Machine Learning Models for Prognostic Assessment of Covid-19 Mortality Using Computed Tomography-Based Radiomics
,
Abstract
Introduction: This study examines the significance of developing a predictive approach for assessing the prognosis of individuals diagnosed with COVID-19. This method can help physicians make treatment decisions that decrease mortality and prevent unnecessary treatments. This study also emphasizes the significance of radiomics features. Therefore, our objective was to assess the predictive capabilities of Computed Tomography-based radiomics models using a dataset comprising 577 individuals diagnosed with COVID-19.
Methods: The U-net model was applied to automatically perform whole lung segmentations, extracting 107 texture, intensity, and morphological features. We utilized two feature selectors and three classifiers. We assessed the random forest, logistic regression, and support vector machines by implementing a five-fold cross-validation approach. The precision, sensitivity, specificity, accuracy, F1-score, and area under the receiver operating characteristic curve were reported.
Result: The random forest model achieved an area under the receiver operating characteristic curve, precision, sensitivity, specificity, accuracy, and F1-score in the range of 0.85 (CI95%: 0.76–0.91), 0.75, 0.82, 0.78, 0.68, and 0.71, respectively. Logistic regression attained an area under the receiver operating characteristic curve of 0.80 (CI95%: 0.72–0.88), corresponding to values of 0.88, 0.62, 0.74, 0.55, and 0.67, respectively. Support Vector Machines computes the above six metrics as an area under the receiver operating characteristic curve, sensitivity, specificity, accuracy, precision, and F1-score in the range of 0.69 (CI95%: 0.59–0.79), 0.68, 0.64, 0.66, 0.5, and 0.57, respectively.
Conclusion: We are developing a robust radiomics classifier that accurately predicts mortality in COVID-19 patients. Lung Computed Tomography radiomics features may aid in identifying high-risk individuals who need supplementary therapy and decrease the propagation of the virus.
2. Nemati M, Ansary J, Nemati N. Machine-Learning Approaches in COVID-19 Survival Analysis and Discharge-Time Likelihood Prediction Using Clinical Data. Patterns (N Y). 2020;1(5):100074.
3. Organization WH. COVID-19 Weekly Epidemiological Update 2023 [Available from: https://www.who.int/publications/m/item/weekly-epidemiological-update-on-covid-19---25-january-2023.
4. Baik SM, Hong KS, Park DJ. Deep learning approach for early prediction of COVID-19 mortality using chest X-ray and electronic health records. BMC Bioinformatics. 2023;24(1):190.
5. Wang XV, Pinter JS, Liu Z, Wang L. A machine learning-based image processing approach for robotic assembly system. Procedia CIRP. 2021;104:906-11.
6. Tchito Tchapga C, Mih TA, Tchagna Kouanou A, Fozin Fonzin T, Kuetche Fogang P, Mezatio BA, et al. Biomedical Image Classification in a Big Data Architecture Using Machine Learning Algorithms. J Healthc Eng. 2021;2021:9998819.
7. Ronneberger O, Fischer P, Brox T, editors. U-net: Convolutional networks for biomedical image segmentation. Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18; 2015: Springer.
8. Dice LR. Measures of the amount of ecologic association between species. Ecology. 1945;26(3):297-302.
9. Reinke A, Tizabi MD, Sudre C, Eisenmann M, Rädsch T, Baumgartner M, et al. Common Limitations of Image Processing Metrics: A Picture Story2022.
10. Hatt M, Vallieres M, Visvikis D, Zwanenburg A. IBSI: an international community radiomics standardization initiative. Journal of Nuclear Medicine. 2018;59(supplement 1):287-.
11. Zhang Y-P, Zhang X-Y, Cheng Y-T, Li B, Teng X-Z, Zhang J, et al. Artificial intelligence-driven radiomics study in cancer: the role of feature engineering and modeling. Military Medical Research. 2023;10(1):22.
12. van Griethuysen JJM, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, et al. Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Res. 2017;77(21):e104-e7.
13. Zwanenburg A, Vallières M, Abdalah MA, Aerts H, Andrearczyk V, Apte A, et al. The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping. Radiology. 2020;295(2):328-38.
14. Saleh N, Ertunc HM, Saleh R, Rassam M. A Simple Mask Detection Model Based On A Multi-Layer Perception Neural Network2021. 1-5 p.
15. Zhang W, Guo Y, Jin Q. Radiomics and Its Feature Selection: A Review. Symmetry. 2023;15(10):1834.
16. Kraiem MS, Sánchez-Hernández F, Moreno-García MN. Selecting the Suitable Resampling Strategy for Imbalanced Data Classification Regarding Dataset Properties. An Approach Based on Association Models. Applied Sciences. 2021;11(18):8546.
17. Rymarczyk T, Kozłowski E, Kłosowski G, Niderla K. Logistic Regression for Machine Learning in Process Tomography. Sensors. 2019;19(15):3400.
18. Kumar D, Verma C, Singh PK, Raboaca MS, Felseghi R-A, Ghafoor KZ. Computational Statistics and Machine Learning Techniques for Effective Decision Making on Student’s Employment for Real-Time. Mathematics. 2021;9(11):1166.
19. Janitza S, Hornung R. On the overestimation of random forest's out-of-bag error. PLoS One. 2018;13(8):e0201904.
20. Sansana J, Joswiak MN, Castillo I, Wang Z, Rendall R, Chiang LH, et al. Recent trends on hybrid modeling for Industry 4.0. Computers & Chemical Engineering. 2021;151:107365.
21. Thanh Noi P, Kappas M. Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery. Sensors (Basel). 2017;18(1).
22. Zhang K, Liu X, Shen J, Li Z, Sang Y, Wu X, et al. Clinically Applicable AI System for Accurate Diagnosis, Quantitative Measurements, and Prognosis of COVID-19 Pneumonia Using Computed Tomography. Cell. 2020;181(6):1423-33.e11.
23. Qiu J, Peng S, Yin J, Wang J, Jiang J, Li Z, et al. A Radiomics Signature to Quantitatively Analyze COVID-19-Infected Pulmonary Lesions. Interdiscip Sci. 2021;13(1):61-72.
24. Wang D, Huang C, Bao S, Fan T, Sun Z, Wang Y, et al. Study on the prognosis predictive model of COVID-19 patients based on CT radiomics. Sci Rep. 2021;11(1):11591.
25. Shiri I, Salimi Y, Pakbin M, Hajianfar G, Avval AH, Sanaat A, et al. COVID-19 prognostic modeling using CT radiomic features and machine learning algorithms: Analysis of a multi-institutional dataset of 14,339 patients. Comput Biol Med. 2022;145:105467.
26. Al-Areqi F, Konyar MZ. Effectiveness evaluation of different feature extraction methods for classification of covid-19 from computed tomography images: A high accuracy classification study. Biomedical Signal Processing and Control. 2022;76:103662.
27. Kim YJ. Machine Learning Model Based on Radiomic Features for Differentiation between COVID-19 and Pneumonia on Chest X-ray. Sensors (Basel). 2022;22(17).
28. Chao H, Fang X, Zhang J, Homayounieh F, Arru CD, Digumarthy SR, et al. Integrative analysis for COVID-19 patient outcome prediction. Med Image Anal. 2021;67:101844.
29. Tang Z, Zhao W, Xie X, Zhong Z, Shi F, Ma T, et al. Severity assessment of COVID-19 using CT image features and laboratory indices. Phys Med Biol. 2021;66(3):035015.
30. Xu Q, Zhan X, Zhou Z, Li Y, Xie P, Zhang S, et al. CT-based Rapid Triage of COVID-19 Patients: Risk Prediction and Progression Estimation of ICU Admission, Mechanical Ventilation, and Death of Hospitalized Patients. medRxiv. 2020.
| Files | ||
| Issue | Vol 10 No 4 (2024): . | |
| Section | Articles | |
| Keywords | ||
| Machine Learning; Radiomics Features; Computed Tomography Scan; Mortality; Covid-19 | ||
| Rights and permissions | |
|
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
