Exercise training is one of the central components of cardiac rehabilitation for people with coronary artery disease, including patients recovering from a heart attack, angioplasty, stent placement, or bypass surgery. Regular, supervised exercise can improve aerobic capacity, vascular function, quality of life, and long-term cardiovascular prognosis. Yet the response to training varies substantially between individuals. While many patients become fitter, a considerable proportion—often estimated at one in five or more—experience minimal change in peak oxygen uptake, commonly written as V̇O₂peak. This measurement reflects the maximum amount of oxygen the body can use during intense exercise and is considered one of the most important indicators of cardiorespiratory fitness. Low or unchanged V̇O₂peak is associated with poorer functional capacity and a higher risk of future cardiovascular complications.

The study included 353 patients with coronary artery disease who completed three to four weeks of inpatient cardiac rehabilitation. The participants had experienced a heart attack or undergone coronary procedures such as angioplasty or bypass surgery. At the beginning of rehabilitation, the research team collected data from cardiopulmonary exercise testing and pulse wave analysis, together with standard demographic and clinical information. Cardiopulmonary exercise testing measures how the heart, lungs, blood vessels, and muscles respond while a person exercises, typically on a bicycle or treadmill. Pulse wave analysis provides non-invasive information about the movement of pressure waves through the arteries, including pulse wave velocity, a widely used indicator of arterial stiffness. The researchers then used baseline information to predict whether each patient would achieve a clinically meaningful improvement in V̇O₂peak by the end of rehabilitation.

Ten machine-learning algorithms were evaluated, including approaches designed to identify complex and non-linear relationships among multiple clinical variables. The strongest results came from a Random Forest model, an ensemble method that combines the predictions of many decision trees. Each tree evaluates the data through a series of branching decisions, while the final model aggregates their outputs to produce a more stable prediction. This approach can be particularly useful in medical datasets where several biological factors interact and where a single variable rarely determines the outcome on its own. In this study, the model correctly classified responders and non-responders 77% of the time. Although that level of accuracy is not sufficient to replace clinical judgment, it suggests that routinely collected physiological data may contain signals that are invisible when patients are assessed using conventional risk factors alone.

The most surprising finding was that responders and non-responders appeared broadly similar at the start of rehabilitation when judged by standard clinical characteristics. Age, sex, body mass index, baseline fitness, and aspects of medical history did not reliably separate the two groups. Explainable artificial-intelligence analysis, using a technique known as SHAP, helped reveal which variables contributed most strongly to the model’s predictions. SHAP, or Shapley Additive Explanations, estimates how much each feature pushes an individual prediction toward one outcome or another. Rather than treating the algorithm as a black box, this method allows researchers to examine the relative influence of physiological measurements and understand why a particular patient may be predicted to respond poorly.

The most influential predictors were linked to breathing efficiency during exercise and the condition of the arteries. Patients who required more ventilation to consume a given amount of oxygen were less likely to achieve a substantial improvement in aerobic capacity. This relationship can be expressed through the ventilatory equivalent for oxygen, which describes how much air a person must move through the lungs for each unit of oxygen taken up by the body. A higher value may indicate that breathing is less efficient during exercise or that the circulation and respiratory systems are working under greater physiological strain. Reduced breathing reserve—the limited capacity remaining between exercise ventilation and the maximum ventilatory ability of the lungs—also contributed to predictions of a weaker training response.

Arterial stiffness provided another important signal. Patients with higher pulse wave velocity were less likely to improve their V̇O₂peak after standard rehabilitation. Healthy arteries expand and recoil as blood is pumped from the heart, helping regulate pressure and maintain efficient blood flow. Stiffer arteries transmit pressure waves more rapidly and can increase the workload placed on the heart while impairing the delivery of blood to working muscles. These vascular limitations may help explain why two patients with similar age, medical history, and baseline exercise capacity can respond very differently to the same training program. The model also identified the use of angiotensin II receptor blockers and calcium channel blockers as factors that influenced predictions, although the study does not establish that these medications directly caused a reduced response.

The findings suggest that the biology of exercise adaptation may be more individualized than traditional rehabilitation models assume. A standard aerobic program can produce strong benefits for many patients, but those with impaired vascular elasticity or inefficient ventilatory responses may require a different dose, intensity, duration, or progression of exercise. Instead of waiting until the end of rehabilitation to measure whether a patient has improved, clinicians could eventually use baseline pulse wave and exercise-test data to identify people who need closer monitoring or an adjusted program. Such interventions might include more carefully controlled aerobic intervals, longer training periods, additional resistance exercise, or treatment of underlying vascular and respiratory limitations. The researchers emphasize that the model is intended to support—not replace—medical decision-making.

Professor Boris Schmitz and Professor Frank Mooren of the University of Witten/Herdecke led the study in collaboration with researchers from DRV Clinic Königsfeld in Germany and FORTH in Greece. The team’s next step is a randomized controlled trial examining whether patients predicted to be non-responders can benefit from individually adjusted aerobic interval training. That experiment will be critical because prediction alone does not demonstrate that changing treatment will improve outcomes. A model may identify a group at higher risk of limited improvement, but only prospective testing can show whether acting on that information leads to greater gains in fitness, better symptoms, or improved cardiovascular health.

The researchers also caution that the current results should not yet be generalized to every cardiac rehabilitation population. The model was developed using patients treated in a specific clinical setting and may perform differently in older adults, people with multiple chronic conditions, or those completing outpatient programs with different exercise schedules. It will need external validation in larger and more diverse groups before it can be integrated into routine care. Even so, the study offers a compelling glimpse of how artificial intelligence could transform rehabilitation: not by replacing exercise, but by helping clinicians determine which kind of exercise is most likely to work for each patient. If future trials confirm the approach, a simple combination of cardiopulmonary exercise testing and pulse wave analysis could help prevent patients from completing rehabilitation without achieving meaningful improvements in cardiovascular fitness.

Subject of Research: People with coronary artery disease undergoing exercise-based cardiac rehabilitation

Article Title: A machine learning approach predicts improvement of physical exercise capacity based on pulse wave analysis in coronary artery disease patients

News Publication Date: 5 May 2026

Web References: https://doi.org/10.1016/j.jshs.2026.101144

References: Journal of Sport and Health Science; DOI: 10.1016/j.jshs.2026.101144

Image Credits: Hendrik Schäfer, University of Witten/Herdecke, Germany

Keywords: cardiac rehabilitation, coronary artery disease, machine learning, Random Forest, exercise response, non-responders, cardiopulmonary exercise testing, pulse wave analysis, arterial stiffness, V̇O₂peak, personalized medicine, cardiovascular health

Coronary artery disease, characterized by the narrowing or blockage of coronary arteries due to plaque buildup, remains a leading cause of mortality globally. The introduction of coronary stents has revolutionized percutaneous coronary interventions by providing mechanical support to the artery walls after angioplasty, dramatically reducing restenosis rates. Traditionally, these stents have been metallic—from bare-metal stents (BMS) to drug-eluting stents (DES) that slowly release medication to inhibit tissue growth that could reblock arteries. Despite their widespread use and documented efficacy, metallic stents carry inherent limitations such as chronic inflammation, late stent thrombosis, and permanent alteration of arterial biomechanics, which frequently necessitate prolonged antiplatelet therapy.

Addressing these challenges, polymeric stents emerged, designed primarily to be biodegradable, gradually resorbing into the body after serving their temporary scaffolding role. These bioresorbable stents, usually fabricated from polymers like polylactic acid (PLA) or polycaprolactone (PCL), aim to preserve natural vessel behavior post-implantation by dissolving once the artery stabilizes. However, polymeric stents have faced hurdles such as limited radial strength compared to metallic counterparts and unpredictable degradation profiles, occasionally leading to restenosis or scaffold collapse before complete artery healing. Advanced polymeric formulations and stent designs are actively being explored to overcome these limitations, contextualizing their place within the broader stent technology landscape.

Meanwhile, valvular heart disease presents a different clinical challenge, involving malfunctioning heart valves often necessitating replacement or repair. Traditionally, valve replacement has relied on mechanical or bioprosthetic valves delivered via open-heart surgery or transcatheter techniques. However, innovative stents designed specifically for valvular applications—namely valve stents—offer minimally invasive solutions by serving as frameworks to support native or prosthetic valve leaflets. Metallic and biodegradable polymeric stents developed for this purpose must balance structural integrity with biocompatibility to ensure optimal valve function and longevity, all while adapting to the dynamic cardiac environment and high mechanical stress encountered during each cardiac cycle.

One of the major restraints in the conventional manufacturing of both coronary and valvular stents lies in their standardized geometries and materials, which often limit the precise fit and functionality essential for patients with complex or atypical cardiac anatomies. This is where the advent of 3D printing—also known as additive manufacturing—introduces a paradigm shift. By enabling layer-by-layer fabrication of stent structures with unprecedented geometric complexity and customizable mechanical properties, 3D printing promises individualized therapy tailored directly to patient-specific vascular and valvular anatomy. This level of customization holds the promise to improve clinical outcomes, reduce procedural risks, and potentially extend stent longevity.

Various 3D printing techniques are being investigated for stent fabrication, each with distinct strengths and limitations. Selective laser melting (SLM) and electron beam melting (EBM) allow for precise metal stent manufacturing with controlled porosity and mechanical characteristics but can involve high thermal stresses impacting material properties. On the other hand, extrusion-based methods such as fused deposition modeling (FDM) and stereolithography (SLA) facilitate the creation of complex polymeric stents with tunable degradation rates by precisely controlling polymer chemistry and scaffold architecture. Despite the technical promise, challenges remain in achieving the necessary resolution, reproducibility, and biocompatibility in 3D printed stents to meet rigorous clinical standards.

Regulatory pathways pose another formidable challenge in the translation of 3D-printed cardiovascular devices from bench to bedside. Medical device agencies must evaluate not only the safety and efficacy of the stents themselves but also the manufacturing process, which in the case of 3D printing, is markedly different from traditional mass production. Issues such as batch-to-batch variability, sterilization protocols, and long-term biostability must be rigorously addressed. The current regulatory framework, originally designed for conventional manufacturing methods, is evolving to accommodate the unique characteristics of additive manufacturing, emphasizing the need for standardized testing methodologies and robust quality controls.

In clinical application, 3D printing enables the possibility to fabricate stents that align perfectly with the variable diameters, lengths, and curvature inherent in individual patient vascular anatomy, something particularly critical for patients with congenital abnormalities or complex disease presentations. Moreover, the integration of biodegradable polymers with 3D printing facilitates the design of stents with controlled degradation kinetics, allowing for scaffolds that not only mechanically support the vessel but also gradually vanish, minimizing long-term foreign body reactions.

Beyond customization, 3D printing introduces multifunctionality into stent technologies. For instance, stents can be embedded with sensors or drug reservoirs, enabling real-time monitoring of physiological parameters or targeted delivery of therapeutics. This multifunctionality promises to transition stents from passive mechanical devices to active biomedical tools that can dynamically interact with the biological environment, potentially revolutionizing post-implantation management and improving patient outcomes.

From a materials science perspective, the fusion of novel biomaterials with 3D printing technology advances the frontiers of stent fabrication. Bioinks composed of biodegradable polymers blended with bioactive agents, or metal alloys enhanced for corrosion resistance and biocompatibility, are under exploration. The ability to finely tune scaffold porosity and microarchitecture through additive manufacturing allows bespoke control over mechanical strength, endothelialization potential, and inflammation response. This integrated approach enhances the precision of stent performance tailored to the pathophysiological demands of CAD or valvular diseases.

The impact of 3D printing extends beyond the patient-specific stent geometry; it transforms the entire procedural workflow. Preoperative imaging—converted into digital models—can be directly leveraged to fabricate the stent, ensuring a seamless alignment between diagnostic and therapeutic phases. This synergy not only truncates the intervention time but also fosters safer and more effective implantations, particularly in anatomically challenging cases where traditional stents may fail to conform to vessel irregularities.

Despite the considerable promise, widespread adoption of 3D printing for cardiovascular stents still faces significant technical and clinical challenges. These include the need for high-resolution printers capable of manufacturing at the microscale required for tiny stents, biocompatible materials compatible with printing processes, and long-term studies proving efficacy and safety in human patients. Moreover, cost-effectiveness and production scalability remain pivotal factors influencing clinical translation.

As research efforts intensify and multidisciplinary collaborations flourish, the horizon for 3D-printed cardiovascular stents appears profoundly transformative. Incorporating patient-specific customization, programmable degradation, multifunctional integration, and streamlined regulatory pathways, this technology is poised to redefine standards of care for coronary and valvular heart diseases. The synthesis of innovations in biomaterials, additive manufacturing, and clinical sciences heralds a new era wherein stents are no longer one-size-fits-all but sophisticated, personalized, and adaptive devices.

The integration of 3D printing also opens avenues for iterative design and rapid prototyping. Engineers and clinicians can work closely to continuously refine stent structures based on immediate feedback from clinical outcomes or biomechanical simulations. This agile development model accelerates innovation cycles and may lead to the discovery of novel stent architectures that optimize flow dynamics, mechanical resilience, and tissue compatibility far beyond current capabilities.

In conclusion, cardiovascular stent technologies stand at the threshold of a bold new era driven by 3D printing. From the molecular engineering of biodegradable polymers to the precision crafting of metallic alloys, the merging of additive manufacturing with cardiovascular therapeutics carries the promise of personalized and multifunctional stents that improve patient prognosis and quality of life. The challenges that remain—technical, regulatory, and clinical—underscore the critical importance of sustained research, tailored clinical trials, and adaptive policymaking. Together, these efforts could soon make 3D-printed coronary and valvular stents standard-of-care devices that embody the future of cardiac medicine.

Subject of Research: Cardiovascular stent technologies with a focus on coronary artery and valvular heart disease treatment and the application of 3D printing in stent fabrication.

Article Title: Cardiovascular stent technologies for coronary and valvular heart disease: the potential of 3D printing for stent fabrication

Article References:
Ehterami, A., Motta, S.E., Generali, M. et al. Cardiovascular stent technologies for coronary and valvular heart disease: the potential of 3D printing for stent fabrication. Nat Rev Cardiol (2026). https://doi.org/10.1038/s41569-026-01275-x

Image Credits: AI Generated

DOI: https://doi.org/10.1038/s41569-026-01275-x

Keywords: Cardiovascular stents, coronary artery disease, valvular heart disease, 3D printing, additive manufacturing, biodegradable stents, polymeric stents, metallic stents, bioresorbable stents, personalized medicine, cardiovascular engineering, minimally invasive interventions

Coronary artery disease remains one of the foremost killers globally, driven largely by the formation of blood clots that obstruct the coronary arteries, depriving heart tissue of oxygen. Central to this disease process are platelets—tiny, anucleated blood cells responsible for clot formation. Antiplatelet therapies, including drugs like aspirin and P2Y12 inhibitors, are cornerstone treatments designed to disrupt platelet activation and aggregation. However, clinicians historically have faced challenges in accurately assessing how well a given therapy is working at the level of individual patients.

Traditional methods for evaluating platelet function tend to be indirect, cumbersome, or limited in their capacity to capture the complex morphology and behavioral heterogeneity of circulating platelets. This new study leverages state-of-the-art imaging technologies, combined with sophisticated computational algorithms, to comprehensively profile circulating platelets from patients undergoing antiplatelet therapy. By directly visualizing platelet characteristics and activity, this method provides unprecedented granularity into the efficacy of individualized treatments.

The research team, spearheaded by Hirose, Kodera, Nishikawa, and collaborators, utilized advanced microscopy coupled with deep-learning analytics to parse the intricate details of platelet morphology, granularity, and activation states. These parameters are essential because activated platelets undergo rapid shape changes, express specific surface markers, and aggregate more readily, all of which contribute to thrombosis. By painstakingly capturing and quantifying these features across thousands of platelets per patient, the team constructed a detailed "image-based platelet signature" that reflects the net effect of antiplatelet agents in vivo.

One of the key innovations in this study lies in its ability to bypass traditional surrogate markers and lab assays, moving directly to a phenotype-driven assessment. This phenotype-centric approach allows the researchers to detect subtle, clinically relevant differences between responders and non-responders to antiplatelet therapy, which could not be teased out by previous tests. Importantly, this may pave the way for dynamically adjusting drug dosage or switching therapies in near real-time, optimizing patient outcomes.

Moreover, the researchers demonstrated that this technology captures not only the static features of platelets at a snapshot in time but also offers temporal resolution, monitoring how platelet profiles evolve over the course of therapy. This dynamic profiling revealed that some patients experience transient resistance or fluctuating platelet reactivity, phenomena that have significant implications for risk stratification and treatment adherence monitoring.

The study cohort included CAD patients on various antiplatelet regimens, and the findings underscored marked heterogeneity in platelet responses that could not be predicted by genetic testing or standard hematological parameters alone. By correlating imaging-derived platelet signatures with clinical endpoints such as major adverse cardiovascular events, the team established the prognostic value of their profiling approach, spotlighting its potential utility in routine clinical practice.

Beyond prognostic implications, this technique opens new avenues for drug development. Pharmaceutical researchers can now utilize comprehensive platelet imaging to assess novel antiplatelet agents, enabling more nuanced mechanistic insights and facilitating the design of therapies that finely tune platelet activity without excessive bleeding risk—an ever-present challenge in balancing efficacy and safety.

Importantly, the image-based profiling method is also minimally invasive, requiring only small volumes of blood, and amenable to integration with existing clinical workflows. The authors envision that, with advances in automation and cost reduction, this platform could be adapted for widespread point-of-care use, transforming cardiovascular care from a one-size-fits-all approach to precision medicine.

The implications extend beyond coronary artery disease. Platelets play vital roles in a range of pathologies—including cerebrovascular disease, peripheral artery disease, and even cancer metastasis—so this imaging-based platform could serve as a versatile tool across multiple disciplines where platelet function is implicated.

Scientific experts have hailed this approach as a significant leap forward. Dr. Emily Carter, a leading thrombosis specialist not involved in the study, commented, “By harnessing the power of high-resolution imaging and machine learning, this study enables us to see the platelet as never before. It holds transformative potential for personalizing antiplatelet therapy, ultimately saving lives.”

The study authors are already advancing their work towards clinical trials aimed at validating the platform’s predictive power and integrating it into therapeutic decision-making algorithms. Additionally, efforts are underway to refine the computational models to identify even more subtle patterns, incorporating multimodal data such as genomics and proteomics to build a holistic understanding of platelet biology.

While promising, challenges remain. Standardizing sample preparation, ensuring reproducibility across diverse clinical settings, and scaling the technology economically are critical next steps. However, the foundational work laid out in this study provides a compelling blueprint for overcoming these hurdles.

In sum, the study by Hirose and colleagues represents a landmark in cardiovascular diagnostics. Their image-based platelet profiling does not merely offer a snapshot of platelet function; it provides a detailed narrative on how antiplatelet therapy modulates the platelet population at the individual level. This heralds a new era of precision cardiovascular medicine that could substantially reduce the burden of coronary artery disease globally.

As the field moves forward, integrating such technological innovations with existing therapeutic regimens promises to enhance efficacy, avoid adverse effects, and ultimately improve survival and quality of life for millions of patients worldwide. With continuous refinement and clinical validation, comprehensive image-based platelet profiling stands poised to become a new standard of care, illuminating the once elusive intricacies of platelet biology in health and disease.

Subject of Research: Direct evaluation of antiplatelet therapy effectiveness in coronary artery disease by comprehensive image-based profiling of circulating platelets.

Article Title: Direct evaluation of antiplatelet therapy in coronary artery disease by comprehensive image-based profiling of circulating platelets.

Article References:
Hirose, K., Kodera, S., Nishikawa, M. et al. Direct evaluation of antiplatelet therapy in coronary artery disease by comprehensive image-based profiling of circulating platelets. Nat Commun 16, 4386 (2025). https://doi.org/10.1038/s41467-025-59664-8

Image Credits: AI Generated