Despite strong predictive results in the clinical machine learning literature, the translation of these models into bedside use remains limited by systems-level barriers: heterogeneous data representations, the absence of standardized deployment workflows, and a mismatch between research prototypes and the concurrency and latency requirements of hospital environments. We present the SepsisAI-Orchestrator, an open-source modular platform that addresses this deployment gap for early sepsis detection. The platform integrates HL7 FHIR-inspired Clinical Document Architecture (CDA) preprocessing, NoSQL storage, a containerized LightGBM classifier served via REST APIs, and a Streamlit clinical dashboard, orchestrated with Docker and Kubernetes. A previously validated LightGBM model (F1 0.87-0.94 on PhysioNet 2019) is reused without modification; the contribution lies in the surrounding infrastructure and its empirical characterization under load. Using k6 with 50-1000 concurrent virtual users, we find that replica count must be matched to the physical CPU thread count of the host: scaling from 3 to 12 replicas on a 12-thread CPU reduces p95 latency from 3.3s to 1.41s (57.3% reduction) and eliminates all request failures, while over-provisioning to 24 or 48 replicas degrades performance due to scheduler contention. To our knowledge this U-shaped scaling behavior has not been quantified previously for clinical AI inference workloads. We do not claim prospective clinical validation. Source code and deployment manifests are available at https://github.com/nucleusai/sepsisai-orchestrator.

翻译：尽管临床机器学习文献已展现出卓越的预测性能，但将此类模型转化为临床床旁应用仍面临系统层面的多重障碍：异构数据表征、标准化部署工作流的缺失，以及研究原型与医院环境并发性及延迟要求之间的不匹配。本文提出开源模块化平台SepsisAI-Orchestrator，旨在填补早期脓毒症检测的部署鸿沟。该平台整合了基于HL7 FHIR（健康信息交换第七层框架的临床文档架构）的预处理模块、NoSQL存储、通过REST API服务的容器化LightGBM分类器、以及基于Streamlit的临床仪表盘，并通过Docker与Kubernetes进行编排。研究中直接复用了先前经PhysioNet 2019验证的LightGBM模型（F1值0.87-0.94），核心贡献在于构建配套基础架构并开展负载下的实证特征分析。通过使用k6模拟50-1000个并发虚拟用户的测试，本研究发现：副本数量必须与宿主机物理CPU线程数匹配——在12线程CPU上将副本数从3扩展至12，可使p95延迟从3.3秒降至1.41秒（降幅57.3%），并消除全部请求失败；而当过度配置至24或48副本时，调度争用导致性能退化。据我们所知，这种U型缩放行为在临床AI推理工作负载中此前尚未被量化。本平台不构成前瞻性临床验证。源代码及部署清单请参见https://github.com/nucleusai/sepsisai-orchestrator。