Search

Abstract Early detection can benefit cancer patients with more effective treatments and better prognosis, but existing early screening tests are limited, especially for multi-cancer detection. This study investigated the most prevalent and lethal cancer types, including primary liver cancer (PLC), colorectal adenocarcinoma (CRC), and lung adenocarcinoma (LUAD). Leveraging the emerging cell-free DNA (cfDNA) fragmentomics, we developed a robust machine learning model for multi-cancer early detection. 1,214 participants, including 381 PLC, 298 CRC, 292 LUAD patients, and 243 healthy volunteers, were enrolled. The majority of patients (N = 971) were at early stages (stage 0, N = 34; stage I, N = 799). The participants were randomly divided into a training cohort and a test cohort in a 1:1 ratio while maintaining the ratio for the major histology subtypes. An ensemble stacked machine learning approach was developed using multiple plasma cfDNA fragmentomic features. The model was trained solely in the training cohort and then evaluated in the test cohort. Our model showed an Area Under the Curve (AUC) of 0.983 for differentiating cancer patients from healthy individuals. At 95.0% specificity, the sensitivity of detecting all cancer reached 95.5%, while 100%, 94.6%, and 90.4% for PLC, CRC, and LUAD, individually. The cancer origin model demonstrated an overall 93.1% accuracy for predicting cancer origin in the test cohort (97.4%, 94.3%, and 85.6% for PLC, CRC, and LUAD, respectively). Our model sensitivity is consistently high for early-stage and small-size tumors. Furthermore, its detection and origin classification power remained superior when reducing sequencing depth to 1× (cancer detection: ≥ 91.5% sensitivity at 95.0% specificity; cancer origin: ≥ 91.6% accuracy). In conclusion, we have incorporated plasma cfDNA fragmentomics into the ensemble stacked model and established an ultrasensitive assay for multi-cancer early detection, shedding light on developing cancer early screening in clinical practice.

Background: High expression of the long non-coding RNA nuclear-enriched abundant transcript 1 (NEAT1) in whole blood has been reported in colorectal cancer patients; however, its' clinical significance and origin are unclear. We evaluated the diagnostic and prognostic value, and origin of whole blood NEAT1 in colorectal cancer. Methods: Expression of NEAT1 variants, NEAT1_v1 and NEAT1_v2 were determined using real-time quantitative PCR. The diagnostic value of whole blood NEAT1 expression was evaluated in test (n = 60) and validation (n = 200) cohorts of colorectal cancer patients and normal controls (NCs). To identify the origin of NEAT1, its expression was analyzed in blood, matched primary tumor tissues, para-tumor tissues, metastatic tissues, and also immune cells from patients or NCs. Function of NEAT1 in colorectal cell lines was also assessed. The correlation of NEAT1 expression with clinical outcomes was assessed in 191 patients. Results: Whole blood NEAT1 expression was significantly higher in colorectal cancer patients than in NCs. NEAT1_v1 and NEAT1_v2 expression were highly accurate in distinguishing colorectal cancer patients from NCs (area under the curve: 0.787 and 0.871, respectively). Knockdown of NEAT1_v1 in vitro could inhibit cell invasion and proliferation, while knockdown of NEAT1_v2 promoted cell growth. However, whole blood expression was not correlated with matched tissues. An elevated expression was seen in neutrophils from CRC patients. Furthermore, high expression of NEAT1_v1 was correlated with worse overall survival. In contrast, high expression of NEAT1_v2 alone was correlated with better overall survival. Conclusion: Whole blood NEAT1 expression is a novel diagnostic and prognostic biomarker of overall survival in colorectal cancer. Elevated NEAT1 may derive from neutrophils. [ABSTRACT FROM AUTHOR]