Search Results (127)

Background/Objectives: Endovascular aneurysm repair (EVAR) is the standard treatment for abdominal aortic aneurysms, but the risk of endoleak compromises its effectiveness. Type IA endoleak, stemming from an inadequate proximal seal, is the most critical complication associated with the highest risk of rupture. Current preoperative planning relies on static anatomical measurements from computed tomography angiography that fail to predict seal failure due to dynamic biomechanical forces. This study aimed to retrospectively validate the predictive accuracy of a novel physics-informed digital twin and artificial intelligence (AI) model for predicting type IA endoleak risk compared to conventional static planning methods. Methods: This was a retrospective, single-center proof-of-concept validation study involving 15 patients who underwent elective EVAR (5 with confirmed type IA endoleak and 10 without type IA endoleak). A patient-specific digital twin was created for each case to simulate stent-graft deployment and capture the dynamic biomechanical interaction with the aortic wall. A logistic regression AI model processed over 16,000 biomechanical measurements to generate a single, objective metric of the endoleak risk index (ERI). The predictive performance of the ERI (using a cutoff of 0.80) was assessed and compared against a 1:3 propensity score-matched conventional control group (n = 45) who received traditional anatomical-based planning. Results: The mean ERI was significantly higher in the endoleak-positive group (0.85 ± 0.10) compared to the endoleak-negative group (0.39 ± 0.11) (p = 0.011). The digital twin/AI model demonstrated superior predictive capability, achieving an overall accuracy of 80% (95% CI: 51.9–95.7) and an area under the curve (AUC) of 0.85 (95% CI: 0.58–0.99). Crucially, the model achieved a sensitivity of 100% and a negative predictive value (NPV) of 100%, correctly identifying all high-risk cases and ruling out endoleak in all low-risk cases. In stark contrast, the matched conventional planning group achieved an overall accuracy of only 51.1% and an AUC of 0.54. Conclusion: This physics-informed digital twin and AI framework successfully validated its capability to accurately and objectively predict the risk of type IA endoleak following EVAR. The derived ERI offers a significant quantitative advantage over traditional static anatomical measurements, establishing it as a highly reliable safety tool (100% NPV) for ruling out endoleak risk. This technology represents a critical advancement toward personalized EVAR planning, enabling surgeons to proactively identify high-risk anatomies and adjust treatment strategies to minimize post-procedural complications. Further large-scale, multicenter prospective trials are necessary to confirm these findings and support clinical adoption. Full article

Major Depressive Disorder (MDD) poses a significant global health burden, characterized by a complex and heterogeneous pathophysiology insufficiently targeted by conventional single-treatment approaches. This review presents an integrative framework incorporating network pharmacology, artificial intelligence (AI), and multi-omics technologies to advance a systems-level understanding and management of MDD. Its central contribution lies in moving beyond reductionist methods by embracing a holistic perspective that accounts for dynamic interactions within biological networks. The primary objective is to demonstrate how AI-powered integration of multi-omics data—spanning genomics, proteomics, and metabolomics—can enable the construction of predictive network models. These models are designed to uncover fundamental disease mechanisms, identify clinically relevant biotypes, and reveal novel therapeutic targets tailored to specific pathological contexts. Methodologically, the review examines the microbiota–gut–brain (MGB) axis as an illustrative case study, detailing its pathogenic roles through neuroimmune alterations, metabolic dysfunction, and disrupted neuro-plasticity. Furthermore, we propose a translational roadmap that includes AI-assisted biomarker discovery, computational drug repurposing, and patient-specific “digital twin” models to advance precision psychiatry. Our analysis confirms that this integrated framework offers a coherent route toward mechanism-based personalized therapies and helps bridge the gap between computational biology and clinical practice. Nevertheless, important challenges remain, particularly pertaining to data heterogeneity, model interpretability, and clinical implementation. In conclusion, we stress that future success will require integrating prospective longitudinal multi-omics cohorts, high-resolution digital phenotyping, and ethically aligned, explainable AI (XAI) systems. These concerted efforts are essential to realize the full potential of precision psychiatry for MDD. Full article

Robots and artificial intelligence have revolutionized the healthcare sector. Transporting patients within hospitals is critical; however, reducing errors and inefficiencies caused by human intervention and increasing task efficiency are necessary. Therefore, there is a clear need to reduce these interventions and increase overall task efficiency. We implemented a digital twin of the situation in which a nurse-following patient transport bed robot (in short, nurse-following bed robot or medical bed robot) transports patients in an infectious disease situation. To operate multiple bed robots, a federated digital twin was implemented, and all processes that occur in a hospital when an infectious disease patient arrives were defined, and scenarios for various situations were constructed. These scenarios were then simulated to validate system performance and preparedness for real-world situations. This study investigates and provides a detailed explanation of the core technologies required for this digital implementation process. Full article

Background/Objectives: Unusual-site venous thrombosis (USVT) lacks robust evidence guiding anticoagulant selection between vitamin K antagonists (VKAs) and direct oral anticoagulants (DOACs). This study aimed to evaluate recanalization, recurrence, and major bleeding outcomes in real-world USVT patients and to replicate these findings through a validated digital twin model with Monte Carlo simulation. Methods: We conducted a retrospective study of 90 USVT patients (72% VKAs, 28% DOACs). A conditional generative adversarial network was used to generate digital twins matched on age, sex, thrombosis site, and malignancy. Logistic regression was applied to estimate treatment-specific outcome probabilities for recanalization, recurrence, and major bleeding. A nested stochastic simulation framework simulated 500 iterations across clinical scenarios, including increased DOAC use, cancer prevalence, cerebral vein thrombosis proportion, and optimized VKA control. Results: The mean age was 67.5 years, and 54.4% were female. 61.1% of splanchnic vein thrombosis, 36.7% of upper extremity deep vein thrombosis, and 2.2% of cerebral vein thrombosis were included. In the real cohort, complete recanalization occurred in 40.0% of patients with DOACs and 36.0% with VKAs. Recurrence was 8.0% with DOACs and 7.7% with VKAs, and major bleeding occurred in 8.0% and 10.8% of cases, respectively. All-cause mortality was 20% in DOAC-treated patients and 60% in those receiving VKAs. Digital Twin-based predictions replicated these results (recanalization 40.3% versus 38.0%; recurrence 10.9% versus 8.6%; bleeding 7.6% versus 9.1%). Simulated scenarios preserved the directionality effect, with the most significant differences observed in high-cerebral vein thrombosis and cancer-enriched patients. Conclusions: DOACs showed comparable efficacy and slightly lower bleeding risk than VKAs in USVT. Digital twin and Monte Carlo modeling provided robust, reproducible simulations of treatment effects under varying clinical conditions. Separating empirical and simulation-based findings, the digital twin supported the internal consistency of real-world observations and demonstrated the potential of in silico modeling as a complementary tool in rare thrombotic diseases. Full article

Background/Objectives: Accurate absorbed dose estimation is essential for optimising targeted radionuclide therapy (TRT) in metastatic castration-resistant prostate cancer, where kidney toxicity is dose-limiting. [¹⁷⁷Lu]Lu-rhPSMA-10.1 is a novel PSMA-targeted radioligand with favourable tumour-to-kidney uptake ratios; however, inter-patient pharmacokinetic variability can lead to differences in organ and tumour absorbed doses under fixed-activity administration. Personalised dosimetry offers a means to address this variability. This work aims to create mouse PBPK model-based digital twins for [¹⁷⁷Lu]Lu-rhPSMA-10.1 to test the model’s resistance to noise and evaluate its impact on accuracy and absorbed dose calculations. Methods: Five CB-17 SCID mice bearing LNCaP tumour xenografts received 2.6–3.1 MBq [¹⁷⁷Lu]Lu-rhPSMA-10.1 intravenously. Biodistribution was assessed 24 h post-injection by organ weighing and gamma counting. The PBPK model, implemented in MATLAB SimBiology (R2023a), was fitted to individual biodistribution data using mouse-specific physiological parameters. Digital twins—combining the model with fitted parameters—were used to generate time–activity curves (TACs) for kidneys, tumours, and the whole body. Gaussian noise ($\sigma$ = 0–0.35) was added to TACs to simulate measurement error. The model was refitted, and absorbed doses from time-integrated activities (TIAs) were compared to digital twin references. Results: The digital twin approach reproduced experimental data with physiologically plausible parameters. Absorbed dose estimates remained consistent and robust, deviating by <2.3% in kidneys and <1.0% in tumours. Conclusions: PBPK-based digital twins enable reliable, individualised dosimetry, even under substantial measurement uncertainty. Full article

Early risk prediction is essential for hospitalized prostate cancer (PCa) patients, who face acute events, such as mortality, ICU transfer, AKI (acute kidney injury), ED30 (unplanned 30-day Emergency Department revisit), and prolonged LOS (length of stay). We developed an MMoE (Multitask Mixture-of-Experts) model that jointly predicts these outcomes from the features of the multimodal EHR (Electronic Health Records) in MIMIC-IV (3956 admissions; 2497 patients). A configuration with six experts delivered consistent gains over strong single-task baselines. On the held-out test set, the MMoE improved rare-event detection (mortality AUPRC (Area Under the Precision-Recall Curve) of $0.163$ vs. $0.091$, $+79\%$) and modestly boosted ED30 discrimination (AUROC (Area Under the Receiver Operating Characteristic Curve) $\approx 0.66$ with leakage-safe ClinicalBERT fusion) while maintaining competitive ICU and AKI performance. Expert-routing diagnostics (top-1 shares, entropy, and task-dead counts) revealed clinically coherent specialization (e.g., renal signals for AKI), supporting interpretability. An efficiency log showed that the model is compact and deployable (∼85 k parameters, $0.34$ MB; $0.027$ s/sample); it replaced five single-task predictors with a single forward pass. Overall, the MMoE offered a practical balance of accuracy, calibrated probabilities, and readable routing for the prognostic layer of digital-twin pipelines in oncology. Full article

Background: Generative AI and synthetic media have enabled realistic human Embodied Conversational Agents (ECAs) or avatars. A subset of this technology replicates faces and voices to create realistic likenesses. When combined with avatars, these methods enable the creation of “digital twins” of physicians, offering patients scalable, 24/7 clinical communication outside the immediate clinical environment. This study evaluated surgical patient perceptions of an AI-generated surgeon avatar for postoperative education. Methods: We conducted a pilot feasibility study with 30 plastic surgery patients at Mayo Clinic, USA (July–August 2025). A bespoke interactive surgeon avatar was developed in Python using the HeyGen IV model to reproduce the surgeon’s likeness. Patients interacted with the avatar through natural voice queries, which were mapped to predetermined, pre-recorded video responses covering ten common postoperative topics. Patient perceptions were assessed using validated scales of usability, engagement, trust, eeriness, and realism, supplemented by qualitative feedback. Results: The avatar system reliably answered 297 of 300 patient queries (99%). Usability was excellent (mean System Usability Scale score = 87.7 ± 11.5) and engagement high (mean 4.27 ± 0.23). Trust was the highest-rated domain, with all participants (100%) finding the avatar trustworthy and its information believable. Eeriness was minimal (mean = 1.57 ± 0.48), and 96.7% found the avatar visually pleasing. Most participants (86.6%) recognized the avatar as their surgeon, although many still identified it as artificial; voice resemblance was less convincing (70%). Interestingly, participants with prior exposure to deepfakes demonstrated consistently higher acceptance, rating usability, trust, and engagement 5–10% higher than those without prior exposure. Qualitative feedback highlighted clarity, efficiency, and convenience, while noting limitations in realism and conversational scope. Conclusions: The AI-generated physician avatar achieved high patient acceptance without triggering uncanny valley effects. Transparency about the synthetic nature of the technology enhanced, rather than diminished, trust. Familiarity with the physician and institutional credibility likely played a key role in the high trust scores observed. When implemented transparently and with appropriate safeguards, synthetic physician avatars may offer a scalable solution for postoperative education while preserving trust in clinical relationships. Full article

The convergence of wearable technologies and digital twin (DT) systems is transforming rehabilitation engineering, enabling continuous monitoring, personalized therapeutic interventions, and predictive modeling of patient recovery pathways. This review examines the growing role of machine learning (ML) in the development and integration of DTs frameworks in rehabilitation, with a focus on wearable sensor data, security and privacy, edge computing architectures, federated learning paradigms, and generative artificial intelligence (GenAI) applications. We first analyze data collection processes, emphasizing multimodal sensing, signal processing, and real-time synchronization between physical and virtual patient models. We then discuss key challenges related to data security, encryption, and privacy protection, especially in distributed clinical environments. The review then assesses the role of edge computing in reducing latency, improving energy efficiency, and enabling real-time local intelligence feedback in wearable devices. Federated learning approaches are discussed as promising strategies for jointly training ML models without compromising sensitive medical data. Finally, we present new GenAI techniques for generating synthetic data, personalizing digital twins, and simulating rehabilitation scenarios. By mapping current progress and identifying research gaps, this article provides a unified view that connects electronic and biomedical engineering with intelligent, secure, and adaptive DT ecosystems for next-generation rehabilitation solutions. Wearable devices with ML and DTs for rehabilitation are developing rapidly, but their current effectiveness still depends on consistent, high-quality data streams and robust clinical validation. The most promising convergence involves combining edge intelligence with federated learning to enable real-time personalization while preserving patient privacy. GenAI further enhances these systems by simulating patient-specific scenarios, accelerating model adaptation, and treatment planning. Key challenges remain related to standardizing data formats, ensuring comprehensive security, and seamlessly integrating these technologies into clinical processes. Full article

As prosthetic technologies become increasingly data-rich and embedded in care systems, traditional human-centred approaches often fall short of addressing evolving use realities. This paper contributes an applied computing framework that enables semantic reasoning and data-driven adaptation within prosthesis aftercare. We present an ontology-driven, cyber–physical prosthesis service system designed to enable personalised and adaptive care. Implemented through the Adaptive Prosthesis Life-Cycle Service System (adProLiSS) framework and demonstrated via a smart prosthesis prototype, the system treats the prosthesis as a semi-autonomous actor within an emotionally responsive and semantically mediated ecosystem. The proposed architecture integrates sensor data acquisition, ontology-based knowledge representation, and semantic reasoning to enable context-aware decision support and adaptive personalisation. A layered cyber–physical infrastructure, comprising embedded sensors, semantic reasoning, and user feedback through a digital twin interface, supports personalised aftercare, cross-disciplinary collaboration, and reflective design engagement. Evaluation with 26 participants across clinical, engineering, and user groups confirmed the system’s value in enhancing functionality, reducing downtime, and supporting emotional well-being. By positioning ontologies as both computational enablers and design support mechanisms, this research contributes a practical and scalable model for prosthetic service systems that adapt across bodily, emotional, and ecological dimensions, advancing more responsive and consequence-aware care practices. Full article

Background/Objectives: Myasthenia gravis (MG) is a rare autoimmune neuromuscular disease. Clinical trials with rigorously collected data provide valuable opportunities for mathematical modeling of patient outcomes over time. However, for rare diseases such as MG, combining data across multiple trials presents challenges due to heterogeneity in outcome measures. This study aims to address these challenges by investigating relationships among commonly used MG outcome measures to support the development of a standardized “Myasthenia Gravis Portrait.” Methods: We integrated three primary data types from multiple clinical studies: (i) laboratory and medication data, (ii) Electronic Health Record (EHR) data (e.g., age, sex, years since diagnosis, BMI), and (iii) disease severity scores. We examined the relationships among several MG-specific scoring systems, including Activities of Daily Living (MG-ADL), Quantitative Myasthenia Gravis (QMG), MG Composite (MG-CE), and MG Quality of Life-15 (MGQOL-15), to evaluate consistency and comparability across studies. Results: Preliminary analyses revealed variable correlations among the different scoring systems, indicating that, while some measures capture overlapping aspects of disease progression, others reflect distinct patient- or clinician-centered perspectives. These findings highlight the need for a harmonized framework that captures both functional and clinical dimensions of MG severity. Conclusions: The proposed “Myasthenia Gravis Portrait” provides a standardized approach for representing patient outcomes across diverse clinical datasets. This framework will facilitate the creation of virtual populations of digital twins, enabling a machine-learning-based modeling of MG progression and prediction of individualized disease trajectories. Full article

Acute Aortic Syndromes (AAS) and Thoracic Aortic Aneurysm (TAA) remain among the most fatal cardiovascular emergencies, with mortality rising by the hour if diagnosis and treatment are delayed. Despite advances in imaging and surgical techniques, current clinical decision-making still relies heavily on population-based parameters such as maximum aortic diameter, which fail to capture the biological and biomechanical complexity underlying these conditions. In today’s data-rich era, where vast clinical, imaging, and biomarker datasets are available, artificial intelligence (AI) has emerged as a powerful tool to process this complexity and enable precision risk prediction. To date, AI has been applied across multiple aspects of aortic disease management, with mortality prediction being the most widely investigated. Machine learning (ML) and deep learning (DL) models—particularly ensemble algorithms and biomarker-integrated approaches—have frequently outperformed traditional clinical tools such as EuroSCORE II and GERAADA. These models provide superior discrimination and interpretability, identifying key drivers of adverse outcomes. However, many studies remain limited by small sample sizes, single-center design, and lack of external validation, all of which constrain their generalizability. Despite these challenges, the consistently strong results highlight AI’s growing potential to complement and enhance existing prognostic frameworks. Beyond mortality, AI has expanded the scope of analysis to the structural and biomechanical behavior of the aorta itself. Through integration of imaging, radiomic, and computational modeling data, AI now allows virtual representation of aortic mechanics—enabling prediction of aneurysm growth rate, remodeling after repair, and even rupture risk and location. Such models bridge data-driven learning with mechanistic understanding, creating an opportunity to simulate disease progression in a virtual environment. In addition to mortality and growth-related outcomes, morbidity prediction has become another area of rapid development. AI models have been used to assess a wide range of postoperative complications, including stroke, gastrointestinal bleeding, prolonged hospitalization, reintubation, and paraplegia—showing that predictive applications are limited only by clinical imagination. Among these, acute kidney injury (AKI) has received particular attention, with several robust studies demonstrating high accuracy in early identification of patients at risk for severe renal complications. To translate these promising results into real-world clinical use, future work must focus on large multicenter collaborations, external validation, and adherence to transparent reporting standards such as TRIPOD-AI. Integration of explainable AI frameworks and dynamic, patient-specific modeling—potentially through the development of digital twins—will be essential for achieving real-time clinical applicability. Ultimately, AI holds the potential not only to refine risk prediction but to fundamentally transform how we understand, monitor, and manage patients with AAS and TAA. Full article

It is essential to assign the correct triage level to patients as soon as they arrive in the emergency department in order to save lives, especially during peak demand. However, many healthcare systems estimate the triage levels by manual eyes-on evaluation, which can be inconsistent and time consuming. This study creates a full Digital Twin-based architecture for patient monitoring and automated triage level recommendation using IoT sensors, AI, and cloud-based services. The system can monitor all patients’ vital signs through embedded sensors. The readings are used to update the Digital Twin instances that represent the present condition of the patients. This data is then used for triage prediction using a pretrained model that can predict the patients’ triage levels. The training of the model utilized the synthetic minority over-sampling technique, combined with Tomek links to lessen the degree of data imbalance. Additionally, Lagrange element optimization was applied to select those features of the most informative nature. The final triage level is predicted using the Tabular Prior-Data Fitted Network, a transformer-based model tailored for tabular data classification. This combination achieved an overall accuracy of 87.27%. The proposed system demonstrates the potential of integrating digital twins and AI to improve decision support in emergency healthcare environments. Full article

Lyophilization (freeze-drying) has become a cornerstone pharmaceutical technology for stabilizing biopharmaceuticals, overcoming the inherent instability of biologics, vaccines, and complex drug formulations in aqueous environments. The appropriate literature for this review was identified through a structured search of several databases (such as PubMed, Scopus) covering publications from late 1990s till date, with inclusion limited to peer-reviewed studies on lyophilization processes, formulation development, and process analytical technologies. This succinct review examines both fundamental principles and cutting-edge advancements in lyophilization technology, with particular emphasis on Quality by Design (QbD) frameworks for optimizing formulation development and manufacturing processes. The work systematically analyzes the critical three-stage lyophilization cycle—freezing, primary drying, and secondary drying—while detailing how key parameters (shelf temperature, chamber pressure, annealing) influence critical quality attributes (CQAs) including cake morphology, residual moisture content, and reconstitution behavior. Special attention is given to formulation strategies employing synthetic surfactants, cryoprotectants, and stabilizers for complex delivery systems such as liposomes, nanoparticles, and biologics. The review highlights transformative technological innovations, including artificial intelligence (AI)-driven cycle optimization, digital twin simulations, and automated visual inspection systems, which are revolutionizing process control and quality assurance. Practical case studies demonstrate successful applications across diverse therapeutic categories, from small molecules to monoclonal antibodies and vaccines, showcasing improved stability profiles and manufacturing efficiency. Finally, the discussion addresses current regulatory expectations (FDA/ICH) and compliance considerations, particularly regarding cGMP implementation and the evolving landscape of AI/ML (machine learning) validation in pharmaceutical manufacturing. By integrating QbD-driven process design with AI-enabled modeling, process analytical technology (PAT) implementation, and regulatory alignment, this review provides both a strategic roadmap and practical insights for advancing lyophilized drug product development to meet contemporary challenges in biopharmaceutical stabilization and global distribution. Despite several publications addressing individual aspects of lyophilization, there is currently no comprehensive synthesis that integrates formulation science, QbD principles, and emerging digital technologies such as AI/ML and digital twins within a unified framework for process optimization. Future work should integrate advanced technologies, AI/ML standardization, and global access initiatives within a QbD framework to enable next-generation lyophilized products with improved stability and patient focus. Full article

Prehabilitation programs for abdominal pre-operative patients are increasingly recognized for improving surgical outcomes, reducing post-operative complications, and enhancing recovery. Internet of Things (IoT)-enabled human movement monitoring systems offer promising support in mixed-mode settings that combine clinical supervision with home-based independence. These systems enhance accessibility, reduce pressure on healthcare infrastructure, and address geographical isolation. However, current implementations often lack personalized movement analysis, adaptive intervention mechanisms, and real-time clinical integration, frequently requiring manual oversight and limiting functional outcomes. This review-based paper proposes a conceptual framework informed by the existing literature, integrating Digital Twin (DT) technology, and machine learning/Artificial Intelligence (ML/AI) to enhance IoT-based mixed-mode prehabilitation programs. The framework employs inertial sensors embedded in wearable devices and smartphones to continuously collect movement data during prehabilitation exercises for pre-operative patients. These data are processed at the edge or in the cloud. Advanced ML/AI algorithms classify activity types and intensities with high precision, overcoming limitations of traditional Fast Fourier Transform (FFT)-based recognition methods, such as frequency overlap and amplitude distortion. The Digital Twin continuously monitors IoT behavior and provides timely interventions to fine-tune personalized patient monitoring. It simulates patient-specific movement profiles and supports dynamic, automated adjustments based on real-time analysis. This facilitates adaptive interventions and fosters bidirectional communication between patients and clinicians, enabling dynamic and remote supervision. By combining IoT, Digital Twin, and ML/AI technologies, the proposed framework offers a novel, scalable approach to personalized pre-operative care, addressing current limitations and enhancing outcomes. Full article

Digital twins (DTs), virtual replicas that integrate mechanistic modeling with real-time clinical data, are emerging as powerful tools in healthcare with particular promise in pediatrics, where age-dependent physiology and ethical considerations complicate infectious disease management. This narrative review examines current and potential applications of DTs across antimicrobial stewardship (AMS), diagnostics, vaccine personalization, respiratory support, and system-level preparedness. Evidence indicates that DTs can optimize antimicrobial therapy by simulating pharmacokinetics and pharmacodynamics to support individualized dosing, enable Bayesian therapeutic drug monitoring, and facilitate timely de-escalation. They also help guide intravenous-to-oral switches and treatment durations by integrating host-response markers and microbiological data, reducing unnecessary antibiotic exposure. Diagnostic applications include simulating host–pathogen interactions to improve accuracy, forecasting clinical deterioration to aid in early sepsis recognition, and differentiating between viral and bacterial illness. Immune DTs hold potential for tailoring vaccination schedules and prophylaxis to a child’s unique immune profile, while hospital- and system-level DTs can simulate outbreaks, optimize patient flow, and strengthen surge preparedness. Despite these advances, implementation in routine pediatric care remains limited by challenges such as scarce pediatric datasets, fragmented data infrastructures, complex developmental physiology, ethical concerns, and uncertain regulatory frameworks. Addressing these barriers will require prospective validation, interoperable data systems, and equitable design to ensure fairness and inclusivity. If developed responsibly, DTs could redefine pediatric infectious disease management by shifting practice from reactive and population-based toward proactive, predictive, and personalized care, ultimately improving outcomes while supporting AMS and health system resilience. Full article