Glendor, Inc
医院和医疗保健
Draper，Utah 173 位关注者
Our mission is to protect patients' privacy while empowering medical data sharing.
关于我们
Do you need to share multimodal medical data? Are you confident in the effectiveness of your current de-identification process? Join us for a live demo to see how easy-to-integrate fully automatic Glendor PHI Sanitizer software can enhance your existing procedures. Hospitals agree that data compliance and correct deidentification are CRUCIAL for their businesses. Unfortunately, many hospitals: - Use manual or semi-automatic methods that make de-identifying large volumes of data infeasible. - Use third party services to de-identify data thus exposing sensitive data to outside companies - Use approaches that expect all data to be uniform and highly structured, and de-identification systems that miss never-seen-before cases. What would be of help is a deidentification solution that: - Covers non-standard and never-seen-before cases - Is scalable and can process millions of data points - Will enable the hospital to do de-identification on premises (basement or cloud) behind firewalls. We at Glendor are on a quest to safeguard patients’ privacy by de-identifying Protected Health Information (PHI) automatically and at source. What sets us apart: - Fully Automatic (unlike templates-based solutions that require customization and tweaking) - At Source (unlike APIs and 3rd party services that require sensitive data to be shared) - Easy to Integrate and Use (no BAA required, 1 min to install and run) - Multiple Modalities/Multiple Formats Our clients include Hospitals, NIH, Lab Networks, Big Pharma. Data Lakes. E.g. https://aws.amazon.com/marketplace/pp/prodview-unw4li5rkivs2 Upgrade to automatic data de-identification behind your firewall! Say goodbye to manual processes and third-party risks. Join us for a live demo to see how Glendor PHI Sanitizer can enhance your existing procedures. https://calendly.com/glendor/demo
- 网站
-
https://glendor.com/
Glendor, Inc的外部链接
- 所属行业
- 医院和医疗保健
- 规模
- 11-50 人
- 总部
- Draper，Utah
- 类型
- 私人持股
- 创立
- 2017
- 领域
- Medical Big Data、Privacy、Healthcare、Protected Health Information、HIPAA、GDPR、AI、PHI Deidentification和AIinHealthcare
产品
![点击此处查看Glendor PHI Sanitizer]()
Glendor PHI Sanitizer
数据屏蔽软件
Glendor PHI Sanitizer is an easily installed AI-based system that fully automatically and in situ (behind the firewall on customer's premises or in customer's cloud) de-identifies PHI (Protected Health Information) in Multimodal Medical Data (Medical Images, Reports, Videos, Photos, Voice). In situ - original images are sanitized on customer's premises/customer's cloud Autonomous - no Internet connection is required to run the software Automatic - does not require tuning, templates, or manual intervention Flexible - works with not-seen-before images by mimicking human behavior in anticipating variability Sanitizes both burned-in pixel data and standard and private metatags Works with a variety of modalities (X-rays, CT Scans, MRIs, …) and formats (DICOM, JPEG, JPEG2000, …) Designed to be easily incorporated as a node in an imaging workflow
地点
-
主要
获取路线
US，Utah，Draper
Glendor, Inc员工
动态
-
CEO & Co-Founder @ Glendor, Inc | AI-based Fully Automatic at Source Software for PHI Deidentification of Multimodal Medical Data (Medical Images, Reports, Videos, Photos, Voice)
On Sunday, I had an interesting conversation with Dr. Carl Rosen and Dr. Jonathan Ditkoff on their YouTube channel Einstein's Eyes. We discussed automatic PHI de-identification of medical data at the source and multimodal medical data lakes for AI large model training. Watch the conversation here: https://lnkd.in/g5bCutFp.
De-identifying Medical Data with AI: Protecting Patient Privacy at the Source | Einstein's Eyes ??
https://www.youtube.com/
-
Most of the medical data for AI Models training is coming from a handful of states. What about the rest of us? AI in Healthcare models are as good as the data they are trained on. Models trained on data from, say, a large north east hospital are not necessarily good for patients in the north west or south east of the US, not to mention rural population in the middle of the country. It is high time we change this disbalance and focus on providing access for AI researchers and AI in Healthcare companies to diverse de-identified multimodal medical data lakes (texts, images, videos, voice recordings), to pave the way to building un-biased generalizable AI models based on derived (e.g., doctor’s notes) and raw?data (e.g., CT scans) that can be applicable to the entire US population. DM me if you would like you and I to talk about how we can do it together. Activate to view larger image,
-
-
I'll be speaking at Safeguarding Patient Health Information in the Digital Age! Join us on November 12 to discuss Medical Data, Protected Health Information and how important it is to deidentify the data to protect patient's privacy while making possible sharing of data for research and AI Models training. #PHI #ProtectedHealthInformation #MedicalDataLakes #Privacy #AIinHealthcare
Join Us for a Critical Roundtable on Safeguarding Patient Health Information! Patient health information (PHI) is at the core of healthcare operations, and safeguarding it is more important than ever in the face of increasing cyber threats. This roundtable brings together industry leaders—Registered Nurses, CNO, NPs, CIOs, CISOs, Directors of Technology, CEOs, CFOs, MDs, DOs, Stakeholders—to discuss best practices, regulatory updates, and the role of technology in protecting sensitive data. Don’t miss this opportunity to learn and collaborate on securing PHI. Register now to secure your spot and be part of this vital conversation! Click to secure your spot: https://lnkd.in/gJspQQpP
此处无法显示此内容
在领英 APP 中访问此内容等
-
I've been invited to be a panelist at the Roundtable Discussion on Transforming Patient Care: The Integration of AI in Healthcare Diagnostics and Treatment. Excited to engage in meaningful conversations about the future of healthcare and the impact of AI on patient outcomes. 6/6/24 at 9:30am MT. YouTube streaming link: https://lnkd.in/gBeM-zjR #Healthcare #AI #PatientCare