Correlation of Lung Lesion Volume Measurement Using Artificial Intelligence and Prognosis of Patients with Severe Coronavirus Disease 2019 Infection
-
摘要: 目的：分析肺部病变体积及伴发基础疾病与重型新冠病毒感染（COVID-19）患者预后的相关性。方法：回顾2022年12月8日至2023年1月31日136例重型COVID-19患者，通过人工智能（AI）定量肺部病变体积、收集伴发基础疾病及实验室检查，分析其对重型COVID-19预后的影响。结果：重症COVID-19不同预后两组比较显示：年龄、低蛋白血症、脑卒中、乳酸脱氢酶、血尿素氮（BUN）、凝血酶原时间、白蛋白、白细胞、淋巴细胞比值、中性粒细胞比值、C反应蛋白、D-二聚体、全肺病灶体积（TLLV）和全肺病灶体积占比（PTLLV）两组之间差异有显著意义，年龄、PTLLV、TLLV、BUN、白细胞与预后不良呈正相关，白蛋白与预后不良呈负相关。结论：年龄越大、TLLV及PTLLV越大，重型COVID-19患者越容易出现预后不良，BUN、白细胞等指标增加以及白蛋白减少是重型COVID-19患者预后不良的危险因素。Abstract: Objective: To analyze the correlation between lung lesion volume and associated underlying diseases and prognosis of patients with severe coronavirus disease infection (COVID-19). Method: We reviewed 136 patients with severe COVID-19 in our hospital from December 8, 2022 to January 31, 2023. We measured the volume of lung lesions using artificial intelligence (AI), collected concomitant basic disease data and laboratory tests, and analyzed their impact on the prognosis of severe COVID-19. Results: The difference in the different prognoses of severe COVID-19, such as age, hypoproteinemia, stroke, lactate dehydrogenase, blood urea nitrogen (BUN), prothrombin time, albumin, leukocyte, lymphocyte ratio, neutrophil ratio, C-reactive protein, D-dimer, total lung lesion volume (TLLV), and percentage of total lung lesion volume (PTLLV), between the two groups was significant. Age, TLLV, PTLLV, BUN, and white blood cells were positively correlated with poor prognosis, while albumin was negatively correlated with poor prognosis. Conclusion: The older, the larger TLLV and PTLLV are, the more likely the patients with severe COVID-19 will have poor prognosis. The increase in indicators, such as BUN and white blood cells, and decrease in albumin are the risk factors for poor prognosis of the patients with severe COVID-19.
-
Keywords:
- artificial intelligence /
- COVID-19 /
- lung lesion volume
-
-
![]()
图 2 男，79岁，重型COVID-19，预后不良，TLLV 1139.86 cm3，PTLLV 46.60％
Figure 2. Male, 79 years old with severe COVID-19 and poor prognosis，TLLV 1139.86 cm3，PTLLV 46.60％
![]()
图 3 男68岁，重型COVID-19，预后好转，TLLV 517.38 cm3，PTLLV 12.96％
Figure 3. Male, 68 years old with severe COVID-19 and good prognosis, TLLV 517.38 cm3, PTLLV 12.96％
![]()
图 4 PTLLV、TLLV评估重型COVID-19患者预后的ROC曲线图
Figure 4. ROC curve for evaluating the prognosis of patients with severe COVID-19 using PTLLV and TLLV
表 1 重症COVID-19患者不同预后两组肺部病灶AI测量指标的比较（
$\bar{x}\pm s$ ）Table 1 Comparison of various indicators of lung lesions between two groups with patients with severe COVID-19 and different prognoses measured using AI
AI测量指标 所有纳入人群（n=136） 预后好转（n=94） 预后不良（n=42） t P 右肺上叶LV/cm3 99.26±115.784 82.30±102.082 137.21±135.534 2.345 0.022* 右肺上叶PLV/％ 14.22±17.011 11.79±15.551 19.65±18.989 2.351 0.022* 右肺中叶LV/cm3 48.44±60.167 38.57±70.516 70.52±72.137 2.591 0.012* 右肺中叶PLV/％ 16.22±18.504 13.65±17.238 21.97±20.109 2.468 0.015* 右肺下叶LV/cm3 187.30±139.077 172.75±133.610 219.87±147.050 -0.338 0.736 右肺下叶PLV/％ 42.76±163.245 45.93±195.969 35.66±23.665 1.842 0.068 左肺上叶LV/cm3 84.79±99.048 76.72±96.225 102.84±104.005 1.427 0.156 左肺上叶PLV/％ 11.86±15.076 10.45±14.354 15.02±16.315 1.645 0.102 左肺下叶LV/cm3 139.30±112.473 123.59±104.904 174.48±121.889 2.485 0.014* 左肺下叶PTLV/％ 24.26±20.080 21.36±19.277 30.75±20.552 2.571 0.011* TLLV/cm3 554.24±393.127 486.90±359.175 704.94±427.312 3.081 0.003* PTLLV/％ 18.11±14.442 15.90±13.844 23.04±14.700 2.724 0.007* 注：*-P<0.05，统计学有显著性差异；LV为病灶体积，PLV为病灶体积占比。 
下载: 导出CSV
表 2 重症COVID-19患者不同预后两组基础疾病及实验室检查的比较（
$\bar{x}\pm s$ ）Table 2 Comparison of observation indicators between two groups with patients with severe COVID-19 and different prognoses
临床及实验室资料 所有纳入人群（n=136） 预后好转（n=94） 预后不良（n=42） $t/\chi^{2}$ P 年龄/岁 74.91±12.006 73.66±11.441 78.07±12.915 1.996 0.039* 男性/例（％） 88（64.71） 60（63.83） 28（66.67） 0.102 0.749 吸烟/例（％） 27（19.85） 20（21.28） 7（16.67） 0.388 0.534 心血管疾病/例（％） 98（72.06） 66（70.21） 32（76.19） 0.515 0.473 低蛋白血症/例（％） 78（57.35） 48（51.06） 30（71.43） 4.922 0.027* 2型糖尿病/例（％） 43（31.62） 34（36.17） 9（21.43） 2.918 0.088 脑卒中/例（％） 6（4.41） 1（1.06） 5（11.90） 8.090 0.004* 恶性肿瘤/例（％） 11（8.09） 8（8.51） 3（7.14） 0.073 0.787 慢性肺部疾病/例（％） 36（26.47） 23（24.47） 13（30.95） 0.672 0.428 慢性肾脏疾病/例（％） 22（16.18） 12（12.77） 10（23.81） 2.611 0.106 慢性肝脏疾病/例（％） 15（11.03） 9（9.57） 6（14.29） 0.657 0.418 总胆红素/（µmol/L） 11.87±9.40 11.79±10.579 12.03±6.076 0.137 0.891 丙氨酸转移酶/（U/L） 36.24±47.173 34.36±43.254 40.45±55.290 0.695 0.488 天门冬氨酸转移酶/（U/L） 40.18±42.563 38.55±48.102 43.84±26.402 0.823 0.412 乳酸脱氢酶/（U/L） 323.54±159.911 305.05±149.402 364.92±176.154 2.041 0.043* BUN/（mmol/L） 8.47±6.653 7.67±6.487 10.25±6.750 2.117 0.036* 肌酐/（µmol/L） 99.10±136.866 103.81±160.405 88.57±56.150 -0.599 0.550 凝血酶原时间/s 13.23±2.601 12.84±2.088 14.09±3.358 2.640 0.009* 白蛋白/（g/L） 34.27±5.787 35.32±5.464 31.93±5.866 -3.269 0.001* 降钙素原/（ng/mL） 2.07±12.058 1.65±10.312 3.00±15.370 0.600 0.549 血红蛋白/（mmol/L） 131.99±23.442 132.16±22.76 131.62±25.193 -0.119 0.906 白细胞/（109/L） 7.40±4.336 6.88±3.839 8.58±5.140 2.149 0.033* 淋巴细胞比值％ 15.33±9.413 16.41±9.331 12.90±9.249 -2.031 0.044* 中性粒细胞比值％ 77.28±12.397 75.55±11.688 81.14±13.192 2.476 0.015* C反应蛋白/（mg/L） 79.07±64.282 71.59±64.539 95.81±61.173 2.098 0.039* D-二聚体/（µg/mL） 1.32±3.062 0.96±1.974 2.13±4.590 2.083 0.039* N-端脑钠肽前体/（pg/mL） 3239.55±7118.443 2797.38±7253.059 4229.14±6787.372 1.112 0.269 注：*-P<0.05，统计学有显著性差异。
下载: 导出CSV
表 3 Logistic回归分析重型COVID-19患者预后与进入方程中的自变量及其参数的估计值
Table 3 Logistic regression analysis of prognosis and estimated values of independent variables and parameters in the entry equation for patients with severe COVID-19
选入变量 B S.E. Wald P 0R 年龄/岁 0.052 0.020 6.739 0.009* 1.053** PTLLV/％ 0.034 0.015 5.081 0.024* 1.034** TLLV/cm3 0.001 0.001 6.431 0.011* 1.001** BUN/（mmol/L） 0.069 0.031 4.902 0.027* 1.072** 白蛋白/（g/L） -0.082 0.039 4.475 0.034* 0.922# 白细胞/（109/L） 0.116 0.048 5.713 0.017* 1.123** 注：*-P<0.05，统计学有显著性差异。**-OR＞1，呈正相关；# -OR＜1，呈负相关。
下载: 导出CSV
表 4 PTLLV和TLLV评估重型COVID-19患者预后的ROC分析结果
Table 4 ROC analysis results of PTLLV and TLLV in the prognosis of patients with severe COVID-19
预测值 AUC 最佳截止点 敏感性/％ 特异性/％ p PTLLV/％ 0.651 19.38 59.50 76.60 0.005 TLLV/cm3 0.650 647.93 54.80 76.60 0.005
下载: 导出CSV
表 5 重型COVID-19患者预后在不同年龄段中的卡方检验
Table 5 Chi-square test for the prognosis of patients with severe COVID-19 in different age groups
年龄 所有纳入人群（n=136） 合计 预后好转/例 预后不良/例 ＜60岁 10 4 14 ≥60且＜70岁 20 2 22 ≥70岁且＜80岁 32 11 43 ≥80岁 32 25 57 合计 94 42 136
下载: 导出CSV
-
[1] 中华人民共和国国家卫生健康委员会. 新型冠状病毒感染诊疗方案(试行第十版)[J]. 中国合理用药探索, 2023,20(1): 1−11. doi: 10.3969/j.issn.2096-3327.2023.01.001 National Health Commission of the People's Republic of China. Diagnosis and treatment of COVID-19 (Trial Version 10)[J]. Chinese Journal of Rational Drug Use, 2023, 20(1): 1−11. (in Chinese). doi: 10.3969/j.issn.2096-3327.2023.01.001
[2] 彭丁, 杨爽, 李邦一, 等. 老年重症及危重症新型冠状病毒感染患者预后的危险因素分析[J]. 中华老年多器官疾病杂志, 2021,20(8): 600−603. doi: 10.11915/j.issn.1671-5403.2021.08.125 PENG D, YANG S, LI B Y, et al. Risk factors of prognosis in severe or critically ill elderly patients infected with 2019 novel coronavirus[J]. Chinese Journal of Multiple Organ Diseases in the Elderly, 2021, 20(8): 600−603. (in Chinese). doi: 10.11915/j.issn.1671-5403.2021.08.125
[3] LIU Y J, LU P, PENG L, et al. High-sensitivity troponin I is an indicator of poor prognosis in patients with severe COVID-19 related pneumonia[J]. International Journal of General Medicine, 2022, 15: 7113−7121. doi: 10.2147/IJGM.S368019
[4] 张炜宗, 袁红, 孙金栋, 等. 新型冠状病毒感染患者院内死亡危险因素的Meta分析[J]. 中国全科医学, 2023,26(5): 607−620. ZHANG W W, YUAN H, SUN J D, et al. Risk factors of in-hospital death in COVID-19 patients: A Meta-analysis[J]. Chinese General Practice, 2023, 26(5): 607−620. (in Chinese).
[5] TORRES-RAMIREZ C A, TIMARAN-MONTENEGRO D, MATEO-CAMACHO Y S, at al. CT-based pathological lung opacities volume as a predictor of critical illness and inflammatory response severity in patients with COVID-19[J]. Heliyon, 2022, 8(12): e11908. doi: 10.1016/j.heliyon.2022.e11908
[6] YANG Y H, LURE F Y M, MIAO H Y, et al. Using artificial intelligence to assist radiologists in distinguishing COVID-19 from other pulmonary infections[J]. Journal of X-ray Science and Technology, 2021, 29(1): 1−17. doi: 10.3233/XST-200735
[7] KUMAR H, FERNANDEZ C J, KOLPATTIL S, et al. Discrepancies in the clinical and radiological profiles of COVID-19: A case-based discussion and review of literature[J]. World Journal of Radiology, 2021, 13(4): 75−93. doi: 10.4329/wjr.v13.i4.75
[8] 孙怡瑶, 李杰, 白茜茜. 基于人工智能技术的新冠肺炎辅助诊断研究[J]. 生物医学工程学进展, 2022,43(1): 21−23. doi: 10.3969/j.issn.1674-1242.2022.01.005 SUN Y Y, LI J, BAI X X. Research progress of auxiliary diagnosis of new coronavirus pneumonia based on artificial intelligence technology[J]. Progress in Biomedical Engineering, 2022, 43(1): 21−23. (in Chinese). doi: 10.3969/j.issn.1674-1242.2022.01.005
[9] 尚红, 王毓三, 申子瑜. 全国临床检验操作规程(第4版)[M]. 北京: 人民卫生出版社, 2015: 200-280. [10] AKITOSHI I, TAKAHASHI H, IBE T, et al. Comparison of semiquantitative chest CT scoring systems to estimate severity in coronavirus disease 2019 (COVID-19) pneumonia[J]. European Radiology, 2022, 32(5): 3513−3524. doi: 10.1007/s00330-021-08435-2
[11] RUBIN G D, RYERSON C J, HARAMATI L B, et al. The role of chest imaging in patient management during the COVID-19 pandemic: A multinational consensus statement from the Fleischner Society[J]. Radiology, 2020, 296(1): 172−180. doi: 10.1148/radiol.2020201365
[12] LI K, FANG Y, LI W, et al. CT image visual quantitative evaluation and clinical classification of coronavirus disease (COVID-19)[J]. European Radiology, 2020, 30(8): 4407−4416. doi: 10.1007/s00330-020-06817-6
[13] LI K, WU J, WU F, et al. The clinical and chest CT features associated with severe and critical COVID-19 pneumonia[J]. Investigative Radiology, 2020, 55(6): 327−331. doi: 10.1097/RLI.0000000000000672
[14] 倪晨峰, 周妙平, 裴磊, 等. CT肺内病灶定量检测技术在新型冠状病毒肺炎诊疗中的应用[J]. 中华医院感染学杂志, 2020,30(21): 3210−3213. NI C F, ZHOU M P, PEI L, et al. Application of CT quantitative detection of pulmonary lesions in diagnosis and treatment of COVID-19[J]. Chinese Journal of Nosocomiology, 2020, 30(21): 3210−3213. (in Chinese).
[15] 中国医师协会神经内科医师分会. 新型冠状病毒感染所致神经系统疾病临床救治专家推荐意见[J]. 解放军医学杂志, 2023,48(2): 123−131. doi: 10.11855/j.issn.0577-7402.2023.02.0123 Neurology Branch of Chinese Medical Doctor Association. Expert recommendations for clinical diagnosis and treatment of coronavirus disease 2019 induced neurological diseases[J]. Medical Journal of Chinese People's Liberation, 2023, 48(2): 123−131. (in Chinese). doi: 10.11855/j.issn.0577-7402.2023.02.0123
[16] 柳舟, 张亮, 詹丽英, 等. 重型/危重型新型冠状病毒肺炎患者临床特征及死亡危险因素分析[J]. 微循环学杂志, 2021,31(2): 46−51,56. doi: 10.3969/j.issn.1005-1740.2021.02.010 LIU Z, ZHANG L, ZHAN L Y, et al. Clinical characteristics and predictors risk factors in hospitalized severe/critical COVID-19 patients[J]. Chinese Journal of Microcirculation, 2021, 31(2): 46−51,56. (in Chinese). doi: 10.3969/j.issn.1005-1740.2021.02.010
[17] HEMRAJ S K, JACOB M J, KOTIAN V, et al. Chest CT findings and their temporal evolution in COVID-19 pneumonia[J]. Cureus, 2022, 14(6): e26021.
[18] MARGINEAN C M, POPESCU M, VASILE C M, et al. Challenges in the differential diagnosis of COVID-19 pneumonia: A pictorial review[J]. Diagnostics (Basel), 2022, 12(11): 2823. doi: 10.3390/diagnostics12112823
[19] MUSSINI C, COZZI-LEPRI A, MENOZZI M, et al. Better prognosis in females with severe COVID-19 pneumonia: Possible role of inflammation as potential mediator[J]. Clinical Microbiology and Infection, 2021, 27(8): 1137−1144. doi: 10.1016/j.cmi.2020.12.010
[20] VIGNERA L S, CANNARELLA R, CONDORELLI R A, et al. Sexspecific SARS-CoV-2 mortality: Among hormone-modulated ACE2 expression, risk of venous thromboembolism and hypovitaminosis D[J]. International Journal of Molecular Sciences, 2020, 21(8): 2948. doi: 10.3390/ijms21082948
[21] KLEIN S L, FLANAGAN K L. Sex differences in immune responses[J]. Nature Reviews Immunology, 2016, 16(10): 626−638. doi: 10.1038/nri.2016.90
计量
- 文章访问数: 166
- HTML全文浏览量: 68
- PDF下载量: 17
