AI for Healthcare: Interview with Shantanu Nigam, Co-Founder and CEO of Jvion

Shantanu Nigam is the Co-Founder and CEO of Jvion, a company that uses artificial intelligence to enable the healthcare system to predict where and when avoidable patients harm will happen in order to intervene in a time and cost effective way.

What is your background and how did you start Jvion? 

I have an engineering degree and did an Artificial Intelligence startup in the late 90s. For most 2000’s I worked in healthcare as management consultant for Arthur Anderson and Accenture.

What is Jvion’s mission?

Jvion’s mission to eliminate avoidable patient harm. Each of our use case or vector as we call it is designed to stop avoidable waste.

Walk us through Jvion’s products, and what problems they solve. 

We have a single product not multiple point solutions for various clinical areas. Our product helps reduce avoidable patient harm by anticipating where it can happen and by finding the right interventions that can stop it.

Product is applied to around 50+ clinical areas of harm or vectors, these are broadly categorized for when the patient is inside the hospital (ex. Sepsis, falls, CDiff, Pressure injury, patient experience, etc) or when the patient is outside the hospital (undiagnosed COPD, avoidable ED visit, health regression, avoidable admissions, avoidable readmissions, mortality etc)

Each vector is designed to reduce avoidable adverse conditions/avoidable harm to patients, thus improving the patient experience. According to our best estimate, till date we have positively impacted over 2 million patient lives.

How do you measure the performance of your products?

Our effectiveness and performance are demonstrated in the ROI we deliver. We have a very thorough ROI measurement framework driven by our client success group. We measure this on two aspects, 1) number of reduced adverse events on patients and 2) financial impact on the health system.

Avoidable waste in healthcare is estimated to be about $400 – $500Billion every year. Avoidable harm on patients comprises a large fraction of this waste that can be avoided. Healthcare AI is a great candidate to eliminate or reduce this problem.  

Tell us about the Jvion team.

The team is comprised of about a 1/3rd data scientists & about a 1/3rd clinicians/researchers and remaining third are other support staff.

Join our weekly newsletter to receive:

  1. Latest articles & interviews
  2. AI events: updates, free passes and discount codes
  3. Opportunities to join AI Time Journal initiatives

What are the primary issues in healthcare that AI can help to solve?

Avoidable waste in healthcare is estimated to be about $400 – $500Billion every year. Avoidable harm on patients comprises a large fraction of this waste that can be avoided. By definition, avoidable harm is ‘avoidable’ and clinicians provided with the right knowledge and tools before it happens can make a positive impact. Healthcare AI is a great candidate to eliminate or reduce this problem.  

AI sifts through patterns in millions of records of data to find unique impactable areas for patients. Humanly such pattern identification may be nearly impossible, however, with the right application of AI, such patterns can help with moving the needle with a more preventative and prescriptive approach.

How will AI affect the work of the doctors?

It cannot replace doctors, at least in the current state. It can help them find the most impactable and risky patients. This enables more proactive and preventative care to avoid adverse events better with the right nudges directed to the right patients. AI sifts through patterns in millions of records of data to find unique impactable areas for patients. Humanly such pattern identification may be nearly impossible, however, with the right application of AI, such patterns can help with moving the needle with a more preventative and prescriptive approach.

How can doctors prepare for an AI-powered healthcare?

Doctors can best prepare for AI-powered healthcare by embracing it while appreciating limitations around the probabilistic nature of such technologies, this will enable them to use it to maximize efforts and resources to the right areas much better than humans can do.

Do you think that AI will drastically change the way patients are cared for?

Yes. As an example, more than 1,000 patients die every year in the country due to avoidable harm or preventable adverse events. Each instance of avoidable harm can be impacted with the right prescriptive AI that can anticipate where such events would occur and which interventions can change the outcome. In addition to mortality, there are multiple other clinical areas of preventable harm that AI can help make a drastic impact.

Most clinical AI as applied today to patients is only focused on risk-identification and not understanding if it is modifiable.

Which healthcare process has the biggest potential for improvement in the coming years and why? 

Preventative care. This can be achieved best by anticipating avoidable adverse events and preventing them even before symptoms show up, this can take out about a third of our high healthcare costs from the system.

What are the current technological limitations of AI which, once overcome, could bring massive improvements to the healthcare system?

Preventable harm is identifiable and modifiable. Most clinical AI as applied today to patients is only focused on risk-identification and not understanding if it is modifiable. This is a limitation with most common AI techniques like neural networks where you can predict risk very easily but cannot understand modifiable aspects.

The mission of AI Time Journal is to divulge information
and knowledge about Artificial Intelligence, the changes that
are coming and new opportunities to use AI technology to
benefit humanity.

About AI Time Journal Editorial Staff

The mission of AI Time Journal is to divulge information and knowledge about Artificial Intelligence, the changes that are coming and new opportunities to use AI technology to benefit humanity.

View all posts by AI Time Journal Editorial Staff →