Bitte verwenden Sie diesen Link, um diese Publikation zu zitieren, oder auf sie als Internetquelle zu verweisen: https://hdl.handle.net/10419/197978 
Erscheinungsjahr: 
2019
Quellenangabe: 
[Journal:] DIW Weekly Report [ISSN:] 2568-7697 [Volume:] 9 [Issue:] 19 [Publisher:] Deutsches Institut für Wirtschaftsforschung (DIW) [Place:] Berlin [Year:] 2019 [Pages:] 169-175
Verlag: 
Deutsches Institut für Wirtschaftsforschung (DIW), Berlin
Zusammenfassung: 
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.
Schlagwörter: 
antibiotic prescribing
prediction policy
machine learning
expert decision-making
JEL: 
C10
C55
I11
I18
L38
O38
Q28
Persistent Identifier der Erstveröffentlichung: 
Dokumentart: 
Article

Datei(en):
Datei
Größe
337.96 kB





Publikationen in EconStor sind urheberrechtlich geschützt.