Global

How AI and integrated diagnostics can help clinicians see the full patient picture

Nov 19, 2026 | 5 minute read

Shez Partovi, MD-Chief Innovation Officer and Chief Business Leader Enterprise Informatics-Philips
Shez Partovi, MD
Chief Innovation Officer and Chief Business Leader Enterprise Informatics
Philips
About the author About the author

Shez Partovi obtained his medical degree from the McGill University, in Montreal, Canada and completed his neuroradiology subspecialty at Barrow Neurological Institute in Phoenix, AZ. He is a serial entrepreneur and has launched several health IT companies, including two on telehealth.

You are about to visit a Philips global content page

Continue

Wherever I go in healthcare, I hear a strong appetite for AI to help alleviate the pressures clinicians face every day. But it’s not just any kind of AI they are looking for. What they want is a particular kind of AI: one that helps them piece together the full patient’s story, rather than seeing only part of it.

A clinician examines a brain scan on blue-lit screens

 

Remember when electronic medical records (EMRs) first entered healthcare, and clinicians worried these technologies would get in the way of patient care? You might expect history would repeat itself with the rise of AI. But something is different this time.
 

Now, clinicians around the world are telling me: “Bring me AI solutions, and bring them fast.” It’s a remarkable shift in sentiment, especially in a risk-averse industry that is inclined to say, “Change is good – but you go first.” 


We saw the same eagerness to embrace AI in this year’s Future Health Index report. Nearly two-thirds of healthcare professionals (64%) turn to personal AI tools when workplace options don’t meet their needs. While this creates its own share of problems (which I won’t go into here), the signal is clear: clinicians are adopting AI faster than institutions can keep up with. 

That eagerness is hardly surprising when you look at the pressure clinicians face – especially in diagnostic imaging. Patient volumes keep rising while studies are becoming more complex. Yet clinicians still have the same number of hours in a day, and workforce shortages aren’t going away. No wonder they’re looking to AI for help.

But clinicians aren’t saying, “Throw any kind of AI at me.” What they’re asking for is more nuanced, and I can relate to it from my own experience working as a neuroradiologist.

What clinicians want from AI – and what they don’t want

 

Arguably the biggest challenge that clinicians face today – and what they want AI to address – is fragmentation. Patient data is scattered across systems. Workflows don’t connect. Or as my colleagues and I used to say when I was a practicing radiologist: we constantly had to “hunt and peck” for patient information, because there was always a missing piece that required us to dig into another disconnected application or call the receptionist at the front desk. 

That fragmentation comes at a human cost. Last year’s Future Health Index report showed that 77% of healthcare professionals had lost clinical time due to issues with incomplete or inaccessible patient data, with a third losing over 45 minutes per shift. That adds up to 23 full working days lost per healthcare professional each year. Patients may have to wait longer for answers as a result, but their care can’t always wait.

What clinicians don’t want from AI is yet another application they need to manage. Research shows this is one of the biggest barriers to AI adoption. Because as the number of AI tools is proliferating, human attention remains finite. What clinicians are looking for is AI that helps them reduce complexity, so they can focus on making confident decisions more quickly. 

The answer? Integrated diagnostics, with AI insights embedded directly into the workflow. 

Whereas much of today’s AI is still focused on helping clinicians interpret different pieces of information – an X-ray of the chest, a CT scan of the lungs – integrated diagnostics is about bringing all that information together in a meaningful way that clinicians can act on. 

That includes not only radiology but also pathology, cardiology and other sources of information. Each can reveal helpful clues. Together, they help clinicians see the full patient picture. And not just a static picture, but a dynamic one that evolves over time, with AI-driven insights supporting clinicians throughout the patient journey, from diagnosis to treatment and follow-up – helping patients get the care they need sooner.

It’s a vision we’re actively building toward with our clinical partners, and I see three layers to making it work:

1. Bringing patient information together through open platforms

 

This is the foundation. You can’t build AI for integrated diagnostics on top of disconnected data, just like you can’t build a house when the materials are scattered across different sites. You need a single place where data from different sources is brought together, harmonized and normalized, so it becomes meaningful for clinicians. And you want to keep that data safe, so you don’t have to worry about it falling into the wrong hands. 

 

That’s where our open and secure cloud-based platform approach comes into play. It’s open for a reason: no company, including Philips, can meet every clinical need on its own. Platforms need to be extensible – we want others to be able to build on them as well. That’s exactly what many of our clinical partners are already doing. Case in point: NYU Langone Health digitized its entire pathology pathway through our ongoing collaboration, laying the groundwork for future AI-enabled diagnostics that could include disease prediction algorithms.

2. Connecting diagnostic workflows across systems and specialties

 

Once you have the right data infrastructure in place, you can start connecting the workflows around the data. That’s where most time is lost in clinical practice today, so it’s also where we can make the biggest gains. By creating a more unified experience across the diagnostic journey – with data flowing among different systems and specialties – clinicians can spend more time focusing on interpreting studies instead of becoming professional data hunters. Plus, it allows them to collaborate more easily around the patient.

Multidisciplinary tumor boards are a great example. It’s where different specialists come together to review complex cancer cases and decide on the best treatment for the patient. A typical case might involve a whole range of imaging studies gathered over time, from chest X-rays to CT scans and PET-CTs, as well as pathology reports, genomic data and molecular test results. Imagine having to pull all that information together manually. It can be a massive time drain. Instead, you want all information to be readily available, so you can spend that time discussing the patient. That’s the kind of integrated diagnostic experience we’re building with clinical partners by connecting workflows across imaging, pathology and other domains.

3. Using AI to help clinicians see the full patient picture

 

With unified data as the foundation and integrated workflows helping that data flow, AI is the third and most exciting layer in integrated diagnostics – because this is where we can begin turning that connected information into insights that help clinicians make confident decisions. Or to put it simply: this is where AI starts helping clinicians see more clearly. But only if it feels like a natural extension of how they already work, not if it becomes yet another window to open. 

That’s why a big focus for us at Philips is to integrate AI and advanced visualization directly into diagnostic workflows. I’ve written before about how the best AI is the AI you barely notice, and that continues to guide our approach to innovation: we start with a clinical need and then work backward to identify how AI can help, rather than adding AI features just because we can. 

In the context of integrated diagnostics, that means asking: how can we help time-pressed clinicians see the full patient context instead of just individual pieces? This is where multimodal AI holds great promise, combining different sources of patient information to help clinicians make better-informed decisions.

Making integrated diagnostics a reality

 

Will it take more than technology to deliver on this vision? Absolutely. 

In the messy reality of healthcare, integrated diagnostics also means rethinking how departments work together, and how they fund and govern solutions. This is where things actually haven’t changed that much since the early EMR days. Back then, I remember how every care unit installed its own EMR as it moved from paper to digital. Only over time did hospitals adopt one enterprise-wide EMR. Moving toward an integrated, AI-enabled diagnostic environment may very well follow a similar path, and I see this happening most quickly when the Chief Information Officer partners with senior clinical leaders to make the change happen together.

So, will it take time to make integrated diagnostics a reality? Yes, but not as long as you might think. Philips is already well on its way.

There’s no doubt in my mind that this is where the industry is heading, as well: a future where AI learns from the full patient context, becoming the sort of smart assistant that would have seemed like science fiction when I practiced as a radiologist. And with the growing pressures on healthcare that clinicians and patients feel every day, we can’t get to that future fast enough.  

To learn more about how Philips is helping customers deliver better care for more people through integrated diagnostics, visit us at RSNA 2026 from November 29 to December 3, 2026.

Share this page with your network

  • https://www.philips.com/a-w/about/news/archive/blogs/innovation-matters/2026/how-ai-and-integrated-diagnostics-can-help-clinicians-see-the-full-patient-picture.html Link copied

You are about to visit a Philips global content page

Continue

Our site can best be viewed with the latest version of Microsoft Edge, Google Chrome or Firefox.