Application of a Gene Modular Approach for Clinical Phenotype Genotype Association and Sepsis Prediction Using Machine Learning in Meningococcal Sepsis

Aug 5, 2026

Upload by Patrick

Sepsis is a major global health concern causing high morbidity and mortality rates. The study used a Meningococcal Septic Shock (MSS) temporal dataset to analyze correlations between gene expression changes and clinical features in infants admitted to a Pediatric Critical Care Unit. Weighted Gene Co-expression Network Analysis (WGCNA) linked transcriptomic data with clinical parameters, while machine learning models including SVM, Naive Bayes, KNN, Decision Tree, Random Forest, and ANN predicted sepsis survival. Results showed temporal pathway transitions and found ANN as the most accurate model for survival prediction, enabling PELOD-linked gene modules that inform precision-based future interventions.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Abstract

Study dataset and gene-expression analysis

WGCNA and clinical parameter correlation

Machine learning models for survival prediction

Key findings and implications

The Jackson Laboratory The Mouseion at the JAXlibrary | Faculty Research 2024 | Faculty & Staff Research | | --- | --- | 2023 Application of a gene modular approach for clinical phenotype genotype association and sepsis prediction using machinApplication of a gene modular approach for clinical phenotype genotype association and sepsis prediction using machine learning in meningococcal sepsise learning in meningococcal sepsis Asrar Rashid Arif Anwary Feras Al-Obeidat Joe Brierley Mohammed Uddin See next page for additional authors Follow this and additional works at: [https://mouseion.jax.org/stfb2024](https://mouseion.jax.org/stfb2024) Authors Asrar Rashid, Arif Anwary, Feras Al-Obeidat, Joe Brierley, Mohammed Uddin, Hoda Alkhzaimi, Amrita Sarpal, Mohammed Toufiq, Zainab Malik, Raziya Kadwa, Praveen Khilnani, M Guftar Shaikh, Govind Benakatti, Javed Sharief, Syed Ahmed Zaki, Abdulrahman Zeyada, Ahmed Al-Dubai, Wael Hafez, and Amir Hussain Informatics in Medicine Unlocked 41 (2023) 101293 Contents lists available at ScienceDirect Informatics in Medicine Unlocked journal [homepage:](homepage: www.elsevier.com/locate/imu)[ www.elsevier.com/locate/imu](homepage: www.elsevier.com/locate/imu) | Application of a gene modular approach for clinical phenotype genotype association and sepsis prediction using machine learning in meningococcal sepsis | | | | | --- | --- | --- | --- | | Asrar Rashida, b, *, Arif R. Anwarya, Feras Al-Obeidatc, Joe Brierleyd, Mohammed Uddine, Hoda Alkhzaimif, Amrita Sarpalg, h, Mohammed Toufiqi, Zainab A. Malike,j, Raziya Kadwab, Praveen Khilnanik, M Guftar Shaikh l, Govind Benakattim, Javed Shariefb, Syed Ahmed Zakin, Abdulrahman Zeyadab, Ahmed Al-Dubai a, Wael Hafez b, o, Amir Hussain a
a Edinburgh Napier University, Merchiston Campus, 10 Colinton Road, Edinburgh, Scotland, EH10 5DT, UK b NMC Royal Khalifa Hospital, Abu Dhabi, United Arab Emirates
c College of Technological Innovation at Zayed University, Abu Dhabi, United Arab Emirates d Great Ormond Street Children’s Hospital, London, UK
e College of Medicine, Mohammed Bin Rashid University of Medicine and Health Sciences, Dubai, United Arab Emirates f New York University Abu Dhabi, United Arab Emirates
g Weill Cornell Medicine, Doha, Qatar h Sidra Medicine, Doha, Qatar
i The Jackson Laboratory for Genomic Medicine, Farmington, Connecticut, USA j Mediclinic City Hospital, Dubai, United Arab Emirates
k Medanta Gururam, Delhi, India
l Royal Hospital for Children, Glasgow, UKm Yas Clinic, Abu Dhabi, United Arab Emirates
n All India Institute of Medical Sciences, Bibinagar, Hyderabad, India
o Medical Research Division, Department of Internal Medicine, The National Research Centre, Cairo, Egypt | | | | | A R T I C L E I N F O | | A B S T R A C T | | | Keywords:
Meningococcal septic shock Machine learning Artificial neural network Gene modular approach | | Sepsis is a major global health concern causing high morbidity and mortality rates. Our study utilized a Meningococcal Septic Shock (MSS) temporal dataset to investigate the correlation between gene expression (GE) changes and clinical features. The research used Weighted Gene Co-expression Network Analysis (WGCNA) to establish links between gene expression and clinical parameters in infants admitted to the Pediatric Critical Care Unit with MSS. Additionally, various machine learning (ML) algorithms, including Support Vector Machine (SVM), Naive Bayes, KNearest Neighbors (KNN), Decision Tree, Random Forest, and Artificial Neural Network (ANN) were implemented to predict sepsis survival. The findings revealed a transition in gene function pathways from nuclear to cytoplasmic to extracellular, corresponding with Pediatric Logistic Organ Dysfunction score (PELOD) readings at 0, 24, and 48 h. ANN was the most accurate of the six ML models applied for survival prediction. This study successfully correlated PELOD with transcriptomic data, mapping

FAQs

What dataset and clinical context does the study use for sepsis prediction?

The study uses a Meningococcal Septic Shock (MSS) temporal dataset and focuses on infants admitted to a Pediatric Critical Care Unit.

How is gene expression related to clinical features in the research?

Weighted Gene Co-expression Network Analysis (WGCNA) is used to connect gene expression changes with clinical parameters, including PELOD readings at 0, 24, and 48 hours.

Which machine learning model performs best for survival prediction?

Among six evaluated models, the Artificial Neural Network (ANN) achieves the highest accuracy for sepsis survival prediction.

Aug 5, 2026

Upload by Patrick