Künstliche Intelligenz: Herausforderungen und Nutzen in der Intensivmedizin

Die intensivmedizinische Arbeit ist von großen Datenmengen, deren Interpretation und Dokumentation geprägt. Künstliche Intelligenz hat vor allem in Form von maschinellem Lernen das Potenzial, diese Probleme anzugehen und zu reduzieren. KI bietet die Möglichkeit, die Arbeitsbelastung zu reduzieren, da auf ihr basierte Algorithmen Muster erkennen, Voraussagen machen und Dokumentation durch Spracherkennung erleichtern können.

Publication History

Article published online:
05 March 2024

• Literatur

• 1 Flohr L, Beaudry S, Johnson KT. et al Clinician-Driven Design of VitalPAD-An Intelligent Monitoring and Communication Device to Improve Patient Safety in the Intensive Care Unit. IEEE J Transl Eng Health Med 2018; 06: 3000114 DOI: 10.1109/JTEHM. 2018.2812162.
• 2 Beecken W-D. Changes – Analyse der Entwicklung der Digitalen Medizin im deutschen Gesundheitssystem aus ärztlicher Sicht. Matusiewicz D (ed.). Think Tanks im Gesundheitswesen. FOM-Edition. Wiesbaden: Springer Fachmedien; 2020: 29-44
• 3 Martin L, Peine A. Was ist neu … Einsatz von künstlicher Intelligenz in der Intensivmedizin: Hype oder schon Realität?. Anaesthesist 2021; 70: 40-41 DOI: 10.1007/s00101-020-00891-7.
• 4 Ahmed A, Chandra S, Herasevich V. et al The effect of two different electronic health record user interfaces on intensive care provider task load, errors of cognition, and performance. Crit Care Med 2011; 39: 1626-1634 DOI: 10.1097/CCM.0b013 e31821858a0.
• 5 Ballermann MA, Shaw NT, Arbeau KJ. et al Impact of a Critical Care Clinical Information System on Interruption Rates During Intensive Care Nurse and Physician Documentation Tasks. Stud Health Technol Inform 2010; 160: 274-278
• 6 Cheung A, van Velden FHP, Lagerburg V. et al The organizational and clinical impact of integrating bedside equipment to an information system: a systematic literature review of patient data management systems (PDMS). Int J Med Inform 2015; 84: 155-165
• 7 Toll E. The Cost of Technology. JAMA 2020; 323: 1661-1662 DOI: 10.1001/jama.2020.2752.
• 8 Butler R, Monsalve M, Thomas GW. et al Estimating Time Physicians and Other Health Care Workers Spend with Patients in an Intensive Care Unit Using a Sensor Network. Am J Med 2018; 131: 972.e9-972.e15
• 9 Momenipur A, Pennathur PR. Balancing Documentation and direct patient care activities: a study of a mature electronic health record system. Int J Ind Ergon 2019; 72: 338-346 DOI: 10.1016/j.ergon.2019.06.012.
• 10 Shanafelt TD, Dyrbye LN, Sinsky C. et al Relationship Between Clerical Burden and Characteristics of the Electronic Environment With Physician Burnout and Professional Satisfaction. Mayo Clin Proc 2016; 91: 836-848 DOI: 10.1016/j.mayocp.201 6.05.007.
• 11 Beil M, Proft I, van Heerden D. et al Ethical considerations about artificial intelligence for prognostication in intensive care. Intensive Care Med Exp 2019; 07: 70 DOI: 10.1186/s4063 5–019–0286–6.
• 12 Cosgriff CV, Celi LA, Stone DJ. Critical Care, Critical Data. Biomed Eng Comput Biol 2019; 10: 1179597219856564 DOI: 10.1177/1179597219856564.
• 13 McCarthy J, Minsky ML, Rochester N. et al A Proposal for the Dartmouth Summer Research Project on Artificial Intelligence. AI Magazine 2006; 27: 12-14
• 14 Peine A, Lütge C, Poszler F. et al Künstliche Intelligenz und maschinelles Lernen in der intensivmedizinischen Forschung und klinischen Anwendung. Anästh Intensivmed 2020; 61: 372-384
• 15 Bini SA. Artificial Intelligence, Machine Learning, Deep Learning, and Cognitive Computing: What Do These Terms Mean and How Will They Impact Health Care?. J Arthroplasty 2018; 33: 2358-2361 DOI: 10.1016/j.arth.2018.02.067.
• 16 Cleophas TJ, Zwinderman AH. Machine Learning in Medicine – a complete Overview. Cham; Heidelberg: Springer International Publishing; 2015
• 17 Schmidhuber J. Deep learning in neural networks: an overview. Neural Networks 2015; 61: 85-117 DOI: 10.1016/j.neunet.201 4.09.003.
• 18 Arntfield R, Wu D, Tschirhart J. et al Automation of Lung Ultrasound Interpretation via Deep Learning for the Classification of Normal versus Abnormal Lung Parenchyma: A Multicenter Study. Diagnostics (Basel) 2021; 11: 2049 DOI: 10.3390/diagn ostics11112049.
• 19 Esteva A, Kuprel B, Novoa RA. et al Dermatologist-level classification of skin cancer with deep neural networks. Nature 2017; 542: 115-118 DOI: 10.1038/nature21056.
• 20 Tai Y, Wei L, Zhou H. et al Machine learning-based haptic-enabled surgical navigation with security awareness. Concurrency Computat Pract Exper 2019; 31: 1-12
• 21 Davoudi A, Malhotra KR, Shickel B. et al Intelligent ICU for Autonomous Patient Monitoring Using Pervasive Sensing and Deep Learning. Sci Rep 2019; 09: 8020 DOI: 10.1038/s41598-0 19–44004-w.
• 22 Greco M, Caruso PF, Cecconi M. Artificial Intelligence in the Intensive Care Unit. Semin Respir Crit Care Med 2021; 42: 2-9 DOI: 10.1055/s-0040-1719037.
• 23 Koczulla AR, Wöhrle H. Digitale Medizin auf der Intensivstation. Pneumologe 2020; 17: 264-266
• 24 Collins S, Couture B, Kang MJ. et al Quantifying and Visualizing Nursing Flowsheet Documentation Burden in Acute and Critical Care. AMIA Annu Symp Proc 2018; 2018: 348-357
• 25 Johnson AEW, Pollard TJ, Shen L. et al MIMIC-III, a freely accessible critical care database. Sci Data 2016; 03: 160035 DOI: 10.1038/sdata.2016.35.
• 26 Pollard TJ, Johnson AEW, Raffa JD. et al The eICU Collaborative Research Database, a freely available multi-center database for critical care research. Sci Data 2018; 05: 180178 DOI: 10.1038/sdata.2018.178.
• 27 Anonymous Medicine in the digital age. Nat Med 2019; 25: 1 DOI: 10.1038/s41591-018-0322-1.
• 28 Dymek C, Kim B, Melton GB. et al Building the evidence-base to reduce electronic health record-related clinician burden. J Am Med Inform Assoc 2021; 28: 1057-1061 DOI: 10.1093/jamia/ocaa238.
• 29 Goss FR, Blackley SV, Ortega CA. et al A clinician survey of using speech recognition for clinical documentation in the electronic health record. Int J Med Inform 2019; 130: 103938 DOI: 10.1016/j.ijmedinf.2019.07.017.
• 30 Slutsky AS, Ranieri VM. Ventilator-induced lung injury. N Engl J Med 2013; 369: 2126-2136 DOI: 10.1056/NEJMc1400293.
• 31 Komorowski M, Celi LA, Badawi O. et al The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care. Nature Med 2018; 24: 1716-1720 DOI: 10.1038/s41591-018–0213–5.
• 32 Jansson M, Rubio J, Gavaldà R. et al Artificial Intelligence for clinical decision support in Critical Care, required and accelerated by COVID-19. Anaesth Crit Care Pain Med 2020; 39: 691-693 DOI: 10.1016/j.accpm.2020.09.010.
• 33 Pirracchio R, Cohen MJ, Malenica I. et al Big data and targeted machine learning in action to assist medical decision in the ICU. Anaesth Crit Care Pain Med 2019; 38: 377-384 DOI: 10.1016/j.accpm.2018.09.008.
• 34 Peine A, Hallawa A, Bickenbach J. et al Development and validation of a reinforcement learning algorithm to dynamically Martin L, et al. Künstliche Intelligenz: Herausforderungen … Anästhesiol Intensivmed Notfallmed 206 Schmerzther. 2022; 57: 199-209 | © 2022. Thieme. All rights reserved. CME-Fortbildung | Topthema Heruntergeladen von: Thieme Gruppe. Urheberrechtlich geschützt. optimize mechanical ventilation in critical care. NPJ Digit Med 2021; 4: 32. doi:10.1038/s41746-021-00388-6
• 35 Marx G, Dusch M, Czaplik M. et al Telemedizin für die vier Säulen der Anästhesiologie: Positionspapier der Deutschen Gesellschaft für Anästhesiologie und Intensivmedizin (DGAI) und der Deutschen Gesellschaft für Telemedizin (DG Telemed). Anästh Intensivmed 2019; 60: 191-207
• 36 Lin Y-W, Zhou Y, Faghri F. et al Analysis and prediction of unplanned intensive care unit readmission using recurrent neural networks with long short-term memory. PLoS One 2019; 14: e0218942 DOI: 10.1371/journal.pone.0218942.
• 37 Sim I, Gorman P, Greenes RA. et al Clinical decision support systems for the practice of evidence-based medicine. J Am Med Inform Assoc 2001; 08: 527-534 DOI: 10.1136/jamia.2001.0080527.
• 38 Rawson TM, Moore LSP, Hernandez B. et al A systematic review of clinical decision support systems for antimicrobial management: are we failing to investigate these interventions appropriately?. Clin Microbiol Infect 2017; 23: 524-532 DOI: 10.1016/j.cmi.2017.02.028.
• 39 Rawson TM, Ahmad R, Toumazou C. et al Artificial intelligence can improve decision-making in infection management. Nat Hum Behav 2019; 03: 543-545 DOI: 10.1038/s41562-019-058 3–9.
• 40 Loo TS, Davis RB, Lipsitz LA. et al Electronic medical record reminders and panel management to improve primary care of elderly patients. Arch Intern Med 2011; 171: 1552-1558 DOI: 10.1001/archinternmed.2011.394.
• 41 McGinn TG, McCullagh L, Kannry J. et al Efficacy of an evidence- based clinical decision support in primary care practices: a randomized clinical trial. JAMA Intern Med 2013; 173: 1584-1591 DOI: 10.1001/jamainternmed.2013.8980.
• 42 Chertow GM, Lee J, Kuperman GJ. et al Guided medication dosing for inpatients with renal insufficiency. JAMA 2001; 286: 2839-2844 DOI: 10.1001/jama.286.22.2839.
• 43 Wright A, Pang J, Feblowitz JC. et al Improving completeness of electronic problem lists through clinical decision support: a randomized, controlled trial. J Am Med Inform Assoc 2012; 19: 555-561 DOI: 10.1136/amiajnl-2011-000521.
• 44 Abràmoff MD, Lavin PT, Birch M. et al Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices. NPJ Digit Med 2018; 01: 39 DOI: 10.1038/s41746-018-0040-6.
• 45 Corny J, Rajkumar A, Martin O. et al A machine learning-based clinical decision support system to identify prescriptions with a high risk of medication error. J Am Med Inform Assoc 2020; 27: 1688-1694 DOI: 10.1093/jamia/ocaa154.
• 46 Cabitza F, Rasoini R, Gensini GF. Unintended Consequences of Machine Learning in Medicine. JAMA 2017; 318: 517-518 DOI: 10.1001/jama.2017.7797.
• 47 Peiffer-Smadja N, Rawson TM, Ahmad R. et al Machine learning for clinical decision support in infectious diseases: a narrative review of current applications. Clin Microbiol Infect 2020; 26: 584-595 DOI: 10.1016/j.cmi.2020.05.020.
• 48 McCoy AB, Thomas EJ, Krousel-Wood M. et al Clinical decision support alert appropriateness: a review and proposal for improvement. Ochsner J 2014; 14: 195-202
• 49 Asan O, Smith PD, Montague E. More screen time, less face time – implications for EHR design. J Eval Clin Pract 2014; 20: 896-901 DOI: 10.1111/jep.12182.
• 50 Margalit RS, Roter D, Dunevant MA. et al Electronic medical record use and physician-patient communication: an observational study of Israeli primary care encounters. Patient Educ Couns 2006; 61: 134-141 DOI: 10.1016/j.pec.2005.03.004.
• 51 Kwan JL, Lo L, Ferguson J. et al Computerised clinical decision support systems and absolute improvements in care: metaanalysis of controlled clinical trials. BMJ 2020; 370: m3216 DOI: 10.1136/bmj.m3216.
• 52 He J, Baxter SL, Xu J. et al The practical implementation of artificial intelligence technologies in medicine. Nat Med 2019; 25: 30-36 DOI: 10.1038/s41591-018-0307-0.
• 53 Muinga N, Abejirinde IO, Paton C. et al Designing paper-based records to improve the quality of nursing documentation in hospitals: A scoping review. J Clin Nurs 2021; 30: 56-71
• 54 Chao C-A. The impact of electronic health records on collaborative work routines: A narrative network analysis. Int J Med Inform 2016; 94: 100-111 DOI: 10.1016/j.ijmedinf.2016.06.019.
• 55 Hodgson T, Magrabi F, Coiera E. Efficiency and safety of speech recognition for documentation in the electronic health record. J Am Med Inform Assoc 2017; 24: 1127-1133 DOI: 10.1093/jamia/ocx073.
• 56 Zuchowski M. Weniger Dokumentationsaufwand, mehr Zeit. Klinik Management aktuell 2020; 25: 72-73
• 57 Blackley SV, Schubert VD, Goss FR. et al Physician use of speech recognition versus typing in clinical documentation: A controlled observational study. Int J Med Inform 2020; 141: 104178 DOI: 10.1016/j.ijmedinf.2020.104178.
• 58 Panch T, Mattie H, Celi LA. The “inconvenient truth” about AI in healthcare. NPJ Digit Med 2019; 77: 1-3 DOI: 10.1038/s41. 746–019–0155–4
• 59 Gijsberts CM, Groenewegen KA, Hoefer IE. et al Race/Ethnic Differences in the Associations of the Framingham Risk Factors with Carotid IMT and Cardiovascular Events. PLoS One 2015; 10: e0132321 DOI: 10.1371/journal.pone.0132321.
• 60 Tran BD, Chen Y, Liu S. et al How does medical scribes’ work inform development of speech-based clinical documentation technologies? A systematic review. J Am Med Inform Assoc 2020; 27: 808-817 DOI: 10.1093/jamia/ocaa020.
• 61 Poncette A-S, Spies C, Mosch L. et al Clinical Requirements of Future Patient Monitoring in the Intensive Care Unit: Qualitative Study. JMIR Med Inform 2019; 07: e13064 DOI: 10.2196/13064.
• 62 U. S. Food, and, Drug Administration. Artificial Intelligence and Machine Learning in Software as a Medical Device. Zugriff am 01.11.2021 unter www.fda.gov/medical-devices/softwaremedical-device-samd/artificial-intelligence-and-machine-learning-software-medical-device