Predictive modeling for clinical tabular data is central to clinical decision support and therefore requires not only strong predictive performance but also transparent decision logic. Although deep learning and tree-based ensemble methods can achieve high accuracy, their black-box nature remains a major obstacle to clinical deployment. This challenge is further compounded by common characteristics of medical data, including limited sample sizes, severe class imbalance, and feature evolution arising from changes in diagnostic criteria and clinical documentation. To address these issues, we propose Medical Heuristic Learning (MHL), an instantiation of the learning-beyond-gradients paradigm for clinical tabular prediction. Instead of relying on neural network weight updates, MHL uses a large language model (LLM)-driven workflow that integrates statistical probes, medical knowledge probes, rule synthesis, and code-level iterative refinement to optimize a deterministic and executable decision system. The resulting model is expressed not as opaque parameters, but as versioned pure-Python decision rules that are explicitly interpretable, fully auditable, and clinically grounded. MHL also supports continual learning by starting from previously validated rules and iteratively revising them using updated feature information under data drift or feature evolution. Comprehensive experiments on medical datasets show that MHL achieves performance comparable to state-of-the-art methods while maintaining strong behavior in small-sample and highly imbalanced settings. The results further indicate that this explicit rule update mechanism can help alleviate catastrophic forgetting under feature evolution. Overall, these findings suggest that non-gradient-based heuristic systems offer a transparent and adaptable alternative for high-stakes clinical decision support.

翻译：临床表格数据的预测建模是临床决策支持的核心，因此不仅需要强大的预测性能，还需要透明的决策逻辑。尽管深度学习和基于树的集成方法能够实现高精度，但其黑箱特性仍是临床部署的主要障碍。医疗数据的常见特性进一步加剧了这一挑战，包括样本量有限、严重的类别不平衡，以及因诊断标准和临床记录变更导致的特征演化。为解决这些问题，我们提出了医学启发式学习（MHL），这是学习超越梯度范式在临床表格预测中的一种具体应用。MHL不依赖神经网络权重更新，而是采用大语言模型（LLM）驱动的工作流，整合统计探针、医学知识探针、规则综合以及代码级迭代优化，来优化一个确定性的、可执行的决策系统。最终模型不以不透明的参数形式呈现，而是表现为有版本控制的纯Python决策规则，这些规则具有明确的可解释性、完全可审计性，并具备临床基础。MHL还支持持续学习，其流程从先前验证过的规则出发，利用数据漂移或特征演化下更新的特征信息迭代修订规则。在医学数据集上的综合实验表明，MHL在达到与最先进方法相当性能的同时，在小样本和高度不平衡场景下仍保持稳健表现。结果进一步表明，这种显式的规则更新机制有助于缓解特征演化下的灾难性遗忘。总体而言，这些发现表明，基于非梯度的启发式系统为高风险临床决策支持提供了一种透明且可适应的替代方案。