Merijn Rijk

Improving the prognostication of lower respiratory tract infections in general practice

Samenvatting

Lower respiratory tract infections (LRTI) are common in general practice. To aid GPs in identifying patients at increased risk of complications, e.g. hospitalisation or mortality, an electronic health records (EHR)-based prediction model was developed and validated as part of this thesis. Information on signs and symptoms, extracted from EHR by natural language processing, did not further improve prediction model performance. Furthermore, this thesis has shown that LRTIs can trigger cardiovascular diseases (CVD), including myocardial infarction and stroke. The risk is particularly increased during the first week following an LRTI, resulting in an estimated five to nine excess CVDs per 1,000 LRTIs. These findings emphasize the need for early recognition and prevention of CVD following LRTI.