Mortality Prediction Utilizing Blood Biomarkers to Predict the Severity of COVID-19 Using Machine Learning Technique.
Tawsifur Rahman,Fajer A. Al-Ishaq,Fatima S. Al-Mohannadi,Reem S Mubarak,Maryam Al-Hitmi,Khandaker Reajul Islam,Amith Khandakar,Ali Ait Hssain,Somaya Al-Madeed,Susu M. Zughaier,Muhammad E. H. Chowdhury +10 more
- Vol. 11, Iss: 9, pp 1582-1582
Reads0
Chats0
TLDR
Wang et al. as mentioned in this paper proposed an early prediction model of high mortality risk for both COVID19 and non-COVID-19 patients, which provides state-of-the-art performance, in an external validation cohort from a different population.Abstract:
Healthcare researchers have been working on mortality prediction for COVID-19 patients with differing levels of severity. A rapid and reliable clinical evaluation of disease intensity will assist in the allocation and prioritization of mortality mitigation resources. The novelty of the work proposed in this paper is an early prediction model of high mortality risk for both COVID-19 and non-COVID-19 patients, which provides state-of-the-art performance, in an external validation cohort from a different population. Retrospective research was performed on two separate hospital datasets from two different countries for model development and validation. In the first dataset, COVID-19 and non-COVID-19 patients were admitted to the emergency department in Boston (24 March 2020 to 30 April 2020), and in the second dataset, 375 COVID-19 patients were admitted to Tongji Hospital in China (10 January 2020 to 18 February 2020). The key parameters to predict the risk of mortality for COVID-19 and non-COVID-19 patients were identified and a nomogram-based scoring technique was developed using the top-ranked five parameters. Age, Lymphocyte count, D-dimer, CRP, and Creatinine (ALDCC), information acquired at hospital admission, were identified by the logistic regression model as the primary predictors of hospital death. For the development cohort, and internal and external validation cohorts, the area under the curves (AUCs) were 0.987, 0.999, and 0.992, respectively. All the patients are categorized into three groups using ALDCC score and death probability: Low (probability 50%) risk groups. The prognostic model, nomogram, and ALDCC score will be able to assist in the early identification of both COVID-19 and non-COVID-19 patients with high mortality risk, helping physicians to improve patient management.read more
Citations
More filters
Journal ArticleDOI
Estimating the Relative Crystallinity of Biodegradable Polylactic Acid and Polyglycolide Polymer Composites by Machine Learning Methodologies
Jing Wang,Mohamed Arselene Ayari,A. Khandakar,Muhammad E. H. Chowdhury,SM Ashfaq Uz Zaman,Tawsifur Rahman,Behzad Vaferi +6 more
TL;DR: In this article , the authors used machine learning methods to estimate the relative crystallinity of biodegradable PLLA/PGA (polyglycolide) composites, and six different artificial intelligent classes were employed to estimate their relative crystallities as a function of crystallization time, temperature, and PGA content.
Journal ArticleDOI
Thermal Change Index-Based Diabetic Foot Thermogram Image Classification Using Machine Learning Techniques
Amith Khandakar,Muhammad E. H. Chowdhury,Mamun Bin Ibne Reaz,Sawal Hamid Md Ali,Tariq Abbas,Tanvir Alam,Mohamed Arselene Ayari,Zaid Bin Mahbub,Rumana Habib,Tawsifur Rahman,Anas Tahir,Ahmad Ashrif A Bakar,Rayaz A. Malik +12 more
TL;DR: The multilayer perceptron (MLP) classifier along with the features extracted from thermogram images showed an accuracy of 90.1% in multi-class classification, which outperformed the literature-reported performance metrics on this dataset.
Journal ArticleDOI
PCovNet: A presymptomatic COVID-19 detection framework using deep learning model using wearables data
Farhan Fuad Abir,Khalid Alyafei,Muhammad E. H. Chowdhury,Amith Khandakar,Rashid Ahmed,Muhammad Maqsud Hossain,Sakib Mahmud,Ashiqur Rahman,Tareq O. Abbas,Susu M. Zughaier,Khalid Kamal Naji +10 more
TL;DR: In this paper , a Long Short-term Memory Variational Autoencoder (LSTM-VAE)-based anomaly detection framework was proposed to detect COVID-19 infection in the presymptomatic stage from the Resting Heart Rate (RHR) derived from the wearable devices, i.e., smartwatch or fitness tracker.
Journal ArticleDOI
Design and Implementation of a Smart Insole System to Measure Plantar Pressure and Temperature
Amith Khandakar,Sakib Mahmud,Muhammad E. H. Chowdhury,Mamun Bin Ibne Reaz,Serkan Kiranyaz,Zaid Bin Mahbub,Sawal Hamid Md Ali,Ahmad Ashrif A Bakar,Mohamed Arselene Ayari,Mohammed I. Alhatou,Mohammed AbdulMoniem,Ahasan Atick Faisal +11 more
TL;DR: A full design for a wearable insole that can detect both plantar pressure and temperature using off-the-shelf sensors is proposed, which can be used for continuous, at-home monitoring of foot problems through pressure patterns and temperature differences between the two feet.
Journal ArticleDOI
COVID-19 Infection Segmentation and Severity Assessment Using a Self-Supervised Learning Approach
TL;DR: This work proposes a novel self-supervised deep learning method for automated segmentation of COVID-19 infection lesions and assessing the severity of infection, which can reduce the dependence on the annotation of the training samples.
References
More filters
Journal ArticleDOI
SMOTE: synthetic minority over-sampling technique
TL;DR: In this article, a method of over-sampling the minority class involves creating synthetic minority class examples, which is evaluated using the area under the Receiver Operating Characteristic curve (AUC) and the ROC convex hull strategy.
Journal ArticleDOI
SMOTE: Synthetic Minority Over-sampling Technique
TL;DR: In this article, a method of over-sampling the minority class involves creating synthetic minority class examples, which is evaluated using the area under the Receiver Operating Characteristic curve (AUC) and the ROC convex hull strategy.
Journal ArticleDOI
mice: Multivariate Imputation by Chained Equations in R
TL;DR: Mice adds new functionality for imputing multilevel data, automatic predictor selection, data handling, post-processing imputed values, specialized pooling routines, model selection tools, and diagnostic graphs.
Journal ArticleDOI
Random forest classifier for remote sensing classification
TL;DR: It is suggested that the random forest classifier performs equally well to SVMs in terms of classification accuracy and training time and the number of user‐defined parameters required byrandom forest classifiers is less than the number required for SVMs and easier to define.
Journal ArticleDOI
How To Build and Interpret a Nomogram for Cancer Prognosis
TL;DR: This guide provides a nonstatistical audience with a methodological approach for building, interpreting, and using nomograms to estimate cancer prognosis or other health outcomes.
Related Papers (5)
ABC2-SPH risk score for in-hospital mortality in COVID-19 patients: development, external validation and comparison with other available scores
Milena Soriano Marcolino,Milena Soriano Marcolino,Magda Carvalho Pires,Magda Carvalho Pires,L. E. F. Ramos,Rafael Guimarães Tavares da Silva,Luana Martins Oliveira,Luana Martins Oliveira,Rafael Lima Rodrigues de Carvalho,Rodolfo Lucas Silva Mourato,Adrián Sánchez-Montalvá,Berta Raventós,Fernando Anschau,José Miguel Chatkin,Matheus Carvalho Alves Nogueira,Milton Henriques Guimarães-Júnior,Giovanna Grunewald Vietta,Helena Duani,Daniela Ponce,Patricia Klarmann Ziegelmann,Patricia Klarmann Ziegelmann,Luís César de Castro,Karen Brasil Ruschel,Christiane Correa Rodrigues cimini,Saionara Cristina Francisco,Maiara Anschau Floriani,Guilherme Fagundes Nascimento,Barbara Lopes Farace,Luanna da Silva Monteiro,Maíra Viana Rego Souza-Silva,Thaís Lorenna Souza Sales,Karina Paula Medeiros Prado Martins,Karina Paula Medeiros Prado Martins,Israel Júnior Borges do Nascimento,Tatiani Oliveira Fereguetti,Daniel Taiar Marinho Oliveira Ferrara,Fernando Antônio Botoni,Ana Paula Beck da Silva Etges,Ana Paula Beck da Silva Etges,Ana Paula Beck da Silva Etges,Alexandre Vargas Schwarzbold,Amanda de Oliveira Maurilio,Ana Luiza Bahia Alves Scotton,Andre Pinheiro Weber,Andre Soares de Moura Costa,Andressa Barreto Glaeser,Angelica Aparecida Coelho Madureira,Angelinda Rezende Bhering,Bruno Mateus de Castro,Carla Thais Candida Alves da Silva,Carolina Marques Ramos,Caroline Danubia Gomes,Cintia Alcantara de Carvalho,Daniel Vitorio Silveira,Edilson Cezar,Elayne Crestani Pereira,Emanuele Marianne Souza Kroger,Felipe Barbosa Vallt,Fernanda Barbosa Lucas,Fernando Graca Aranha,Frederico Bartolazzi,Gabriela Petry Crestani,Gisele Alsina Nader Bastos,Glicia Cristina de Castro Madeira,Helena Carolina Noal,Heloisa Reniers Vianna,Henrique Cerqueira Guimaraes,Isabela Moraes Gomes,Israel Molina,Israel Molina,Joanna d'Arc L. Batista,Joanna d'Arc L. Batista,Joice Coutinho de Alvarenga,Julia Di Sabatino Santos Guimaraes,Julia Drumond Parreiras de Morais,Juliana Machado Rugolo,Karen Cristina Jung Rech Pontes,Kauane Aline Maciel dos Santos,Leonardo Seixas de Oliveira,Lilian Santos Pinheiro,Liliane Souto Pacheco,Lucas de Deus Sousa,Luciana Siuves Ferreira Couto,Luciane Kopittke,Luis Cesar Souto de Moura,Luisa Elem Almeida Santos,Máderson Alvares de Souza Cabral,Maira Dias Souza,Marcela Goncalves Trindade Tofani,Marcelo Carneiro,Maria Angelica Pires Ferreira,Maria Aparecida Camargos Bicalho,Maria Clara Pontello Barbosa Lima,Mariana Frizzo de Godoy,Marilia Mastrocolla de Almeida Cardoso,Meire Pereira de Figueiredo,Natalia da Cunha Severino Sampaio,Natalia Lima Rangel,Natalia Trifiletti Crespo,Neimy Ramos de Oliveira,Pedro Ledic Assaf,Petrônio José de Lima Martelli,Rafaela dos Santos Charao de Almeida,Raphael Castro Martins,Raquel Lutkmeier,Reginaldo Aparecido Valacio,Renan Goulart Finger,Ricardo Bertoglio Cardoso,Ricardo Bertoglio Cardoso,Roberta Pozza,Roberta Xavier Campos,Rochele Mosmann Menezes,Roger Mendes de Abreu,Rufino de Freitas Silva,Rufino de Freitas Silva,Silvana Mangeon Meirelles Guimarães,Silvia Ferreira Araujo,Susany Anastacia Pereira,Talita Fischer Oliveira,Tatiana Kurtz,Thainara Conceicao de Oliveira,Thaiza Simonia Marinho Albino de Araujo,Thulio Henrique Oliveira Diniz,Veridiana Baldon dos Santos Santos,Virginia Mara Reis Gomes,Vitor Augusto Lima do Vale,Yuri Carlotto Ramires,Eric Boersma,Carisi Anne Polanczyk,Carisi Anne Polanczyk +129 more
Early prediction of mortality risk among patients with severe COVID-19, using machine learning.
COVID-19 Mortality Risk Assessment: An International Multi-Center Study
Dimitris Bertsimas,Galit Lukin,Luca Mingardi,Omid Nohadani,Agni Orfanoudaki,Bartolomeo Stellato,Holly Wiberg,Sara González-García,Carlos Luis Parra-Calderón,Ken Robinson,Michelle Schneider,Barry Stein,Alberto Estirado,Lia a Beccara,Rosario Canino,Martina Dal Bello,Federica Pezzetti,Angelo Pan +17 more