| Sonstiges: |
- Nachgewiesen in: MEDLINE
- Sprachen: German
- Transliterated Title: Künstliche Intelligenz in der Intensivmedizin.
- Publication Type: English Abstract; Journal Article; Review
- Language: German
- [Med Klin Intensivmed Notfmed] 2024 Apr; Vol. 119 (3), pp. 189-198. <i>Date of Electronic Publication: </i>2024 Mar 28.
- MeSH Terms: Artificial Intelligence* ; Medicine* ; Humans ; Critical Care ; Algorithms ; Health Personnel
- References: International Medical Device Regulators Forum (2021) Machine learning-enabled medical devices: a subset of AI-enabled medical devices: key terms and definitions. 16. Sept. 2021 (Vorgeschlagenes Dokument zur öffentlichen Konsultation veröffentlicht,). ; OECD (2019) Recommendation of the Council on Artificial Intelligence. https://legalinstruments.oecd.org/en/instruments/OECD-LEGAL-0449. ; DeSalvo K (2023) The AI-assisted, mobile-first health care journey. Catalyst. https://doi.org/10.1056/CAT.23.0263. (PMID: 10.1056/CAT.23.0263) ; Hashimoto DA, Witkowski E, Gao L, Meireles O, Rosman G (2020) Artificial intelligence in anesthesiology: current techniques, clinical applications, and limitations. Anesthesiology 132(2):379–394. https://doi.org/10.1097/ALN.0000000000002960. (PMID: 10.1097/ALN.000000000000296031939856) ; Okada Y, Mertens M, Liu N, Lam SSW, Ong MEH (2023) AI and machine learning in resuscitation: Laufende Forschung, neue Konzepte und zentrale Herausforderungen. Resusc Plus 15:100435. https://doi.org/10.1016/j.resplu.2023.100435. (PMID: 10.1016/j.resplu.2023.1004353754754010400904) ; Alfieri F et al (2023) Continuous and early prediction of future moderate and severe acute kidney injury in critically ill patients: development and multi-centric, multi-national external validation of a machine-learning model. PLoS ONE 18(7):e287398. https://doi.org/10.1371/journal.pone.0287398. (PMID: 10.1371/journal.pone.02873983749048210368244) ; Flechet M et al (2019) Machine learning versus physicians’ prediction of acute kidney injury in critically ill adults: a prospective evaluation of the AKIpredictor. Crit Care 23(1):282. https://doi.org/10.1186/s13054-019-2563-x. (PMID: 10.1186/s13054-019-2563-x314200566697946) ; Mollura M, Lehman LH, Mark RG, Barbieri R (2021) A novel artificial intelligence based intensive care unit monitoring system: Using physiological waveforms to identify sepsis. Philos Trans A Math Phys Eng Sci 379(2212):20200252. https://doi.org/10.1098/rsta.2020.0252. (PMID: 10.1098/rsta.2020.0252346896148805602) ; Giri J et al (2023) A comparative study on predication of appropriate mechanical ventilation mode through machine learning approach. Bioengineering 10(4):418. https://doi.org/10.3390/bioengineering10040418. (PMID: 10.3390/bioengineering100404183710660510136217) ; Poweleit EA, Vinks AA, Mizuno T (2023) Artificial intelligence and machine learning approaches to facilitate therapeutic drug management and model-informed precision dosing. Ther Drug Monit 45(2):143–150. https://doi.org/10.1097/FTD.0000000000001078. (PMID: 10.1097/FTD.00000000000010783675047010378651) ; Sander J, Simon P, Hinske C (2023) Big Data und künstliche Intelligenz in der Anästhesie. Anaesthesiologie. https://doi.org/10.1007/s00101-023-01362-5. (PMID: 10.1007/s00101-023-01362-53806621510022556) ; Arina P et al (2024) Prediction of complications and prognostication in perioperative medicine: a systematic review and PROBAST assessment of machine learning tools. Anesthesiology 140(1):85–101. https://doi.org/10.1097/ALN.0000000000004764. (PMID: 10.1097/ALN.000000000000476437944114) ; D. Ethikrat (2023) Mensch und Maschine – Herausforderungen durch Künstliche Intelligenz. https://www.ethikrat.org/fileadmin/Publikationen/Stellungnahmen/deutsch/stellungnahme-mensch-und-maschine.pdf. ; Maheshwari K, Cywinski JB, Papay F, Khanna AK, Mathur P (2023) Artificial intelligence for perioperative medicine: perioperative Intelligenz. Anästh Analg 136(4) ( https://journals.lww.com/anesthesia-analgesia/fulltext/2023/04000/artificial_intelligence_for_perioperative.5.aspx ). ; Nadkarni GN, Sakhuja A (2023) Clinical Informatics in critical care medicine. Yale J Biol Med 96(3):397–405. https://doi.org/10.59249/WTTU3055. (PMID: 10.59249/WTTU30553778099410524812) ; Meier JM, Tschoellitsch T (2022) Artificial intelligence and machine learning in patient blood management: a scoping review. Anesth Analg 135(3) ( https://journals.lww.com/anesthesia-analgesia/fulltext/2022/09000/artificial_intelligence_and_machine_learning_in.11.aspx ). ; Peine A, Hallawa A, Bickenbach J et al (2021) Development and validation of a reinforcement learning algorithm to dynamically optimize mechanical ventilation in critical care. Npj Digit Med 4:32. https://doi.org/10.1038/s41746-021-00388-6. (PMID: 10.1038/s41746-021-00388-6336086617895944) ; Campbell R (2013) The five ’rights’ of clinical decision support. J AHIMA 84(10):42–47. https://doi.org/10.3233/JAH-2013-0003 (quiz 48). (PMID: 10.3233/JAH-2013-000324245088) ; Auerbach AD et al (2024) Diagnostic errors in hospitalized adults who died or were transferred to intensive care. JAMA Intern Med. https://doi.org/10.1001/jamainternmed.2023.7347. (PMID: 10.1001/jamainternmed.2023.734738190122) ; Webster P (2023) Six ways large language models are changing healthcare. Nat Med 29(12):2969–2971. https://doi.org/10.1038/s41591-023-02700-1. (PMID: 10.1038/s41591-023-02700-138036704) ; Martin L, Peine A, Gronholz M, Marx G, Bickenbach J (2022) Künstliche Intelligenz: Herausforderungen und Nutzen in der Intensivmedizin. Anästhesiol Intensivmed Notfallmed Schmerzther 57(3):199–209. https://doi.org/10.1055/a-1423-8006. (PMID: 10.1055/a-1423-800635320842) ; Hyland SL, Faltys M, Esteban C et al (2020) Early prediction of circulatory failure in the intensive care unit using machine learning. Nat Med 26(3):364–373. (PMID: 10.1038/s41591-020-0789-432152583) ; Bitker L, Talmor D, Richard JC (2022) Emerging applications of artificial intelligence in acute respiratory distress syndrome. Intensive Care Med 48(8):995–1008. (PMID: 10.1007/s00134-022-06809-8358339589281340) ; Goh KH, Wang L, Yeow JJL et al (2021) Artificial intelligence in predicting acute kidney injury: from theory to practice. Nat Commun 12(1):711. (PMID: 10.1038/s41467-021-20910-4335146997846756) ; Böck M, Malle J, Heitzinger C et al (2022) Artificial intelligence approaches for sepsis prediction. PLoS ONE 17(11):e275358. ; Bologheanu R, Kapral L, Zeiner S et al (2023) AI in sepsis prediction and management. J Clin Med 12(4):1513. https://doi.org/10.3390/jcm12041513. (PMID: 10.3390/jcm12041513368360469961939) ; Zhang H, Wang AY, He X et al (2022) AI-enhanced diagnosis of acute kidney injury. BMC Nephrol 23(1):405. (PMID: 10.1186/s12882-022-03025-w365363179761969) ; Bishara A, Chiu C, Butte AJ et al (2022) AI in detection and management of postoperative delirium. BMC Anesthesiol 22(1):8. (PMID: 10.1186/s12871-021-01543-y349799198722098) ; Marx G et al (2021) Algorithmic surveillance of ICU patients with acute respiratory distress syndrome (ASIC): protocol for a multicentre stepped-wedge cluster randomised quality improvement strategy. BMJ Open. https://doi.org/10.1136/bmjopen-2020-045589. (PMID: 10.1136/bmjopen-2020-045589345509018039261) ; Graeßner M et al (2023) Enabling personalized perioperative risk prediction by using a machine-learning model based on preoperative data. Sci Rep 13(1):7128. https://doi.org/10.1038/s41598-023-33981-8. (PMID: 10.1038/s41598-023-33981-83713088410153050) ; Falini S, Angelotti G, Cecconi M (2020) ICU management based on big data. Curr Opin Anesthesiol 33(2) ( https://journals.lww.com/co-anesthesiology/fulltext/2020/04000/icu_management_based_on_big_data.7.aspx ). ; Peine A, Lütge C, Poszler F, Celi L, Schöffski O, Marx G et al (2020) Künstliche Intelligenz und maschinelles Lernen in der intensivmedizinischen Forschung und klinischen Anwendung. Anästh Intensivmed 61:372–384. https://doi.org/10.19224/ai2020.372. (PMID: 10.19224/ai2020.372) ; Clusmann J et al (2023) The future landscape of large language models in medicine. Commun Med 3(1):141. https://doi.org/10.1038/s43856-023-00370-1. (PMID: 10.1038/s43856-023-00370-13781683710564921) ; Singhal K et al (2023) Large language models encode clinical knowledge. Nature 620(7972):172–180. https://doi.org/10.1038/s41586-023-06291-2. (PMID: 10.1038/s41586-023-06291-23743853410396962) ; Thirunavukarasu AJ, Ting DSJ, Elangovan K, Gutierrez L, Tan TF, Ting DSW (2023) Large language models in medicine. Nat Med 29(8):1930–1940. https://doi.org/10.1038/s41591-023-02448-8. (PMID: 10.1038/s41591-023-02448-837460753) ; Wachter RM, Brynjolfsson E (2024) Will generative artificial intelligence deliver on its promise in health care? JAMA 331(1):65–69. https://doi.org/10.1001/jama.2023.25054. (PMID: 10.1001/jama.2023.2505438032660) ; Goodman RS et al (2023) Accuracy and reliability of Chatbot responses to physician questions. JAMA Netw Open 6(10):e2336483. https://doi.org/10.1001/jamanetworkopen.2023.36483. (PMID: 10.1001/jamanetworkopen.2023.364833778249910546234) ; Sonntagbauer M, Haar M, Kluge S (2023) Künstliche Intelligenz: Wie werden ChatGPT und andere KI-Anwendungen unseren ärztlichen Alltag verändern? Med Klin Intensivmed Notfallmed 118(5):366–371. https://doi.org/10.1007/s00063-023-01019-6. (PMID: 10.1007/s00063-023-01019-6) ; Schweingruber N, Gerloff C (2021) Künstliche Intelligenz in der Neurointensivmedizin [Artificial intelligence in neurocritical care]. Nervenarzt 92(2):115–126. https://doi.org/10.1007/s00115-020-01050-4. (PMID: 10.1007/s00115-020-01050-4334911527829030) ; Daneshjou R, Smith MP, Sun MD, Rotemberg V, Zou J (2021) Lack of transparency and potential bias in artificial intelligence data sets and algorithms: a scoping review. JAMA Dermatol 157(11):1362–1369. https://doi.org/10.1001/jamadermatol.2021.3129. (PMID: 10.1001/jamadermatol.2021.3129345503059379852) ; Marx G (2022) Chancen der Digitalisierung für innovative Gesundheitsforschung und -versorgung. Anästhesiol Intensivmed Notfallmed Schmerzther 57(3):169–171. https://doi.org/10.1055/a-1736-9540. (PMID: 10.1055/a-1736-954035320839) ; Wilkinson MD et al The FAIR guiding principles for scientific data management and stewardship. Sci Data 3:160018. https://doi.org/10.1038/sdata.2016.18. ; Fritsch S, Maassen O, Riedel M (2022) Künstliche Intelligenz: Infrastrukturen und Voraussetzungen auf europäischer Ebene. Anästhesiol Intensivmed Notfallmed Schmerzther 57:172–184. https://doi.org/10.1055/a-1423-8052. (PMID: 10.1055/a-1423-805235320840) ; Dohmen S, Wahl A, Benstoem C (2022) Digital gestützte intensivmedizinische Versorgungsnetzwerke. Anästhesiol Intensivmed Notfallmed Schmerzther 57:211–220. https://doi.org/10.1055/a-1423-7982. (PMID: 10.1055/a-1423-798235320843) ; Johnson AEW, Bulgarelli L, Shen L, Gayles A, Shammout A, Horng S, Pollard TJ, Hao S, Moody B, Gow B, Lehman LH, Celi LA, Mark RG (2023) MIMIC-IV, a freely accessible electronic health record dataset. Sci Data 10(1):1. https://doi.org/10.1038/s41597-022-01899-x (Erratum in: Sci Data. 2023 Jan 16;10(1):31. Erratum in: Sci Data. 2023 Apr 18;10(1):219). (PMID: 10.1038/s41597-022-01899-x365968369810617) ; Saeed M, Villarroel M, Moody G et al (2011) Multiparameter intelligent monitoring in intensive care II (MIMIC-II): a public-access intensive care unit database. Crit Care Med 39(5):952–960. (PMID: 10.1097/CCM.0b013e31820a92c6212830053124312) ; Pollard TJ, Johnson AEW, Badawi O et al (2018) A public ICU database with high temporal resolution. Sci Data 5:180178. (PMID: 10.1038/sdata.2018.178302041546132188) ; Plana D, Shung DL, Grimshaw AA, Saraf A, Sung JJY, Kann BH (2022) Randomized clinical trials of machine learning interventions in health care: a systematic review. JAMA Netw Open 5(9):e2233946. https://doi.org/10.1001/jamanetworkopen.2022.33946. (PMID: 10.1001/jamanetworkopen.2022.33946361736329523495) ; Kwong JCC et al (2023) APPRAISE-AI tool for quantitative evaluation of AI studies for clinical decision support. JAMA Netw Open 6(9):e2335377. https://doi.org/10.1001/jamanetworkopen.2023.35377. (PMID: 10.1001/jamanetworkopen.2023.353773774773310520738) ; Hart B, Lundh A, Bero L (2012) Effect of reporting bias on meta-analyses of drug trials: reanalysis of meta-analyses. BMJ 344:d7202. (PMID: 10.1136/bmj.d720222214754) ; Jones CW, Keil LG, Platts-Mills TF et al (2015) Non-publication of large randomized clinical trials: cross-sectional analysis. BMC Med 13:282. (PMID: 10.1186/s12916-015-0520-3265811914650202) ; Schulz KF, Altman DG, Moher D (2010) CONSORT 2010 Statement: updated guidelines for reporting parallel group randomised trials. BMJ 340:c332. (PMID: 10.1136/bmj.c332203325092844940) ; Kirkham JJ, Dwan KM, Smyth R et al (2010) The CONSORT statement: revised recommendations for improving the quality of reports of parallel-group randomised trials. BMJ 340:c365. (PMID: 10.1136/bmj.c36520156912) ; Liu X, Rivera SC, Denniston AK et al (2020) Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension. Nat Med 26(9):1364–1374. (PMID: 10.1038/s41591-020-1034-x329082837598943) ; Rivera SC, Liu X, Calvert MJ et al (2020) Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI Extension. Nat Med 26(9):1351–1363. (PMID: 10.1038/s41591-020-1037-7) ; Rivera SC, Liu X, Calvert MJ et al (2020) SPIRIT-AI and CONSORT-AI 2020 guidelines: better reporting of AI trials in health care. Lancet Digit Health 2(10):e549–e560. (PMID: 8212701) ; Wolff RF et al (2019) PROBAST: a tool to assess the risk of bias and applicability of prediction model studies. Ann Intern Med 170(1):51–58. https://doi.org/10.7326/M18-1376. (PMID: 10.7326/M18-137630596875) ; Liu Y, Chen P‑HC, Krause J, Peng L (2019) How to read articles that use machine learning: users’ guides to the medical literature. JAMA 322(18):1806–1816. https://doi.org/10.1001/jama.2019.16489. (PMID: 10.1001/jama.2019.1648931714992) ; Tretter M, Samhammer D, Dabrock P (2023) Künstliche Intelligenz in der Medizin: Von Entlastungen und neuen Anforderungen im ärztlichen Handeln. Ethik Med. ; Hashimoto DA, Varas J, Schwartz TA (2024) Practical guide to machine learning and artificial intelligence in surgical education research. JAMA Surg. https://doi.org/10.1001/jamasurg.2023.6687. (PMID: 10.1001/jamasurg.2023.668738170510) ; De S, Jackson CD, Jones DB (2023) Intelligent virtual operating room for enhancing nontechnical skills. JAMA Surg 158(6):662–663. https://doi.org/10.1001/jamasurg.2022.6721. (PMID: 10.1001/jamasurg.2022.67213692040410753974) ; Estrada Alamo CE, Diatta F, Monsell SE, Lane-Fall MB (2023) Artificial intelligence in anesthetic care: a survey of physician anesthesiologists. Anesth Analg ( https://journals.lww.com/anesthesia-analgesia/fulltext/9900/artificial_intelligence_in_anesthetic_care__a.673.aspx ). ; World Health Organization (2023) Regulatory considerations on artificial intelligence for health. Weltgesundheitsorganisation, Genf. ; U.S. Food and Drug Administration (FDA) (2023) Artificial intelligence and machine learning (AI/ML)-enabled medical devices. ; Lee JT, Moffett AT, Maliha G, Faraji Z, Kanter GP, Weissman GE (2023) Analysis of devices authorized by the FDA for clinical decision support in critical care. JAMA Intern Med 183(12):1399–1401. https://doi.org/10.1001/jamainternmed.2023.5002. (PMID: 10.1001/jamainternmed.2023.500237812404) ; EU-Kommission (2023) EU AI Act: first regulation on artificial intelligence. ; EU-Parlament (2023) EU AI Act: first regulation on artificial intelligence. ; Shah NH et al (2023) A nationwide network of health AI assurance laboratories. JAMA. https://doi.org/10.1001/jama.2023.26930. (PMID: 10.1001/jama.2023.269303805132610461525) ; TUEV AI-LAB (2023) TUV AI.LAB. ; OECD (2022) OECD framework for the classification of AI systems Bd. 323. https://doi.org/10.1787/cb6d9eca-en. (PMID: 10.1787/cb6d9eca-en) ; Nagendran M, Festor P, Komorowski M, Gordon AC, Faisal AA (2023) Quantifying the impact of AI recommendations with explanations on prescription decision making. Npj Digit Med 6(1):206. https://doi.org/10.1038/s41746-023-00955-z. (PMID: 10.1038/s41746-023-00955-z3793595310630476) ; WHO (Hrsg) (2024) Ethics and governance of artificial intelligence for health. Guidance on large multi-modal models. Licence: CC BY-NC-SA 3.0 IGO. World Health Organization, Geneva. ; Cazzaniga et al (2024) Gen-AI: artificial intelligence and the future of work. IMF Staff Discussion Note SDN2024/001. International Monetary Fund, Washington, DC. (PMID: 10.5089/9798400262548.006) ; Vassilev A, Oprea A, Fordyce A, Anderson H (2024) Adversarial machine learning: a taxonomy and terminology of attacks and mitigations. NIST Artifcial Intelligence (AI) Report, NIST Trustworthy and Responsible AI NIST AI 100-2e2023. National Institute of Standards and Technology, Gaithersburg https://doi.org/10.6028/NIST.AI.100-2e2023. (PMID: 10.6028/NIST.AI.100-2e2023) ; Perschinka F, Peer A, Joannidis M (2024) Künstliche Intelligenz und akute Nierenschädigung. Med Klin Intensivmed Notfmed. https://doi.org/10.1007/s00063-024-01111-5. (PMID: 10.1007/s00063-024-01111-538396124)
- Contributed Indexing: Keywords: Clinical decision-support; Information management; Information science; Maschine Learning; Natural language processing ; Local Abstract: [Publisher, German] Die Integration von künstlicher Intelligenz (KI) in die Intensivmedizin zeigt in neuesten Studien besonders in den Bereichen der prädiktiven Analytik, der Früherkennung von Komplikationen und der Entwicklung von Entscheidungsunterstützungssystemen beachtliche Fortschritte. Die Hauptherausforderungen bestehen weiterhin in der Verfügbarkeit und Qualität der Daten, der Reduzierung von Verzerrungen und der Notwendigkeit erklärbarer Ergebnisse von Algorithmen und Modellen. Methoden zur Erklärung dieser Systeme sind essenziell, um Vertrauen, Verständnis und ethische Überlegungen bei Gesundheitsfachkräften und Patienten zu stärken. Eine fundierte Ausbildung des medizinischen Personals in KI-Prinzipien, Terminologie, ethischen Überlegungen und in der praktischen Anwendung ist für den erfolgreichen Einsatz von KI entscheidend. Die sorgfältige Bewertung der Auswirkungen von KI auf Patientenautonomie und Datenschutz ist unabdingbar für deren verantwortungsvolle Nutzung in der Intensivmedizin. Hierbei ist die Balance zwischen ethischen und praktischen Erwägungen zu wahren, um eine patientenzentrierte Versorgung bei gleichzeitiger Einhaltung von Datenschutzbestimmungen zu gewährleisten. Eine synergistische Zusammenarbeit zwischen Klinikern, KI-Ingenieuren und Regulierungsbehörden ist entscheidend, um das volle Potenzial der KI in der Intensivmedizin zu realisieren und ihre positive Wirkung auf die Patientenversorgung zu maximieren. Zukünftige Forschungs- und Entwicklungsanstrengungen sollten sich auf die Verbesserung von KI-Modellen für Echtzeitvorhersagen, die Steigerung der Genauigkeit und des Nutzens KI-basierter Closed-loop-Systeme sowie die Überwindung ethischer, technischer und regulatorischer Herausforderungen, insbesondere bei generativen KI-Systemen, fokussieren.
- Entry Date(s): Date Created: 20240328 Date Completed: 20240405 Latest Revision: 20240405
- Update Code: 20240405
|
