ICCA-Based ICU Physiological State Space Monitor
2026年8月14日 更新者：Ming Zhong、Shanghai Zhongshan Hospital
Development of an ICU Physiological State Space Monitor Based on the ICCA Database: A Single-Center Retrospective Observational Study
Critically ill patients can deteriorate rapidly across multiple organ systems.
Most intensive care unit (ICU) risk tools rely on measurements collected at a single time point and may not fully capture how physiology evolves or how quickly a patient recovers from disturbance.
This single-center retrospective observational study will use routinely collected data from the ICCA reporting database at Zhongshan Hospital, Fudan University to develop and internally validate a research prototype called the ICU Physiological State Space Monitor.
Adult ICU admissions will be represented as daily state vectors across 10 physiological domains.
The study will characterize each patient's position and movement in a multidimensional state space, identify high-risk regions and possible critical transitions, and quantify physiological resilience using trajectory features such as variability, autocorrelation, curvature, recovery slope, and cross-domain coupling.
The primary validation outcome is a composite clinical deterioration event within 72 hours after an eligible index patient-day.
The monitor is an analytic and visualization framework for retrospective research and will not be deployed for real-time clinical decision-making in this study.
研究概览
详细说明
This is a single-center, retrospective, non-interventional methodological cohort study using routinely collected structured data from the ICCA reporting-layer database at Zhongshan Hospital, Fudan University. The source population comprises adult ICU patients admitted between September 2021 and May 31, 2026 who have an extractable and uniquely identifiable ICU encounter. No intervention will be assigned, no clinical decision will be altered, and no additional examination, treatment, follow-up visit, or biospecimen collection will be performed.
The unit of participant-level registration is the patient, while the principal analytic structure is the ICU encounter and the patient-day. ICU admission time will serve as the common temporal anchor. Monitoring, laboratory, fluid, medication, organ-support, diagnostic, and demographic data will be extracted from the ICCA reporting layer and aggregated primarily into consecutive 24-hour windows. Alternative 12-hour or shorter windows may be evaluated in sensitivity analyses.
Daily physiological state vectors will be constructed across 10 domains: oxygenation; ventilation and respiratory drive; hemodynamic perfusion; renal-fluid balance; hepatic-metabolic clearance; inflammation-immune activation; coagulation-blood integrity; brain-autonomic regulation; bioenergetic and acid-base status; and treatment-support burden. Prespecified data-governance rules will be used for variable-source mapping, unit harmonization, time alignment, limited carry-forward, missing-data handling, and physiological-range checks.
Principal component analysis will provide the primary low-dimensional state-space representation. UMAP may be used for supplementary visualization and local-structure exploration but will not be the sole primary analytical framework. Enhanced trajectory features will include state position, displacement, trajectory length, speed, acceleration, turning angle, curvature, local variability, lag-1 autocorrelation, recovery slope, and cross-domain coupling. These features will be used to characterize high-risk regions, possible basin crossings and critical transitions, and physiological resilience.
Eligible records will be divided chronologically into an earlier derivation cohort and a later temporal validation cohort, with an intended split of approximately 70% and 30%, respectively. The exact cutoff will be locked before analysis. The primary analysis will evaluate the association between state-space and trajectory features and a composite clinical deterioration outcome occurring within 72 hours after each eligible index patient-day. Multivariable logistic regression or discrete-time risk models will be used for the primary outcome. ICU and in-hospital mortality may be evaluated using Cox regression or competing-risk methods, and other outcomes will be analyzed with appropriate regression or time-to-event models. Internal validation will use the temporal validation cohort and bootstrap resampling to assess discrimination, calibration, and robustness.
The source data will remain in the hospital-controlled information environment. Investigators will use a deidentified research dataset without direct identifiers and without access to the reidentification key. Only aggregated results, model parameters, and approved figures will be released. The study seeks a waiver of written informed consent because it is retrospective, non-interventional, uses deidentified existing data, and does not affect participants' current or future care.
研究类型
观察性的
注册 (估计的)
60000
联系人和位置
本节提供了进行研究的人员的详细联系信息，以及有关进行该研究的地点的信息。
学习地点
-
-
Shanghai Municipality
-
Shanghai、Shanghai Municipality、中国、200032
- Zhongshan hospital
-
-
参与标准
研究人员寻找符合特定描述的人，称为资格标准。这些标准的一些例子是一个人的一般健康状况或先前的治疗。
资格标准
适合学习的年龄
- 成人
- 年长者
接受健康志愿者
不
取样方法
概率样本
研究人群
Adult patients admitted to an ICU at Zhongshan Hospital, Fudan University between September 2021 and May 31, 2026 who have an extractable, uniquely identifiable ICU encounter in the ICCA reporting-layer database and meet the prespecified eligibility criteria.
The study will use a fixed-time-window census of all eligible records.
The principal participant count will be based on unique patients; ICU encounters and patient-days will form the analytic units for longitudinal modeling.
描述
Inclusion Criteria:
- Age 18 years or older.
- Admission to an ICU at Zhongshan Hospital, Fudan University between September 2021 and May 31, 2026, with a uniquely identifiable ICU encounter in the ICCA reporting-layer database.
- ICU length of stay of at least 24 hours.
- Availability of core variables from at least four physiological domains and at least one patient-day suitable for modeling.
Exclusion Criteria:
- Duplicate import of the same ICU encounter that cannot be reliably deduplicated.
- Severe missingness, inconsistency, or irreconcilable error in key identifiers, ICU admission/discharge times, or core timestamps.
- Test data, demonstration data, or records determined through data governance to be non-genuine patient records.
- Inability to lock the primary source mapping for key variables, or overall data quality insufficient to support construction of the physiological state vector.
学习计划
本节提供研究计划的详细信息，包括研究的设计方式和研究的衡量标准。
研究是如何设计的？
设计细节
队列和干预
团体/队列 |
干预/治疗 |
|---|---|
|
Derivation Cohort
This cohort will be used to construct the physiological state vectors, estimate standardization parameters, develop the low-dimensional state-space representation, characterize trajectory features, and fit the primary prediction/association models.
|
The exposure of interest is the participant's multidimensional physiological state and trajectory derived from routinely collected ICU monitoring, laboratory, fluid, medication, organ-support, diagnostic, and demographic data.
Daily state vectors will cover 10 physiological domains.
Enhanced trajectory features will include state position, displacement, trajectory length, speed, acceleration, turning angle, curvature, local variability, lag-1 autocorrelation, recovery slope, and cross-domain coupling.
The investigators will not assign any exposure, treatment, or clinical intervention.
|
|
Temporal Validation Cohort
This cohort will be held out for temporal internal validation of state-space features, trajectory measures, and associations with prespecified clinical outcomes.
|
The exposure of interest is the participant's multidimensional physiological state and trajectory derived from routinely collected ICU monitoring, laboratory, fluid, medication, organ-support, diagnostic, and demographic data.
Daily state vectors will cover 10 physiological domains.
Enhanced trajectory features will include state position, displacement, trajectory length, speed, acceleration, turning angle, curvature, local variability, lag-1 autocorrelation, recovery slope, and cross-domain coupling.
The investigators will not assign any exposure, treatment, or clinical intervention.
|
研究衡量的是什么？
主要结果指标
结果测量 |
措施说明 |
大体时间 |
|---|---|---|
|
Composite Clinical Deterioration Within 72 Hours
大体时间：Within 72 hours following each eligible index patient-day
|
A binary composite outcome defined by the occurrence of at least one of the following events during the 72-hour window after an eligible index patient-day: ICU death; new initiation of invasive mechanical ventilation; new initiation of continuous renal replacement therapy (CRRT); new initiation of extracorporeal membrane oxygenation (ECMO); or a prespecified significant escalation in vasoactive medication support.
A participant/index window meeting more than one component will be counted once for the composite outcome.
|
Within 72 hours following each eligible index patient-day
|
次要结果测量
结果测量 |
措施说明 |
大体时间 |
|---|---|---|
|
ICU mortality
大体时间：From ICU admission through ICU discharge, an average of approximately 5 days
|
Death from any cause before discharge from the ICU.
|
From ICU admission through ICU discharge, an average of approximately 5 days
|
|
In-Hospital Mortality
大体时间：From hospital admission through hospital discharge, an average of approximately 30 days
|
Death from any cause before discharge from the index hospitalization.
|
From hospital admission through hospital discharge, an average of approximately 30 days
|
|
Duration of Invasive Mechanical Ventilation
大体时间：From ICU admission through ICU discharge, an average of approximately 5 days
|
Total number of calendar days during which invasive mechanical ventilation is used during the ICU stay.
|
From ICU admission through ICU discharge, an average of approximately 5 days
|
|
Duration of Continuous Renal Replacement Therapy
大体时间：From ICU admission through ICU discharge, an average of approximately 5 days
|
Total number of calendar days during which CRRT is used during the ICU stay.
|
From ICU admission through ICU discharge, an average of approximately 5 days
|
|
Duration of Vasoactive Medication Exposure
大体时间：From ICU admission through ICU discharge, an average of approximately 5 days
|
Total number of calendar days with recorded vasoactive medication support during the ICU stay.
|
From ICU admission through ICU discharge, an average of approximately 5 days
|
|
ICU Length of Stay
大体时间：From ICU admission through ICU discharge, an average of approximately 5 days
|
Time from ICU admission to ICU discharge, reported in days.
|
From ICU admission through ICU discharge, an average of approximately 5 days
|
|
Hospital Length of Stay
大体时间：From hospital admission through hospital discharge, an average of approximately 30 days
|
Time from hospital admission to hospital discharge, reported in days.
|
From hospital admission through hospital discharge, an average of approximately 30 days
|
其他结果措施
结果测量 |
措施说明 |
大体时间 |
|---|---|---|
|
Estimated 72-Hour Composite Deterioration Risk by Physiological State-Space Location
大体时间：Within 72 hours following each eligible index patient-day
|
Estimated probability of the 72-hour composite deterioration outcome associated with locations in the low-dimensional physiological state space derived from the prespecified state-space model.
The estimated probability will be reported as a percentage ranging from 0% to 100%.
High-risk bands, pockets, and local risk landscapes will be considered descriptive features of the estimated risk surface rather than separate outcome measures.
|
Within 72 hours following each eligible index patient-day
|
|
State-Space Displacement Between Consecutive Patient-Days
大体时间：Across consecutive eligible patient-days from ICU admission through ICU discharge, an average of approximately 5 days
|
Magnitude of change in the participant's position in the PCA-derived low-dimensional physiological state space between two consecutive eligible patient-days, calculated using the prespecified trajectory algorithm and reported in standardized state-space units.
|
Across consecutive eligible patient-days from ICU admission through ICU discharge, an average of approximately 5 days
|
|
Physiological State-Space Trajectory Length
大体时间：From the first through the last eligible patient-day during the ICU stay, an average of approximately 5 days
|
Cumulative path length of the participant's trajectory across consecutive positions in the PCA-derived physiological state space, calculated as the accumulated state-space displacement and reported in standardized state-space units.
|
From the first through the last eligible patient-day during the ICU stay, an average of approximately 5 days
|
|
Physiological State-Space Trajectory Speed
大体时间：Across consecutive eligible patient-days from ICU admission through ICU discharge, an average of approximately 5 days
|
Rate of change in physiological state-space position between consecutive eligible patient-days, calculated from state-space displacement over elapsed time and reported in standardized state-space units per day.
|
Across consecutive eligible patient-days from ICU admission through ICU discharge, an average of approximately 5 days
|
|
Physiological State-Space Trajectory Acceleration
大体时间：Across consecutive eligible patient-days from ICU admission through ICU discharge, an average of approximately 5 days
|
Change in physiological state-space trajectory speed between successive eligible patient-day intervals, calculated using the prespecified trajectory algorithm and reported in standardized state-space units per day squared.
|
Across consecutive eligible patient-days from ICU admission through ICU discharge, an average of approximately 5 days
|
|
Physiological State-Space Turning Angle
大体时间：Across consecutive eligible patient-days from ICU admission through ICU discharge, an average of approximately 5 days
|
Angular change in trajectory direction between successive trajectory segments derived from consecutive physiological state-space positions, reported in degrees.
|
Across consecutive eligible patient-days from ICU admission through ICU discharge, an average of approximately 5 days
|
|
Physiological State-Space Trajectory Curvature
大体时间：Across consecutive eligible patient-days from ICU admission through ICU discharge, an average of approximately 5 days
|
Curvature of the participant's physiological state-space trajectory derived from consecutive state-space positions using the prespecified trajectory algorithm.
Higher values indicate greater local directional change in the trajectory.
|
Across consecutive eligible patient-days from ICU admission through ICU discharge, an average of approximately 5 days
|
|
Local Physiological State-Space Variability
大体时间：Across consecutive eligible patient-days from ICU admission through ICU discharge, an average of approximately 5 days
|
Within-participant variability in physiological state-space position across consecutive eligible patient-days, calculated using the prespecified trajectory analysis and reported in standardized state-space units.
Higher values indicate greater short-term physiological variability.
|
Across consecutive eligible patient-days from ICU admission through ICU discharge, an average of approximately 5 days
|
|
Lag-1 Autocorrelation of Physiological State-Space Trajectory
大体时间：Across consecutive eligible patient-days from ICU admission through ICU discharge, an average of approximately 5 days
|
Lag-1 autocorrelation coefficient quantifying the correlation between consecutive physiological state-space observations within the participant's trajectory.
The coefficient ranges from -1 to 1, with higher positive values indicating greater persistence of the preceding physiological state.
|
Across consecutive eligible patient-days from ICU admission through ICU discharge, an average of approximately 5 days
|
|
Area Under the Receiver Operating Characteristic Curve for 72-Hour Composite Deterioration
大体时间：Within 72 hours following each eligible index patient-day in the temporal validation cohort
|
Discrimination of the prespecified state-space and trajectory prediction model in the temporal validation cohort, assessed using the area under the receiver operating characteristic curve (AUROC) for the 72-hour composite deterioration outcome.
AUROC ranges from 0 to 1, with higher values indicating better discrimination.
|
Within 72 hours following each eligible index patient-day in the temporal validation cohort
|
|
Calibration Slope for Predicted 72-Hour Composite Deterioration Risk
大体时间：Within 72 hours following each eligible index patient-day in the temporal validation cohort
|
Calibration of the prespecified state-space and trajectory prediction model in the temporal validation cohort, assessed using the calibration slope comparing predicted probabilities with observed 72-hour composite deterioration outcomes.
A calibration slope of 1 indicates ideal calibration.
|
Within 72 hours following each eligible index patient-day in the temporal validation cohort
|
|
Brier Score for Prediction of 72-Hour Composite Deterioration
大体时间：Within 72 hours following each eligible index patient-day in the temporal validation cohort
|
Overall prediction error of the prespecified state-space and trajectory prediction model in the temporal validation cohort, assessed using the Brier score, calculated as the mean squared difference between predicted probabilities and observed binary 72-hour composite deterioration outcomes.
The Brier score ranges from 0 to 1, with lower values indicating better predictive accuracy.
|
Within 72 hours following each eligible index patient-day in the temporal validation cohort
|
合作者和调查者
在这里您可以找到参与这项研究的人员和组织。
出版物和有用的链接
负责输入研究信息的人员自愿提供这些出版物。这些可能与研究有关。
一般刊物
- Thoral PJ, Peppink JM, Driessen RH, Sijbrands EJG, Kompanje EJO, Kaplan L, Bailey H, Kesecioglu J, Cecconi M, Churpek M, Clermont G, van der Schaar M, Ercole A, Girbes ARJ, Elbers PWG; Amsterdam University Medical Centers Database (AmsterdamUMCdb) Collaborators and the SCCM/ESICM Joint Data Science Task Force. Sharing ICU Patient Data Responsibly Under the Society of Critical Care Medicine/European Society of Intensive Care Medicine Joint Data Science Collaboration: The Amsterdam University Medical Centers Database (AmsterdamUMCdb) Example. Crit Care Med. 2021 Jun 1;49(6):e563-e577. doi: 10.1097/CCM.0000000000004916.
- Johnson AEW, Bulgarelli L, Shen L, Gayles A, Shammout A, Horng S, Pollard TJ, Hao S, Moody B, Gow B, Lehman LH, Celi LA, Mark RG. MIMIC-IV, a freely accessible electronic health record dataset. Sci Data. 2023 Jan 3;10(1):1. doi: 10.1038/s41597-022-01899-x.
- Duggal A, Scheraga R, Sacha GL, Wang X, Huang S, Krishnan S, Siuba MT, Torbic H, Dugar S, Mucha S, Veith J, Mireles-Cabodevila E, Bauer SR, Kethireddy S, Vachharajani V, Dalton JE. Forecasting disease trajectories in critical illness: comparison of probabilistic dynamic systems to static models to predict patient status in the intensive care unit. BMJ Open. 2024 Feb 6;14(2):e079243. doi: 10.1136/bmjopen-2023-079243.
- Xu Z, Mao C, Su C, Zhang H, Siempos I, Torres LK, Pan D, Luo Y, Schenck EJ, Wang F. Sepsis subphenotyping based on organ dysfunction trajectory. Crit Care. 2022 Jul 3;26(1):197. doi: 10.1186/s13054-022-04071-4.
- Soo A, Zuege DJ, Fick GH, Niven DJ, Berthiaume LR, Stelfox HT, Doig CJ. Describing organ dysfunction in the intensive care unit: a cohort study of 20,000 patients. Crit Care. 2019 May 23;23(1):186. doi: 10.1186/s13054-019-2459-9.
- Scheffer M, Bolhuis JE, Borsboom D, Buchman TG, Gijzel SMW, Goulson D, Kammenga JE, Kemp B, van de Leemput IA, Levin S, Martin CM, Melis RJF, van Nes EH, Romero LM, Olde Rikkert MGM. Quantifying resilience of humans and other animals. Proc Natl Acad Sci U S A. 2018 Nov 20;115(47):11883-11890. doi: 10.1073/pnas.1810630115. Epub 2018 Oct 29.
- Scheffer M, Carpenter SR, Lenton TM, Bascompte J, Brock W, Dakos V, van de Koppel J, van de Leemput IA, Levin SA, van Nes EH, Pascual M, Vandermeer J. Anticipating critical transitions. Science. 2012 Oct 19;338(6105):344-8. doi: 10.1126/science.1225244.
- Pollard TJ, Johnson AEW, Raffa JD, Celi LA, Mark RG, Badawi O. The eICU Collaborative Research Database, a freely available multi-center database for critical care research. Sci Data. 2018 Sep 11;5:180178. doi: 10.1038/sdata.2018.178.
研究记录日期
这些日期跟踪向 ClinicalTrials.gov 提交研究记录和摘要结果的进度。研究记录和报告的结果由国家医学图书馆 (NLM) 审查，以确保它们在发布到公共网站之前符合特定的质量控制标准。
研究主要日期
学习开始 (实际的)
2026年6月15日
初级完成 (估计的)
2027年12月31日
研究完成 (估计的)
2029年12月31日
研究注册日期
首次提交
2026年8月4日
首先提交符合 QC 标准的
2026年8月14日
首次发布 (实际的)
2026年8月19日
研究记录更新
最后更新发布 (实际的)
2026年8月19日
上次提交的符合 QC 标准的更新
2026年8月14日
最后验证
2026年8月1日
更多信息
与本研究相关的术语
其他相关的 MeSH 术语
其他研究编号
- B2026-484
计划个人参与者数据 (IPD)
计划共享个人参与者数据 (IPD)？
不
IPD 计划说明
Deidentified participant-level data will not be made publicly available because the source data are governed by institutional privacy, ethics, and information-security requirements.
The data will remain in the hospital-controlled environment.
Aggregated results, model parameters, analytic methods, or approved code may be shared where permitted by the ethics committee and institutional data-governance procedures.
药物和器械信息、研究文件
研究美国 FDA 监管的药品
不
研究美国 FDA 监管的设备产品
不
此信息直接从 clinicaltrials.gov 网站检索，没有任何更改。如果您有任何更改、删除或更新研究详细信息的请求，请联系 register@clinicaltrials.gov. clinicaltrials.gov 上实施更改，我们的网站上也会自动更新.