用动态系统+大模型，从临床数据中挖掘可解释的患者亚群。
Integrating Dynamical Systems Learning with Foundational Models: A Meta-Evolutionary AI Framework for Clinical Trials
- 基于收缩映射与进化算法，将患者特征压缩到稳定吸引子中。
- 在精神分裂症等案例中，仅用2-4个变量就将模型AUC提升至接近完美。
- 适合需要可解释性与自适应推理的医疗AI研究者使用。
人工智能已发展为多个专精‘物种’的生态体系。本文分析两种代表：6710亿参数的DeepSeek-V3大语言模型（体现规模驱动的泛化能力），以及基于动力系统框架的NetraAI，该框架针对小样本临床试验数据具备稳定性与可解释性。我们形式化了NetraAI的理论基础，融合收缩映射、信息几何与进化算法，识别预测性患者亚群。特征嵌入度量空间并迭代收缩至稳定吸引子，定义潜在分组；伪时间嵌入与长程记忆支持高阶特征交互探索；内部进化环路筛选出紧凑、可解释的2-4变量组合（称作'人格特征'）。引入大模型策略师作为元进化层，观察人格输出、优先筛选关键变量、注入领域知识并评估鲁棒性。该双层架构模拟人类科研过程：NetraAI为实验者，大模型为理论家，形成自优化循环。在精神分裂症、抑郁症及胰腺癌案例中，NetraAI发现效应量高的微小亚群，使原始弱模型（AUC ~0.50–0.68）转化为近乎完美的分类器，仅依赖少数特征。我们定位NetraAI于动力系统、信息几何与进化学习交汇点，契合如LeCun提出的联合嵌入预测架构（JEPA）等概念级推理范式。通过优先可靠、可解释的知识，NetraAI提供新一代自反思、自适应的AI，加速临床发现。
原文摘要 · Abstract (English)
Artificial intelligence (AI) has evolved into an ecosystem of specialized "species," each with unique strengths. We analyze two: DeepSeek-V3, a 671-billion-parameter Mixture of Experts large language model (LLM) exemplifying scale-driven generality, and NetraAI, a dynamical system-based framework engineered for stability and interpretability on small clinical trial datasets. We formalize NetraAI's foundations, combining contraction mappings, information geometry, and evolutionary algorithms to identify predictive patient cohorts. Features are embedded in a metric space and iteratively contracted toward stable attractors that define latent subgroups. A pseudo-temporal embedding and long-range memory enable exploration of higher-order feature interactions, while an internal evolutionary loop selects compact, explainable 2-4-variable bundles ("Personas"). To guide discovery, we introduce an LLM Strategist as a meta-evolutionary layer that observes Persona outputs, prioritizes promising variables, injects domain knowledge, and assesses robustness. This two-tier architecture mirrors the human scientific process: NetraAI as experimentalist, the LLM as theorist, forming a self-improving loop. In case studies (schizophrenia, depression, pancreatic cancer), NetraAI uncovered small, high-effect-size subpopulations that transformed weak baseline models (AUC ~0.50-0.68) into near-perfect classifiers using only a few features. We position NetraAI at the intersection of dynamical systems, information geometry, and evolutionary learning, aligned with emerging concept-level reasoning paradigms such as LeCun's Joint Embedding Predictive Architecture (JEPA). By prioritizing reliable, explainable knowledge, NetraAI offers a new generation of adaptive, self-reflective AI to accelerate clinical discovery.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。