{
  "abstract": "Digital twins for physiological forecasting require robust mechanisms for continuously assimilating streaming data and adapting to patient-specific dynamics. Threshold-triggered model updates can restore predictive performance after substantial drift, but their reactive nature limits continuous adaptation. We propose a proactive digital twin framework that couples a pretrained PatchTST foundation model with an Actor-Critic reinforcement learning (RL) agent for residual correction. Using a 30-minute look-back window and recent residual history, the agent generates bounded corrections ({+/-}0.05) to the first-step baseline forecast, with corrected predictions recursively propagated over a 15- step horizon. We evaluate both an RL-only workflow and a hybrid workflow combining RL correction with threshold-triggered fine-tuning using minute-by-minute continuous glucose monitoring data from 10 critically ill patients with sepsis. Across all patients, the pretrained RL agent improves forecasting accuracy without patient-specific retraining. Both workflows reduce trajectory-averaged mean absolute percentage error, ensemble relative error, and maximum errors compared with the uncorrected baseline and previously developed reactive digital twin models. These findings support residual reinforcement learning as a lightweight mechanism for continuous, real-time data assimilation that preserves the foundation models global predictive prior while enabling patient-specific forecast adaptation, with potential applications in critical care decision support.",
  "abstract_shown": true,
  "affiliations": [
    "University of South Carolina"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "name": "X. Cao"
    },
    {
      "affs": [
        0
      ],
      "name": "Q. Wang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/943pmbprhh0sy.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.23.26366163",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.10.23.26366163v1.full",
  "id": "943pmbprhh0sy",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.10.23.26366163v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "intensive care and critical care medicine"
    ],
    [
      "openalex",
      "1702|Machine Learning in Healthcare"
    ]
  ],
  "openalex": "W7223457014",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.10.23.26366163v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-23",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/943pmbprhh0sy.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:40Z",
      "native_id": "10.64898/2026.10.23.26366163",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.10.23.26366163v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:intensive care and critical care medicine",
      "subfield": "general"
    }
  ],
  "title": "Digital Twin Workflow for Continuous Glucose Forecasting: Real-Time Data Assimilation Using Reinforcement Learning",
  "title_text": "Digital Twin Workflow for Continuous Glucose Forecasting: Real-Time Data Assimilation Using Reinforcement Learning",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:40Z",
  "url": "https://research.draconitic.com/paper/943pmbprhh0sy",
  "venue": "medRxiv",
  "versions": []
}