Mining Adverse Drug Events Using Multiple Feature Hierarchies and Patient History Windows

Bampa, MariaStockholms universitet,Institutionen för data- och systemvetenskap (författare)

We study the problem of detecting adverse drug events in electronic health records. The challenge is this work is to aggregate heterogeneous data types involving lab measurements, diagnoses codes and medications codes. An earlier framework proposed for the same problem demonstrated promising predictive performance for the random forest classifier by using only lab measurements as data features. We extend this framework, by additionally including diagnosis and drug prescription codes, concurrently. In addition, we employ the concept of hierarchies of clinical codes as proposed by another work, in order to exploit the inherently complex nature of the medical data. Moreover, we extended the state-of-the-art by considering variable patient history lengths before the occurrence of an ADE event rather than a patient history of an arbitrary length. Our experimental evaluation on eight medical datasets of adverse drug events, five different patient history lengths, and six different classifiers, suggests that the integration of these additional features on the different window lengths provides significant improvements in terms of AUC while employing medically relevant features.

Papapetrou, PanagiotisStockholms universitet,Institutionen för data- och systemvetenskap(Swepub:su)ppapa (författare)
Stockholms universitetInstitutionen för data- och systemvetenskap (creator_code:org_t)

Ingår i:19th IEEE International Conference on Data Mining Workshops: IEEE97817281489779781728148960

Om ämnet

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.