Predicting Avatrombopag response in children with immune thrombocytopenia: A multi-view learning framework for
Yuntian Wang1, Yongqiang Tang2, Xiaoling Cheng3
1The School of Information and Communication Engineering, Hainan University, Haikou, 570228, Hainan, China; The State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, 100190, Beijing, China.
Insights
Predicting avatrombopag treatment response in children with chronic immune thrombocytopenia is now more accurate. Our novel computational framework improves early prediction, enabling personalized pediatric hematology care.
Area of Science:
- Computational biology
- Pediatric hematology
- Machine learning in medicine
Background:
- Chronic immune thrombocytopenia (ITP) affects children, requiring effective treatments like avatrombopag.
- Early prediction of avatrombopag treatment response is crucial for personalized care and minimizing drug exposure.
- Challenges in predicting response include missing data, small sample sizes, and high-dimensional features in clinical data.
Purpose of the Study:
- To develop an effective computational framework for early prediction of avatrombopag treatment response in pediatric chronic ITP.
- To address challenges posed by missing data, small sample size, and high-dimensional features.
Main Methods:
- A multi-view learning framework was developed, creating diverse data views using various imputation techniques.
- A feature selection encoder was used for dimensionality reduction and interpretability.
- Multi-view fusion, co-regularization, and contrastive learning were integrated to enhance prediction accuracy and robustness.
Main Results:
- The proposed multi-view learning framework demonstrated superior performance compared to baseline models in predicting treatment response.
- Experiments on real-world clinical data validated the framework's effectiveness.
Conclusions:
- The study presents a practical and interpretable multi-view learning framework for early avatrombopag treatment response prediction in pediatric chronic ITP.
- This framework supports personalized treatment strategies and efficient decision-making in pediatric hematology.
Background And Objective:
Avatrombopag is a thrombopoietin receptor agonist that has demonstrated clinical efficacy in rapidly increasing platelet counts and achieving bleeding control in children with chronic immune thrombocytopenia. Early prediction of treatment response is critical for reducing unnecessary drug exposure and guiding personalized treatment strategies. However, accurate prediction remains challenging due to the inherent characteristics of clinical tabular data, including missing values caused by inconsistent data recording, small sample size, and high-dimensional clinical features. This study aims to develop an effective computational framework for early prediction of treatment response under these conditions.
Methods:
We propose a multi-view learning framework that constructs multiple views by applying diverse imputation methods to the same dataset, with each view capturing unique assumptions about missingness. A feature selection encoder is employed to reduce feature redundancy and improve model interpretability. Multi-view fusion and co-regularization are integrated at the prediction level to learn complementary patterns across different views. In addition, contrastive learning is introduced to alleviate the small data problem and enhance representation robustness.
Results:
Experiments on real-world clinical data of children treated with avatrombopag demonstrate that the proposed method consistently outperforms multiple competitive baseline models in predicting treatment response.
Conclusions:
This study provides a practical and interpretable multi-view learning framework for early identification of treatment response in chronic immune thrombocytopenia, supporting more personalized and efficient treatment decisions in pediatric hematology.
Related Concept Videos
01:23Pharmacokinetics in Pediatric Patients: Overview and Drug Absorption
00:59Model-Independent Approaches for Pharmacokinetic Data: Noncompartmental Analysis
One important characteristic of noncompartmental analyses is that drug exposure increases proportionally with increasing doses. This relationship...
01:24Pharmacokinetics in Pediatric Patients: Drug Metabolism
01:17Pharmacokinetics in Pediatric Patients: Drug Distribution
01:14Model Approaches for Pharmacokinetic Data: Compartment Models
Two primary types of compartment models are recognized: mammillary and catenary. The more...
01:26Pharmacokinetics in Pediatric Patients: Drug Excretion