Side Effect Alerts Generation from EHR in Polish
Autor: | Wojciech Jaworski, Malgorzata Marciniak, Agnieszka Mykowiecka |
---|---|
Rok vydání: | 2021 |
Předmět: |
Computer science
business.industry media_common.quotation_subject WordNet computer.software_genre Public healthcare Task (project management) Side effect (computer science) Action (philosophy) Drug side effects In patient Artificial intelligence business Function (engineering) computer Natural language processing media_common |
Zdroj: | Computational Science – ICCS 2021 ISBN: 9783030779665 ICCS (3) |
Popis: | The paper addresses the problem of extending an existing and widely used program for Polish public healthcare with a function for detecting possible occurrences of drug side effects. The task is performed in two steps. First, we extract information that binds names of drugs with side effects and their frequency. In the next step, we look for similar phrases in the list of side effect phrases. For all words in phrases, we use Polish Wordnet to find similar ones, and check if phrases with replaced words exist in the list. For long side effect phrases, which never occur in patient records, we look for simpler internal side effect phrases to generate alarms. Finally, we evaluate to what extent this action increases the efficiency of side effect alarms. |
Databáze: | OpenAIRE |
Externí odkaz: |