Evaluating electrocardiogram (ECG) traces using a new deep-learning model known as EchoNext looks set to save lives by flagging patients at high risk of structural heart disease (SHD) who might otherwise be missed.

SHD encompasses a range of conditions affecting millions worldwide, including heart failure and valvular heart disease. It is, however, currently underdiagnosed because the diagnostic test for SHD, an echocardiogram, is relatively expensive and complex and thus not routinely performed. Late diagnosis results in unnecessary deaths, reductions in patient quality-of-life and an additional burden on healthcare services. EchoNext could reduce these problems as it provides a way of determining which patients should be sent for an echocardiogram – ultrasound imaging that shows the valves and chambers and how the heart is beating – by analysing the inexpensive and commonly collected ECG traces that record electrical activity in the heart.

The EchoNext model was developed by researchers at Columbia University and NewYork-Presbyterian Hospital in the US, led by Pierre Elias, assistant professor at Columbia University Vagelos College of Physicians and Surgeons and medical director for artificial intelligence at NewYork-Presbyterian. EchoNext is a convolutional neural network, which uses the mathematical operation of convolution to generate information and make predictions. In this case, EchoNext scans through the ECG data in bite-sized segments, generating information about each segment and subsequently assigning it a numerical “weight”. From these values, the AI model then determines if a patient is showing markers of SHD and so requires an echocardiogram. EchoNext learns from retrospective data by checking the accuracy of its predictions, with more than 1.2 million ECG traces from 230,000 patients used in its initial training.

In their study, reported in Nature, the researchers describe running EchoNext on ECG data from 85,000 patients. The AI model identified 9% of those patients as being in the high-risk category for undiagnosed SHD, 55% of whom subsequently had their first echocardiogram. This resulted in a positive diagnosis in almost three-quarters of cases; double the rate of positivity normally seen in first-time echocardiograms.

EchoNext also outperformed 13 cardiologists in making diagnoses based on 3200 ECGs by correctly flagging 77% of structural heart problems while its human colleagues were only 64% accurate – a result so good that it shocked the researchers.

“The really challenging thing here was that from medical school I was taught that you can’t detect things like heart failure or valvular disease from an electrocardiogram. So we initially asked: would the model actually pick out patients with disease that we were missing? I have read more than 10,000 ECGs in my career and I can’t look at an ECG and see what an AI model is seeing,” enthuses Elias. “It’s able to pick up on different sets of patterns that are not necessarily perceptible to us.”

Elias instigated the EchoNext project after an upsetting incident in which he was unable to save a patient transferred from another hospital with critical valvular heart disease because they had been diagnosed too late. “You can’t take care of the patient you don’t know about. So we said: is there a way that we can do a better job with diagnoses?”

EchoNext is now undergoing a clinical trial, based in eight hospital emergency departments, that ends in 2026. “My number one priority is to produce the right clinical evidence that is necessary to prove this technology is safe and efficacious, can be widely adopted and has value in helping patients,” says Elias.

He stresses that it is still early days for all AI technologies, but that even in these trial phases EchoNext – which was recently designated a breakthrough technology by the US Food and Drug Administration (FDA) – is already improving patient lives.

“It’s a really wonderful thing that every week we get to meet the patients that this helped. Our goal is for this to impact as many patients as possible over the next 12 months,” states Elias, adding that since EchoNext is successfully detecting 13 types of heart disease, a similar system should be useful in other healthcare domains too. “We think these kinds of AI-augmented biomarkers can become something that is routinely ordered and used as part of clinical practice,” he concludes.

The post Deep-learning model outperforms cardiologists in identifying hidden heart disease appeared first on Physics World.

The webinar will present the overall experience of a radiotherapy department that utilized RTsafe’s QA solutions in preparation for achieving ISRS certification. The session will focus on the use of RTsafe’s Prime phantom in combination with film remote dosimetry services, demonstrating how this approach enables End-to-End QA testing and supports accurate, reproducible film dosimetry audits. Attendees will gain insights into how these tools can be employed to validate the entire SRS treatment workflow, from imaging and planning to dose delivery, while aligning with the rigorous standards required for ISRS certification.

Serenella Russo is senior medical physicist and Reference MPE at the Radiation Oncology Unit, Santa Maria Annunziata Hospital, Florence. She brings expertise in external beam radiation therapy dosimetry, with a focus on small field measurements and detector characterization, as well as clinical implementation and planning of VMAT/IMRT, SRS/SBRT techniques. Russo is responsible for the Italian Association of Medical Physics (AIFM) audit service for radiotherapy megavoltage photons beams. Coordinator of (AIFM) SBRT Working Group and responsible for the Italian multi-center project “Inter-comparison on small field dosimetry” proposed by the SBRT WG.

Professor of Radiotherapy Dosimetry at the Medical Physics Specialization School, University of Florence and serves as editor for Physica Medica. Author and co-author of numerous scientific publications about SRS/SBRT and small field dosimetry.

Silvia Scoccianti is head of Radiation Oncology at Santa Maria Annunziata Hospital and Azienda USL Toscana Centro, Italy. She brings expertise in Linac-based radiosurgery, stereotactic radiotherapy and gamma knife radiosurgery for brain metastases, recurrent gliomas, intercranial benign tumors, AVM, and trigeminal neuralgia. She is Head of the Italian Association of Radiotherapy and Clinical Oncology (AIRO) Brain Tumor Group; Chief of the multidisciplinary tumor board for CNS a multi-hospital network of Azienda USL Toscana Centro; and Study director and Principal investigator for multicenter neuro-oncological trials.

Scoccianti co-authored Italian national CNS tumor guidelines published by the Italian Association of Medical Oncology (AIOM). She is author and co-author of numerous scientific publications about primary and secondary brain tumors.

The post Preparation for ISRS certification using RTsafe’s solutions. An overall experience appeared first on Physics World.

Deep learning algorithms have been trained to classify different types of biological tissue, based purely on the tissue’s natural optical responses to laser light. The work was done by researchers led by Travis Sawyer at the University of Arizona in US, who hope that their new approach could be used in the future to diagnose diseases using optical microscopy.

Precision medicine is a fast-growing field whereby medical treatments are tailored to individual patients – taking factors like genetics and lifestyle into account. A key part of this process is phenotyping, which involves identifying the molecular characteristics of diseased tissues.

Previously, phenotyping most often involved labelling tissues with fluorescent biomarkers, which allowed clinicians to create clear medical images using optical microscopy. However, the process of labelling tissues is often invasive, expensive and time-consuming, limiting its accessibility in practical treatments.

More recently, advances have been made in label-free imaging, which can phenotype tissues by observing how they interact with laser light. This is difficult, however, because tissues will often display complex nonlinear responses in the light they emit, which are deeply intertwined with their surrounding molecular environments. As Sawyer explains, this creates a whole new set of challenges.

Altering abundance

“In general, the potential of label-free imaging has been limited by a lack of specificity in understanding what is producing the measured signal,” he says. “This is because many different high-level disease processes can lead to an altering abundance of downstream measurable biomarkers.”

Sawyer’s team addressed these challenges by exploring how deep learning algorithms could be trained to recognize these nonlinear optical responses, and identify them in microscopy images.

To do this, they used a technique called spatial transcriptomics, which maps out variations in RNA levels across tissue samples. RNA molecules carry copies of the instructions stored in DNA, offering a snapshot of gene activity in different regions of tissue.

Alongside transcriptomics data from six different types of tissue, the team also probed the samples with two different optical microscopy techniques. These are autofluorescence, which detects the specific frequencies of molecules excited by a laser, providing details on the tissue’s composition; and second harmonic generation, which detects highly ordered structures (such as collagen) by capturing photons they emit at twice the frequency of a laser probe.

One-to-one matching

The researchers then co-registered these label-free microscopy images with their spatial transcriptomics data. “This allowed us to match one-to-one the transcriptomic signature of a small area of tissue with a surrounding image region capturing the microenvironment of the tissue,” Sawyer explains. “The transcriptomic signature was used to generate tissue and disease phenotypes.”

Based on these simultaneous measurements, the team developed a deep learning algorithm that could accurately predict the unique phenotypes of each tissue. Once trained, the model could classify tissues using only the label-free microscopy images, without any need for transcriptomics data from the samples being studied. “Using deep learning, we were able to accurately predict tissue phenotypes defined by the transcriptomic signature to almost 90% accuracy using label-free microscopy images,” Sawyer says.

Compared with classical image analysis algorithms, the team’s deep learning approach was vastly more reliable in predicting tissue characteristics. This showcased the need to account for the influence of tissues’ surrounding environments on their optical responses.

For now, the technique is still in its early stages, and will require assessments with far larger groups of patients, and with other types of tissue and diseases before it can be applied clinically. Still, the team’s results are a promising step towards label-free imaging, which could have important implications for precision medicine.

“This could lead to transformative technology that could have major clinical impact by enabling precision medicine approaches, in addition to basic science applications by allowing minimally invasive and longitudinal measurement of biological signatures,” Sawyer explains.

The technique is described in Biophotonics Discovery.

The post Deep learning classifies tissue for precision medicine appeared first on Physics World.

An imbalance in sodium ions in the blood causes a number of physiological problems, but so far it has not been possible to measure these ion concentrations in vivo. Now researchers have successfully applied their terahertz optoacoustic technology to measure blood ion concentrations non-invasively, overcoming the challenges posed by previous approaches. They report their findings in Optica.

The idea to combine terahertz spectroscopy with optoacoustic detection came about during a recruitment trip when Zhen Tian from the School of Precision Instrument and Optoelectronics Engineering at Tianjin University in China got chatting with colleague Jiao Li – co-author of this latest study. At the time, Tian’s work was focused primarily on terahertz technology while Li had been working on optoacoustics, but the more they talked, the more interested they became in each other’s fields, and took “every available opportunity to discuss these topics in depth” during the trip.

Putting their heads together on their return, in 2021 they successfully demonstrated terahertz optoacoustic detection of ions in water, despite the challenges of the pandemic. “We thought things would progress smoothly from there, but deeper investigations revealed a series of technical challenges,” Tian tells Physics World. “What began as a fortunate opportunity soon turned into a demanding endeavour.”

The sodium focus

Since ions are strongly polar, they absorb highly in the terahertz range, making them easy to detect. As such, Tian and Li were keen to find a scenario where the tracking of ions might be useful. Another colleague at Tianjin University (also a co-author on this new study) pointed out that ion imbalances in the blood can cause kidney disease and serious neurological conditions. The most abundant ion in the blood is sodium, and as Li explains, not only do imbalances in sodium ions need prompt correction, but the lack of means for monitoring sodium ions in vivo poses risks of neural demyelination and brain damage during sodium ion supplementation.

One of the key challenges was the high water content of body tissues, because water absorbs terahertz radiation so strongly. The researchers turned this to an advantage by using the water to detect emitted terahertz radiation from the sample, exploiting the fact that the optoacoustic response is temperature dependent. At cold temperatures, absorbing terahertz radiation emitted from the sample heats up the water, which detectably impacts its optoacoustic signal. Therefore, comparing the sample’s optoacoustic response to terahertz radiation with values for pure water gives a quantitative indication of the absorption by the sample and thus the concentration of ions present.

Although the researchers demonstrated a proof-of-principle for this approach in 2021, they then had to battle with several other issues. They improved the stability of the light source by reducing thermal fluctuations and making other optimizations to the experimental environment; they used higher-intensity light sources and enhanced detectors to increase the detection sensitivity; and they used spectral filtering to achieve molecular specificity in the optoacoustic detection. Tian expresses his gratitude to Yixin Yao, a co-first author of the paper, as well as to the students involved. “It was their commitment and perseverance that helped us overcome each hurdle,” he says.

The team demonstrated that the enhanced system could detect sodium ions in human blood flowing through a microfluid chip and measure increases in blood sodium levels in living mice. The operating temperature for the technique was 8 °C, cold enough to cause damage to many parts of the body. However, the researchers noted that the ear is particularly resilient to temperature, so they cooled and monitored just the animal’s ear, limiting the experiment duration to 30 min. This way they were able to complete their measurements without incurring any tissue damage.

Although the numerous previous in vitro experiments had left the researchers full of “anticipation” for the success of the attempts in vivo, Tian tells Physics World, “when we saw the terahertz optoacoustic signal enhance after sodium ion injection, all of us, including the students conducting the experiment, cheered with excitement”.

“It is very nice to see [that] fundamental studies on dielectric response of aqueous salt solutions may result in a sensor for human health,” says Andrea Markelz from the University at Buffalo, whose research focuses on biomolecular dynamics and terahertz time domain spectroscopy, although she was not directly involved in this study. She notes that tagless terahertz-based biomonitoring is challenging, due to both the strong aqueous background and the lack of narrowband signatures. “It will be very interesting to see if the sensitivity remains robust for different organisms under different conditions,” she adds.

Next, Tian and his collaborators plan to apply the approach to detect neural ion activity without the need for labelling. “It’s admittedly a bold and ambitious idea – but one that has truly excited our team,” he says.

The post Terahertz optoacoustics allows real-time monitoring of blood sodium levels appeared first on Physics World.