Artificial intelligence and big data can help contain resistance to antibiotics

Artikel

Improving physicians' prescription practices is a primary strategy for countering the rise in resistance to antibiotics. This would prevent physicians from incorrectly prescribing antibiotics, one of the main causes of antibiotic resistance. The increasing availability of medical data and methods of machine learning provide an opportunity to generate instant diagnoses. In the present study, the example of urinary tract infections in Denmark is used to demonstrate how data-based predictions can improve clinical practice in the face of increasing antibiotic resistance. For this purpose, comprehensive administrative and medical data, in combination with machine learning methods and economic modeling, were used to develop rules for prescribing antibiotics. The total number of prescriptions could be reduced by 7.42 percent by applying the recommended policy measures without reducing the number of treated bacterial infections. This demonstrates the great potential of this method. However, in Germany this potential cannot be tapped until more information is digitized. The information that must be supplied to the IT systems in physicians' practices and hospitals is often collected and saved by decentralized institutions; linking it is key.

Angaben zum Objekt

• Sprache: Englisch

Verweise und Beziehungen

• Erschienen in: Journal: DIW Weekly Report ; ISSN: 2568-7697 ; Volume: 9 ; Year: 2019 ; Issue: 19 ; Pages: 169-175 ; Berlin: Deutsches Institut für Wirtschaftsforschung (DIW)

Klassifikation und Themen

• Klassifikation: Wirtschaft ; Econometric and Statistical Methods and Methodology: General ; Large Data Sets: Modeling and Analysis ; Analysis of Health Care Markets ; Health: Government Policy; Regulation; Public Health ; Public Policy ; Technological Change: Government Policy ; Renewable Resources and Conservation: Government Policy
• Thema: antibiotic prescribing ; prediction policy ; machine learning ; expert decision-making

Beteiligte, Orts- und Zeitangaben

• Ereignis: Geistige Schöpfung
• (wer): Ribers, Michael ; Ullrich, Hannes
• Ereignis: Veröffentlichung
• (wer): Deutsches Institut für Wirtschaftsforschung (DIW)
• (wo): Berlin
• (wann): 2019

Weitere Informationen

• DOI: doi:10.18723/diw_dwr:2019-19-1
• Handle: http://hdl.handle.net/10419/197978
• Letzte Aktualisierung: 10.03.2025, 11:42 MEZ