Forecasting cumulative intraoperative hypotension burden: patient-disjoint evaluation of quantile boosting and alert policies

Yunfan Zhao

cs.AINov 6, 2026

Forecasting cumulative intraoperative hypotension burden: patient-disjoint evaluation of quantile boosting and alert policies

Authors: Yunfan Zhao

Organizations: GE Healthcare

Abstract

Background: Binary hypotension forecasts do not describe the depth and duration of future low pressure. Burden forecasts may support graded early warning, but better forecast scores need not yield more useful alerts. Objective: To evaluate conditional quantiles of the next 15-minute mean arterial pressure (MAP) deficit below 65 mmHg and distinguish forecasting performance from episode-warning performance. Methods: Public VitalDB numeric arterial MAP was reduced to 10-second medians without forward filling. Subject-disjoint training, validation and test splits included 70,402, 14,270 and 15,575 labeled windows. We compared climatology, calibrated persistence, last-MAP-only boosting, and direct and residual quantile boosting, with and without additional MAP-history features. Patient-weighted pinball loss and subject-bootstrap intervals evaluated forecasting. Validation selected alert thresholds before a hash-recorded test evaluation. Results: In the test split, the prespecified residual-versus-persistence comparison at the 90th percentile yielded losses of 2.256 and 2.900 mmHg-min, respectively (difference -0.644; 95% interval -0.814 to -0.487). Direct prediction achieved 2.196, and direct prediction with additional MAP features achieved 2.193. Episode-warning results were sensitive to the alert rule and operating threshold. Conclusions: This retrospective benchmark separates burden-forecast skill from warning-policy performance. Findings support further study of direct burden estimation; they do not establish patient benefit, prospective reliability or transportability beyond the source hospital.

Figures & tables

Split	Cases	Subjects	Windows	Positive
Train	2,395	2,307	70,402	23,473
Validation	505	491	14,270	4,689
Test	523	506	15,575	4,924

Table 1: Reconstructed labeled-window cohort. Positive windows have burden greater than zero; overlapping windows are not independent events.

Split	Episodes	Opportunities	Subjects
Train	6798	2762	1135
Validation	1362	535	240
Test	1472	589	242

Table 2: Operational episodes and eligible warning opportunities under the corrected run and censoring rules.

Model	Val. $q_{.90}$	Val. $q_{.95}$	Test $q_{.90}$	Test $q_{.95}$
Climatology	4.500	3.635	4.458	3.621
Calibrated persistence	2.910	2.240	2.900	2.262
Last MAP only	2.552	1.902	2.538	1.908
Direct, base features	2.239	1.590	2.196	1.596
Residual, base features	2.295	1.640	2.256	1.636
Direct, additional MAP	2.205	1.562	2.193	1.588

Table 3: Patient-weighted pinball loss (mmHg

\cdot

min). Validation informed development; test was evaluated after the analysis freeze.

Model	Onset loss	No-jump loss	$P(B<Q)$ %	$P(B\leq Q)$ %
Calibrated persistence	3.018	2.552	90.6	90.7
Last MAP only	2.595	2.249	90.9	90.9
Direct, base features	2.275	1.837	90.7	91.2
Residual, base features	2.267	1.923	90.8	91.2
Direct, additional MAP	2.252	1.811	90.8	91.3
Residual, additional MAP	2.255	1.897	90.9	91.3

Table 4: Test sensitivities and patient-weighted coverage for the 90th-percentile head. The jump restriction is retrospective.

Figure 1: Patient-weighted test pinball losses. Lower is better. All models were fitted on training data only; full bootstrap contrasts are supplied with the analysis.

Score	Rule	Sens. %	Prec. %	False/h	Alerts/h	Turns/h
Persistence score	Threshold	1.9	1.6	0.03	0.46	0.91
Persistence score	2-origin	0.0	–	0.00	0.00	0.00
Persistence score	Hysteresis	1.9	1.6	0.03	0.44	0.89
Direct base	Threshold	13.4	9.7	0.16	0.53	1.06
Direct base	2-origin	16.3	14.3	0.23	0.44	0.87
Direct base	Hysteresis	13.8	11.7	0.19	0.45	0.91

Table 5: Test alert results at the validation budget of 0.25 unmatched alerts per decision-exposure hour. False rates and total activation rates are distinct.

Figure 2: Test sensitivity and achieved unmatched-alert rate for validation-selected policies using direct prediction with additional MAP history. Points correspond to the three validation budgets; connecting lines aid identification and do not imply a continuous estimated frontier.

Clinical Prediction

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

See all 220 papers

Pharmacokinetic State Space Models for Unbiased Prediction of Haemodynamic Collapse
Sep 21, 2026Rithin Nagaraj, Sudiksha Chindula, Bhaskarjyoti DasClinical Prediction Clinical Risk Prediction
Department of Computer Science and Engineering, PES University, Bengaluru, 560085, India · Department of Computer Science and Engineering (AIML), PES University, Bengaluru, 560085, India
From Prediction to Practice: A Task-Aware Evaluation Framework for Blood Glucose Forecasting
May 1, 2026Alireza Namazi, Heman ShakeriHealthcare Clinical Decision Support
Department of Computer Science University of Virginia Charlottesville, VA, USA · School of Data Science University of Virginia Charlottesville, VA, USA
Online Quantile Omniprediction for Proper Losses
Oct 15, 2026Hyunsuk Kim, Isaac Gibbs, Michael W. Mahoney +1Probabilistic Forecasting Quantile Regression
Department of Statistics, University of California, Berkeley · Department of Statistics, University of Toronto · ICSI, LBNL, and Dept. of Statistics, University of California, Berkeley

Sep 21, 2026J/K move · Enter open · S save

Pharmacokinetic State Space Models for Unbiased Prediction of Haemodynamic Collapse

Rithin Nagaraj, Sudiksha Chindula, Bhaskarjyoti Das

Department of Computer Science and Engineering, PES University, Bengaluru, 560085, India · Department of Computer Science and Engineering (AIML), PES University, Bengaluru, 560085, India

Clinical Prediction Clinical Risk Prediction State Space Models

Open paper AskPDF arXiv

An Intraoperative Hypotension (IOH) event is a frequent complication during administration of general anaesthesia with serious downstream consequences, yet clinical management remains reactive and not predictive. Existing predictive models, however, ignore drug infusion history as a valuable signal for prediction despite its direct pharmacological relevance. Our model achieves an Area Under the Receiver Operating Characteristic curve (AUROC) of 0.7360 and an Area Under the Precision-Recall Curve (AUPRC) of 0.1794, representing a 2.73-fold lift over the random guessing AUPRC baseline (0.0657), with the removal of propofol and remifentanil effect-site concentrations resulting in a 13.9% AUPRC drop compared to the full model. This is consistent with the hypothesis that pharmacokinetic trajectories encode impending haemodynamic changes before they manifest in the Mean Arterial Pressure (MAP). Additionally, this paper shows that training without lead-gap filtering degraded AUROC by 16.7%, empirically confirming that unfiltered models learn to detect ongoing hypotension rather than predict future events. Finally, a Mamba-based architecture achieves the aforementioned high prediction performance while maintaining a constant memory footprint across a range of sequence lengths, unlike the quadratic VRAM overhead typical of vanilla Transformers, making it the more practical choice for continuous intraoperative deployment.

Abstract

Clinical Prediction

Explore similar work

Pharmacokinetic State Space Models for Unbiased Prediction of Haemodynamic Collapse

From Prediction to Practice: A Task-Aware Evaluation Framework for Blood Glucose Forecasting

Online Quantile Omniprediction for Proper Losses