Explainable artificial intelligence approaches for COVID-19 prognosis prediction using clinical markers.

Explainable artificial intelligence approaches for COVID-19 prognosis prediction using clinical markers.

Publication date: Jan 20, 2024

The COVID-19 influenza emerged and proved to be fatal, causing millions of deaths worldwide. Vaccines were eventually discovered, effectively preventing the severe symptoms caused by the disease. However, some of the population (elderly and patients with comorbidities) are still vulnerable to severe symptoms such as breathlessness and chest pain. Identifying these patients in advance is imperative to prevent a bad prognosis. Hence, machine learning and deep learning algorithms have been used for early COVID-19 severity prediction using clinical and laboratory markers. The COVID-19 data was collected from two Manipal hospitals after obtaining ethical clearance. Multiple nature-inspired feature selection algorithms are used to choose the most crucial markers. A maximum testing accuracy of 95% was achieved by the classifiers. The predictions obtained by the classifiers have been demystified using five explainable artificial intelligence techniques (XAI). According to XAI, the most important markers are c-reactive protein, basophils, lymphocytes, albumin, D-Dimer and neutrophils. The models could be deployed in various healthcare facilities to predict COVID-19 severity in advance so that appropriate treatments could be provided to mitigate a severe prognosis. The computer aided diagnostic method can also aid the healthcare professionals and ease the burden on already suffering healthcare infrastructure.

Open Access PDF

Concepts Keywords
Elderly Algorithms
Fatal Artificial
Influenza Classifiers
Laboratory Clinical
Lymphocytes Covid
Explainable
Healthcare
Intelligence
Learning
Markers
Prognosis
Severe
Severity
Symptoms
Xai

Semantics

Type Source Name
disease MESH COVID-19
disease MESH influenza
disease VO population
disease MESH chest pain
drug DRUGBANK Coenzyme M
disease MESH sore throat
disease MESH syndrome
disease VO organ
drug DRUGBANK Nonoxynol-9
disease MESH Cytokine storm
pathway REACTOME Immune System
disease MESH hypertension
disease VO effective
disease IDO algorithm
disease IDO blood
disease IDO colony
disease VO organization
disease VO frequency
drug DRUGBANK Isoxaflutole
drug DRUGBANK Creatinine
drug DRUGBANK Creatine
drug DRUGBANK Potassium
drug DRUGBANK Oxygen
drug DRUGBANK L-Alanine
drug DRUGBANK Alkaline Phosphatase
disease MESH infections
disease IDO infection
disease MESH blood clot
drug DRUGBANK Iron
disease VO IroN
drug DRUGBANK Urea
drug DRUGBANK Penciclovir
disease VO efficiency
drug DRUGBANK Aspartame
disease IDO process
disease VO efficient
drug DRUGBANK Saquinavir
disease VO age
drug DRUGBANK Ciclosporin
drug DRUGBANK MCC
disease MESH Lymphopenia
drug DRUGBANK Human Serum Albumin
disease VO time
disease MESH hepatocellular carcinoma
pathway KEGG Hepatocellular carcinoma
disease VO report
disease MESH diabetes mellitus
disease MESH tuberculosis
pathway KEGG Tuberculosis
disease MESH abnormalities
disease MESH Cysts
disease MESH tumors
disease MESH polycystic ovary syndrome
disease MESH Clinical significance
disease MESH critical illness
drug DRUGBANK Parathyroid hormone
drug DRUGBANK (S)-Des-Me-Ampa
disease MESH obesity
disease MESH long COVID
disease MESH inflammation
disease MESH morbidity
disease MESH Allergy
disease MESH lung diseases

Original Article

(Visited 1 times, 1 visits today)