Tokiko ospitale bateko COVID-19 pazienteen datu-multzoaren Triajea

• Autores: Goizalde Badiola Zabala, José Manuel López Guede , Manuel Graña Romay
• Localización: Ingeniaritza eta Arkitektura: VI. Ikergazte Nazioarteko ikerketa euskaraz: 2025eko maitzaren 28, 29 eta 30 Bilbo, Euskal Herria / coord. por Olatz Arbelaiz Gallego , Ainhoa Latatu, Izortze Santin Gomez, 2025, ISBN 978-84-8438-928-6, págs. 181-186
• Idioma: euskera
• Enlaces
  • Texto Completo Libro
• Resumen
  • euskara

    COVID-19aren pandemiak algoritmo prediktiboetan oinarritutako erabaki-sistemak garatzeko presioa areagotu du, osasun-sistemen karga kudeaezina arintzeko helburuarekin. Osasun-egoera erronkatsu honii aurre egiteko, ikerketa honetan tokiko ospitale bateko COVID-19 pazienteen datu-multzo erreal baten azterketa sakona burutu dugu. Artikuluak triajea iragarpen-arazo gisa planteatzen du, klase anitzeko sailkapen baten bidez formulatua, aldagai fisiologikoen adinarekiko normalizazioa bereziki aztertuz. Lortutako emaitza esperimentalak aurkezten ditugu, tokiko ospitale batean onartutako COVID-19ko pazienteen datuetan oinarrituta. Emaitzek aplikazio praktikoetarako aukera itxaropentsuak eskaintzen dituzte, datuen oreka eta sailkapena hobetuz, medikuek paziente kritikoei esleituko dieten triaje-iragarpena optimizatzeko.

  • English

    The COVID-19 pandemic has increased the pressure on developing clinical decision-making systems based on predictive algorithms, potentially helping to reduce the unmanageable strain on healthcare systems. In an attempt to address this challenging health situation, we attempted to provide a contribution to this endeavour with an in-depth study of a real-life dataset of covid-19 patients from a local hospital. In this paper, we approach the problem as triage prediction problem, formulated as multi-class classification problem, with special care on the age normalization of physiological variables. We report experimental results obtained on a data sample covering COVID-19 patients assisted in a local hospital. To do this, we tried to emulate the triage decisions of the physicians recorded in a dataset containing the measurements of physiological variables and the triage decision. We obtained results that provide encouragement for a real-life application development of the data balancing and classification in the prediction of the triage that the medical doctors will assign the critical patients.