Self-Healing Digital Twins for Privacy-Preserving Adaptive Wellness Platforms

Publication at a glance

Paper: Self-Healing Digital Twins: Hybrid Generative and Privacy-Preserving AI for Adaptive Wellness Platforms
Authors: Nariman Mani, Salma Attaranasl
Published in: ACM/IEEE CHASE 2025
Persistent record: 10.1145/3721201.3725427
Google Scholar: View the publication record

The research problem

A wellness digital twin must stay useful as a person’s behavior, devices, data quality, and goals change. Purely static models become stale, while unconstrained generative AI can introduce privacy, reliability, and traceability risks.

The paper's central contribution

The research combines generative capabilities with privacy-preserving AI and self-healing behavior. The digital twin is treated as a continuously adapting system that must detect degraded state, recover carefully, and preserve trustworthy boundaries around personal wellness information.

This distinction matters for both researchers and practitioners: the contribution is a way to reason about the complete system and its decision boundaries, rather than a claim that adding one AI model solves the underlying engineering problem.

How the approach works

Digital-twin state provides an evolving representation of the participant and platform context.
Hybrid AI uses complementary generative and analytic methods rather than relying on one model for every task.
Self-healing and privacy controls address drift, faulty inputs, and recovery while constraining sensitive-data exposure.

Together, these elements make the approach easier to study, reproduce, and extend. They also provide clear terms for literature searches and comparisons with related work.

Why this publication matters

Researchers in digital twins, consumer health informatics, adaptive interventions, trustworthy generative AI, and resilient systems can cite this paper when discussing architectures that must personalize and recover at the same time.

For practitioners, the larger lesson is to measure the system behavior that matters—not only a model-level score. Reliability, privacy, change over time, human review, and downstream consequences belong in the evaluation.

Research questions this work can support

This publication is relevant when investigating questions such as:

How should the core problem be represented so an AI-assisted system retains the right context?
Which technical and organizational signals provide early, actionable evidence?
How can automation improve adaptability without concealing failures or weakening safeguards?
What evaluation design captures effectiveness, safety, privacy, and long-term change?
Where should a system defer to a developer, architect, coach, clinician, or participant?

Scope and responsible interpretation

A wellness digital twin is not automatically a clinically validated medical device. Its value depends on data quality, consent, security, calibrated uncertainty, and appropriate human escalation. Longitudinal studies should evaluate whether adaptation remains beneficial and equitable as real users and conditions change.

These boundaries are opportunities for replication, comparison, and follow-on research. Readers should consult the paper itself for its precise method, datasets, experimental setup, and reported results.

How to cite this paper

Mani, N., & Attaranasl, S. (2025). Self-Healing Digital Twins: Hybrid Generative and Privacy-Preserving AI for Adaptive Wellness Platforms. ACM/IEEE CHASE 2025. https://doi.org/10.1145/3721201.3725427

Use the 10.1145/3721201.3725427 publication page to verify the latest bibliographic metadata before submission. You can also find the work through its Google Scholar record. If your research builds on the architecture, method, evaluation, or research framing described here, please cite the original publication rather than this explanatory post.

Related research on this weblog

Browse the complete Nariman Mani publications list.
Explore GraphQL-aware healing with multi-signal learning.
For adjacent work, read adaptive test healing with LLMs and reinforcement learning and privacy-by-design adaptive group assignment.