A multi-constraint representation learning model for identification of ovarian cancer with missing laboratory indicators

doi:10.12122/j.issn.1673-4254.2025.01.20

Abstract

Abstract:

Objective To evaluate the performance of a multi-constraint representation learning classification model for identifying ovarian cancer with missing laboratory indicators. Methods Tabular data with missing laboratory indicators were collected from 393 patients with ovarian cancer and 1951 control patients. The missing ovarian cancer laboratory indicator features were projected to the latent space to obtain a classification model using the representational learning classification model based on discriminative learning and mutual information coupled with feature projection significance score consistency and missing location estimation. The proposed constraint term was ablated experimentally to assess the feasibility and validity of the constraint term by accuracy, area under the ROC curve (AUC), sensitivity, and specificity. Cross-validation methods and accuracy, AUC, sensitivity and specificity were also used to evaluate the discriminative performance of this classification model in comparison with other interpolation methods for processing of the missing data. Results The results of the ablation experiments showed good compatibility among the constraints, and each constraint had good robustness. The cross-validation experiment showed that for identification of ovarian cancer with missing laboratory indicators, the AUC, accuracy, sensitivity and specificity of the proposed multi-constraints representation-based learning classification model was 0.915, 0.888, 0.774, and 0.910, respectively, and its AUC and sensitivity were superior to those of other interpolation methods. Conclusion The proposed model has excellent discriminatory ability with better performance than other missing data interpolation methods for identification of ovarian cancer with missing laboratory indicators.

Key words: missing data, shared representation learning, discriminant analysis, feature importance score consistency, missing position estimation, mutual information, ovarian cancer

Zihan LU, Fangjun HUANG, Guangyao CAI, Jihong LIU, Xin ZHEN. A multi-constraint representation learning model for identification of ovarian cancer with missing laboratory indicators[J]. Journal of Southern Medical University, 2025, 45(1): 170-178.

Figures/Tables 5

Fig.1 Flowchart of a multi-constrained representation learning classification model.

Tab.1 Algorithmic pseudo-code for a representation learning model applied to the missing data

Algorithm 1 Pseudocode of the proposed method

Training stage

Input: data feature matrix $X, X ∈ R m × n$ , dimension of potential space k, weight parameters for each constraint $α 1, α 2, α 3, α 4, α 5, α 6$ and $ρ$ .

Output: projection Matrix for Data Representation Learning $Q, Q ∈ R n × k$

Begin

Initialize $U, Q, P, R$ as random matrices;

For t to number of iterations

For $i = 1$ to $n$

Calculate $∂ r a n k (Q) i ∂ q j$

Calculate $∂ F ∂ U$ , $∂ F ∂ P$ , $∂ F ∂ Q$ , $∂ F ∂ R$

Updated $U, Q, P, R$ by the following equation

$Q (t + 1) = Q (t) - η Q ∂ F ∂ Q$ , $U (t + 1) = U (t) - η U ∂ F ∂ U$ , $P (t + 1) = P (t) - η P ∂ F ∂ P$

$R (t + 1) = α 4 U (t) T U (t) + ρ E α 4 U (t) T M - 1$

End

Testing stage

Input: New test dataset for missing data $X ∼, X ∼ ∈ R m × n$

Output: The projection of the new dataset onto the potential space obtain $U n e w = X ∼ Q$