构建可扩展的AI平台，实现脓毒症早期检测模型的实时部署与监控。
SepsisAI Orchestrator: A Containerized and Scalable Platform for Deploying AI Models and Real-Time Monitoring in Early Sepsis Detection
- 用容器化技术整合数据处理、模型服务与可视化，支持医院级并发需求。
- 实测表明12线程服务器上12个副本时延迟最低（p95降至1.41秒），过量部署反而降效。
- 开源平台适配临床场景，特别适合需快速部署和性能调优的医疗AI团队。
尽管临床机器学习在脓毒症预测方面表现优异，但其床边应用受限于系统层面障碍：数据格式异构、缺乏标准化部署流程，以及研究原型与医院环境对并发性和延迟的要求不匹配。本文提出SepsisAI-Orchestrator，一个开源模块化平台，解决早期脓毒症检测的部署难题。平台集成基于HL7 FHIR的CDA预处理、NoSQL存储、通过REST API提供服务的容器化LightGBM分类器，以及Streamlit临床仪表板，由Docker与Kubernetes编排。复用已验证的LightGBM模型（在PhysioNet 2019上F1为0.87-0.94），贡献在于基础设施设计及其负载下的实证分析。使用k6测试50-1000个并发虚拟用户，发现副本数应与宿主机物理CPU线程数匹配：在12线程服务器上，副本数从3增至12时，p95延迟由3.3秒降至1.41秒（降低57.3%），且消除所有请求失败；而过度配置至24或48个副本因调度竞争导致性能下降。据我们所知，这是首个针对临床AI推理工作负载量化描述的U型缩放行为。未进行前瞻性临床验证。源码与部署文件见https://github.com/nucleusai/sepsisai-orchestrator。
原文摘要 · Abstract (English)
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.
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。