Rolling Day-Wise Mortality Prediction in Critically Ill Patients With AKI on CRRT Utilizing Machine Pressure Waveforms

Shehan Irteza Pranto; Joanna Yang; Joshua Lambert; Stuart L. Goldstein; Lili Chan; Girish N. Nadkarni; Tiago K. Colicchio; Javier A. Neyra

cs.LGSep 11, 2026

Rolling Day-Wise Mortality Prediction in Critically Ill Patients With AKI on CRRT Utilizing Machine Pressure Waveforms

Authors: Shehan Irteza Pranto, Joanna Yang, Joshua Lambert, Stuart L. Goldstein, Lili Chan, Girish N. Nadkarni, Tiago K. Colicchio, Javier A. Neyra,

Organizations: Department of Biomedical Informatics and Data Science, University of Alabama at Birmingham, AL, USA · Windreich Department of Artificial Intelligence and Human Health at the Icahn School of Medicine at Mount Sinai, New York, NY, USA · College of Nursing, University of Cincinnati, OH, USA · Department of Pediatrics, University of Cincinnati, OH, USA ·

Abstract

Critically ill patients with acute kidney injury (AKI) on continuous renal replacement therapy (CRRT) face high mortality, yet current risk assessment relies primarily on clinical parameters from electronic health records (EHR) and ignores minute-level circuit pressure waveforms generated by CRRT machines that track the extracorporeal circuit's interaction with the patient. Clinicians therefore cannot see deterioration as it develops. Risk is reassessed only when labs are drawn, while this continuous record is discarded because it is contaminated by shared-device records, non-physiological minutes, and sensor artifacts. To make the stream usable, we aligned machine records to charted therapy intervals to prevent cross-patient leakage, removed priming and downtime minutes, tuned denoising on a synthetic spike-injection benchmark, and masked unobserved intervals rather than imputing them. On this cleaned stream, we define a rolling day-wise task and a transformer-based stacked ensemble that late-fuses a window-reduced sequence transformer with classical models using circuit-instability features and clinical EHR variables. In a leak-safe benchmark on the multi-center CRRTnet cohort (976 patients, 4,585 treatment days), the machine-only model had the lowest standalone prognostic value (AUROC 0.625), followed by the EHR-only model (0.717). Integrating EHR and machine streams reached a one-day mortality AUROC of 0.766. SHAP attribution showed that circuit-instability descriptors raised the machine share of the top 15 combined-model features from 3 to 7 (20.0% to 46.7%), highlighting filter pressure, transmembrane pressure (TMP), and access-to-return difference (ARD). To our knowledge, this is the first patient-level mortality prediction incorporating CRRT machine data, turning a discarded bedside stream into a continuous risk signal.

Figures & tables

Fig. 1: Rolling day-wise prediction framework. The window advances one day at a time ( $t{-}3,\dots,t$ ). Each treatment day defines a model-input window (dark), separated from the prediction horizon (green) by an excluded gap window (red) to guarantee causal, prospective risk estimates.

Variable	Survivors ( $n{=}451$ )	Non-surv. ( $n{=}525$ )	$p$
Age (Years)	57.0 [48.0–67.0]	63.0 [55.0–70.2]	$<$ .001
Sex (Male)	205 (58.7%)	238 (63.3%)	.237
BMI, kg/m 2	30.1 [25.2–36.6]	29.7 [25.2–36.1]	.944
Charlson score	2.0 [1.0–3.0]	2.0 [1.0–4.0]	$<$ .001
APACHE-II (part.)	9.0 [5.0–25.0]	13.0 [5.0–25.0]	.037

TABLE I: Patient baseline characteristics by in-hospital mortality.

Fig. 2: Signal-processing pipeline (top) and evaluation (bottom). The raw pressure stream is temporally aligned to clinical events, stripped of priming and downtime minutes, and denoised. The denoising operating point is optimized on a synthetic spike-injection benchmark (5% corruption): grid searches over detection parameters (window length, standard-score threshold) and smoothing configurations (neighbor count, mean/median aggregation) maximize spike-localization

F_{1}

and minimize reconstruction error (MAE, MSE).

Family	Features	/ch.	Ch.	N
Base set (133): distribution and within-day dynamics
Distribution	mean, std, min, max, median, q25/q75, IQR, range, skew, kurtosis, coefficient of variation, valid-minute count	13	7	91
Temporal	slope, trend $R^{2}$ , mean $\|\Delta\|$ , max jump, lag-1 autocorr., excursion frac.	6	7	42
Base subtotal				133
Enriched circuit-instability set (67)
Spectral	entropy, low/high band power, dominant period [ 27 ]	4	7	28

TABLE II: Taxonomy of engineered machine features. Pipelines use the full 200, reduced by mRMR to the selected machine budget (40 in the deployed model).

Fig. 3: Two-level stacked ensemble. (A) Each denoised treatment day yields a $144{\times}30$ window-reduced machine sequence (gap windows masked) and a 60-d mRMR clinical vector. (B) A Transformer encoder with a [CLS] token encodes the sequence, an MLP branch encodes the clinical vector, and a fusion head over the concatenated embeddings yields $P_{\text{DL}}$ . (C) Classical learners on the 100-d grouped-mRMR vector (40 machine $+$ 60 clinical) emit $P_{1},\dots,P_{K}$ , ranked by validation AUROC. (D) A logistic-regression meta-learner, fit on validation, combines the four probabilities into $P_{\text{stack}}$ , thresholded at the validation max- $F_{1}$ point.

Fig. 4: Peak-detection performance on CRRT pressure waveforms. (a) Precision, recall, and $F_{1}$ for the best outlier-detection model at each window length $L$ ( $F_{1}$ peaks at $L=40$ , $F_{1}=0.850$ ). (b) Reconstruction error for smoothing variants at $L=40$ (mean $N=2$ is lowest, RMSE $9.14$ ).

Fig. 5: Held-out test AUROC of the Windowed-Transformer Fusion Stack across the grouped-mRMR feature budget ( $n_{\mathrm{machine}}\times n_{\mathrm{clinical}}$ ). The red box marks the validation-selected optimum, $40$ machine $\times$ $60$ clinical.

Fig. 6: Training and validation loss curves for the deployed combined fusion model (one-day mortality, class-weighted BCE, mean over five seeds with shaded range). The small train–validation gap indicates effective regularization; curves are truncated at the early-stopping patience limit.

Clinical-only
	Full (imbalanced) test					Balanced 1:1		Balanced 1:2
Model	AUROC	AUPRC	F1	Prec.	Rec.	AUROC	AUPRC	AUROC	AUPRC
Clinical MLP	0.710	0.177	0.242	0.229	0.258	0.717	0.716	0.712	0.561
Machine-only
CNN1D a [ 32 ]	0.579	0.095	0.026	0.071	0.016	0.575	0.585	0.579	0.415
RNN (BiLSTM/GRU) a [ 33 ]	0.584	0.094	0.159	0.098	0.419	0.583	0.583	0.585	0.412

TABLE III: Deep-learning benchmark across clinical only, machine only and combined pipeline.

Clinical-only
	Full (imbalanced) test					Balanced 1:1		Balanced 1:2
Model	AUROC	AUPRC	F1	Prec.	Rec.	AUROC	AUPRC	AUROC	AUPRC
LogReg	0.710	0.222	0.264	0.232	0.306	0.714	0.726	0.710	0.583
DecisionTree	0.617	0.117	0.215	0.177	0.274	0.614	0.608	0.614	0.444
RandomForest	0.711	0.233	0.239	0.173	0.387	0.713	0.731	0.709	0.589
GradBoost	0.717	0.209	0.277	0.203	0.435	0.720	0.721	0.716	0.575

TABLE IV: Classical benchmark across all three pipelines (one-day horizon; per-day, current denoised). Full imbalanced test with prevalence-balanced 1:1 and 1:2 resamples (mean of 100). Threshold

=

max-

F_{1}

on validation. Feature budget: clinical-only

=

60 clinical, machine-only

=

40 machine, combined

=

40 machine

+

60 clinical (grouped-mRMR).

Cumulative configuration ladder (windowed-Transformer encoder)
Configuration	AUROC
Raw signal	0.737
+ Enriched features (feature set)	0.730
+ Priming & downtime removal	0.747
+ Peak removal (full preprocessing)	0.766
Sequence encoder (full preprocessing)

TABLE V: Ablation of the deployed combined model (1-day; 40 machine

\times

60 clinical grouped-mRMR features), along two axes: signal preprocessing and sequence encoder. Held-out test AUROC; best in bold .

Combined model	Best rank	top-5	top-10	top-15	% top-15
Base	5	1	2	3	20.0
Enriched	2	1	5	7	46.7

TABLE VI: Machine features in the combined-model SHAP ranking: counts among the top-5/10/15 by mean

|\text{SHAP}|

, and the machine share of the top-15. Enriched

=

deployed optimal model (40 machine

+

60 clinical grouped-mRMR).

Fig. 7: SHAP beeswarm (top-15 by mean $|$ SHAP $|$ ) for the Windowed-Transformer Fusion Stack, attributed via its Random-Forest tabular backbone. Red-boxed labels mark CRRT machine descriptors; positive values increase predicted mortality risk.

Time Series Modeling

See all 51 papers

A Leakage-Aware Multimodal Evaluation Framework for Early Intraoperative Acute Kidney Injury Prediction
Sep 22, 2026Quang Minh Nguyen, Duc Minh Le, Ho Nhat Minh Nguyen +2Temporal Convolutional Networks Clinical Prediction
National Economics University, Hanoi, Vietnam
A Data-Driven Approach to Support Clinical Renal Replacement Therapy
Feb 26, 2026Alice Balboni, Luis Escobar, Andrea Manno +5Healthcare Clinical Risk Prediction
Department of Applied Science and Technology Politecnico di Torino Turin, Italy · Department of Inf. Eng., Computer Science and Mathematics University of L’Aquila L’Aquila, Italy · Dipartimento di Scienze della Salute University of Florence Florence, Italy +1
Causal-Transformer with Adaptive Mutation-Locking for Early Prediction of Acute Kidney Injury
Apr 22, 2026Weizhi Nie, Haolin ChenCausal Interpretability Longitudinal EHR Modeling
School of Electrical and Information Engineering, Tianjin University

Sep 22, 2026J/K move · Enter open · S save

A Leakage-Aware Multimodal Evaluation Framework for Early Intraoperative Acute Kidney Injury Prediction

Quang Minh Nguyen, Duc Minh Le, Ho Nhat Minh Nguyen, Thuy Quynh Nguyen+1

National Economics University, Hanoi, Vietnam

Temporal Convolutional Networks Clinical Prediction Clinical Risk Prediction

Open paper AskPDF arXiv

Postoperative acute kidney injury (AKI) after major non-cardiac surgery carries substantial morbidity, yet early intraoperative risk stratification remains difficult. In this retrospective cohort study, we propose SynerT, a waveform-only hybrid temporal backbone that combines a causal dilated TCN with a hierarchy of dilated recurrent layers to encode early intraoperative physiologic trajectories for AKI risk prediction. Building on SynerT, we further design two model variants that extend the backbone with structured clinical context: SynerT-MM, a late-fusion multimodal extension that integrates hemodynamic burden summaries and preoperative covariates, and SynerTStack, a leakage-safe stacked ensemble that combines cross-validated predictions from SynerT-MM with strong tabular baselines at the meta-learning stage. All models are evaluated under a strict leakage-aware framework on VitalDB, a high-fidelity perioperative database, with prediction restricted to information available within the first 60 intraoperative minutes. Among 2,413 waveform-usable cases (180 AKI-positive; 7.46% prevalence), SynerT fell well below strong structured-data baselines, demonstrating that waveform-only temporal modeling is insufficient under strict early constraints. SynerTMM recovered discrimination by incorporating hemodynamic burden summaries and preoperative covariates, and SynerT-Stack achieved the best overall performance across AUROC, AUPRC, and F1-max. Cross-fitted Platt recalibration substantially corrected calibration defects in both multimodal variants, and decision-curve analysis confirmed the recalibrated stacked model delivered the strongest net clinical benefit across low-to-intermediate thresholds.

Abstract

Time Series Modeling

Explore similar work

A Leakage-Aware Multimodal Evaluation Framework for Early Intraoperative Acute Kidney Injury Prediction

A Data-Driven Approach to Support Clinical Renal Replacement Therapy

Causal-Transformer with Adaptive Mutation-Locking for Early Prediction of Acute Kidney Injury