Literature DB >> 34354361

Early Prediction of COVID-19 Ventilation Requirement and Mortality from Routinely Collected Baseline Chest Radiographs, Laboratory, and Clinical Data with Machine Learning.

Abdulrhman Fahad Aljouie1,2, Ahmed Almazroa2,3, Yahya Bokhari1,2, Mohammed Alawad1,2, Ebrahim Mahmoud4, Eman Alawad4, Ali Alsehawi5, Mamoon Rashid1,2, Lamya Alomair1,2, Shahad Almozaai6, Bedoor Albesher6, Hassan Alomaish5, Rayyan Daghistani5, Naif Khalaf Alharbi2,7, Manal Alaamery2,8,9,10, Mohammad Bosaeed2,3,4, Hesham Alshaalan5.   

Abstract

BACKGROUND: Coronavirus disease 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), emerged in Wuhan, China, in late 2019 and created a global pandemic that overwhelmed healthcare systems. COVID-19, as of July 3, 2021, yielded 182 million confirmed cases and 3.9 million deaths globally according to the World Health Organization. Several patients who were initially diagnosed with mild or moderate COVID-19 later deteriorated and were reclassified to severe disease type.
OBJECTIVE: The aim is to create a predictive model for COVID-19 ventilatory support and mortality early on from baseline (at the time of diagnosis) and routinely collected data of each patient (CXR, CBC, demographics, and patient history).
METHODS: Four common machine learning algorithms, three data balancing techniques, and feature selection are used to build and validate predictive models for COVID-19 mechanical requirement and mortality. Baseline CXR, CBC, demographic, and clinical data were retrospectively collected from April 2, 2020, till June 18, 2020, for 5739 patients with confirmed PCR COVID-19 at King Abdulaziz Medical City in Riyadh. However, of those patients, only 1508 and 1513 have met the inclusion criteria for ventilatory support and mortalilty endpoints, respectively.
RESULTS: In an independent test set, ventilation requirement predictive model with top 20 features selected with reliefF algorithm from baseline radiological, laboratory, and clinical data using support vector machines and random undersampling technique attained an AUC of 0.87 and a balanced accuracy of 0.81. For mortality endpoint, the top model yielded an AUC of 0.83 and a balanced accuracy of 0.80 using all features with balanced random forest. This indicates that with only routinely collected data our models can predict the outcome with good performance. The predictive ability of combined data consistently outperformed each data set individually for intubation and mortality. For the ventilator support, chest X-ray severity annotations alone performed better than comorbidity, complete blood count, age, or gender with an AUC of 0.85 and balanced accuracy of 0.79. For mortality, comorbidity alone achieved an AUC of 0.80 and a balanced accuracy of 0.72, which is higher than models that use either chest radiograph, laboratory, or demographic features only.
CONCLUSION: The experimental results demonstrate the practicality of the proposed COVID-19 predictive tool for hospital resource planning and patients' prioritization in the current COVID-19 pandemic crisis.
© 2021 Aljouie et al.

Entities:  

Keywords:  CBC; COVID-19; NIV; SMOTE; machine learning; X-rays; mortality; random forest

Year:  2021        PMID: 34354361      PMCID: PMC8331117          DOI: 10.2147/JMDH.S322431

Source DB:  PubMed          Journal:  J Multidiscip Healthc        ISSN: 1178-2390


  46 in total

1.  Dysregulation of Immune Response in Patients With Coronavirus 2019 (COVID-19) in Wuhan, China.

Authors:  Chuan Qin; Luoqi Zhou; Ziwei Hu; Shuoqi Zhang; Sheng Yang; Yu Tao; Cuihong Xie; Ke Ma; Ke Shang; Wei Wang; Dai-Shi Tian
Journal:  Clin Infect Dis       Date:  2020-07-28       Impact factor: 9.079

2.  Clinical Characteristics of Coronavirus Disease 2019 in China.

Authors:  Wei-Jie Guan; Zheng-Yi Ni; Yu Hu; Wen-Hua Liang; Chun-Quan Ou; Jian-Xing He; Lei Liu; Hong Shan; Chun-Liang Lei; David S C Hui; Bin Du; Lan-Juan Li; Guang Zeng; Kwok-Yung Yuen; Ru-Chong Chen; Chun-Li Tang; Tao Wang; Ping-Yan Chen; Jie Xiang; Shi-Yue Li; Jin-Lin Wang; Zi-Jing Liang; Yi-Xiang Peng; Li Wei; Yong Liu; Ya-Hua Hu; Peng Peng; Jian-Ming Wang; Ji-Yang Liu; Zhong Chen; Gang Li; Zhi-Jian Zheng; Shao-Qin Qiu; Jie Luo; Chang-Jiang Ye; Shao-Yong Zhu; Nan-Shan Zhong
Journal:  N Engl J Med       Date:  2020-02-28       Impact factor: 91.245

Review 3.  Sex differences in severity and mortality from COVID-19: are males more vulnerable?

Authors:  Ajay Pradhan; Per-Erik Olsson
Journal:  Biol Sex Differ       Date:  2020-09-18       Impact factor: 5.027

4.  A Machine Learning Prediction Model of Respiratory Failure Within 48 Hours of Patient Admission for COVID-19: Model Development and Validation.

Authors:  Douglas Barnaby; Theodoros P Zanos; Siavash Bolourani; Max Brenner; Ping Wang; Thomas McGinn; Jamie S Hirsch
Journal:  J Med Internet Res       Date:  2021-02-10       Impact factor: 5.428

5.  Continuously available ratio of SpO2/FiO2 serves as a noninvasive prognostic marker for intensive care patients with COVID-19.

Authors:  Xiaofan Lu; Liyun Jiang; Taige Chen; Yang Wang; Bing Zhang; Yizhou Hong; Jun Wang; Fangrong Yan
Journal:  Respir Res       Date:  2020-07-22

6.  Frequency and Distribution of Chest Radiographic Findings in Patients Positive for COVID-19.

Authors:  Ho Yuen Frank Wong; Hiu Yin Sonia Lam; Ambrose Ho-Tung Fong; Siu Ting Leung; Thomas Wing-Yan Chin; Christine Shing Yen Lo; Macy Mei-Sze Lui; Jonan Chun Yin Lee; Keith Wan-Hang Chiu; Tom Wai-Hin Chung; Elaine Yuen Phin Lee; Eric Yuk Fai Wan; Ivan Fan Ngai Hung; Tina Poy Wing Lam; Michael D Kuo; Ming-Yen Ng
Journal:  Radiology       Date:  2020-03-27       Impact factor: 11.105

7.  Neutrophil extracellular traps and thrombosis in COVID-19.

Authors:  Yu Zuo; Melanie Zuo; Srilakshmi Yalavarthi; Kelsey Gockman; Jacqueline A Madison; Hui Shi; Wrenn Woodard; Sean P Lezak; Njira L Lugogo; Jason S Knight; Yogendra Kanthi
Journal:  J Thromb Thrombolysis       Date:  2020-11-05       Impact factor: 2.300

8.  Clinical characteristics of COVID-19 in Saudi Arabia: A national retrospective study.

Authors:  Yousef M Alsofayan; Saqer M Althunayyan; Anas A Khan; Ahmed M Hakawi; Abdullah M Assiri
Journal:  J Infect Public Health       Date:  2020-06-08       Impact factor: 3.718

9.  The Clinical and Chest CT Features Associated With Severe and Critical COVID-19 Pneumonia.

Authors:  Kunhua Li; Jiong Wu; Faqi Wu; Dajing Guo; Linli Chen; Zheng Fang; Chuanming Li
Journal:  Invest Radiol       Date:  2020-06       Impact factor: 10.065

View more
  6 in total

1.  Design of an artificial neural network to predict mortality among COVID-19 patients.

Authors:  Mostafa Shanbehzadeh; Raoof Nopour; Hadi Kazemi-Arpanahi
Journal:  Inform Med Unlocked       Date:  2022-05-29

2.  Predictive modeling for COVID-19 readmission risk using machine learning algorithms.

Authors:  Mostafa Shanbehzadeh; Azita Yazdani; Mohsen Shafiee; Hadi Kazemi-Arpanahi
Journal:  BMC Med Inform Decis Mak       Date:  2022-05-20       Impact factor: 3.298

3.  Threshold of increase in oxygen demand to predict mechanical ventilation use in novel coronavirus disease 2019: A retrospective cohort study incorporating restricted cubic spline regression.

Authors:  Ryo Yamamoto; Ryo Takemura; Asako Yamamoto; Kazuki Matsumura; Daiki Kaito; Koichiro Homma; Michihiko Wada; Junichi Sasaki
Journal:  PLoS One       Date:  2022-07-14       Impact factor: 3.752

4.  Management skin manifestation of multisystem inflammatory syndrome associated with SARS-CoV-2.

Authors:  Yeter Eylul Bayram; Dilek Yildiz-Sevgi; Ayse Yavuz; Merve Cancetin; Mehmet Yavuz Gurler
Journal:  Virol J       Date:  2022-01-06       Impact factor: 4.099

5.  Derivation and Validation of a Predictive Score for Respiratory Failure Worsening Leading to Secondary Intubation in COVID-19: The CERES Score.

Authors:  Alexandre Gaudet; Benoit Ghozlan; Annabelle Dupont; Erika Parmentier-Decrucq; Mickael Rosa; Emmanuelle Jeanpierre; Constance Bayon; Anne Tsicopoulos; Thibault Duburcq; Sophie Susen; Julien Poissy
Journal:  J Clin Med       Date:  2022-04-13       Impact factor: 4.964

6.  Predicting prognosis in COVID-19 patients using machine learning and readily available clinical data.

Authors:  Thomas W Campbell; Melissa P Wilson; Heinrich Roder; Samantha MaWhinney; Robert W Georgantas; Laura K Maguire; Joanna Roder; Kristine M Erlandson
Journal:  Int J Med Inform       Date:  2021-09-23       Impact factor: 4.046

  6 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.