Scholarlink

Objective <p>To develop and validate a noninvasive model for classifying T stage in gastrointestinal malignancies using circulating tumor cells (CTCs) and serum tumor markers and to compare the predictive value of CTCs with that of conventional tumor markers.</p> Methods <p>This retrospective study included 328 patients with gastrointestinal malignancies from two hospitals in the same region. The internal modelling cohort comprised 214 patients (T1 + T2, <i>n</i> = 49; T3 + T4, <i>n</i> = 165), and the independent validation cohort comprised 114 patients (T1 + T2, <i>n</i> = 55; T3 + T4, <i>n</i> = 59). Univariable and multivariable logistic regression analyses were used to identify stage-related factors associated with CTCs. Three-dimensional-matched feature sets were constructed to minimize bias from unequal feature numbers. Repeated stratified fivefold cross-validation, the foldwise synthetic minority oversampling technique, and weighted cross-entropy loss were used to address severe class imbalance. Model performance was evaluated using AUC, balanced accuracy, F1 score, and calibration metrics rather than overall accuracy. Logistic regression, decision tree, support vector machine, k-nearest neighbors, and the newly developed CTC-AttnNet were compared. K‒M and Cox analyses were performed as exploratory recurrence analyses.</p> Results <p>CTC count alone moderately discriminated the overall TNM stage (AUC = 0.742) but poorly discriminated the T stage (AUC = 0.595); the AUCs of all four conventional tumor markers were &lt; 0.60. Advanced overall TNM stage was independently associated with CTC positivity (OR = 1.844, 95% CI: 1.255–2.710; <i>P</i> = 0.002). Under dimension-matched conditions, the CTC-containing feature set achieved an external validation AUC of 0.76, outperforming the dimension-reduced conventional marker combination (AUC = 0.65). CTC-AttnNet achieved an external validation AUC of 0.82, a balanced accuracy of 0.78, and an F1 score of 0.76. Ablation analysis revealed that the attention module improved the recognition of minority class T1 + T2 cases. CTC positivity was also independently associated with recurrence (HR = 5.263, 95% CI 1.637–16.927; <i>P</i> = 0.005).</p> Conclusion <p>CTCs were significantly associated with gastrointestinal tumor stage and postoperative recurrence. Multivariable CTC-based models discriminated T stage better than models based on four conventional serum tumor markers did, although the CTC count alone had limited discriminatory ability. CTC-AttnNet represents an exploratory noninvasive stratification tool for this retrospective regional cohort and provides a methodological framework for developing liquid biopsy prediction models.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

CTC-AttnNet: development and validation of an attention-based neural network for staging gastrointestinal malignancies

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年8月1日

查看全文
  • Liang Li,
  • Chudi Sun,
  • Shuiri Wang,
  • Hao Qiang,
  • Zhou Liu,
  • Haojie Wang,
  • Zhengtang Qi,
  • Lin Zhang,
  • Zhining Liu

摘要

Objective

To develop and validate a noninvasive model for classifying T stage in gastrointestinal malignancies using circulating tumor cells (CTCs) and serum tumor markers and to compare the predictive value of CTCs with that of conventional tumor markers.

Methods

This retrospective study included 328 patients with gastrointestinal malignancies from two hospitals in the same region. The internal modelling cohort comprised 214 patients (T1 + T2, n = 49; T3 + T4, n = 165), and the independent validation cohort comprised 114 patients (T1 + T2, n = 55; T3 + T4, n = 59). Univariable and multivariable logistic regression analyses were used to identify stage-related factors associated with CTCs. Three-dimensional-matched feature sets were constructed to minimize bias from unequal feature numbers. Repeated stratified fivefold cross-validation, the foldwise synthetic minority oversampling technique, and weighted cross-entropy loss were used to address severe class imbalance. Model performance was evaluated using AUC, balanced accuracy, F1 score, and calibration metrics rather than overall accuracy. Logistic regression, decision tree, support vector machine, k-nearest neighbors, and the newly developed CTC-AttnNet were compared. K‒M and Cox analyses were performed as exploratory recurrence analyses.

Results

CTC count alone moderately discriminated the overall TNM stage (AUC = 0.742) but poorly discriminated the T stage (AUC = 0.595); the AUCs of all four conventional tumor markers were < 0.60. Advanced overall TNM stage was independently associated with CTC positivity (OR = 1.844, 95% CI: 1.255–2.710; P = 0.002). Under dimension-matched conditions, the CTC-containing feature set achieved an external validation AUC of 0.76, outperforming the dimension-reduced conventional marker combination (AUC = 0.65). CTC-AttnNet achieved an external validation AUC of 0.82, a balanced accuracy of 0.78, and an F1 score of 0.76. Ablation analysis revealed that the attention module improved the recognition of minority class T1 + T2 cases. CTC positivity was also independently associated with recurrence (HR = 5.263, 95% CI 1.637–16.927; P = 0.005).

Conclusion

CTCs were significantly associated with gastrointestinal tumor stage and postoperative recurrence. Multivariable CTC-based models discriminated T stage better than models based on four conventional serum tumor markers did, although the CTC count alone had limited discriminatory ability. CTC-AttnNet represents an exploratory noninvasive stratification tool for this retrospective regional cohort and provides a methodological framework for developing liquid biopsy prediction models.