Artificial intelligence computed tomography helps evaluate the severity of COVID-19 patients: A retrospective study

doi:10.5847/wjem.j.1920-8642.2022.026

Abstract

Abstract:

BACKGROUND: Computed tomography (CT) is a noninvasive imaging approach to assist the early diagnosis of pneumonia. However, coronavirus disease 2019 (COVID-19) shares similar imaging features with other types of pneumonia, which makes differential diagnosis problematic. Artificial intelligence (AI) has been proven successful in the medical imaging field, which has helped disease identification. However, whether AI can be used to identify the severity of COVID-19 is still underdetermined.
METHODS: Data were extracted from 140 patients with confirmed COVID-19. The severity of COVID-19 patients (severe vs. non-severe) was defined at admission, according to American Thoracic Society (ATS) guidelines for community-acquired pneumonia (CAP). The AI-CT rating system constructed by Hangzhou YITU Healthcare Technology Co., Ltd. was used as the analysis tool to analyze chest CT images.
RESULTS: A total of 117 diagnosed cases were enrolled, with 40 severe cases and 77 non-severe cases. Severe patients had more dyspnea symptoms on admission (12 vs. 3), higher acute physiology and chronic health evaluation (APACHE) II (9 vs. 4) and sequential organ failure assessment (SOFA) (3 vs. 1) scores, as well as higher CT semiquantitative rating scores (4 vs. 1) and AI-CT rating scores than non-severe patients (P<0.001). The AI-CT score was more predictive of the severity of COVID-19 (AUC=0.929), and ground-glass opacity (GGO) was more predictive of further intubation and mechanical ventilation (AUC=0.836). Furthermore, the CT semiquantitative score was linearly associated with the AI-CT rating system (Adj R²=75.5%, P<0.001).
CONCLUSIONS: AI technology could be used to evaluate disease severity in COVID-19 patients. Although it could not be considered an independent factor, there was no doubt that GGOs displayed more predictive value for further mechanical ventilation.

Key words: COVID-19, Artificial intelligence, Chest computed tomography

Yi Han, Su-cheng Mu, Hai-dong Zhang, Wei Wei, Xing-yue Wu, Chao-yuan Jin, Guo-rong Gu, Bao-jun Xie, Chao-yang Tong. Artificial intelligence computed tomography helps evaluate the severity of COVID-19 patients: A retrospective study[J]. World Journal of Emergency Medicine, 2022, 13(2): 91-97.

Figures/Tables 6

Table 1

Figure 1.

Table 2

Figure 2.

Figure 3.

Figure 4.

References 26

1	Guan WJ, Ni ZY, Hu Y, Liang WH, Ou CQ, He JX, et al. Clinical characteristics of coronavirus disease 2019 in China. N Engl J Med. 2020; 382(18):1708-20. doi: 10.1056/NEJMoa2002032
2	World Health Organization. Coronavirus disease (COVID-19) outbreak. Available at https://www.who.int/emergencies/diseases/novel-coronavirus-2019 .
3	Bernheim A, Mei XY, Huang MQ, Yang Y, Fayad ZA, Zhang N, et al. Chest CT findings in coronavirus disease-19 (COVID-19): relationship to duration of infection. Radiology. 2020; 295(3):200463. doi: 10.1148/radiol.2020200463 pmid: 32077789
4	Pan F, Ye TH, Sun P, Gui S, Liang B, Li LL, et al. Time course of lung changes at chest CT during recovery from coronavirus disease 2019 (COVID-19). Radiology. 2020; 295(3):715-21. doi: 10.1148/radiol.2020200370
5	Ye Z, Zhang Y, Wang Y, Huang ZX, Song B. Chest CT manifestations of new coronavirus disease 2019 (COVID-19): a pictorial review. Eur Radiol. 2020; 30(8):4381-9. doi: 10.1007/s00330-020-06801-0
6	Zhou SC, Wang YJ, Zhu TT, Xia LM. CT features of coronavirus disease 2019 (COVID-19) pneumonia in 62 patients in Wuhan, China. AJR Am J Roentgenol. 2020; 214(6):1287-94. doi: 10.2214/AJR.20.22975
7	Shi F, Wang J, Shi J, Wu Z, Wang Q, Tang Z, et al. Review of artificial intelligence techniques in imaging data acquisition, segmentation and diagnosis for COVID-19. IEEE Rev Biomed Eng. 2021; 14:4-15. doi: 10.1109/RBME.4664312
8	Li L, Qin LX, Xu ZG, Yin YB, Xia J. Artificial intelligence distinguishes COVID-19 from community acquired pneumonia on chest CT. Radiology. 2020; 296(2):200905.
9	Li L, Qin LX, Xu ZG, Yin YB, Wang X, Kong B, et al. Using artificial intelligence to detect COVID-19 and community-acquired pneumonia based on pulmonary CT: evaluation of the diagnostic accuracy. Radiology. 2020; 296(2):E65-71. doi: 10.1148/radiol.2020200905
10	Jacob J, Alexander D, Baillie JK, Berka R, Bertolli O, Blackwood J, et al. Using imaging to combat a pandemic: rationale for developing the UK National COVID-19 Chest Imaging Database. Eur Respir J. 2020; 56(2):2001809. doi: 10.1183/13993003.01809-2020
11	Bai HX, Wang R, Xiong Z, Hsieh B, Chang K, Halsey K, et al. Artificial intelligence augmentation of radiologist performance in distinguishing COVID-19 from pneumonia of other origin at chest CT. Radiology. 2021; 299(1):E225. doi: 10.1148/radiol.2021219004
12	Metlay JP, Waterer GW, Long AC, Anzueto A, Brozek J, Crothers K, et al. Diagnosis and Treatment of Adults with Community-acquired Pneumonia. An Official Clinical Practice Guideline of the American Thoracic Society and Infectious Diseases Society of America. Am J Respir Crit Care Med. 2019; 200(7):e45-7. doi: 10.1164/rccm.201908-1581ST
13	Ji M, Yuan L, Shen W, Lv J, Li Y, Chen J, et al. A predictive model for disease progression in non-severely ill patients with coronavirus disease 2019. Eur Respir J. 2020; 56(1):2001234. doi: 10.1183/13993003.01234-2020
14	Liang HY, Tsui BY, Ni H, Valentim CCS, Baxter SL, Liu GJ, et al. Evaluation and accurate diagnoses of pediatric diseases using artificial intelligence. Nat Med. 2019; 25(3):433-8. doi: 10.1038/s41591-018-0335-9
15	Luo X, Jiaerken Y, Shen Z, Wang Q, Liu B, Zhou H, et al. Obese COVID-19 patients show more severe pneumonia lesions on CT. Diabetes Obes Metab. 2021; 23(1):290-3. doi: 10.1111/dom.v23.1
16	Pan F, Li L, Liu B, Ye TH, Li LL, Liu DH, et al. A novel deep learning-based quantification of serial chest computed tomography in Coronavirus Disease 2019 (COVID-19). Sci Rep. 2021; 11(1):417. doi: 10.1038/s41598-020-80261-w
17	Huang PK, Liu TZ, Huang LS, Liu HL, Lei M, Xu WD, et al. Use of chest CT in combination with negative RT-PCR assay for the 2019 novel coronavirus but high clinical suspicion. Radiology. 2020; 295(1):22-3. doi: 10.1148/radiol.2020200330
18	Yang R, Li X, Liu H, Zhen YL, Zhang XX, Xiong QX, et al. Chest CT severity score: an imaging tool for assessing severe COVID-19. Radiol Cardiothorac Imaging. 2020; 2(2):e200047. doi: 10.1148/ryct.2020200047 pmid: 33778560
19	Jiang XG, Coffee M, Bari A, Wang JZ, Jiang XY, Huang JP, et al. Towards an artificial intelligence framework for data-driven prediction of coronavirus clinical severity. Comput Mater Continua. 2020; 62(3):537-51.
20	Shen C, Yu N, Cai S, Zhou J, Sheng J, Liu K, et al. Quantitative computed tomography analysis for stratifying the severity of Coronavirus Disease 2019. J Pharm Anal. 2020; 10(2):123-9. doi: 10.1016/j.jpha.2020.03.004
21	Tang ZY, Zhao W, Xie XZ, Zhong Z, Shi F, Liu J, et al. Severity assessment of Coronavirus Disease 2019(COVID-19) using quantitative features from chest CT images. arXiv:200311988 2020. Available at https://www.semanticscholar.org/paper/Severity-Assessment-of-Coronavirus-Disease-2019-CT-Tang-Zhao/a9ad10ebac0e5012f278c715ccbc9c87deebe0aa .
22	Aylett-Bullock J, Luccioni A, Pham KH, Lam CS, Luengo-Oroz MA. Mapping the landscape of artificial intelligence applications against COVID-19. J Artif Intell Res. 2020; 69:807-45. doi: 10.1613/jair.1.12162
23	McCall B. COVID-19 and artificial intelligence: protecting health-care workers and curbing the spread. Lancet Digit Health. 2020; 2(4):e166-7.
24	Bai HX, Hsieh B, Xiong Z, Halsey K, Choi JW, Tran TML, et al. Performance of radiologists in differentiating COVID-19 from non-COVID-19 viral pneumonia at chest CT. Radiology. 2020; 296(2):E46-54. doi: 10.1148/radiol.2020200823
25	Zhang K, Liu X, Shen J, Li Z, Sang Y, Wu X, et al. Clinically applicable AI system for accurate diagnosis, quantitative measurements, prognosis of COVID-19 pneumonia using computed tomography. Cell. 2020; 181(6):1423-3.e1411.
26	Naudé W. Artificial intelligence vs COVID-19: limitations, constraints and pitfalls. AI Soc. 2020;1-5.

Parameters	All patients (n=117)	Non-severe patients (n=77)	Severe patients (n=40)	P value
Age (years)	63.5 (48.8-70.2)	62.0 (44.0-69.0)	69.0 (57.5-75.0)	0.002
Gender	-	-	-	0.147
Male	67 (57.3)	40 (51.9)	27 (67.5)
Female	50 (42.7)	37 (48.1)	13 (32.5)
History
Hypertension	32 (27.3)	16 (20.8)	16 (40.0)	0.034
DM	20 (17.1)	14 (18.2)	6 (15.0)	0.625
CHD	6 (5.1)	4 (5.2)	2 (5.0)	0.941
Symptoms
Highest temperature (℃)	38.1 (37.7-38.7)	38.0 (37.2-38.6)	38.4 (38.0-38.9)	0.150
Cough	69 (59.0)	49 (63.6)	20 (50.0)	0.119
Dyspnea	25 (21.4)	13 (16.9)	12 (30.0)	0.117
Length of stay (d)	25.5 (12.75-37.00)	20.0 (10.0-28.0)	38.0 (31.5-43.5)	<0.001
APACHE II	6.0 (3.0-8.0)	4.0 (2.0-6.0)	9.0 (7.0-11.0)	<0.001
SOFA	1.0 (1.0-2.0)	1.0 (0.0-1.0)	3.0 (2.0-4.0)	<0.001
PSI	67.45±32.71	56.03±26.26	88.63±33.19	<0.001
CURB-65	1.0 (0.0-1.0)	0.0 (0.0-1.0)	1.0 (1.0-2.0)	<0.001
CT score	2.0 (1.0-4.0)	1.0 (1.0-3.0)	4.0 (3.0-5.0)	<0.001
AI-CT score	8.86 (2.32-36.61)	4.59 (1.04-10.97)	49.71 (27.87-60.25)	<0.001
Oxygenation
Nasal tube	88 (75.2)	48 (62.3)	40 (100.0)	<0.001
Facial mask	45 (38.5)	8 (10.4)	37 (92.5)	<0.001
HFNC	33 (28.2)	3 (3.9)	30 (75.0)	<0.001
NIV	15 (12.8)	0 (0.0)	15 (37.5)	<0.001
MV	11 (9.4)	0 (0.0)	11 (27.5)	<0.001
ECMO	1 (0.9)	0 (0.0)	1 (2.5)	0.319
Discharge	83 (70.9)	71 (92.2)	12 (30.0)	<0.001
Mortality	8 (6.8)	4 (5.2)	4 (10.0)	0.555

Parameters	All patients (n=117)	Non-severe patients (n=77)	Severe patients (n=40)	P value
White blood cell (×10⁹/L)	5.81 (4.23-8.02)	5.52 (4.22-7.38)	7.14 (4.40-10.70)	0.150
Neutrophil (×10⁹/L)	3.88 (2.69-6.34)	3.41 (2.27-4.85)	5.98 (3.63-9.63)	<0.001
Lymphocyte (×10⁹/L)	1.04 (0.68-1.50)	1.28 (0.93-1.69)	0.68 (0.52-0.92)	<0.001
Monocyte (×10⁹/L)	0.48±0.21	0.52±0.20	0.41±0.21	0.004
CD3⁺ (/μL)	565 (341-858)	769 (527-1065)	365 (304-540)	<0.001
CD4⁺ (/μL)	348 (228-544)	466 (314-649)	236 (170-314)	<0.001
CD8⁺ (/μL)	192 (118-318)	238 (170-367)	140 (74-186)	<0.001
CD19 (/μL)	128 (77-203)	163 (74-211)	111 (77-174)	0.223
CD16+56 (/μL)	112.5 (65.8-185.8)	130 (78-203)	100 (62-162)	0.085
CRP (mg/L)	27.8 (5.0-77.5)	8.1 (5.0-50.9)	103.8 (30.2-175.3)	<0.001
PaO₂/FiO₂ (mmHg)	240.39±147.17	330.69±162.12	215.68±143.27	0.016
IL-2 (pg/mL)	3.62 (3.17-4.08)	3.62 (3.17-4.12)	3.54 (3.13-4.06)	0.646
IL-4 (pg/mL)	3.21 (2.90-3.79)	3.21 (2.84-3.91)	3.22 (2.98-3.63)	0.895
IL-6 (pg/mL)	8.24 (5.59-22.79)	7.90 (4.57-10.92)	16.11 (7.59-102.31)	0.002
IL-10 (pg/mL)	5.91 (4.69-7.95)	5.34 (4.44-6.42)	7.86 (5.46-13.53)	0.005
TNF-α (pg/mL)	3.21 (2.68-5.01)	3.46 (2.66-5.08)	3.18 (2.71-4.01)	0.491
IFN-γ (pg/mL)	3.63 (2.80-5.40)	3.85 (2.71-6.02)	3.47 (2.96-4.33)	0.569
PCT (ng/mL)	0.10 (0.04-0.21)	0.04 (0.03-0.12)	0.19 (0.12-0.40)	<0.001

[1]	Rong Xiong, Jieping Zhou, Wenning Li, Jie Liu, Jing Lou, Sijia Tian, Huixin Lian, Shengmei Niu, Luxi Zhang, Wenhang Li, Jinjun Zhang. Effects of a closed-loop system against SARS-CoV-2 at the Beijing 2022 Olympic Winter Games: a descriptive and modeling study [J]. World Journal of Emergency Medicine, 2023, 14(6): 471-476.
[2]	Jiafa Lu, Xin Wang, Linghao Chen, Xuedong Sun, Rui Li, Wanjing Zhong, Yajing Fu, Le Yang, Weixiang Liu, Wei Han. Unmanned aerial vehicle based intelligent triage system in mass-casualty incidents using 5G and artificial intelligence [J]. World Journal of Emergency Medicine, 2023, 14(4): 273-279.
[3]	Wei-hua Li, Bin Dong, Han-song Wang, Jia-jun Yuan, Han Qian, Ling-ling Zheng, Xu-lin Lin, Zhao Wang, Shi-jian Liu, Bo-tao Ning, DanTian , Lie-bin Zhao. Artificial intelligence promotes shared decision-making through recommending tests to febrile pediatric outpatients [J]. World Journal of Emergency Medicine, 2023, 14(2): 106-111.
[4]	Gui-ying Dong, Fei-fei Jin, Qi Huang, Chun-bo Wu, Ji-hong Zhu, Tian-bing Wang. Exploratory COVID-19 death risk score based on basic laboratory tests and physiological clinical measurements [J]. World Journal of Emergency Medicine, 2022, 13(6): 453-458.