Digital Twins Generated by Artificial Intelligence in Personalized Healthcare

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(20), P. 9404 - 9404

Published: Oct. 15, 2024

Digital society strategies in healthcare include the rapid development of digital twins (DTs) for patients and human organs medical research use artificial intelligence (AI) clinical practice to develop effective treatments a cheaper, quicker, more manner. This is facilitated by availability large historical datasets from previous trials other real-world data sources (e.g., patient biometrics collected wearable devices). DTs can AI models create predictions future health outcomes an individual form AI-generated twin support assessment silico intervention strategies. are gaining ability update real time relation their corresponding physical connect multiple diagnostic therapeutic devices. Support this personalized medicine necessary due complex technological challenges, regulatory perspectives, issues security trust approach. The challenge also combine different omics quickly interpret order generate disease indicators improve sampling longitudinal analysis. It possible care through various means (simulated trials, prediction, remote monitoring apatient’s condition, treatment progress, adjustments plan), especially environments smart cities territories wider 6G, blockchain (and soon maybe quantum cryptography), Internet Things (IoT), as well technologies, such multiomics. From practical point view, requires not only efficient validation but seamless integration with existing infrastructure.

Language: Английский

---

Enhancing IoT Healthcare with Federated Learning and Variational Autoencoder

Sensors, Journal Year: 2024, Volume and Issue: 24(11), P. 3632 - 3632

Published: June 4, 2024

The growth of IoT healthcare is aimed at providing efficient services to patients by utilizing data from local hospitals. However, privacy concerns can impede sharing among third parties. Federated learning offers a solution enabling the training neural networks while maintaining data. To integrate federated into healthcare, hospitals must be part network jointly train global central model on server. Local using their patient datasets and send trained localized models These are then aggregated enhance process. aggregation dramatically influences performance training, mainly due heterogeneous nature Existing solutions address this issue iterative, slow, susceptible convergence. We propose two novel approaches that form groups efficiently assign weightage considering essential parameters vital for training. Specifically, our method utilizes an autoencoder extract features learn divergence between latent representations groups, facilitating more handling heterogeneity. Additionally, we another process several factors, including extracted data, maximize further. Our proposed group formation weighting outperform existing conventional methods. Notably, significant results obtained, one which shows achieves 20.8% higher accuracy 7% lower loss reduction compared

Language: Английский

---

The Potential Use of Digital Twin Technology for Advancing CAR-T Cell Therapy

Current Issues in Molecular Biology, Journal Year: 2025, Volume and Issue: 47(5), P. 321 - 321

Published: April 30, 2025

CAR-T cell therapy is a personalized immunotherapy that has shown promising results in treating hematologic cancers. However, its therapeutic efficacy solid cancers often limited by tumor evasion mechanisms, resistance pathways, and an immunosuppressive microenvironment. These challenges highlight the need for advanced predictive models to better capture intricate interactions between cells tumors enhance their potential. Digital Twins represent transformative approach optimizing providing virtual representation of therapy-tumor trajectory using high-dimensional patient data. In this review, we first define outline fundamental steps development. We then explore critical parameters required designing CAR-T-specific Twins. examine published case studies demonstrating few applications addressing key therapy, including impact on clinical trials manufacturing processes. Finally, discuss limitations associated with integrating into therapy. As Twin technology continues evolve, potential through precision modeling real-time adaptation could redefine landscape cancer treatment.

Language: Английский

---

Applications of Artificial Intelligence-Based Patient Digital Twins in Decision Support in Rehabilitation and Physical Therapy

Electronics, Journal Year: 2024, Volume and Issue: 13(24), P. 4994 - 4994

Published: Dec. 19, 2024

Artificial intelligence (AI)-based digital patient twins have the potential to make breakthroughs in research and clinical practices rehabilitation. They it possible personalise treatment plans by simulating different rehabilitation scenarios predicting patient-specific outcomes. DTs can continuously monitor a patient’s progress, adjusting therapy real time optimise recovery. also facilitate remote providing virtual models that therapists use guide patients without having be physically present. Digital (DTs) help identify complications or failures at an early stage, enabling proactive interventions. support training of professionals offering realistic simulations conditions. increase engagement visualising progress future outcomes, motivating adherence therapy. enable integration multidisciplinary care, common platform for collaborate improve strategies. The article aims trace current state knowledge, priorities, gaps order properly further shape decision

Language: Английский

---