Combining artificial neural networks and hematological data to diagnose Covid-19 infection in Brazilian population

Fast and accurate diagnosis of COVID-19 is important to prevent dissemination and disease progression. Artificial Intelligence is known as a universal fitting tool and can be used on the formulation of predictive models for the disease’s diagnosis. Thus, we aimed to obtain a neural network (ANN) to...

Full description

Saved in:
Bibliographic Details
Published in:Neural computing & applications 2024-03, Vol.36 (8), p.4387-4399
Main Authors: Martins, Tiago D., Martins, Sandra D., Montalvão, Silmara, Al Bannoud, Mohamad, Ottaiano, Gabriel Y., Silva, Letícia Q., Huber, Stephany C., Diaz, Tassiana S. P., Wroclawski, Carolina, Filho, Cyrillo Cavalheiro, Maciel-Filho, Rubens, Annichino-Bizzacchi, Joyce M.
Format: Article
Language:English
Subjects:
Artificial Intelligence
Artificial neural networks
Blood tests
Body size
Body temperature
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer Science
COVID-19
Creatinine
Data Mining and Knowledge Discovery
Diagnosis
Heart rate
Hypertension
Image Processing and Computer Vision
Lactate dehydrogenase
Lymphocytes
Model accuracy
Neural networks
Neurons
Original Article
Oxygen content
Patients
Prediction models
Probability and Statistics in Computer Science
Prothrombin
Thromboplastin
Viral diseases
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Fast and accurate diagnosis of COVID-19 is important to prevent dissemination and disease progression. Artificial Intelligence is known as a universal fitting tool and can be used on the formulation of predictive models for the disease’s diagnosis. Thus, we aimed to obtain a neural network (ANN) to diagnose patients as positive or negative COVID-19 based on patient data and blood tests. Data from 1003 patients followed between June/2020 and October/2020 were used. Covid-19 was confirmed in 777 patients by RT-PCR. The inputs considered were: sex, age, ethinicity, body mass index, tabagism, ex-tabagism, alveolar infiltrate, arterial hypertension, diabetes, heart rate, respiration rate, body temperature, oxygen saturation, D-dimer, activated partial thromboplastin time, prothrombin time, levels of: hemoglobin, platelet, leukocytes, lymphocytes, monocytes, neutrophils, lactate dehydrogenase, C-reactive protein, and creatinine. Blood was collected at the patient’s admission. The ANNs had 25 inputs and the output was the Covid-19 diagnosis. ANNs with one and two hidden layers were proposed. The number of neurons ranged from 5 to 35. The best result was obtained with an ANN containing 15 neurons in the first and second hidden layers, respectively. The model presented accuracy of 83%, and high capacity for the prediction of true positives (precision of 0.90). The results showed that the ANNs are promising to diagnose Covid-19 based on clinical parameters and blood tests. After future refinements and proper validation, this model could be used to diagnose Covid-19 on daily basis.
ISSN:0941-0643
1433-3058
DOI:10.1007/s00521-023-09312-3