tetano
Editor, Senior Moderator
J Intensive Med
. 2024 Dec 16;5(3):252-261.
doi: 10.1016/j.jointm.2024.11.001. eCollection 2025 Jul. Deep learning integration of chest computed tomography and plasma proteomics to identify novel aspects of severe COVID-19 pneumonia
Yucai Hong[SUP] 1 [/SUP], Lin Chen[SUP] 2 3 [/SUP], Yang Yu[SUP] 2 [/SUP], Ziyue Zhao[SUP] 4 [/SUP], Ronghua Wu[SUP] 5 [/SUP], Rui Gong[SUP] 6 [/SUP], Yandong Cheng[SUP] 7 [/SUP], Lingmin Yuan[SUP] 7 [/SUP], Shaojun Zheng[SUP] 8 [/SUP], Cheng Zheng[SUP] 9 [/SUP], Ronghai Lin[SUP] 9 [/SUP], Jianping Chen[SUP] 10 [/SUP], Kangwei Sun[SUP] 10 [/SUP], Ping Xu[SUP] 11 [/SUP], Li Ye[SUP] 12 [/SUP], Chaoting Han[SUP] 11 [/SUP], Xihao Zhou[SUP] 13 [/SUP], Yaqing Liu[SUP] 14 [/SUP], Jianhua Yu[SUP] 14 [/SUP], Yaqin Zheng[SUP] 15 [/SUP], Jie Yang[SUP] 1 [/SUP], Jiajie Huang[SUP] 1 [/SUP], Juan Chen[SUP] 16 [/SUP], Junjie Fang[SUP] 16 [/SUP], Chensong Chen[SUP] 16 [/SUP], Bo Fan[SUP] 17 [/SUP], Honglong Fang[SUP] 18 [/SUP], Baning Ye[SUP] 19 [/SUP], Xiyun Chen[SUP] 20 [/SUP], Xiaoli Qian[SUP] 21 [/SUP], Junxiang Chen[SUP] 22 [/SUP], Haitao Yu[SUP] 23 [/SUP], Jun Zhang[SUP] 23 [/SUP], Xi-Ming Pan[SUP] 24 [/SUP], Yi-Xing Zhan[SUP] 24 [/SUP], You-Hai Zheng[SUP] 24 [/SUP], Zhang-Hong Huang[SUP] 25 [/SUP], Chao Zhong[SUP] 26 [/SUP], Ning Liu[SUP] 1 [/SUP], Hongying Ni[SUP] 27 [/SUP], Gengsheng Zhang[SUP] 28 [/SUP], Zhongheng Zhang[SUP] 1 29 30 [/SUP]; Chinese Multi-omics Advances In Sepsis (CMAISE) Consortium
Affiliations
Background: Heterogeneity is a critical characteristic of severe coronavirus disease 2019 (COVID-19) pneumonia. Integrating chest computed tomography (CT) imaging and plasma proteomics holds the potential to elucidate Image-Expression Axes (IEAs) that can effectively address this disease heterogeneity.
Methods: A cohort of subjects diagnosed with severe COVID-19 pneumonia at 12 participating hospitals between December 2022 and March 2023 was prospectively screened for eligibility. Context-aware self-supervised representation learning (CSRL) was employed to extract intricate features from CT images. Quantification of plasma proteins was achieved using the Olink® inflammation panel. A deep learning model was meticulously trained, with CSRL features serving as input and the proteomic data as the target. This trained model facilitated the construction of IEAs, offering a representation of the underlying disease heterogeneity. The potential of these IEAs for prognostic and predictive enrichment was subsequently explored via conventional regression models.
Results: The study cohort comprised 1979 eligible patients, who were stratified into a training set of 630 individuals and a testing set of 1349 individuals. Three distinct IEAs were identified: IEA1 was correlated with shock conditions, IEA2 was associated with the systemic inflammatory response syndrome (SIRS), and IEA3 was reflective of the coagulation profile. Notably, IEA1 (odds ratio [OR]= 0.52, 95 % confidence interval [CI]: 0.40 to 0.67, P < 0.001) and IEA2 (OR=0.74, 95 % CI: 0.62 to 0.90, P=0.002) exhibited significant associations with the risk of mortality. Intriguingly, patients characterized by lower IEA1 values (<-2, indicative of more severe shock) demonstrated a reduced mortality risk when administered with steroids. Conversely, patients with higher IEA2 values seemed to benefit from a judicious approach to fluid infusion.
Conclusions: Our comprehensive approach, seamlessly integrating advanced deep learning techniques, proteomic profiling, and clinical data, has unraveled intricate interdependencies between IEAs, protein abundance patterns, therapeutic interventions, and ultimate patient outcomes in the context of severe COVID-19 pneumonia. These discoveries make a significant contribution to the rapidly advancing field of precision medicine, paving the way for tailored therapeutic strategies that can significantly impact patient care.
Keywords: Covid-19; Heterogeneity; Self-supervised representation learning; Systemic inflammatory response syndrome.
. 2024 Dec 16;5(3):252-261.
doi: 10.1016/j.jointm.2024.11.001. eCollection 2025 Jul. Deep learning integration of chest computed tomography and plasma proteomics to identify novel aspects of severe COVID-19 pneumonia
Yucai Hong[SUP] 1 [/SUP], Lin Chen[SUP] 2 3 [/SUP], Yang Yu[SUP] 2 [/SUP], Ziyue Zhao[SUP] 4 [/SUP], Ronghua Wu[SUP] 5 [/SUP], Rui Gong[SUP] 6 [/SUP], Yandong Cheng[SUP] 7 [/SUP], Lingmin Yuan[SUP] 7 [/SUP], Shaojun Zheng[SUP] 8 [/SUP], Cheng Zheng[SUP] 9 [/SUP], Ronghai Lin[SUP] 9 [/SUP], Jianping Chen[SUP] 10 [/SUP], Kangwei Sun[SUP] 10 [/SUP], Ping Xu[SUP] 11 [/SUP], Li Ye[SUP] 12 [/SUP], Chaoting Han[SUP] 11 [/SUP], Xihao Zhou[SUP] 13 [/SUP], Yaqing Liu[SUP] 14 [/SUP], Jianhua Yu[SUP] 14 [/SUP], Yaqin Zheng[SUP] 15 [/SUP], Jie Yang[SUP] 1 [/SUP], Jiajie Huang[SUP] 1 [/SUP], Juan Chen[SUP] 16 [/SUP], Junjie Fang[SUP] 16 [/SUP], Chensong Chen[SUP] 16 [/SUP], Bo Fan[SUP] 17 [/SUP], Honglong Fang[SUP] 18 [/SUP], Baning Ye[SUP] 19 [/SUP], Xiyun Chen[SUP] 20 [/SUP], Xiaoli Qian[SUP] 21 [/SUP], Junxiang Chen[SUP] 22 [/SUP], Haitao Yu[SUP] 23 [/SUP], Jun Zhang[SUP] 23 [/SUP], Xi-Ming Pan[SUP] 24 [/SUP], Yi-Xing Zhan[SUP] 24 [/SUP], You-Hai Zheng[SUP] 24 [/SUP], Zhang-Hong Huang[SUP] 25 [/SUP], Chao Zhong[SUP] 26 [/SUP], Ning Liu[SUP] 1 [/SUP], Hongying Ni[SUP] 27 [/SUP], Gengsheng Zhang[SUP] 28 [/SUP], Zhongheng Zhang[SUP] 1 29 30 [/SUP]; Chinese Multi-omics Advances In Sepsis (CMAISE) Consortium
Affiliations
- PMID: 40933743
- PMCID: PMC12417366
- DOI: 10.1016/j.jointm.2024.11.001
Background: Heterogeneity is a critical characteristic of severe coronavirus disease 2019 (COVID-19) pneumonia. Integrating chest computed tomography (CT) imaging and plasma proteomics holds the potential to elucidate Image-Expression Axes (IEAs) that can effectively address this disease heterogeneity.
Methods: A cohort of subjects diagnosed with severe COVID-19 pneumonia at 12 participating hospitals between December 2022 and March 2023 was prospectively screened for eligibility. Context-aware self-supervised representation learning (CSRL) was employed to extract intricate features from CT images. Quantification of plasma proteins was achieved using the Olink® inflammation panel. A deep learning model was meticulously trained, with CSRL features serving as input and the proteomic data as the target. This trained model facilitated the construction of IEAs, offering a representation of the underlying disease heterogeneity. The potential of these IEAs for prognostic and predictive enrichment was subsequently explored via conventional regression models.
Results: The study cohort comprised 1979 eligible patients, who were stratified into a training set of 630 individuals and a testing set of 1349 individuals. Three distinct IEAs were identified: IEA1 was correlated with shock conditions, IEA2 was associated with the systemic inflammatory response syndrome (SIRS), and IEA3 was reflective of the coagulation profile. Notably, IEA1 (odds ratio [OR]= 0.52, 95 % confidence interval [CI]: 0.40 to 0.67, P < 0.001) and IEA2 (OR=0.74, 95 % CI: 0.62 to 0.90, P=0.002) exhibited significant associations with the risk of mortality. Intriguingly, patients characterized by lower IEA1 values (<-2, indicative of more severe shock) demonstrated a reduced mortality risk when administered with steroids. Conversely, patients with higher IEA2 values seemed to benefit from a judicious approach to fluid infusion.
Conclusions: Our comprehensive approach, seamlessly integrating advanced deep learning techniques, proteomic profiling, and clinical data, has unraveled intricate interdependencies between IEAs, protein abundance patterns, therapeutic interventions, and ultimate patient outcomes in the context of severe COVID-19 pneumonia. These discoveries make a significant contribution to the rapidly advancing field of precision medicine, paving the way for tailored therapeutic strategies that can significantly impact patient care.
Keywords: Covid-19; Heterogeneity; Self-supervised representation learning; Systemic inflammatory response syndrome.