Multi-Task Learning and Soft-Label Supervision for Psychosocial Burden Profiling in Cancer Peer-Support Text
Wang, Z.; Cao, Y.; Shen, X.; Ding, Z.; Liu, Y.; Zhang, Y.
Show abstract
Objective: Online cancer peer-support text contains signals of psychosocial burden beyond emotional tone, including treatment burden, financial strain, uncertainty, and unmet support needs. We evaluated 2 modeling extensions: multi-task learning (MTL) for joint prediction of health economics and outcomes research (HEOR) burden dimensions, and soft-label supervision using large language model (LLM)-derived probability distributions. Materials and Methods: We analyzed 10,392 cancer peer-support posts. GPT-4o-mini generated proxy annotations for HEOR burden subscales, composite burden, high-need status, speaker role, cancer type, and emotion probabilities. Study 1 trained a shared ALBERT encoder under 4 MTL conditions: composite and subscale burden targets, each with and without auxiliary heads, using Kendall uncertainty weighting. Study 2 compared soft-label training on LLM emotion distributions with hard-label baselines under regular and token-augmented inputs, evaluating performance against both human labels and AI distributions. Results: Composite-only MTL achieved R2=0.446 for burden regression and weighted F1=0.810 for high-need screening; subscale classification achieved mean weighted F1=0.646. Adding auxiliary role and cancer-type heads reduced regression performance ({triangleup}R2 = -0.209). Soft-label training reduced weighted F1 by 0.16 versus hard-label baselines (0.68 vs. 0.86), and token augmentation did not improve performance under soft supervision. Discussion: Composite-only MTL supported modeling of multidimensional burden-related signals from forum text, whereas auxiliary prediction heads appeared to compete with primary tasks. Soft-label training aligned poorly with human-labeled emotion categories, suggesting that uncalibrated LLM distributions may propagate bias rather than improve supervision. Conclusion: Composite-only MTL was the strongest burden-modeling approach, and hard-label supervision remained preferable for emotion classification.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Continuous-Time and Dynamic Suicide Attempt Risk Prediction with Neural Ordinary Differential Equations 92%
- Clinical Knowledge Extraction via Sparse Embedding Regression (KESER) with Multi-Center Large Scale Electronic Health Record Data 91%
- Zero Shot Health Trajectory Prediction Using Transformer 91%
Similar papers in this journal
- Actionability of Synthetic Data in a Heterogeneous and Rare Healthcare Demographic; Adolescents and Young Adults (AYAs) with Cancer 92%
- Towards Predicting 30-Day Readmission among Oncology Patients: Identifying Timely and Actionable Risk Factors 91%
- Histology-based Prediction of Therapy Response to Neoadjuvant Chemotherapy for Esophageal and Esophagogastric Junction Adenocarcinomas Using Deep Learning 91%
Similar papers in this journal
- CONSORT-TM: Text classification models for assessing the completeness of randomized controlled trial publications 94%
- Evaluation of Domain Generalization and Adaptation on Improving Model Robustness to Temporal Dataset Shift in Clinical Medicine 93%
- EHR Foundation Models Improve Robustness in the Presence of Temporal Distribution Shift 92%
Similar papers in this journal
Similar papers in this journal
- Transformer-based deep learning model for the diagnosis of suspected lung cancer in primary care based on electronic health record data 92%
- Enhancing Early Detection of Cognitive Decline in the Elderly through Ensemble of NLP Techniques: A Comparative Study Utilizing Large Language Models in Clinical Notes 92%
- Weakly-Supervised Tumor Purity Prediction FromFrozen H&E Stained Slides 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.