Value of AI in Critical Care Using Real-World Evidence on Intensive Care Unit Mortality Prediction: Cost-Utility Analysis
Value von KI in der Intensivmedizin anhand von Real-World-Evidence zur Mortalitätsvorhersage auf der Intensivstation: Kosten-Nutzen-Analyse
Journal of Medical Internet Research · 18.08.2026 · 28 · e93466-e93466
DOI: 10.2196/93466 ↗Auf einen Blick
Eine Modellstudie ergab für eine KI-gestützte Mortalitätsvorhersage auf der Intensivstation eine ICER von 8,37 Millionen KRW pro QALY und damit unter dem WTP-Schwellenwert in Korea.
Fragestellung
Wie kosteneffektiv ist eine KI-basierte Mortalitätsvorhersagestrategie bei ICU-Aufnahme in Korea?
Methode
Lebenszeit-Markov-Modell mit hypothetischer Kohorte koreanischer Erwachsener ab 19 Jahren; Deterministische und probabilistische Sensitivitätsanalysen.
Ergebnisse
Die KI-gestützte Strategie ergab eine ICER von 8,37 Millionen KRW (ca. US $6200) pro QALY. Die Wahrscheinlichkeit der Kosteneffektivität bei 40 Millionen KRW lag bei 83,94 %.
Einschränkungen
Modellannahmen; keine direkte Evidenz, dass das KI-System die ICU-Mortalität bei realen Patient:innen senkt.
Schlussfolgerung der Autor:innen
Unter Modellannahmen zeigte die KI-gestützte ICU-Mortalitätsvorhersage Potenzial für Kosteneffektivität gegenüber der Regelversorgung.
Kernaussagen
- ICER: 8,37 Millionen KRW pro QALY
- 83,94 % Wahrscheinlichkeit der Kosteneffektivität bei 40 Millionen KRW
- Autor:innen betonen den Modellcharakter der Ergebnisse
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift Journal of Medical Internet Research, online erschienen am 18.08.2026. Verfasst von Gyeong Min Lee und 8 weiteren Autor:innen. Beteiligte Einrichtung: Research Institute for Healthcare Policy, Dankook University, Dandae-ro 119, Cheonan, Chungcheongnam-do, 31116, Republic of Korea, 82 10-8438-8353. Hauptthemen laut MEDLINE: Intensive Care Units, Predictive Learning Models, Cost-Benefit Analysis, Critical Illness. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Themen: Intensivpflege
Abstract (Originalsprache)
Background
AI-based models for predicting mortality have shown potential for intensive care unit (ICU) patients, but evidence regarding their cost-effectiveness remains limited.
Objective
This study aimed to evaluate the population-level cost-utility of an AI-based mortality prediction strategy activated during ICU admission in Korea.
Methods
A lifetime Markov model followed a hypothetical cohort of Korean adults from age 19 years in the general-population state to capture ICU admissions, including recurrent ICU admissions, occurring over the lifetime horizon. AI-based mortality risk monitoring and its implementation cost were applied only when an individual entered the ICU state. Model inputs were derived from national claims data, published utility estimates, and cost sources. Outcomes were expressed as incremental cost-effectiveness ratios (ICERs) in Korean won (KRW) per quality-adjusted life year (QALY). Deterministic and probabilistic sensitivity analyses were conducted.
Results
The AI-assisted strategy yielded an ICER of 8.37 million KRW (approximately US $6200) per QALY, below the societal willingness-to-pay (WTP) threshold of 40 million KRW (approximately US $29,600) per QALY in Korea. The incremental costs and QALYs were lifetime expected values per member of the general-population starting cohort rather than outcomes per directly monitored ICU admission. Probabilistic sensitivity analysis showed an 83.94% probability of cost-effectiveness at the threshold. One-way sensitivity analysis identified the true-positive rate, AI implementation cost, and postdischarge well-state utility value as the most influential parameters. Additional claims-based analyses indicated that ICU transition pathways and patient age were strongly associated with survival outcomes.
Conclusions
Under modeled assumptions, AI-assisted ICU mortality prediction showed potential cost-effectiveness compared with usual care in the Korean critical care setting. These findings should be interpreted as decision-analytic estimates rather than direct evidence that the AI system reduces ICU mortality in real patients. Prospective real-world evaluations are needed to confirm clinical effectiveness and implementation value.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Research Institute for Healthcare Policy, Dankook University, Dandae-ro 119, Cheonan, Chungcheongnam-do, 31116, Republic of Korea, 82 10-8438-8353.
- AITRICS Corp, Seoul, Republic of Korea.
- Division of Pulmonology, Department of Internal Medicine, Institute for Innovation in Digital Healthcare, Severance Hospital, Yonsei University College of Medicine, Seoul, Republic of Korea.
- Department of Health Administration, College of Public Health Sciences, Dankook University, Cheonan, Chungcheongnam-do, Republic of Korea.
Zitieren
APA
Lee, G. M., Won, J. Y., Cho, E. Y., Kim, J. H., Chung, K. S., Kim, K. J., Yun, S. J., Lee, H. J., & Kim, J. H. (2026). Value of AI in Critical Care Using Real-World Evidence on Intensive Care Unit Mortality Prediction: Cost-Utility Analysis. Journal of Medical Internet Research, 28, e93466-e93466. https://doi.org/10.2196/93466
Vancouver
Lee GM, Won JY, Cho EY, Kim JH, Chung KS, Kim KJ, et al. Value of AI in Critical Care Using Real-World Evidence on Intensive Care Unit Mortality Prediction: Cost-Utility Analysis. Journal of Medical Internet Research. 2026;28:e93466-e93466. doi:10.2196/93466
BibTeX
@article{Lee2026,
author = {Lee, Gyeong Min and Won, Joo-Yun and Cho, Eun Young and Kim, Ji-Hyun and Chung, Kyung Soo and Kim, Kwang Joon and Yun, Seok Jin and Lee, Hyun Jun and Kim, Jae-Hyun},
title = {Value of AI in Critical Care Using Real-World Evidence on Intensive Care Unit Mortality Prediction: Cost-Utility Analysis},
journal = {Journal of Medical Internet Research},
year = {2026},
volume = {28},
pages = {e93466--e93466},
doi = {10.2196/93466}
}
EUVIMED