Comparing Traditional Risk Scores and an AI-Based Multimodal Model for Predicting Cardiovascular Events After Gastrointestinal Surgery

Official title

Value of Some Risk Scores in Predicting Cardiovascular Events After Gastrointestinal Surgery

Overview

The goal of this observational study is to develop and evaluate an artificial intelligence (AI)-based multimodal model for predicting major cardiovascular events within 30 days after gastrointestinal surgery in adults at Bach Mai Hospital. The study will also compare the predictive performance of this AI-based model with commonly used traditional risk scores. The main questions it aims to answer are: Can an AI-based multimodal model predict major cardiovascular events within 30 days after gastrointestinal surgery? Does the AI-based model show better predictive performance than the Revised Cardiac Risk Index (RCRI), the American College of Surgeons National Surgical Quality Improvement Program Myocardial Infarction or Cardiac Arrest calculator (ACS NSQIP MICA), and the ACS NSQIP Surgical Risk Calculator (ACS NSQIP SRC)? Researchers will compare the AI-based multimodal model with traditional risk scores using measures of predictive performance, including discrimination, calibration, net reclassification improvement, and integrated discrimination improvement. Participants will be adults undergoing gastrointestinal surgery. Researchers will review medical record data from patients treated in 2025 and will also collect the same types of clinical data prospectively in 2026. The clinical outcome being predicted is the occurrence of major cardiovascular events within 30 days after surgery. The study will not change routine clinical care.

Detailed description

Major cardiovascular events after gastrointestinal surgery remain an important cause of early postoperative complications and poor outcomes. Traditional perioperative cardiac risk scores, including the Revised Cardiac Risk Index (RCRI), the American College of Surgeons National Surgical Quality Improvement Program Myocardial Infarction or Cardiac Arrest calculator (ACS NSQIP MICA), and the ACS NSQIP Surgical Risk Calculator (ACS NSQIP SRC), are widely used in clinical practice. However, their performance may be limited in specific surgical populations and may not fully capture complex interactions among clinical, laboratory, physiologic, and procedural variables.

This observational study aims to develop and evaluate an artificial intelligence (AI)-based multimodal model for predicting major cardiovascular events within 30 days after gastrointestinal surgery and to compare its predictive performance with traditional risk scores. The study will be conducted at Bach Mai Hospital and will include adult patients undergoing gastrointestinal surgery. The study uses a mixed retrospective-prospective design, with retrospective data collection from patients treated in 2025 and prospective data collection in 2026.

The target clinical outcome for prediction is the occurrence of major cardiovascular events within 30 days after surgery. These events include cardiovascular death, nonfatal myocardial infarction, cardiac arrest with return of spontaneous circulation, new stroke, and clinically significant arrhythmias requiring treatment. Data used for model development and comparison may include demographic characteristics, medical history, cardiovascular comorbidities, surgical characteristics, anesthetic information, preoperative laboratory results, electrocardiographic findings, biomarkers when available, and functional or risk assessment variables.

The primary outcome of the study is the discrimination performance of the AI-based multimodal model compared with traditional risk scores, measured by the area under the receiver operating characteristic curve for predicting 30-day major cardiovascular events after gastrointestinal surgery. Secondary outcomes include calibration performance, net reclassification improvement, and integrated discrimination improvement of the AI-based multimodal model compared with traditional risk scores, including RCRI, ACS NSQIP MICA, and ACS NSQIP SRC.

The study is observational and will not alter routine perioperative management. Data will be obtained from existing medical records and prospective clinical collection, coded for confidentiality, and analyzed to support risk stratification and model comparison in patients undergoing gastrointestinal surgery.

Primary outcome measures

• Area under the receiver operating characteristic curve of the AI-based multimodal model for predicting 30-day major adverse cardiovascular events after gastrointestinal surgery [Time frame: From the preoperative period to 30 days after surgery.]

Secondary outcome measures (6)

• Brier score of the AI-based multimodal model for predicting 30-day major cardiovascular events after gastrointestinal surgery [Time frame: From the preoperative period to 30 days after surgery]
• Net Reclassification Improvement of the AI-Based Multimodal Model Compared With Traditional Risk Scores for Predicting 30-Day Major Cardiovascular Events After Gastrointestinal Surgery [Time frame: Using perioperative data collected from the preoperative period through 30 days after surgery]
• Integrated Discrimination Improvement of the AI-Based Multimodal Model Compared With Traditional Risk Scores for Predicting 30-Day Major Cardiovascular Events After Gastrointestinal Surgery [Time frame: Using perioperative data collected from the preoperative period through 30 days after surgery]
• Area under the receiver operating characteristic curve of the Revised Cardiac Risk Index for predicting 30-day major cardiovascular events after gastrointestinal surgery [Time frame: From the preoperative period to 30 days after surgery]
• Area under the receiver operating characteristic curve of the ACS NSQIP Surgical Risk Calculator for predicting 30-day major cardiovascular events after gastrointestinal surgery [Time frame: From the preoperative period to 30 days after surgery]
• Calibration slope of the AI-based multimodal model for predicting 30-day major cardiovascular events after gastrointestinal surgery [Time frame: From the preoperative period to 30 days after surgery]

Eligibility criteria

Inclusion criteria

• Adults aged 18 years or older.
• Undergoing gastrointestinal surgery at Bach Mai Hospital between January 2025 and December 2026.
• Available preoperative, intraoperative, and postoperative data sufficient for analysis.

Exclusion criteria

• Death within 24 hours after surgery due to a clearly non-cardiovascular cause.
• Incomplete data required for analysis.

Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.

Healthy volunteers: No

Study design

Observational model

Cohort

Study locations

Vietnam · 1 center

• Bach Mai hospital — Hà Nội

Publications

• Gautam N, Mueller J, Alqaisi O, Gandhi T, Malkawi A, Tarun T, Alturkmani HJ, Zulqarnain MA, Pontone G, Al'Aref SJ. Machine Learning in Cardiovascular Risk Prediction and Precision Preventive Approaches. Curr Atheroscler Rep. 2023 Dec;25(12):1069-1081. doi: 10.1007/s11883-023-01174-3. Epub 2023 Nov 27. PMID 38008807
• Liu T, Krentz A, Lu L, Curcin V. Machine learning based prediction models for cardiovascular disease risk using electronic health records data: systematic review and meta-analysis. Eur Heart J Digit Health. 2024 Oct 27;6(1):7-22. doi: 10.1093/ehjdh/ztae080. eCollection 2025 Jan. PMID 39846062
• Cheng CH, Lee BJ, Nfor ON, Hsiao CH, Huang YC, Liaw YP. Using machine learning-based algorithms to construct cardiovascular risk prediction models for Taiwanese adults based on traditional and novel risk factors. BMC Med Inform Decis Mak. 2024 Jul 22;24(1):199. doi: 10.1186/s12911-024-02603-2. PMID 39039467
• Li C, Liu X, Shen P, Sun Y, Zhou T, Chen W, Chen Q, Lin H, Tang X, Gao P. Improving cardiovascular risk prediction through machine learning modelling of irregularly repeated electronic health records. Eur Heart J Digit Health. 2023 Oct 17;5(1):30-40. doi: 10.1093/ehjdh/ztad058. eCollection 2024 Jan. PMID 38264696
• Kothari P, Vanneman MW, Choi C, Diehl R, Fielding-Singh V. Highlights from the American College of Cardiology and American Heart Association 2024 Guideline for Perioperative Cardiovascular Management for Noncardiac Surgery. J Cardiothorac Vasc Anesth. 2025 Sep;39(9):2408-2420. doi: 10.1053/j.jvca.2025.05.014. Epub 2025 May 14. PMID 40480877
• Writing Committee for the VISION Study Investigators; Devereaux PJ, Biccard BM, Sigamani A, Xavier D, Chan MTV, Srinathan SK, Walsh M, Abraham V, Pearse R, Wang CY, Sessler DI, Kurz A, Szczeklik W, Berwanger O, Villar JC, Malaga G, Garg AX, Chow CK, Ackland G, Patel A, Borges FK, Belley-Cote EP, Duceppe E, Spence J, Tandon V, Williams C, Sapsford RJ, Polanczyk CA, Tiboni M, Alonso-Coello P, Faruqu PMID 28444280
• Vascular Events In Noncardiac Surgery Patients Cohort Evaluation (VISION) Study Investigators; Devereaux PJ, Chan MT, Alonso-Coello P, Walsh M, Berwanger O, Villar JC, Wang CY, Garutti RI, Jacka MJ, Sigamani A, Srinathan S, Biccard BM, Chow CK, Abraham V, Tiboni M, Pettit S, Szczeklik W, Lurati Buse G, Botto F, Guyatt G, Heels-Ansdell D, Sessler DI, Thorlund K, Garg AX, Mrkobrada M, Thomas S, Rods PMID 22706835
• Writing Committee Members; Thompson A, Fleischmann KE, Smilowitz NR, de Las Fuentes L, Mukherjee D, Aggarwal NR, Ahmad FS, Allen RB, Altin SE, Auerbach A, Berger JS, Chow B, Dakik HA, Eisenstein EL, Gerhard-Herman M, Ghadimi K, Kachulis B, Leclerc J, Lee CS, Macaulay TE, Mates G, Merli GJ, Parwani P, Poole JE, Rich MW, Ruetzler K, Stain SC, Sweitzer B, Talbot AW, Vallabhajosyula S, Whittle J, Will PMID 39320289

Identifiers

NCT: NCT07539532 · BM_2025_238

Primary sources (government registries)

• ClinicalTrials.gov (US NIH)

View this study on ClinicalTrials.gov ↗