Artificial intelligence and acute kidney injury
© 2024. The Author(s)..
Digitalization is increasingly finding its way into intensive care units and with it artificial intelligence (AI) for critically ill patients. One promising area for the use of AI is in the field of acute kidney injury (AKI). The use of AI is primarily focused on the prediction of AKI, but further approaches are also being used to classify existing AKI into different phenotypes. Different AI models are used for prediction. The area under the receiver operating characteristic curve values (AUROC) achieved with these models vary and are influenced by several factors, such as the prediction time and the definition of AKI. Most models have an AUROC between 0.650 and 0.900, with lower values for predictions further into the future and when applying Acute Kidney Injury Network (AKIN) instead of KDIGO criteria. Classification into phenotypes already makes it possible to categorize patients into groups with different risks of mortality or requirement of renal replacement therapy (RRT), but the etiologies or therapeutic consequences derived from this are still lacking. However, all the models suffer from AI-specific shortcomings. The use of large databases does not make it possible to promptly include recent changes in therapy and the implementation of new biomarkers in a relevant proportion. For this reason, serum creatinine and urinary output, with their known limitations, dominate current AI models for prediction impairing the performance of the current models. On the other hand, the increasingly complex models no longer allow physicians to understand the basis on which the warning of a threatening AKI is calculated and subsequent initiation of therapy should take place. The successful use of AIs in routine clinical practice will be highly determined by the trust of the physicians in the systems and overcoming the aforementioned weaknesses. However, the clinician will remain irreplaceable as the decisive authority for critically ill patients by combining measurable and nonmeasurable parameters.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:119 |
|---|---|
| Enthalten in: |
Medizinische Klinik, Intensivmedizin und Notfallmedizin - 119(2024), 3 vom: 19. Apr., Seite 199-207 |
| Sprache: |
Deutsch |
|---|
| Weiterer Titel: |
Künstliche Intelligenz und akute Nierenschädigung |
|---|
| Beteiligte Personen: |
Perschinka, Fabian [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
AKI Phenotypes |
|---|
| Anmerkungen: |
Date Completed 05.04.2024 Date Revised 07.04.2024 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1007/s00063-024-01111-5 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM36886104X |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM36886104X | ||
| 003 | DE-627 | ||
| 005 | 20240407232324.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240229s2024 xx |||||o 00| ||ger c | ||
| 024 | 7 | |a 10.1007/s00063-024-01111-5 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1368.xml |
| 035 | |a (DE-627)NLM36886104X | ||
| 035 | |a (NLM)38396124 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a ger | ||
| 100 | 1 | |a Perschinka, Fabian |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Artificial intelligence and acute kidney injury |
| 246 | 3 | 3 | |a Künstliche Intelligenz und akute Nierenschädigung |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 05.04.2024 | ||
| 500 | |a Date Revised 07.04.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a © 2024. The Author(s). | ||
| 520 | |a Digitalization is increasingly finding its way into intensive care units and with it artificial intelligence (AI) for critically ill patients. One promising area for the use of AI is in the field of acute kidney injury (AKI). The use of AI is primarily focused on the prediction of AKI, but further approaches are also being used to classify existing AKI into different phenotypes. Different AI models are used for prediction. The area under the receiver operating characteristic curve values (AUROC) achieved with these models vary and are influenced by several factors, such as the prediction time and the definition of AKI. Most models have an AUROC between 0.650 and 0.900, with lower values for predictions further into the future and when applying Acute Kidney Injury Network (AKIN) instead of KDIGO criteria. Classification into phenotypes already makes it possible to categorize patients into groups with different risks of mortality or requirement of renal replacement therapy (RRT), but the etiologies or therapeutic consequences derived from this are still lacking. However, all the models suffer from AI-specific shortcomings. The use of large databases does not make it possible to promptly include recent changes in therapy and the implementation of new biomarkers in a relevant proportion. For this reason, serum creatinine and urinary output, with their known limitations, dominate current AI models for prediction impairing the performance of the current models. On the other hand, the increasingly complex models no longer allow physicians to understand the basis on which the warning of a threatening AKI is calculated and subsequent initiation of therapy should take place. The successful use of AIs in routine clinical practice will be highly determined by the trust of the physicians in the systems and overcoming the aforementioned weaknesses. However, the clinician will remain irreplaceable as the decisive authority for critically ill patients by combining measurable and nonmeasurable parameters | ||
| 650 | 4 | |a English Abstract | |
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Review | |
| 650 | 4 | |a AKI Phenotypes | |
| 650 | 4 | |a Algorithms | |
| 650 | 4 | |a Forecasting | |
| 650 | 4 | |a Kidney failure | |
| 650 | 4 | |a Machine learning | |
| 650 | 7 | |a Biomarkers |2 NLM | |
| 700 | 1 | |a Peer, Andreas |e verfasserin |4 aut | |
| 700 | 1 | |a Joannidis, Michael |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Medizinische Klinik, Intensivmedizin und Notfallmedizin |d 2012 |g 119(2024), 3 vom: 19. Apr., Seite 199-207 |w (DE-627)NLM216019842 |x 2193-6226 |7 nnns |
| 773 | 1 | 8 | |g volume:119 |g year:2024 |g number:3 |g day:19 |g month:04 |g pages:199-207 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1007/s00063-024-01111-5 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 119 |j 2024 |e 3 |b 19 |c 04 |h 199-207 | ||