Oops, you're using an old version of your browser so some of the features on this page may not be displaying properly.

MINIMAL Requirements: Google Chrome 24+Mozilla Firefox 20+Internet Explorer 11Opera 15–18Apple Safari 7SeaMonkey 2.15-2.23

Poster session 04

1268P - Liquid biopsy and CT-based multi-omics fusion enhances differential diagnosis of early-stage lung adenocarcinoma

Date

21 Oct 2023

Session

Poster session 04

Topics

Tumour Site

Non-Small Cell Lung Cancer

Presenters

Yanwei Zhang

Citation

Annals of Oncology (2023) 34 (suppl_2): S732-S745. 10.1016/S0923-7534(23)01265-6

Authors

Y. Zhang1, Y. Yu2, Y. Lou3, J. Lu4, F. Qian5, H. Zhong6, L. Wu7, B. Han8

Author affiliations

  • 1 Pulmonary Medicine, Shanghai Chest Hospital Affiliated to Shanghai Jiao Tong University, 200030 - shanghai/CN
  • 2 Shanghai Jiaotong University, Shanghai Jiaotong University, 200030 - Shanghai/CN
  • 3 Department Of Respiration, Shanghai Chest Hospital Affiliated to Shanghai Jiao Tong University, 200030 - Shanghai/CN
  • 4 Department Of Pulmonary Medicine, Shanghai Chest Hospital Affiliated to Shanghai Jiao Tong University, 200030 - Shanghai/CN
  • 5 Pulmonary Medicine Dept, Shanghai Chest Hospital Affiliated to Shanghai Jiao Tong University, 200030 - Shanghai/CN
  • 6 Department Of Pulmonary, Shanghai Chest Hospital Affiliated to Shanghai Jiao Tong University, 200030 - Shanghai/CN
  • 7 Center For Excellence In Molecular Cell Science, SIBCB - Shanghai Institute of Biochemistry and Cell Biology, 200031 - Shanghai/CN
  • 8 Respiratory Department, Shanghai Chest Hospital, Shanghai Jiao Tong University, 200030 - Shanghai/CN

Resources

Login to get immediate access to this content.

If you do not have an ESMO account, please create one for free.

Abstract 1268P

Background

Lung cancer is a leading cause of cancer-related deaths worldwide. Early detection using low-dose CT (LDCT) has shown promise in reducing mortality rates. Nevertheless, LDCT screening poses challenges, including a high false-positive rate and the risk of overdiagnosis. AI and biomarkers are crucial directions for the future of lung cancer screening. This study investigates the potential of multi-omics fusion, combining liquid biopsy biomarkers and computed tomography (CT) features, to enhance lung cancer differential diagnosis.

Methods

A total of 146 participants were enrolled, including 111 early-stage lung adenocarcinoma patients and 35 controls. High throughput extracellular vesicle long RNA (evlRNA) sequencing were performed using serum samples obtained before lung surgery. A fusion model was developed to combine image-based features and evlRNA features.

Results

Our findings suggest that evlRNA and image-based features complement each other, achieving improved performance when evlRNA features are fused with radiological features from AI, CTR, or human experts. Our methods achieve notable differential diagnosis performance; for example, combining evlRNA and radiological AI yields a 4-class AUC of 0.919 and a benign-malignant AUC of 0.948 (sensitivity: 89.1%, specificity: 94.3%). Integrating multi-omics analysis with human experts further enhances diagnostic accuracy. Additionally, we provide post-hoc explanations using Shapley values to understand feature importance in the multi-omics modeling. Table: 1268P

Method
4-Class Analysis (IA, MIA, AIS) vs Benign (IA, MIA) vs (AIS, Benign)
AUC AUC Sens Spec AUC Sens Spec
evlRNA 79.2 86.4 83.9 85.7 75.8 73.3 78.9
CTR 77.6 75.7 59.5 94.3 62.9 77.3 59.2
vCTR 84.0 85.1 71.0 97.1 75.9 68.0 80.3
Rad 89.0 92.2 79.2 94.3 82.9 76.0 85.8
Junior expert / / 83.7 51.4 / 76.0 66.2
Senior expert / / 91.9 80.0 / 85.3 77.4
evlRNA + CTR 88.0 90.5 87.4 88.6 84.0 72.0 90.0
evlRNA + vCTR 89.1 91.0 84.6 91.4 82.7 68.0 91.4
evlRNA + Rad 91.9 94.8 89.1 94.3 87.2 80.0 87.1
evlRNA + Junior expert 83.4 89.9 86.4 88.6 82.8 73.3 84.5
evlRNA + Senior expert 89.3 95.1 86.5 97.1 87.8 86.7 80.2
evlRNA + Rad + Junior expert 92.4 96.0 95.5 91.4 87.3 78.7 88.6
evlRNA + Rad + Senior expert 93.4 97.9 91.8 100.0 88.9 92.0 80.1

Conclusions

In summary, our study demonstrated that the combination of evlRNA-based and image-based features can complement each other and that the collaborative approach between multi-omics and human analysis can further enhance the performance. These findings highlight the importance of integrating multiple modalities including effective biomarkers and CT analysis with AI algorithms, into LDCT screening through multi-omics fusion.

Clinical trial identification

Editorial acknowledgement

Legal entity responsible for the study

Yanwei Zhang.

Funding

Shanghai Science and Technology Committee.

Disclosure

All authors have declared no conflicts of interest.

This site uses cookies. Some of these cookies are essential, while others help us improve your experience by providing insights into how the site is being used.

For more detailed information on the cookies we use, please check our Privacy Policy.

Customise settings
  • Necessary cookies enable core functionality. The website cannot function properly without these cookies, and you can only disable them by changing your browser preferences.