Related Experiment Video
Updated: May 12, 2026
Systematic Scoring Analysis for Intestinal Inflammation in a Murine Dextran Sodium Sulfate-Induced Colitis Model
Published on: February 14, 2021
AI-MET: A deep learning-based clinical decision support system for distinguishing multisystem inflammatory syndrome
Abraham Bautista-Castillo1, Angela Chun2, Tiphanie P Vogel2
1Computational Biomedicine Lab, University of Houston, 4349 Martin Luther King Boulevard, Houston, 77204, TX, USA; Department of Biomedical Engineering, University of Houston, 3605 Cullen Boulevard, Houston, 77204, TX, USA.
Insights
A new AI-MET system accurately distinguishes multisystem inflammatory syndrome in children (MIS-C) from typhus using early clinical data. This clinical decision support system is crucial for timely diagnosis and treatment of these distinct pediatric conditions.
Area of Science:
- Pediatric Infectious Diseases
- Clinical Informatics
- Artificial Intelligence in Healthcare
Background:
- The COVID-19 pandemic highlighted diagnostic challenges, including distinguishing multisystem inflammatory syndrome in children (MIS-C) from other conditions like typhus.
- Early differentiation is critical as MIS-C and typhus require different treatment approaches, impacting patient prognosis.
- Existing diagnostic methods may not provide rapid differentiation, necessitating advanced decision support tools.
Purpose of the Study:
- To develop and validate a Clinical Decision Support System (CDSS) named AI-MET for differentiating MIS-C from typhus.
- To create a scoring system utilizing early clinical and laboratory features for rapid diagnosis within six hours of Emergency Department presentation.
- To assess the performance of AI-MET against established statistical and machine learning models.
Main Methods:
- Development of the AI-MET CDSS incorporating a scoring system based on clinical and laboratory data.
- Training and testing the AI-MET system on datasets comprising 87 typhus patients and 133 MIS-C patients.
- Validation of AI-MET's effectiveness and robustness on a separate dataset of 111 MIS-C patients.
- Comparative analysis against five benchmark statistical and machine learning models using sensitivity, specificity, accuracy, and precision.
Main Results:
- The AI-MET system achieved 100% sensitivity, specificity, accuracy, and precision on its training and testing datasets.
- AI-MET demonstrated 99% performance on the validation dataset, confirming its effectiveness and robustness.
- Statistical analyses confirmed the significant performance advantage of AI-MET over baseline models.
Conclusions:
- The AI-MET system provides a highly accurate and rapid method for distinguishing MIS-C from typhus using readily available early clinical information.
- This CDSS has the potential to significantly improve diagnostic timeliness and patient management in pediatric emergency settings.
- AI-MET represents a valuable advancement in leveraging artificial intelligence for critical clinical decision support in infectious diseases.
Abstract:
The COVID-19 pandemic brought several diagnostic challenges, including the post-infectious sequelae multisystem inflammatory syndrome in children (MIS-C). Some of the clinical features of this syndrome can be found in other pathologies such as Kawasaki disease, toxic shock syndrome, and endemic typhus. Endemic typhus, or murine typhus, is an acute infection treated much differently than MIS-C, so early detection is crucial to a favorable prognosis for patients with these disorders. Clinical Decision Support Systems (CDSS) are computer systems designed to support the decision-making of medical teams about their patients and intended to improve uprising clinical challenges in healthcare. In this article, we present a CDSS to distinguish between MIS-C and typhus, which includes a scoring system that allows the timely distinction of both pathologies using only clinical and laboratory features typically available within the first six hours of presentation to the Emergency Department. The proposed approach was trained and tested on datasets of 87 typhus patients and 133 MIS-C patients. A comparison was made against five well-known statistical and machine-learning models. A second dataset with 111 MIS-C patients was used to verify the effectiveness and robustness of the AI-MET system. The performance assessment for AI-MET and the five statistical and machine learning models was performed by computing sensitivity, specificity, accuracy, and precision. The AI-MET system scores 100 percent in the five metrics used on the training and testing dataset and 99 percent on the validation dataset. Statistical analysis tests were also performed to evaluate the robustness and ensure a thorough and balanced evaluation, in addition to demonstrating the statistical significance of MET-30 performance compared to the baseline models.
Related Concept Videos
01:27Myocarditis II: Clinical Features and Diagnostic Tests
01:24Automated Microbial Diagnostics