EUVIMEDSkopri EUVIMED
Randomisierte kontrollierte StudieStudienprotokollOpen access

Nurse-Led Large Language Model Chatbot for Predicting and Preventing Complications After Coronary Artery Bypass Grafting: Protocol for a Randomized Controlled Trial

Nurse-gesteuerter Large-Language-Model-Chatbot zur Vorhersage und Prävention von Komplikationen nach Koronararterien-Bypass-Operation: Protokoll für eine randomisierte kontrollierte Studie

Salini K iD, Ajee K L iD, Praveen Kerala Varma iD, Premjith B iD, Anila K P iD, Vandana Agnihotri iD, Priyalatha Muthu iD, Renjitha Bhaskaran iD, Namrata Nair iD

JMIR Research Protocols · 2026-08-04 · 15 · e103717-e103717

DOI: 10.2196/103717 ↗

Auf einen Blick

Das Protokoll beschreibt Smart CABGuard, einen nurse-geführten LLM-Chatbot mit ECG-Monitoring nach isoliertem CABG. Geprüft werden Vorhersage und Prävention von Komplikationen und 30-Tage-Wiederaufnahmen.

Fragestellung

Kann Smart CABGuard nach isoliertem CABG postoperative Komplikationen und 30-Tage-Wiederaufnahmen verhindern?

Methode

Multiphase-Studie in Kochi, Indien; Phase III: prospektive, parallele, offene RCT mit 1:1-Randomisierung und Verblindung der Auswertenden.

Ergebnisse

Geplant sind 800 Patient:innen (400 je Arm). Interventionsarm: Smart CABGuard mit täglichen Check-ins, CRI-Risikostratifizierung, ECG-Monitoring und nurse-led Triage für etwa 24 Tage nach Entlassung; Kontrolle: Standardversorgung mit strukturierter Telefonnachverfolgung zur Ergebniserfassung.

Einschränkungen

Protokoll, daher keine Ergebnisse; Phase III-Rekrutierung erst für August 2026 bis September 2027 geplant.

Schlussfolgerung der Autor:innen

Smart CABGuard soll als erstes RCT-Protokoll eines LLM-basierten nurse-geführten CDS-Systems die Nützlichkeit, Sicherheit und Machbarkeit KI-gestützter postoperativer Überwachung prüfen.

Kernaussagen

  • Phase III ist eine offene, parallele RCT nach isoliertem CABG
  • Primärer Endpunkt: 30-Tage-Wiederaufnahme wegen jeglicher Ursache
  • Ziel: 800 Patient:innen, 50 % relative Reduktion bei α=.10 und 80 % Power

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Randomisierte kontrollierte Studie in JMIR Research Protocols, published online on 2026-08-04. Written by Salini K and 8 co-authors. Institution: Department of Medical Surgical Nursing, Amrita College of Nursing, Amrita Vishwa Vidyapeetham, Amrita Institute of Medical Sciences and Research Cent…. Major MEDLINE topics: Coronary Artery Bypass, Postoperative Complications. 57 references. The full text is freely available in PubMed Central.

Auf einen BlickAstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Background

Thirty-day unplanned readmission following coronary artery bypass grafting (CABG) affects 10%-20% of patients and is a key quality indicator, particularly in low- and middle-income countries (LMICs) where access to cardiac rehabilitation is limited. Existing risk models are static, lack real-time engagement, and no validated large language model (LLM)–based clinical decision support (CDS) system exists for post-CABG readmission prevention.

Objective

This protocol describes the development, validation, and evaluation of Smart CABGuard, a nurse-led, LLM-based CDS chatbot with continuous remote electrocardiographic (ECG) monitoring, to predict and prevent postoperative complications, and 30-day unplanned readmission after isolated CABG.

Methods

This multiphase translational study is conducted at Amrita Institute of Medical Sciences, Kochi, India, following TRIPOD-LLM (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis–Large Language Model) and CONSORT (Consolidated Standards of Reporting Trials) AI reporting guidelines. Phase I uses an ambispective design (retrospective: January 2020 to December 2024; prospective needs survey: June 2025 to January 2026) to develop a logistic regression-based Complication Risk Index (CRI), assessed via receiver operating characteristic area under the curve, Brier score, and decision curve analysis. Phase II refines Smart CABGuard by integrating a frozen Mistral-7B LLM (low-rank adaptation fine-tuned), the CRI engine, explainable AI, and single-lead ECG telemetry (Amrita Spandanam device), with a usability threshold of ≥80%. Phase III is a prospective, parallel-group, open-label randomized controlled trial (RCT). Adults aged ≥18 years undergoing isolated CABG with smartphone access are randomized 1:1 via permuted block randomization, with allocation concealment. The intervention arm receives Smart CABGuard–assisted care (daily chatbot check-ins, CRI-based risk stratification, ECG monitoring, and nurse-led triage) for approximately 24 days postdischarge plus standard care; the control arm receives standard care with structured telephone follow-up for outcome ascertainment only. Outcome assessors and statisticians are blinded; analyses follow the intention-to-treat principle. The primary outcome is 30-day all-cause unplanned readmission. Based on a baseline rate of 10.71%, a 50% relative reduction, α=.10, and 80% power, the target sample size is 800 patients (400 per arm, including 10% attrition).

Results

Ethics approval was granted by the Institutional Ethics Committee of Amrita Institute of Medical Sciences on April 16, 2025. Funding was awarded by Sigma Theta Tau International Honor Society of Nursing, Small Grants Program (grant 21650) in June 2025. Phase I data extraction commenced in May 2025 and is projected to be completed by April 2026; the patient needs survey (June 2025 to January 2026) is ongoing. Phase II usability evaluation is projected from May to July 2026. Phase III recruitment is anticipated from August 2026 to September 2027. Results are expected to be published in early 2028.

Conclusions

Smart CABGuard is the first RCT protocol of an LLM-based nurse-led CDS system for post-CABG readmission prevention in an LMIC setting, aiming to establish the usefulness, safety, and feasibility of AI-augmented postoperative surveillance.

Subjects

MeSH terms (MEDLINE)

Coronary Artery BypassPostoperative ComplicationsHumansLarge Language ModelsRandomized Controlled Trials as TopicProspective StudiesElectrocardiographyIndiaDecision Support Systems, Clinical

Author keywords

artificial intelligencecoronary artery bypass graftingelectrocardiographic monitoringhospital readmissionlarge language modelpostoperative carepostoperative complicationsrandomized controlled trialremote patient monitoringthirty-day hospital readmission

Authors and institutions

  • Department of Medical Surgical Nursing, Amrita College of Nursing, Amrita Vishwa Vidyapeetham, Amrita Institute of Medical Sciences and Research Center, Kochi Campus, Ponekkara, Edappally, Kochi, Kerala, 682041, India,…
  • Department of Cardiovascular and Thoracic Surgery (CVTS), Amrita School of Medicine, Amrita Vishwa Vidyapeetham, Kochi, Kerala, India.
  • Department of Artificial Intelligence, Amrita School of Artificial Intelligence, Amrita Vishwa Vidyapeetham, Coimbatore, Tamil Nadu, India.
  • Department of Medical Surgical Nursing, College of Nursing, Armed Forces Medical College, Pune, Maharashtra, India.
  • Department of Medical Surgical Nursing, College of Nursing, RAK Medical & Health Sciences University, Al Juwais, Ras Al Khaimah, United Arab Emirates.
  • Amrita Institute of Medical Sciences, Amrita Vishwa Vidyapeetham, Kochi, Kerala, India.

ORCID profiles: Salini K, Ajee K L, Praveen Kerala Varma, Premjith B, Anila K P, Vandana Agnihotri, Priyalatha Muthu, Renjitha Bhaskaran, Namrata Nair

Cite

APA

K, S., K L, A., Kerala Varma, P., B, P., K P, A., Agnihotri, V., Muthu, P., Bhaskaran, R., & Nair, N. (2026). Nurse-Led Large Language Model Chatbot for Predicting and Preventing Complications After Coronary Artery Bypass Grafting: Protocol for a Randomized Controlled Trial. JMIR Research Protocols, 15, e103717-e103717. https://doi.org/10.2196/103717

Vancouver

K S, K L A, Kerala Varma P, B P, K P A, Agnihotri V, et al. Nurse-Led Large Language Model Chatbot for Predicting and Preventing Complications After Coronary Artery Bypass Grafting: Protocol for a Randomized Controlled Trial. JMIR Research Protocols. 2026;15:e103717-e103717. doi:10.2196/103717

BibTeX
@article{K2026,
  author = {K, Salini and K L, Ajee and Kerala Varma, Praveen and B, Premjith and K P, Anila and Agnihotri, Vandana and Muthu, Priyalatha and Bhaskaran, Renjitha and Nair, Namrata},
  title = {Nurse-Led Large Language Model Chatbot for Predicting and Preventing Complications After Coronary Artery Bypass Grafting: Protocol for a Randomized Controlled Trial},
  journal = {JMIR Research Protocols},
  year = {2026},
  volume = {15},
  pages = {e103717--e103717},
  doi = {10.2196/103717}
}
Start for free →