
Predictive modeling of suicidal behavior among older
Torsdag 22 maj 2025 13:00 - 13:20 F1
Föreläsare: Mahmoud Rahat
Spår: Future Health and Care
This presentation is about a master thesis work, a collaboration between a group of researchers from Halmstad University and Statistikkonsulterna AB. The project investigated how machine learning and survival analysis can be used to predict suicidal behavior among older adults in Sweden. The study analyzed historical data from the Swedish National Registry, including medication use, medical conditions, and sociodemographic details. The research aimed to improve prediction accuracy by combining survival analysis techniques — such as Cox Proportional Hazards (CoxPH), Random Survival Forest (RSF), and Gradient Boosting Survival Analysis (GBSA) — alongside sequential machine learning approaches, like Long Short-Term Memory (LSTM) networks. The findings highlighted the potential of utilizing historical data to predict suicide risks using advanced machine learning models.
Ämne
Data och information
Seminarietyp
Live + på plats
Föreläsningsformat
Presentation
Föreläsningssyfte
Verktyg för implementering
Kunskapsnivå
Fördjupning
Målgrupp
Chef/Beslutsfattare
Tekniker/IT/Utvecklare
Forskare (även studerande)
Omsorgspersonal
Vårdpersonal
Patientorganisationer/Brukarorganisationer
Nyckelord
Exempel från verkligheten (goda/dåliga)
Nytta/effekt
Föreläsare
Mahmoud Rahat Föreläsare
Assistant professor in machine learning
Halmstad University.