Tehran University of Medical Sciences

Science Communicator Platform

Stay connected! Follow us on X network (Twitter):
Share this content! On (X network) By
Covid-19 Prognostic Modeling Using Ct Radiomic Features and Machine Learning Algorithms: Analysis of a Multi-Institutional Dataset of 14,339 Patients: Covid-19 Prognostic Modeling Using Ct Radiomics and Machine Learning Publisher Pubmed



Shiri I1 ; Salimi Y1 ; Pakbin M2 ; Hajianfar G3 ; Avval AH4 ; Sanaat A1 ; Mostafaei S5 ; Akhavanallaf A1 ; Saberi A1 ; Mansouri Z1 ; Askari D6 ; Ghasemian M7 ; Sharifipour E8 ; Sandoughdaran S9 Show All Authors
Authors
  1. Shiri I1
  2. Salimi Y1
  3. Pakbin M2
  4. Hajianfar G3
  5. Avval AH4
  6. Sanaat A1
  7. Mostafaei S5
  8. Akhavanallaf A1
  9. Saberi A1
  10. Mansouri Z1
  11. Askari D6
  12. Ghasemian M7
  13. Sharifipour E8
  14. Sandoughdaran S9
  15. Sohrabi A10
  16. Sadati E11
  17. Livani S12
  18. Iranpour P13
  19. Kolahi S14
  20. Khateri M15
  21. Bijari S11
  22. Atashzar MR16
  23. Shayesteh SP17
  24. Khosravi B18
  25. Babaei MR19
  26. Jenabi E20
  27. Hasanian M21
  28. Shahhamzeh A22
  29. Foroghi Ghomi SY23
  30. Mozafari A24
  31. Teimouri A13
  32. Movaseghi F24
  33. Ahmari A25
  34. Goharpey N26
  35. Bozorgmehr R27
  36. Shirzadaski H28
  37. Mortazavi R29
  38. Karimi J30
  39. Mortazavi N31
  40. Besharat S32
  41. Afsharpad M10
  42. Abdollahi H33
  43. Geramifar P20
  44. Radmard AR18
  45. Arabi H1
  46. Rezaeikalantari K3
  47. Oveisi M34
  48. Rahmim A35, 36
  49. Zaidi H1, 37, 38, 39
Show Affiliations
Authors Affiliations
  1. 1. Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, 1211, Switzerland
  2. 2. Imaging Department, Qom University of Medical Sciences, Qum, Iran
  3. 3. Rajaie Cardiovascular, Medical & Research Center, Iran University of Medical Science, Tehran, Iran
  4. 4. School of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran
  5. 5. Division of Clinical Geriatrics, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, Sweden
  6. 6. Department of Radiology Technology, Shahid Beheshti University of Medical Sciences, Tehran, Iran
  7. 7. Department of Radiology, Shahid Beheshti Hospital, Qom University of Medical Sciences, Qum, Iran
  8. 8. Neuroscience Research Center, Qom University of Medical Sciences, Qum, Iran
  9. 9. Men's Health and Reproductive Health Research Center, Shahid Beheshti University of Medical Sciences, Tehran, Iran
  10. 10. Cancer Control Research Center, Cancer Control Foundation, Iran University of Medical Sciences, Tehran, Iran
  11. 11. Department of Medical Physics, Faculty of Medical Sciences, Tarbiat Modares University, Tehran, Iran
  12. 12. Clinical Research Development Unit (CRDU), Sayad Shirazi Hospital, Golestan University of Medical Sciences, Gorgan, Iran
  13. 13. Medical Imaging Research Center, Department of Radiology, Shiraz University of Medical Sciences, Shiraz, Iran
  14. 14. Department of Radiology, School of Medicine, Advanced Diagnostic and Interventional Radiology Research Center (ADIR), Imam Khomeini Hospital, Tehran University of Medical Sciences, Tehran, Iran
  15. 15. Department of Medical Radiation Engineering, Science and Research Branch, Islamic Azad University, Tehran, Tehran, Iran
  16. 16. Department of Immunology, School of Medicine, Fasa University of Medical Sciences, Fasa, Iran
  17. 17. Department of Physiology, Pharmacology and Medical Physics, Alborz University of Medical Sciences, Karaj, Iran
  18. 18. Department of Radiology, Shariati Hospital, Tehran University of Medical Sciences, Tehran, Iran
  19. 19. Department of Interventional Radiology, Firouzgar Hospital, Iran University of Medical Sciences, Tehran, Iran
  20. 20. Research Centre for Nuclear Medicine, Shariati Hospital, Tehran University of Medical Sciences, Tehran, Iran
  21. 21. Department of Radiology, Arak University of Medical Sciences, Arak, Iran
  22. 22. Clinical Research Development Center, Qom University of Medical Sciences, Qum, Iran
  23. 23. Clinical Research Development Center, Shahid Beheshti Hospital, Qom University Of Medical Sciences, Qom, Iran
  24. 24. Department of Medical Sciences, Qom Branch, Islamic Azad University, Qum, Iran
  25. 25. Ayatolah Khansary Hospital, Arak University of Medical Sciences, Arak, Iran
  26. 26. Department of Radiation Oncology, Shohadaye Tajrish Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran
  27. 27. Clinical Research Development Unit, Shohadaye Tajrish Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran
  28. 28. Infectious Diseases Research Center, Golestan University of Medical Sciences, Gorgan, Iran
  29. 29. Department of Internal Medicine, Shiraz University of Medical Sciences, Shiraz, Iran
  30. 30. Department of Infectious Disease, School of Medicine, Fasa University of Medical Sciences, Fasa, Iran
  31. 31. Dental Research Center, Golestan University of Medical Sciences, Gorgan, Iran
  32. 32. Golestan Research Center of Gastroenterology and Hepatology, Golestan University of Medical Sciences, Gorgan, Iran
  33. 33. Department of Radiologic Technology, Faculty of Allied Medical Sciences, Kerman University of Medical Sciences, Kerman, Iran
  34. 34. Comprehensive Cancer Centre, School of Cancer & Pharmaceutical Sciences, Faculty of Life Sciences & Medicine, King's College London, London, United Kingdom
  35. 35. Departments of Radiology and Physics, University of British Columbia, Vancouver, BC, Canada
  36. 36. Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, BC, Canada
  37. 37. Geneva University Neurocenter, Geneva University, Geneva, Switzerland
  38. 38. Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen, Groningen, Netherlands
  39. 39. Department of Nuclear Medicine, University of Southern Denmark, Odense, Denmark

Source: Computers in Biology and Medicine Published:2022


Abstract

Background: We aimed to analyze the prognostic power of CT-based radiomics models using data of 14,339 COVID-19 patients. Methods: Whole lung segmentations were performed automatically using a deep learning-based model to extract 107 intensity and texture radiomics features. We used four feature selection algorithms and seven classifiers. We evaluated the models using ten different splitting and cross-validation strategies, including non-harmonized and ComBat-harmonized datasets. The sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were reported. Results: In the test dataset (4,301) consisting of CT and/or RT-PCR positive cases, AUC, sensitivity, and specificity of 0.83 ± 0.01 (CI95%: 0.81–0.85), 0.81, and 0.72, respectively, were obtained by ANOVA feature selector + Random Forest (RF) classifier. Similar results were achieved in RT-PCR-only positive test sets (3,644). In ComBat harmonized dataset, Relief feature selector + RF classifier resulted in the highest performance of AUC, reaching 0.83 ± 0.01 (CI95%: 0.81–0.85), with a sensitivity and specificity of 0.77 and 0.74, respectively. ComBat harmonization did not depict statistically significant improvement compared to a non-harmonized dataset. In leave-one-center-out, the combination of ANOVA feature selector and RF classifier resulted in the highest performance. Conclusion: Lung CT radiomics features can be used for robust prognostic modeling of COVID-19. The predictive power of the proposed CT radiomics model is more reliable when using a large multicentric heterogeneous dataset, and may be used prospectively in clinical setting to manage COVID-19 patients. © 2022 The Authors
3. Combat Harmonization of Image Reconstruction Parameters to Improve the Repeatability of Radiomics Features, 2021 IEEE Nuclear Science Symposium and Medical Imaging Conference Record# NSS/MIC 2021 and 28th International Symposium on Room-Temperature Semiconductor Detectors# RTSD 2022 (2021)
4. Pet Image Radiomics Feature Variability in Lung Cancer: Impact of Image Segmentation, 2021 IEEE Nuclear Science Symposium and Medical Imaging Conference Record# NSS/MIC 2021 and 28th International Symposium on Room-Temperature Semiconductor Detectors# RTSD 2022 (2021)
6. Cardiac Pattern Recognition From Spect Images Using Machine Learning Algorithms, 2021 IEEE Nuclear Science Symposium and Medical Imaging Conference Record# NSS/MIC 2021 and 28th International Symposium on Room-Temperature Semiconductor Detectors# RTSD 2022 (2021)
7. Lung Cancer Recurrence Prediction Using Radiomics Features of Pet Tumor Sub-Volumes and Multi-Machine Learning Algorithms, 2021 IEEE Nuclear Science Symposium and Medical Imaging Conference Record# NSS/MIC 2021 and 28th International Symposium on Room-Temperature Semiconductor Detectors# RTSD 2022 (2021)
8. Lymphovascular Invasion Prediction in Lung Cancer Using Multi-Segmentation Pet Radiomics and Multi-Machine Learning Algorithms, 2021 IEEE Nuclear Science Symposium and Medical Imaging Conference Record# NSS/MIC 2021 and 28th International Symposium on Room-Temperature Semiconductor Detectors# RTSD 2022 (2021)
Experts (# of related papers)
Other Related Docs
9. Robust Versus Non-Robust Radiomic Features: Machine Learning Based Models for Nsclc Lymphovascular Invasion, 2022 IEEE NSS/MIC RTSD - IEEE Nuclear Science Symposium# Medical Imaging Conference and Room Temperature Semiconductor Detector Conference (2022)
10. Machine Learning-Based Overall Survival Prediction in Gbm Patients Using Mri Radiomics, 2022 IEEE NSS/MIC RTSD - IEEE Nuclear Science Symposium# Medical Imaging Conference and Room Temperature Semiconductor Detector Conference (2022)
16. Mri Radiomic Features Harmonization: A Multi-Center Phantom Study, 2022 IEEE NSS/MIC RTSD - IEEE Nuclear Science Symposium# Medical Imaging Conference and Room Temperature Semiconductor Detector Conference (2022)
20. Covid-19: Features, Clinical Course and Concerns, Journal of Cellular and Molecular Anesthesia (2020)