Tag: Health & Life Science

ENHANCED CLINICAL TRIAL ENROLLMENT

Written by Nick Brown on . Posted in USE CASES.

Situation

85% of clinical trials end with less than expected enrollment, while 19% are terminated or fail to meet accrual goals at all. This scenario has significant impact on the viability of trials, leading to insufficient results, loss of time and financial resources and ultimately a reduction in innovation.

Problem

One of the biggest challenges associated with clinical trial enrollment is identifying candidates due to the vast amounts of siloed and unstructured data needed. In fact, over half of eligibility criteria is unstructured, making it incredibly complex to search and access. Attempting to make sense of this content, combined with searching across data silos such as patient records and genomics data is incredibly time intensive, with key insights and candidates missed.

Solution

A leading U.S. cancer research center is turning to Vyasa to solve this problem. By establishing an intelligent data fabric with Vyasa Layar, the research center has created a unified data platform to search and identify relationships between clinical trials and its patient population to improve trial enrollment and viability. With Vyasa, the research center can:

  • Unify siloed data sources including patient records, genomics files and clinical trials into a single platform without moving or replicating files.
  • Search across multiple data sources and quickly identify insights with the power of deep learning.
  • Explore data in natural language. No coding or data science experience required.
  • Discover relationships in their data through dynamic knowledge graphs.
  • Visualize their data in smart spreadsheets and real-time dashboards.

With Vyasa, organizations empower users across skill sets to leverage deep learning and gain new value from their data. In turn, users have experienced a 25% improvement in productivity around data analysis tasks, all without compromising on accuracy.

ACCELERATING DATA ACCESSIBILITY FOR PEDIATRIC ONCOLOGY

Written by Nick Brown on . Posted in USE CASES.

Situation

The NIH’s Childhood Cancer Data Initiative is set to revolutionize the data landscape around pediatric cancers and treatments. While important progress is being made, hospitals and oncology departments still face an uphill battle with the resources they have available to understand patient illnesses and gain the insights they need.

Problem

The healthcare industry faces a number of data challenges, all of which are impacting pediatric oncology. These include:

  • Data silos across departments and institutions.
  • Limited access to the latest research and trials on pediatric cancer and treatments.
  • Tools for quickly accessing insights in complex data. Ex: published research, biomedical images, drug-like compounds, genomics files.

Solution

Advancements in deep learning combined with a novel data architecture developed by Vyasa are changing the way hospitals, researchers and oncologists can collect and analyze data related to pediatric cancer. Known as an intelligent data fabric, Vyasa enables organizations to unify disparate data sources regardless of cloud or on-premise storage location and without moving or replicating the data. Once connected, Vyasa applies deep learning on the data making it easily searchable and accessible. With an intelligent data fabric, users improve search accuracy by 97% while decreasing manual analysis time by 25% through the ability to:

  • Collaborate and share data across departments, and identify trends across patient populations.
  • Easily search and extract insights from genomics data, including processing VCF and BAM files.
  • Harmonize multiple data sources together, including structured and unstructured content. (ex: scientific literature & images).
  • Discover terms and insights not listed in ontologies with Vyasa’s named entity recognition (NER).

The Vyasa intelligent data fabric comes with a suite of low code interfaces that enable users to search and visualize their data in natural language, accellerating access to insights for physicians, oncologists, researchers and more.

SMARTER RESEARCH: AI-POWERED SYSTEMATIC LITERATURE REVIEW

Written by vyasa on . Posted in USE CASES.

More than 90% of clinical-trial compounds fail to demonstrate sufficient efficacy and safety. To mitigate this issue, many look to third-parties to conduct extensive research via systematic literature review (SLR) to gather the relevant information needed to validate the investment and approach to a trial. While providing valuable insight, each SLR can cost over $140,000.

Problem

SLRs are largely conducted via manual processes – with researchers needing to compile, review and analyze large sets of unstructured content. As a result, these processes are incredibly time consuming due to the amount of data and grey literature that needs to be consumed and reported on to make SLRs successful. Due to the nature of this work, insights can be missed and timelines can be delayed which hold up productivity for the end customer.

Solution

Advancements in deep learning text analytics are enhancing systematic literature reviews by improving the accessibility and searchability of unstructured content. Vyasa has developed high-performing deep learning models that understand context and can identify key terms that improve the accuracy and time spent on systematic literature reviews. We then take this a step further with our Layar data fabric, a novel data architecture that unifies content sources into a single platform. With the Vyasa platform, users can:

  • Integrate siloed data sets into a single, searchable platform.
  • Search unstructured content in natural language.
  • Explore their data via highly-visual knowledge graphs, dashboards and smart spreadsheets.
  • Export unstructured content into structured formats.

By leveraging Vyasa, users can improve query accuracy by 97% while reducing research times by as much as 90%, leading to smarter, more efficient systematic literature reviews.

BEYOND THE VISUAL: EXTRACTING INSIGHT FROM MEDICAL IMAGERY

Written by vyasa on . Posted in USE CASES.

The adage “a picture is worth a thousand words” isn’t just a reflection on traditional photographs. In fact, as much as 90% of healthcare data comes from imagery.1 Within each image hides key insights from disease type to patient demographics to dimensions, voxel size and repetition time. This data can influence diagnoses from healthcare providers, rare disease research, clinical trial design and much more.

Problem

While rich in insight, managing and analyzing medical imagery is incredibly complex. Images come in a variety of modalities, are produced by different departments such as radiology and pathology and are utilized differently across the healthcare organization – from providers to researchers to analysts.

In addition, image files are much larger than traditional data sources – making them difficult to share while taking up valuable storage. As a result, healthcare organizations spend far too much time and financial resources on imagery – from tasking highly-skilled professionals with tedious image analysis to managing the IT infrastructure needed to utilize these assets.

Solution

Most think of applying deep learning for image recognition, but these solutions provide much greater value when applied to analyzing metadata within medical imagery. Vyasa is changing the way healthcare organizations approach managing and from their content. Advanced deep learning image analytics built by Vyasa enable users to:

  • Unify and catalog image assets across the organization.
  • Enhance image detection and classification.
  • Make images easily searchable via simple annotation.

With a streamlined approach to image analytics with Vyasa, users can easily filter their image libraries to just their most relevant content, quickly identify cohorts for clinical trials, improve research accuracy for pathology and radiology reports and much more.

1. GE (2018) Beyond Imaging:the paradox of AI and medical imaging innovation https://www.gehealthcare.com/article/beyond-imagingthe-paradox-of-ai-and-medical-imaging-innovation#_ftn- ref1

DON’T MOVE YOUR DATA. UNIFY IT.

Written by vyasa on . Posted in USE CASES.

It’s never been easier to share, store and replicate data thanks to our increasingly digital working environments. While this scenario has made activities like collaboration and remote work seamless, the deluge of new data produced within organizations is creating strains on IT systems and resulting headaches for the professionals in charge of managing them. Considering that 64.2ZB1 of data was created or replicated in 2020 alone, it’s no wonder data has not only become the lifeblood, but also the thorn in the side of enterprise IT departments.

Problem

Over 80% of organizational data is dark2. IT teams are suffering from dark data if they’re challenged with:

  • Multiple data silos
  • Redundant or obsolete files
  • Unstructured content such as images, PDFs, presentations decks, etc.

Largely inaccessible, yet rich in insight, simply sitting on this data can lead to missed intelligence that can influence product development, sales strategies or competitor research that can drive successful businesses. Tasked with solving this problem, IT teams traditionally turn to unsustainable solutions that require expensive and time consuming data migrations.

Solution

A new data architecture is changing the way IT professionals can approach data management. Known as the data fabric, IT teams can unify data sources across their environment, regardless of whether files are stored on premise or in the cloud. No need to duplicate your data or storage and no data lake required.

Vyasa takes this a step further with its Layar deep learning data fabric. Combining the data fabric architecture with novel approaches to deep learning, IT teams that integrate their data within Layar make their content easy to search, explore and visualize, regardless of file format.

Listed as the #1 strategic technology trend for 2020 by Gartner3, data fabrics are poised to eliminate the need for costly data migrations that can impact productivity and create new data management issues for IT teams.

1 Reinsel, D and Rydning, J. (2021). IDC Global DataSphere https://www.idc.com/getdoc.jsp?containerId=IDC_P38353

2 IBM (2015, November 23). The Future of Cognitive Computing. https://www.ibm.com/blogs/cloud0archive/2015/future-of-cognitive-computiving/

3 Gartner (2021). Gartner Top Strategic Technology Trends for 2022 https://www.gartner.com/en/information-technology/insights/top-technology-trends

TACKLING DATA SILOS POST HEALTHCARE M&A

Written by vyasa on . Posted in USE CASES.

The health services industry is ripe with mergers & acquisitions (M&A). In fact, 2021 deal volumes have exceeded levels from the past three years.1 While healthcare M&A can have significant benefits to patients including access to a larger breadth of services or decreased costs, it often causes major pain points for IT teams tasked with maintaining operational efficiency. Research firm Deloitte notes that IT system integration accounts for 70% of organizational synergies.2

Problem

Healthcare organizations produce and collect mountains of data every day that is subsequently stored in various formats and silos. When healthcare providers merge, IT teams are faced with swamps of data consisting of valuable insight from content such as:

  • Patient records
  • Clinician notes
  • Published research
  • Financial records
  • Medical imagery

Privacy & security protocols as well as interoperability issues make accessing and unifying this data a challenge.

Solution

Advancements in deep learning are revolutionizing the way healthcare organizations can manage, access and extract insights from their most important content. With Vyasa’s Layar data fabric, those in charge of managing data across the healthcare network can unify data sources regardless of file format or where it’s stored and without requiring a data lake. Deep learning models built within Layar automatically catalog the integrated data making it easily accessible.

By leveraging a deep learning data fabric architecture, healthcare organizations can make access to insights a matter of seconds or minutes, instead of days or weeks. Research and analysis is accelerated, as is the accuracy of outcomes, leading to safer clinical trials, improved disease research and a healthier patient population.

1 PwC (2021). Health services deals insights: 2021 midyear outlook https://www.pwc.com/us/en/industries/health-industries/library/health-services-deals-insights.html

2 Deloitte (2018). Health care mergers and acquisitions | The IT factor https://www2.deloitte.com/us/en/pages/life-sciences-and-health-care/articles/healthcare-it-mergers-and-acquisi- tions-technology.html

Unifying Data. Accelerating Insights.

Applications

Layar

Cortex

Synapse

Axon

Signal