Back

From Code to Critical Care Time: Implementing an AI-Driven ICU Length-of-Stay Clinical Decision Support System Under European Governance Constraints

Althammer, A.; Hummel, A.; Steghoefer, J.-P.; Reichel, F.; Kolonko, J.; Hartfield, S.; Fischer, M.; Schloegl-Flierl, K.; Ziethmann, P.; Weiss, M.; Simon, P.; Moegerlein, M.; Mamtschur, E.; Spring, O.; Shmygalev, S.; Ortmann, N.; Raffler, J.; Hinske, L. C.; Brunner, J. O.; Heller, A. R.; Bartenschlager, C.

2026-02-05 intensive care and critical care medicine
10.64898/2026.02.04.26345355
Show abstract

BackgroundML models in critical care often perform well retrospectively but deliver limited bedside value once deployed under European governance constraints. ObjectiveEvaluate feasibility and early sociotechnical lessons from an offline Clinical Decission Support System (CDSS) predicting ICU LoS on a surgical ICU in practice MethodsWe conducted a prospective implementer study. Residents used AI and recorded estimates (n=136), consultants provided blinded estimates (n=162), AI outputs were logged (n=221). Version 1 showed LoS prediction, Version 2 updated the model and added a compact feature importance panel by using TreeSHAP. Human factors were assessed with Psychological Assessment of AI-based Decision Support (PAAI) and an embedded ethicist informed design and onboarding. Ethics Projekt.Nr 24-0336-KB, registry: DRKS00037851. ResultsOffline deployment was feasible but caused coordination burden. Version 2 reduced MAE for AI (5.80[-&gt;]4.92) and resident+AI estimates (6.18[-&gt;]3.84; both p<0.05). PAAI identified user groups. ConclusionsEarly embedding exposed governance-driven costs and highlighted iterative upgrading to address the translation gap.

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

1
BMJ Open
based on 553 papers
Top 8%
12.5%
2
PLOS ONE
based on 1737 papers
Top 58%
7.6%
3
JAMA Network Open
based on 125 papers
Top 2%
7.6%
4
PLOS Digital Health
based on 88 papers
Top 3%
5.3%
5
Journal of General Internal Medicine
based on 19 papers
Top 0.5%
4.5%
6
Frontiers in Public Health
based on 135 papers
Top 7%
4.5%
7
Journal of the American Medical Informatics Association
based on 53 papers
Top 3%
4.5%
8
npj Digital Medicine
based on 85 papers
Top 5%
4.5%
50% of probability mass above
9
F1000Research
based on 28 papers
Top 0.4%
2.9%
10
Frontiers in Medicine
based on 99 papers
Top 5%
2.9%
11
Critical Care Explorations
based on 15 papers
Top 0.7%
2.9%
12
BMC Medical Informatics and Decision Making
based on 36 papers
Top 4%
2.8%
13
Journal of Biomedical Informatics
based on 37 papers
Top 3%
2.4%
14
Trials
based on 24 papers
Top 1%
2.4%
15
BMJ
based on 49 papers
Top 4%
1.6%
16
Journal of Clinical Medicine
based on 77 papers
Top 10%
1.6%
17
JAMIA Open
based on 35 papers
Top 4%
1.6%
18
BMC Public Health
based on 148 papers
Top 18%
1.3%
19
DIGITAL HEALTH
based on 11 papers
Top 1%
1.3%
20
British Journal of Anaesthesia
based on 13 papers
Top 2%
1.3%
21
Wellcome Open Research
based on 34 papers
Top 2%
1.3%
22
JMIR Formative Research
based on 31 papers
Top 4%
1.3%
23
BMJ Open Quality
based on 15 papers
Top 2%
1.3%
24
Journal of Medical Internet Research
based on 81 papers
Top 12%
1.2%
25
JMIR Public Health and Surveillance
based on 45 papers
Top 11%
0.8%
26
JMIR Research Protocols
based on 18 papers
Top 3%
0.8%
27
Healthcare
based on 14 papers
Top 3%
0.8%
28
Scientific Reports
based on 701 papers
Top 84%
0.8%
29
BMC Medicine
based on 155 papers
Top 25%
0.7%
30
Applied Sciences
based on 10 papers
Top 2%
0.7%