Engineering Multimodal Medical Digital Twins: Sensor Fusion, Multimodal Learning, and Edge–Cloud AI for Real-Time Personalized Care

Dear Colleagues,

Medical digital twins—patient-specific, continuously updated computational replicas—are achieving practical viability when grounded in rigorous engineering. This Special Issue in Electronics foregrounds core technical advances that make multimodal medical digital twins reliable and scalable with low latency. We particularly welcome contributions on sensor fusion and synchronization that integrate 3D human kinematics (multi-view/markerless motion capture, IMUs, force/pressure sensing) with physiological signals (ECG/EMG/EEG/PPG and other waveforms) under real-world noise, drift, and bandwidth constraints; multimodal learning that aligns time-synchronized pose, force, and biosignals with clinical text via representation learning, contrastive objectives, grounding, cross-modal retrieval/generation, and event linking; and systems-level innovations for edge/embedded AI and edge–cloud orchestration, including on-device inference, model compression/quantization/distillation, hardware acceleration (GPU/FPGA/ASIC), streaming runtimes, and principled energy–latency–accuracy trade-offs.

We encourage hybrid physics–AI approaches—differentiable simulators, reduced-order surrogates, and real-time inverse dynamics/musculoskeletal models—combined with online calibration, data assimilation, and patient-specific personalization. Submissions should address verification, validation, and uncertainty quantification (VVUQ), robustness to distribution shift, and online performance/drift monitoring in embedded and clinical environments. Works on interoperability and information systems (digital-twin state management, time-series storage, messaging middleware, and bridges to FHIR/OMOP) are welcome insofar as they enable algorithmic and systems deployment. Privacy-preserving/federated learning for multimodal time series and text is within scope.

By centering algorithms, sensor technologies, and information systems, this Special Issue aims to translate multimodal evidence into trustworthy, real-time medical digital twins for rehabilitation, neuro-musculoskeletal and cardiopulmonary care, ICU monitoring, and home settings—bridging electronics and embedded AI to actionable, personalized decisions.

We invite research articles, reviews, datasets/benchmarks, and software/application notes.

Topics of interest include (but are not limited to) the following:

Multisensor fusion and synchronization: Markerless/multi-view MoCap; IMUs; force/pressure; time alignment; clock drift; self-calibration.

Multimodal learning: Pose–signal–text representation learning; grounding; contrastive alignment; cross-modal retrieval/generation; event linking.

Hybrid physics–AI twins: Differentiable simulators; surrogate/reduced-order models; real-time inverse dynamics and musculoskeletal modeling.

Edge/embedded AI: On-device inference; compression/distillation; quantization/TinyML; energy–latency optimization.

Hardware acceleration and systems: GPU/FPGA/ASIC pipelines; streaming runtimes; twin-state management; edge–cloud orchestration.

Robustness and VVUQ: Calibration; reliability under distribution shift; online performance/drift monitoring; safety monitoring.

Data assimilation and personalization: Bayesian filters; sequential/transfer/continual learning for patient-specific twins.

Interoperability and standards: APIs; time-series stores; messaging middleware; FHIR/OMOP bridges enabling algorithms/systems.

Security and privacy-preserving learning: Federated learning; secure aggregation; differential privacy for multimodal data.

Visualization and HCI: Real-time clinician/patient interfaces; explainability for embedded decisions; interactive what-if simulation.

Dr. Jingkun Chen
Dr. Xiao Zhang
Dr. Ying Huang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.