Philips maps AI’s route via healthcare – Gadget

Philips is pushing healthcare AI into sensible instruments that change how scans, screenings and affected person monitoring are carried out.

During a go to to the Philips Customer Experience Centre within the Netherlands final week, the showcased applied sciences pointed to methods AI may ease healthcare workloads, shorten examinations and produce screening nearer to sufferers.

The demonstrations included a handheld being pregnant ultrasound system, AI-assisted cardiac MRI, AI-supported CT imaging and a wearable coronary heart monitor that may be posted to a affected person’s residence.

A central theme ran via all of them: AI is getting used much less as a alternative for clinicians and extra as a strategy to information individuals via complicated medical processes, automate repetitive duties, and determine sufferers who want specialist consideration.

One of the clearest examples was SmartSweep, an AI-powered ultrasound system meant for being pregnant screening in areas the place entry to educated sonographers is restricted.

The system combines a wired handheld ultrasound probe with an Android pill. The software guides the consumer via the examination step-by-step, asking for primary affected person info, then instructing the operator to carry out vertical and horizontal sweeps throughout the stomach. The probe can match inside a backpack or purse, whereas all processing runs regionally on the pill, with out requiring an web connection.

“Our goal isn’t simply to generate an ultrasound image,” mentioned Jeroen Maas, Philips director for entry to care know-how and partnerships. “Our goal is to provide the right clinical information while solving the shortage of trained medical personnel.”

During the demonstration, Maas scanned a being pregnant coaching mannequin containing a simulated 20- to 21-week foetus. The software program coached every sweep in actual time, rejecting actions when the probe was tilted or moved incorrectly, and accepting the sweep solely as soon as the operator corrected the angle.

_{Jeroen Maas (left) takes a journalist via a SmartSweep demo. Photo: FRANK VAN BEEK.}

The goal is to not exchange a full diagnostic ultrasound. SmartSweep features as a screening device that may estimate gestational age, calculate the anticipated supply date, determine a attainable a number of being pregnant, assess foetal cardiac exercise, consider foetal presentation the place related, and flag attainable issues, corresponding to irregular amniotic fluid ranges. Patients with alerts can then be referred for a complete ultrasound examination by a certified skilled.

The system is being clinically evaluated in Kenya and India, with a number of African nations additionally displaying curiosity. Philips says the product is being ready for industrial launch, topic to native regulatory approvals.

In a separate demonstration, Gwen Herigault, Philips head of scientific programmes for MR, confirmed how AI is altering cardiac MRI, a subject that has historically required lengthy scan occasions and extremely specialised workers.

Cardiac MRI can present detailed photos of the guts muscle, however restricted scanner capability, examination complexity and workers shortages have restricted wider use. Philips says AI and automation can now scale back a cardiac MRI examination that beforehand took about an hour to round quarter-hour.

_{Gwen Herigault throughout a presentation. Photo: JASON BANNIER.}

The firm’s SmartHeart workflow automates a lot of the planning required earlier than a cardiac scan. According to the demonstration, a course of that would beforehand require round 130 mouse clicks will be decreased to 3, with the technologist nonetheless checking that the automated planning is appropriate. 

“The goal isn’t simply automation,” mentioned Herigault. “The goal is autonomy.”

AI can assist quicker picture acquisition, with some scan sequences falling from roughly one minute to about ten seconds. Patient setup has been simplified as properly, with camera-based heart-rate detection changing the necessity for electrocardiogram (ECG) electrodes in some workflows.

Herigault mentioned autonomous techniques don’t take away the healthcare skilled from the method.

“The technology performs more of the work, but the healthcare professional always remains responsible.”

Philips highlighted helium-free MRI techniques as a part of the entry story. Traditional MRI scanners require liquid helium and extra complicated set up situations. The newer techniques are designed to provide hospitals better flexibility in the place scanners will be put in, together with cell vehicles and group healthcare environments.

A CT scanner demonstration targeted on a special stress level: affected person quantity.

Bas Stam, Philips enterprise improvement supervisor for CT and AMI, described CT because the “backbone” of a radiology division as a result of the modality helps neurological, stroke, cardiac, oncology, trauma and different examinations.

CT scans are quick. A chest, stomach and pelvis scan, or perhaps a full-body scan, can take between two and 6 seconds. However, some hospitals scan much more sufferers per machine than others, with high-volume areas reaching 150 to 250 sufferers per scanner per day. That creates a necessity for extra autonomous workflows.

“So, when we look at the transformation of CT services through AI, we’re asking one central question,” mentioned Stam. “How can we create enough capacity to scan even more patients?”

Philips makes use of AI throughout the CT workflow, from affected person positioning to picture reconstruction and post-processing. A ceiling-mounted digital camera, known as Precise Positioning, helps place the affected person extra constantly, lowering reliance on handbook positioning by radiographers.

_{Bas Stam, Philips enterprise improvement supervisor for CT and AMI. Photo: JASON BANNIER.}

Deep-learning picture reconstruction can enhance CT picture high quality from the identical uncooked scan knowledge, slightly than rising radiation dose. The firm says that helps sharpen photos, scale back noise and enhance distinction whereas sustaining concentrate on dose discount.

Automation can play a task in supporting post-processing. In trauma circumstances, instruments corresponding to Precise Rib can robotically determine and label ribs inside seconds after picture reconstruction begins, whereas different workflows can standardise mind scan orientation when a affected person can’t be positioned completely.

Philips introduced Spectral CT as a step past standard anatomical imaging. The know-how may help determine supplies corresponding to iodine and calcium, giving clinicians extra quantitative details about what they’re seeing, not solely the place a construction is situated.

The most consumer-like machine proven throughout the go to was ePatch, a small wearable coronary heart monitor used to detect arrhythmias corresponding to atrial fibrillation. The patch will be worn for as much as 14 days and works with Philips’ Cardiologs AI platform to assist clinicians determine clinically vital coronary heart rhythm occasions from giant volumes of ECG knowledge. Gadget featured the machine this week as a Product of the Day for serving to docs spot irregular coronary heart rhythms that quick hospital assessments might miss.

The go to confirmed us that healthcare AI is changing into most helpful when the know-how disappears into workflow: a progress bar guiding a being pregnant scan, a digital camera serving to place a CT affected person, software program planning an MRI examination, or an algorithm sorting via days of coronary heart rhythm knowledge.

Philips’ dwell process know-how, seen individually by Gadget at St Antonius Hospital, applies the identical precept within the working room, the place AI-guided imaging helps docs navigate cardiac restore gadgets contained in the beating coronary heart throughout minimally invasive procedures. The full story will seem as Gadget’s lead article on Monday (13 July 2026).

• See Gadget’s report on Philips’ Future Health Index 2026, which discovered that clinicians are adopting AI quicker than many well being techniques can assist the know-how safely and constantly, right here.

* Jason Bannier is an information analyst at World Wide Worx and deputy editor of Gadget.co.za. Follow him on Bluesky at @jas2bann.