsoft Genomics: The general availability on Microsoft Azure, providing researchers and clinicians with highly accelerated, cloud-powered genomic processing services. The flagship partner for this launch is St. Jude Children’s Research Hospital.
Microsoft Azure Security and Compliance Blueprint: HIPAA/HITRUST – Health Data & AI: The general availability of an end-to-end application development foundation to help health organizations move to the cloud with greater simplicity, compliance, security and industry-standard compatibility.
AI Network for Healthcare: An expansion of the Microsoft Intelligent Network for Eyecare, now AI Network for Healthcare, to create an AI-focused network in cardiology, in partnership with one of the largest health systems in India, Apollo Hospitals.
Microsoft 365 Huddle Solution Templates: The publication of new developer templates that extend Microsoft Teams, so health teams can benefit from state-of-the-art collaboration tools to drive quality and care outcomes in Microsoft 365.
Project Empower MD: Project EmpowerMD, a research collaboration with UPMC, will create a system that listens and learns from what doctors say and do, to dramatically reduce the burden of note-taking for physicians.
Project InnerEye: Announcing new integrations with TeraRecon and Intuitive Surgical.
We will also continue progress on current Healthcare NExT research-based projects like our Health Bot project as well as our partnerships with UPMC and Adaptive Biotechnologies.
Several themes emerge at the convergence of healthcare and technology. The explosion of data, incredible advances in computational biology, genomics and medical imaging have created vast amounts of data well beyond the ability of humans to comprehend. Clinicians and care teams are yearning to swivel their chairs from the computer and pay more attention to the patient, yet still they spend two-thirds of their time interacting with burdensome IT systems. And healthcare organizations everywhere still struggle with the lack of operational and regulatory clarity in managing and analyzing the datasets that they are generating every day. Providing cloud- and AI-powered tools will unlock the vast potential at these points of convergence. It’s why our focus is threefold: developing foundations for precision health care, enabling the health industry’s move to the cloud, and empowering the people that make healthcare work.

Read more..

Project EmpowerMD: Medical conversations to medical intelligence

Physicians continuously integrate new information, such as research studies, patient-supplied information, and new protocols into clinical practice. Physicians also collaborate with other clinicians and patients to get new insights and develop care plans. EmpowerMD captures and integrates medical expertise at scale and provides an intelligent consult, or virtual collaborator, to the physician at the point-of-care.

Our first effort is an Intelligent Scribe, initiated as part of our collaboration with UPMC. The Intelligent Scribe is a learning system that captures and synthesizes patient-physician conversations in the form of encounter note suggestions. This allows physicians to spend more face-to-face time with patients, and to use every patient interaction to achieve the best outcomes.

https://youtu.be/c6exHAzNwy4

The Intelligent Scribe leverages many services from Microsoft’s Intelligent Cloud including Custom Speech Services (CSS) and Language Understanding Intelligent Services (LUIS), customized for the medical domain. We are building a rich medical knowledge graph and a recommendation system. We have also developed an Azure-powered architecture for secure sharing of speech data with our healthcare partners.

While we are starting with the Intelligent Scribe, our long-term vision is a learning system that incorporates data from longitudinal medical records, medical devices, genomics, population health, research papers, and more. This learning system will improve as it grows and learns. We look forward to working with partners as we turn our vision into reality.

Microsoft to drive ‘intelligent health’ with new AI, cloud computing projects

Microsoft has announced a slew of projects aimed at helping global healthcare providers harness the power of artificial intelligence and the cloud.

The computing company said it wanted to help speed up innovation in the healthcare sector by providing clinicians with “intelligent health” tools that drive interoperability, while allowing for more face-to-face time with patients.

Amongst the announcements is the launch of new collaboration tools for health workers within Microsoft 365 and the development of an artificial intelligence (AI)-driven clinical platform that listens to and transcribes doctor-patient interactions.

Called Project EmpowerMD, developed in collaboration with University of Pittsburgh Medical Center (UPMC), the platform leverages Microsoft’s speech-to-text and natural language engines to record speech data, the primary aim of which is to enable hands-free note taking.

According to the project’s information page, Microsoft’s ambition is to develop “a learning system that incorporates data from longitudinal medical records, medical devices, genomics, population health, research papers, and more.”

Additional AI projects noted by Microsoft include the expansion of the company’s AI Network for Healthcare, which is being developed in partnership with India’s Apollo Hospitals and seeks to create new machine learning models for reducing the risk of cardiovascular disease in patients.

Microsoft also announced new integrations with TeraRecon and Intuitive Surgical for Project InnerEye, a machine learning-powered medical imaging initiative.

Elsewhere, Microsoft is expanding the availability of its HIPAA/HITRUST- certified security and compliance blueprint for Microsoft Azure to help care providers move health data into the cloud safely.

Microsoft Genomics has also been made generally available to healthcare providers.

The announcements come ahead of the annual HiMSS health conference, which has started today in Las Vegas and ends on Friday.

Writing on the company’s blog Peter Lee, Microsoft’s corporate vice president of AI + Research, said: “Clinicians and care teams are yearning to swivel their chairs from the computer and pay more attention to the patient, yet still they spend two-thirds of their time interacting with burdensome IT systems.

“Providing cloud and AI-powered tools will unlock the vast potential at these points of convergence. It’s why our focus is threefold: developing foundations for precision health care, enabling the health industry’s move to the cloud, and empowering the people that make healthcare work.

“Our ambition is that innovators will be able to use AI and the cloud to unlock biological insight and break data from silos for a truly personal understanding of human health and in turn, enable better access to care, lower costs and improved outcomes.”

Aside from AI, Microsoft has also delved into the world of mixed reality in health care and surgeons at Imperial College Healthcare NHS Trust have started using the technology to look inside patients before they operate on them, in an effort to make procedures safer and more time-efficient.

Zorg voor innoveren

Zorg voor innoveren faciliteert zorgvernieuwers. Zo kunnen zij het innovatieproces van idee tot toepassing zelfstandig en snel doorlopen en wordt dit proces eenvoudiger en transparanter. Zorg voor innoveren is een initiatief waarin vier overheidsorganisaties, samen met partners, hun krachten bundelen: dit zijn Zorginstituut Nederland, de Nederlandse Zorgautoriteit, Ministerie van Volksgezondheid, Welzijn en Sport en ZonMw. Lees meer >

Stroomlijnen procedures
De vier initiatiefnemers werken nauw met elkaar samen om beoordelingsprocedures voor innovaties zo goed mogelijk op elkaar af te stemmen, met als doel het innovatieproces te versnellen.

Video
Via de video op ons YouTube kanaal krijgt u een indruk van het werk van Zorg voor innoveren.

Activiteiten
Onderstaand vindt u onze activiteiten op rij.

Informeren
Deskundig antwoord
Kennisbank
GIDSen
Nieuwsbrief
Netwerkbijeenkomsten
LinkedIn

http://www.zorgvoorinnoveren.nl/

e-Health challenge; een unieke kans om bij te dragen aan zorginnovatie!

DE UITDAGING: Bedenk een lumineuze (technische) innovatie waarmee je patiënten verleidt en begeleidt om online met hun gezondheid aan de slag te gaan en om dit ook te blijven doen.

Het gaat om een product of dienst die aansluit bij de individuele behoefte van mensen met een chronische aandoening zodat deze mensen met hun gezondheid aan de slag gaan en dit blijven doen.

Deze challenge is een initiatief van Philips, Zilveren Kruis en Stichting Zorg Binnen Bereik.

Waar aanmelden: http://www.zorgbinnenbereik.nl/challenge

Wanneer aanmelden: deadline is 04-09-2016

Prijs:

De winnaar van de challenge wordt bekend gemaakt tijdens het symposium Expeditie Zelfzorg op 4 oktober. Ben jij die winnaar? Dan zal je verder worden begeleid door Philips en het Zilveren Kruis om je idee te realiseren en op te schalen. Philips helpt de winnaar om zijn idee verder uit te werken in een accelerator programma. Het Zilveren Kruis biedt de winnaar 6 maanden persoonlijke begeleiding en coaching. Een prijs ter waarde van ruim 30.000 euro! Met als uiteindelijke doel: dat de innovatie een stevige plek kan krijgen in de wereld van eHealth.

E-health

E-health is een belangrijk middel om de zorg beter, dichterbij, klantvriendelijker en goedkoper te organiseren. En om te helpen gezond te leven. De technologie die mensen in het dagelijks leven gebruiken, kan hen in de zorg ook ondersteunen. Zo is zorg op afstand mogelijk. En kan beter gekeken worden of een behandeling nodig of nuttig is, of ten koste gaat van kwaliteit van leven. Ook kan het van grote toegevoegde waarde zijn in preventie. Door bijvoorbeeld vroege en betere opsporing en herkennen van symptomen. Ook kunnen serious gaming, apps en andere innovaties mensen motiveren gezonde keuzes te maken.