cs.LGOct 30, 2026

Physiological Trajectories and Observation Patterns in ICU Mortality Prediction: Transportability Under Changing Measurement Conditions

Authors: Benjamin T. Pike

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Objective: To distinguish the transferable predictive value of physiological trajectories from that of observation patterns in ICU mortality prediction, and to assess whether measurement timing affects performance independently of observation quantity. Materials and Methods: In-hospital mortality was predicted at 48 hours using MIMIC-III, MIMIC-IV, and eICU. Nested representations progressively integrated latest-value snapshots (R1), longitudinal physiological summaries (R2), and measurement frequency and timing features (R3). Models fitted on 7,762 MetaVision patients were evaluated on 21,682 MIMIC-IV patients and 43,878 eICU patients across 204 hospitals. The effect of measurement timing was assessed while holding the number of retained observations constant. Results: Physiological trajectories improved external prediction in eICU (R2-R1 log-loss difference -0.00922, 95% CI -0.01148 to -0.00704). Observation-pattern features improved locally developed eICU models (R3-R2 -0.00257, 95% CI -0.00370 to -0.00146), but not clearly after transfer from MetaVision (-0.00012, 95% CI -0.00206 to +0.00208). R3 was favoured in 10 of 30 source bootstrap refits. At matched observation counts, retaining measurements spread throughout the window reduced log loss relative to random retention by 0.03280 for R3 versus 0.00703 for R2. Removing the final 12 hours increased log loss relative to count-matched random removal by 0.01947 for R3 versus 0.00822 for R2. Under reduced availability, the local R3 increment changed from beneficial to harmful. Discussion: Physiological trajectories transferred more consistently, while observation-pattern features were particularly sensitive to the timing and availability of measurements. Conclusion: Clinical prediction models should be evaluated not only in new patient populations but also under the measurement conditions that supply their inputs.

Figures & tables

CohortPatientsDeaths (%)AgeFemaleHospitals
CareVue12,5181,733 (13.8)67 (53–78)5,4881
MetaVision7,7621,005 (12.9)66 (54–79)3,4851
MIMIC-IV21,6822,978 (13.7)67 (56–77)9,3871
eICU43,8785,393 (12.3)66 (55–77)19,909204
Table 1: Eligible MIMIC cohorts and the eICU evaluation population. Age is reported as median (interquartile range) in years. CareVue, MetaVision, and MIMIC-IV relate to the same institution. Seven eICU test records have sex outside the female/male categories shown. The separate 10,909-patient adaptation population is not included.
TierInterpretationMIMICSharedInformation added
R0Baseline1010Static inputs and latest values of six physiological variables.
R1Snapshot4342Additional scalar values, urine output, and ventilation indicators.
R2Trajectory335334Physiological severity, trend, and variability summaries.
R3Observation patterns524514Measurement frequency, timing, and observation-pattern summaries.
R4Rich summary940918Additional physiological and observation summaries.
Table 2: Nested information representations. Feature counts are reported before categorical variables are expanded during encoding. Shared counts indicate the subset retained after harmonisation between MetaVision and eICU.
CohortModelLog lossAUROCBrierInterceptSlope
MIMIC-IVR10.295890.851400.089700.2981.196
R20.282910.872580.086590.5461.272
R30.275190.880260.084310.5041.265
eICUR10.301160.806660.08895-0.0891.055
R20.291940.823970.086160.0431.141
R30.291820.822920.086700.0471.078
Table 3: External performance of MetaVision-trained models in MIMIC-IV (n = 21,682) and eICU (n = 43,878). Results use uncalibrated predictions, with negative paired log-loss differences favouring the richer representation. Unadjusted 95% CIs use patient bootstrapping for MIMIC-IV and hospital bootstrapping for eICU.
Figure 1: Incremental value of physiological trajectories (R2–R1; A) and observation patterns (R3–R2; B) across evaluation settings. Points show patient-weighted log-loss differences with 95% paired-bootstrap CIs, using patient resampling for MIMIC and hospital resampling for eICU. Negative differences favour the richer representation.
Figure 2: External eICU effects of observation timing at matched observation counts. A: most recent observations versus random retention. B: observations spread through the window versus random retention. C: final 12-hour outage versus matched random removal. Negative differences favour recent or spread retention, while positive outage differences indicate worse performance. Points show patient-weighted log-loss differences averaged across restriction iterations, with 95% hospital-bootstrap CIs.
Figure 3: Local eICU effects of changing observation availability. A: R2–R1 and R3–R2 differences when models trained on complete records are evaluated on complete or restricted records. B: R3–R2 differences before and after restriction-matched recalibration using a separate calibration cohort. Points show patient-weighted log-loss differences averaged across allocations, with 95% hospital-bootstrap CIs.
More in this topic

Clinical Prediction

Clinical prediction uses patient records, signals, and images to estimate diagnoses, risks, outcomes, and treatment responses for care.

See all 213 papers

Explore similar work

CardsList
Mar 16, 2026

Multimodal Deep Learning for Early Prediction of Patient Deterioration in the ICU: Integrating Time-Series EHR Data with Clinical Notes

Early identification of patients at risk for clinical deterioration in the intensive care unit (ICU) remains a critical challenge. Delayed recognition of impending adverse events, including mortality, vasopressor initiation, and mechanical ventilation, contributes to preventable morbidity and mortality. We present a multimodal deep learning approach that combines structured time-series data (vital signs and laboratory values) with unstructured clinical notes to predict patient deterioration within 24 hours. Using the MIMIC-IV database, we constructed a cohort of 74,822 ICU stays and generated 5.7 million hourly prediction samples. Our architecture employs a bidirectional LSTM encoder for temporal patterns in physiologic data and ClinicalBERT embeddings for clinical notes, fused through a cross-modal attention mechanism. We also present a systematic review of existing approaches to ICU deterioration prediction, identifying 31 studies published between 2015 and 2024. Most existing models rely solely on structured data and achieve area under the curve (AUC) values between 0.70 and 0.85. Studies incorporating clinical notes remain rare but show promise for capturing information not present in structured fields. Our multimodal model achieves a test AUROC of 0.7857 and AUPRC of 0.1908 on 823,641 held-out samples, with a validation-to-test gap of only 0.6 percentage points. Ablation analysis validates the multimodal approach: clinical notes improve AUROC by 2.5 percentage points and AUPRC by 39.2% relative to a structured-only baseline, while deep learning models consistently outperform classical baselines (XGBoost AUROC: 0.7486, logistic regression: 0.7171). This work contributes both a thorough review of the field and a reproducible multimodal framework for clinical deterioration prediction.

Binesh Sadanandan

Clinical Risk PredictionLongitudinal EHR ModelingMultimodal Learning
AskPDF
Jul 28, 2026

DRIFT: Direct-Recursive Intervention-Conditioned Forecasting of ICU Physiological Trajectories

Many time-series forecasts depend not only on prior observations but also on actions specified during the forecast period. In intensive care units (ICUs), future vital signs and laboratory values are influenced by treatments such as vasopressors. However, models that predict the full future sequence all at once make little use of these treatments, whereas autoregressive models can accumulate errors. We introduce DRIFT, a hybrid framework in which a direct model produces the primary forecast and a recursive, action-conditioned model contributes constrained corrections. We evaluate DRIFT on 6,046 admissions from MIMIC-IV and 8,345 admissions from eICU-CRD. Averaged across the 8-, 24-, and 48-hour forecast endpoints, DRIFT reduces mean absolute error for mean arterial pressure (MAP) by 0.673% relative to an action-conditioned Temporal Fusion Transformer (TFT-action) on MIMIC-IV and achieves the lowest corresponding error among the compared models on eICU-CRD. Although the overall accuracy improvement is modest, a MIMIC-IV audit restricted to windows in which the supplied treatment sequence was altered showed that DRIFT achieved lower observed-target MAP error than TFT-action at 8 and 24 hours. Treatment-sequence alteration increased DRIFT's MAP error by 0.21-0.26 mmHg more than it increased TFT-action's error, with prediction changes occurring primarily after the supplied paths diverged. In a separate robustness experiment, the MAP advantage persisted under three shared checkpoint-selection rules emphasizing overall endpoint error, MAP error, or both equally.

Weixin Liu, Juming Xiong, Congning Ni +4

Vanderbilt University, Nashville, Tennessee, USA · Vanderbilt University Medical Center, Nashville, Tennessee, USA

Multivariate Time Series ForecastingTime Series ForecastingLongitudinal EHR Modeling
AskPDF
Aug 29, 2026

Predicting Future Organ Dysfunction in ICU Patients Using Temporal Convolutional Networks on MIMIC-IV Data

Predicting future organ dysfunction in Intensive Care Unit (ICU) patients is critical for early clinical intervention, yet existing machine learning approaches have largely treated the Sequential Organ Failure Assessment (SOFA) score as an input to binary mortality prediction rather than as a continuous clinical outcome in its own right. We investigate the extent to which a Temporal Convolutional Net work (TCN) can predict next-day SOFA scores from multivariate ICU time-series data extracted from MIMIC-IV, characterise the relative contribution of each organ system to total SOFA variance and deterioration, and identify distinct trajectory patterns across ICU stays. A residual TCN trained on three-day sliding windows achieved a five-fold cross-validation R2 of 0.740 +- 0.013 and MAE of 1.431 +- 0.022, outperforming a naive persistence baseline on RMSE and R2. SHAP interpretability analysis revealed that the model functions primarily as a severity-anchoring mechanism rather than a true sequence model, with predictions dominated almost entirely by the most recent observation day. Cardiovascular dysfunction emerged as the strongest discriminator of both cross-sectional severity and acute deterioration, and unsupervised trajectory clustering identified two clinically meaningful phenotypes, an improving group (58.9%) and a persistently severe group (41.1%), differentiated by cardiovascular, hepatic, coagulation, and renal involvement. We conclude that TCNs can extract meaningful predictive signal from ICU physiological data, but that short input windows and complete-case selection bias currently limit their clinical utility, motivating future work on longer input horizons, alternative missing-data strategies, and external validation.

Razan Albouq, Asra Aslam

University of Sheffield, UK

Clinical Outcome PredictionTemporal Convolutional Networks
AskPDF