Szczegóły publikacji
Opis bibliograficzny
Comparative pharmacokinetics of nicotine from e-cigarettes and traditional cigarettes: a PBPK modeling and machine learning approach / Joanna Chwał, Arkadiusz Banasik, Radosław Dzik, Piotr PAŃTAK, Ewaryst Tkacz // W: Progress in Polish artificial intelligence research 6 [Dokument elektroniczny] : 6th Polish Conference on Artifical Intelligence (PP-RAI'2025) : 07–09.04.2025, Katowice, Poland / ed. by Rafał Doroz, Beata Zielosko. — Wersja do Windows. — Dane tekstowe. — Katowice : Wydawnictwo Uniwersytetu Śląskiego, 2025. — e-ISBN: 978-83-226-4405-8. — S. 43–49. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 48–49, Abstr.
Autorzy (5)
- Chwał Joanna
- Banasik Arkadiusz
- Dzik Radosław
- AGHPańtak Piotr
- Tkacz Ewaryst
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 165792 |
|---|---|
| Data dodania do BaDAP | 2026-02-03 |
| Tekst źródłowy | URL |
| Rok publikacji | 2025 |
| Typ publikacji | fragment monografii pokonferencyjnej |
| Otwarty dostęp |  |
| Creative Commons | |
| Wydawca | Uniwersytet Śląski w Katowicach |
Abstract
Nicotine addiction remains a major public health concern, withe-cigarettes altering exposure dynamics by delivering nicotine in aerosolform. This study uses Physiologically Based Pharmacokinetic (PBPK) modeling combined with eXtreme Gradient Boosting (XGBoost) to simulate nicotine distribution and assess individual variability. Results show that e-cigarettes lead to more sustained nicotine exposure, while traditional cigarettes cause rapid peaks in blood and brain concentra-tions. Blood-brain permeability was identified as the key factor influencingbrain accumulation. ML integration significantly enhanced prediction accuracy (𝑅2> 0.9998). These findings underscore the pharmacokinetic differences between delivery methods and demonstrate the value of combiningPBPK and ML approaches for personalized exposure modeling and publichealth guidance.
