# Certified AI Triage of ICU Alarms

arXiv: https://arxiv.org/abs/2609.12365 · HTML: https://mlsanity.com/paper/2609.12365/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 32 references that are in the map.
- First posted on arXiv 11 Sep 2026.

## Builds on (most cited first, 9 of 9)

- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [Measuring Calibration in Deep Learning](https://mlsanity.com/paper/1904.01685/) (2019)
- [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://mlsanity.com/paper/1611.06455/) (2016)
- [Conformal Risk Control](https://mlsanity.com/paper/2208.02814/) (2022)
- [Distribution-Free, Risk-Controlling Prediction Sets](https://mlsanity.com/paper/2101.02703/) (2021)
- [Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control](https://mlsanity.com/paper/2110.01052/) (2021)
- [Are Multimodal Transformers Robust to Missing Modality?](https://mlsanity.com/paper/2204.05454/) (2022)
- [Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection](https://mlsanity.com/paper/2409.15844/) (2024)
- [QualityFM: a Multimodal Physiological Signal Foundation Model with Self-Distillation for Signal Quality Challenges in Critically Ill Patients](https://mlsanity.com/paper/2509.06516/) (2025)

## Abstract (arXiv)

In the VTaC benchmark 71% of ventricular-tachycardia alarms are false, but silencing a real one can delay recognition of a dangerous arrhythmia. We reframe alarm reduction as three-way triage (retain, suppress, or defer) and bound the decision this analysis treats as harmful: among suppressed alarms, the fraction that were genuine stays below a user-set budget with 95% confidence, under i.i.d. event sampling. Alarms sharing a waveform record are dependent, so the clustered analysis is a sensitivity check. On the official split a 5% budget certifies in all three seeds, suppressing 74.8% of false alarms while silencing 1.5% of genuine ones, at AUROC 0.953 and Challenge Score 83.33, numerically comparable to the strongest of the eleven published systems. Our central finding measures what multiplicity costs: the correction charges for every candidate, so a finer grid can certify strictly less. Under held-out calibration the 885-cell grid we declared certifies 1 of 15 fold-runs, while choosing the grid on a separate selection partition certifies 8. We project the calibration volume each budget needs, making an uncertifiable budget a design parameter. Finally, adding a learned reliability dimension to the policy grid did not sharpen the certified frontier.