EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Modal FHIR Sensor Fusion for Real-Time Clinical Decision Support: An Architecture for the Hospital Bedside and Its Extension Toward Remote Patient Monitoring

Pierre Boulanger iD

Sensors · 06.11.2026 · 26 (21) · 7026

DOI: 10.3390/s26217026 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 06.11.2026. Verfasst von Pierre Boulanger. Beteiligte Einrichtung: Department of Computing Science, University of Alberta, Edmonton, AB T6G 2E8, Canada. Hauptthemen laut MEDLINE: Decision Support Systems, Clinical. Die Arbeit nennt 80 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

MedROAD V3 is a real-time FHIR R4 streaming platform that turns clinical sensor streams into calibrated deterioration risk, evaluated retrospectively on a cardiac ICU cohort. FHIR event sourcing, Kafka and Faust assemble an 86-element feature vector every five minutes. An XGBoost, LSTM and Transformer ensemble, combined by logistic meta-learning with SHAP attribution, scores each window; a write-back client returns the alert to the chart with a runtime-filtered language-model narrative. On 5049 held-out MIMIC-IV patients it reaches AUROC 0.816 at an Expected Calibration Error of 0.001, with a median inference path of 3.1 ms, so latency is governed by the EHR rather than by computation. The FHIR Observation resource is device-agnostic, so the pipeline ingests wearable streams unmodified. Three limits qualify these results. It is retrospective, and the remote-monitoring figures are a feature-restriction analysis on ICU data, not a wearable validation. Twenty-nine columns recording only how a patient was documented and managed, none physiological, reach AUROC 0.767 on the same split, so much of the discrimination reflects care process rather than physiology, although removing them costs only 0.007. Because OpenEMR 7.0.2 reference server grants no clinical FHIR write scope, the loop closes over an alternative path using its REST API, writing the alert as a Subjective-Objective-Assessment-Plan (SOAP) note on the encounter. The substitution works but is vendor-specific rather than portable, so the closed loop shown here is conditional on the target server.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Decision Support Systems, ClinicalHumansRemote Patient MonitoringMonitoring, PhysiologicIntensive Care UnitsDigital HealthAlgorithmsLong Short Term MemoryBoosting Machine Learning AlgorithmsHospitals

Stichwörter der Autor:innen

FHIR R4clinical decision supportensemble learningexplainable AImulti-modal data integrationreal-time streamingremote patient monitoringsensor fusiontelemedicinewearable sensors

Autor:innen und Institutionen

  • Department of Computing Science, University of Alberta, Edmonton, AB T6G 2E8, Canada.
  • Department of Radiology and Diagnostic Imaging, University of Alberta, Edmonton, AB T6G 2B7, Canada.

ORCID-Profile: Pierre Boulanger

Zitieren

APA

Boulanger, P. (2026). Multi-Modal FHIR Sensor Fusion for Real-Time Clinical Decision Support: An Architecture for the Hospital Bedside and Its Extension Toward Remote Patient Monitoring. Sensors, 26(21), 7026. https://doi.org/10.3390/s26217026

Vancouver

Boulanger P. Multi-Modal FHIR Sensor Fusion for Real-Time Clinical Decision Support: An Architecture for the Hospital Bedside and Its Extension Toward Remote Patient Monitoring. Sensors. 2026;26(21):7026. doi:10.3390/s26217026

BibTeX
@article{Boulanger2026,
  author = {Boulanger, Pierre},
  title = {Multi-Modal FHIR Sensor Fusion for Real-Time Clinical Decision Support: An Architecture for the Hospital Bedside and Its Extension Toward Remote Patient Monitoring},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {21},
  pages = {7026},
  doi = {10.3390/s26217026}
}
Kostenlos starten →