Faces of Digital Health
Healthcare Data Series 4/5: Synthetic Data, Automation of Care Tasks, and Better Insights from EHR data in Acute and Oncology Care
Electronic health records and digital data gathering have now been around long enough that the focus has shifted from gathering to using the data for research, AI development, and clinical decision support systems. Various companies are trying to build solutions to help clinicians navigate care, and workflows, and have the right information in front of them to make decisions fast without losing time searching through the whole patient’s record. This is the fourth episode in the series about healthcare data management in the US. In the first episode, we heard how Komodo health collects data about various encounters people have with healthcare. In the second episode, we learn about Epic Cosmos – a research environment consisting of clinical data from the electronic medical records of 178 million patients. In the third episode, we heard how Palantir Foundry helps healthcare enterprises, regulatory agencies, and governments optimize their workforce planning and crisis response through an open-data approach and experience from other industries. Today, you’ll hear a panel discussion recorded at HLTH, in which industry experts shared their experience with building solutions on top of EHRs, challenges related to connecting to electronic health record and needs for better interoperability APIs to really enable data to be used for health outcomes improvement. Today, you will hear from: (Kathy Dalton Ford Chief Product and Strategy Officer at Project Ronin, Josh Rubel, Chief Commercial Officer for MDClone, David Lareau, CEO of Medicomp Systems, Inc. , Greg Miller, CGO of Lumeon).
www.facesofdigitalhealth.com
Monthly newsletter: https://fodh.substack.com/
Healthcare Data Series 3/5: Palantir Foundry and Making Data-Driven Decision Healthcare
This is the third episode in a series of discussions about healthcare data challenges and data management practices in the US. One thing is clear to everybody: regardless of the efforts, patient data is still scattered around in different organizations.
In the first episode, you can listen to a discussion with the CEO and co-founder of Komodo Health, Arif Nathoo. Komodo Health currently has some part of the healthcare data of 330 million people in the US. One of the leading providers of electronic healthcare records systems in the US is EPIC. EPIC holds around a third of the US EHR market share and has some part of the medical data of 250 million patients.
In the second episode, Phil Lindemann, VP of Business Intelligence at Epic, and Epic’s Clinical Informaticist Dave Little, MD explained a bit more about EPic Cosmos – a database built to enable easier clinical research. Epic Cosmos currently combines 178 million de-identified patient records from over 6.5 billion encounters, representing patients in all 50 US states.
In this episode, you’ll hear from Samir Unni, Healthcare Business Development Lead at Palantir Foundry.
Palantir Foundry connects the back-office software systems and analytics teams directly with caregivers. Foundry is used across the healthcare and life sciences value chain, from drug discovery and development, through to manufacturing, marketing, and sales. At the Federal level in the US Palantir is partnering with Centers for Disease Control and Prevention (CDC), Department of Health and Human Services (HHS), Food and Drug Administration (FDA), National Institutes of Health (NIH), Department of Veterans Affairs (VA), and more. In this short discussion recorded at HLTH 2022, Samir Unni, Healthcare Business Development Lead at Palantir Foundy explained the principles of Palantir in healthcare, why they support the open-data approach, how do they choose their customers and more.
www.facesofdigitalhealth.com
This discussion is part of a broader series of talks about healthcare data management in the US. An in-depth summary will be published in the monthly newsletter:
fodh.substack.com
Healthcare data series 2/4: EPIC Cosmos – Next Step in EHR Data Mining
If you work in healthcare IT, you must have heard the name EPIC. EPIC is a renowned EHR provider, that covers around a third of the US healthcare market. In 2019, Epic launched Cosmos, a special program for data mining of patient records data gathered in EPIC systems. Today, EPIC Cosmos, which was built to enable easier clinical research for contributing EPIC customers, contains over 178 million patient records from over 6.5 billion encounters, representing patients in all 50 states. In this episode’s discussion with Phil Lindemann, VP of Business Intelligence at EPIC and EPIC’s Clinical Informaticist Dave Little, you will hear more about the growth of data in EPIC Cosmos, collaboration with external healthcare IT and app providers that can join EPIC’s App Orchard ecosystem. Dave and Phil also talked about needed improvements for easier collaboration with healthcare IT vendors and innovators outside EPIC, how they hope EHRs will evolve with novel technologies and AI, and more.
This discussion is part of a broader series of talks about healthcare data management in the US. An in-depth summary will be published in the monthly newsletter:
fodh.substack.com
The January edition offers an overview into natural language processing development in healthcare and the potential of ChatGPT in healthcare: https://fodh.substack.com/p/natural-language-processing-is-the
www.facesofdigitalhealth.com
Healthcare Data Series 1/4: How is Komodo Health Gathering and Analysing Health Data of the Whole US Population?
The words healthcare data carry many associations: from frustrations around data interoperability, outrage about the value and monetization of healthcare data, anger due to poor access to medical records by patients, and we could go on.
In the next few episodes, you will hear a little bit more about healthcare data management in the US healthcare system. We’re starting with a discussion recorded at HLTH 2022, where Arif Nathoo – CEO of Komodo Health describes how the company plans to capture and de-identify every encounter patients have with the US healthcare system. Komodo Health is currently tracking individual encounters with the healthcare system for over 330 million patients. Companies such as Pfizer, AppliedVR, Turquoise Health, Janssen, and others, use Komnodo’s de-identified patient-level data and insights to inform drug development, discovery, clinical trials, clinical research, and innovation.
Make sure to subscribe to the podcast to be notified about new episodes automatically! In the next episode, you will hear why Palantir Foundy is betting on open data standards in healthcare, what a few healthcare data management vendors think about the current state of interoperability and data governance, and more.
www.facesofdigitalhealth.com
Newsletter: fodh.substack.com
Leave a rating or a review: lovethepodcast.com/facesofdigitalhealth
NLP in Healthcare 3/3: ChatGPT, MedPalm and the impact of NLP in healthcare
This episode is the last on in the series of three discussions about natural language processing in healthcare. In the first episode, I discussed the state of symptom checkers with Jeff Cutler, CCO of Ada Health – the leading symptom-checking provider. In the second episode, CEO of Suki, Punit Singh Soni, explained where voice technology is today in helping doctors better manage their medical records and notes taking. And today’s discussion will give you a comment and critical perspective on using ChatGPT in healthcare and other large language models such as Google’s MedPalm.
OBJECTIVES OF THE DISCUSSION:
- To clarify the state of natural language processing in healthcare – to which extent is this moving from research to practical use,
- To create a clear, realistic picture of ChatGPT and MedPaLM implications
Speakers:
Alexandre Lebrun – CEO of Nabla – a french company that has created an AI-based medical assistant that makes healthcare professionals more efficient. For instance, it automates clinical documentation and patient engagement.
Israel Krush, CEO of Hyro – mostly present in the US market – the world’s first headache-free conversational AI, especially focused on healthcare. It’s used for automation across call centers, mobile apps, websites and SMS include physician search, scheduling, prescription refills, FAQs and more. You’re doing this mostly in the US, supporting patient communications for health systems like Mercy Health, Baptist Health and Novant Health.
Video recording: https://www.youtube.com/watch?v=nzKTcjPX-qg&t=3s
Newsletter: https://fodh.substack.com/
www.facesofdigitalhealth.com
NLP in Healthcare 2/3: The Power of Voice and NLP for Medical Practice Optimization (Punit Singh Soni, Suki)
The promise of voice is great: doctors speak to their patients, while their words get correctly transcribed, interpreted and recorded in a structured way in a clinical system. No more long hours spent on typing clinical notes on the computer. While this may seem futuristic, it’s actually already in use in some places. At HLTH in November, I spoke with Punit Singh Sonu, CEO of Suki, which provides doctors with an AI-powered voice assistant for healthcare designed to save doctors time and energy. We discussed how Suki works, how it translates text to structured data, and how clinically risky is to rely on AI to interpret medication names which can very quickly sound alike correctly.
The biggest issue, says Punit Singh Sonu, is not specialty phrases, it’s regular English. “The problem typically happens not in medical terminology. It happens in regular English. I’ll give you a very funny example. The doctor would just say “bilateral knee,” and it would actually understand it as “beyonce knowles”. Regular English is where speech recognition trips and falls in, in specific medical terminology,” he explained.
Recap: https://www.facesofdigitalhealth.com/blog/nlp-in-healthcare-suki-voicetech
Suki: suki.ai
Monthly. newsletter: https://fodh.substack.com/
Leave a rating or a review: lovethepodcast.com/facesofdigitalhealth
Responses