Projektportal

Startsida Om denna webbplats

Logga in

Applying Deep Learning Models to Predict Long-term Culture Conversion in TB Treatment

Terrmin

HT24

Beskrivning

Background: Tuberculosis (TB) is one of the top 10 causes of death and the leading cause of death from a single infectious agent [1]. After decades of limited progress, the development of novel anti-TB medicines was revitalized at the start of the 21st century due to the re-purposing of existing drugs and finding new drugs [2]. However, progress has been still slow for a disease that, until the emergence of the COVID-19 pandemic, has remained the top infectious killer worldwide. Therefore, the WHO announces the new goal to reach the ambitious target of ‘‘ending TB’’ set by the WHO within its new Global Strategy (2016–2030) [3].
Long-term culture conversion in TB treatment is a critical endpoint, where sputum samples of a treated patient consistently show no growth of Mycobacterium tuberculosis. Traditionally, the assessment of culture conversion can be time-consuming and resource-intensive. Deep learning models, which have shown their power in pre-clinical discovery [4], could be a method to speed up the process.
Aim: To develop and validate deep learning models for predicting long-term culture conversion in TB patients.
Method: The project focuses on developing deep learning models using python to predict long-term culture conversion in TB treatment. Data for training and validation will come from longitudinal studies on TB patients. Performance will be evaluated based on statistical metrics and graphs.

References:
1. Mello FCQ, Silva DR, Dalcolmo MP. Tuberculosis: where are we?. J Bras Pneumol. 2018;44(2):82. doi:10.1590/s1806-37562017000000450
2. Guy ES, Mallampalli A. Managing TB in the 21st century: existing and novel drug therapies. Ther Adv Respir Dis. 2008 Dec;2(6):401-8. doi: 10.1177/1753465808099522. PMID: 19124385.
3. Floyd K, Glaziou P, Houben RMGJ, Sumner T, White RG, Raviglione M. Global tuberculosis targets and milestones set for 2016-2035: definition and rationale. Int J Tuberc Lung Dis. 2018;22(7):723-730. doi:10.5588/ijtld.17.0835
4. Paul D, Sanap G, Shenoy S, Kalyane D, Kalia K, Tekade RK. Artificial intelligence in drug discovery and development. Drug Discov Today. 2021;26(1):80-93. doi:10.1016/j.drudis.2020.10.010

Huvudområde

Farmaceutisk vetenskap

Ämne

Farmakometri

Typ

Beräkningsstudie

Företag

Uppsala University

Ort/Plats

Uppsala

Handledarens namn

Huifang You och Ulrika Simonsson

Handledarens e-post

huifang.you@uu.se

Institution

Institutionen för farmaceutisk biovetenskap

Program

Masterprogram i läkemedelsmodellering

Kurs

Degree Project in Pharmaceutical Modelling within Pharmacometrics 30 c - 3FB007

Omfattning/hp

30hp