Your browser doesn't support javascript.
loading
A machine learning-based prediction of tau load and distribution in Alzheimer's disease using plasma, MRI and clinical variables.
Karlsson, Linda; Vogel, Jacob; Arvidsson, Ida; Åström, Kalle; Strandberg, Olof; Seidlitz, Jakob; Bethlehem, Richard A I; Stomrud, Erik; Ossenkoppele, Rik; Ashton, Nicholas J; Zetterberg, Henrik; Blennow, Kaj; Palmqvist, Sebastian; Smith, Ruben; Janelidze, Shorena; Joie, Renaud La; Rabinovici, Gil D; Binette, Alexa Pichet; Mattsson-Carlgren, Niklas; Hansson, Oskar.
Affiliation
  • Karlsson L; Clinical Memory Research Unit, Department of Clinical Sciences in Malmö, Lund University, Lund, Sweden.
  • Vogel J; Clinical Memory Research Unit, Department of Clinical Sciences in Malmö, Lund University, Lund, Sweden.
  • Arvidsson I; Department of Clinical Sciences, SciLifeLab, Lund University, Lund, Sweden.
  • Åström K; Centre for Mathematical Sciences, Lund University, Lund, Sweden.
  • Strandberg O; Centre for Mathematical Sciences, Lund University, Lund, Sweden.
  • Seidlitz J; Clinical Memory Research Unit, Department of Clinical Sciences in Malmö, Lund University, Lund, Sweden.
  • Bethlehem RAI; Penn/CHOP Lifespan Brain Institute, University of Pennsylvania, Philadelphia, PA 19104, USA.
  • Stomrud E; Department of Psychiatry, University of Pennsylvania, Philadelphia, PA, 19104 USA.
  • Ossenkoppele R; Department of Child and Adolescent Psychiatry and Behavioral Science, The Children's Hospital of Philadelphia, Philadelphia, PA, 19104 USA.
  • Ashton NJ; Institute for Translational Medicine and Therapeutics, University of Pennsylvania, Philadelphia, PA, 19104 USA.
  • Zetterberg H; University of Cambridge, Department of Psychology, Cambridge Biomedical Campus, Cambridge, CB2 3EB, UK.
  • Blennow K; Clinical Memory Research Unit, Department of Clinical Sciences in Malmö, Lund University, Lund, Sweden.
  • Palmqvist S; Memory Clinic, Skåne University Hospital, Malmö, Sweden.
  • Smith R; Clinical Memory Research Unit, Department of Clinical Sciences in Malmö, Lund University, Lund, Sweden.
  • Janelidze S; Alzheimer Center Amsterdam, Department of Neurology, Amsterdam Neuroscience, Amsterdam UMC, Amsterdam, Netherlands.
  • Joie R; Department of Psychiatry and Neurochemistry, Institute of Neuroscience and Physiology, the Sahlgrenska Academy, University of Gothenburg, Mölndal, Sweden.
  • Rabinovici GD; Institute of Psychiatry, Psychology and Neuroscience, Maurice Wohl Institute Clinical Neuroscience, King's College London, London, UK.
  • Binette AP; Department of Psychiatry and Neurochemistry, Institute of Neuroscience and Physiology, the Sahlgrenska Academy, University of Gothenburg, Mölndal, Sweden.
  • Mattsson-Carlgren N; Clinical Neurochemistry Laboratory, Sahlgrenska University Hospital, Mölndal, Sweden.
  • Hansson O; Department of Neurodegenerative Disease, UCL Institute of Neurology, Queen Square, London, UK.
medRxiv ; 2024 Sep 23.
Article in En | MEDLINE | ID: mdl-38853877
ABSTRACT
Tau positron emission tomography (PET) is a reliable neuroimaging technique for assessing regional load of tau pathology in the brain, commonly used in Alzheimer's disease (AD) research and clinical trials. However, its routine clinical use is limited by cost and accessibility barriers. Here we explore using machine learning (ML) models to predict clinically useful tau-PET composites from low-cost and non-invasive features, e.g., basic clinical variables, plasma biomarkers, and structural magnetic resonance imaging (MRI). Results demonstrated that models including plasma biomarkers yielded the most accurate predictions of tau-PET burden (best model R-squared=0.66-0.68), with especially high contribution from plasma P-tau217. In contrast, MRI variables stood out as best predictors (best model R-squared=0.28-0.42) of asymmetric tau load between the two hemispheres (an example of clinically relevant spatial information). The models showed high generalizability to external test cohorts with data collected at multiple sites. Based on these results, we also propose a proof-of-concept two-step classification workflow, demonstrating how the ML models can be translated to a clinical setting. This study uncovers current potential in predicting tau-PET information from scalable cost-effective variables, which could improve diagnosis and prognosis of AD.

Full text: 1 Collection: 01-internacional Database: MEDLINE Language: En Journal: MedRxiv Year: 2024 Document type: Article Affiliation country: Sweden Country of publication: United States

Full text: 1 Collection: 01-internacional Database: MEDLINE Language: En Journal: MedRxiv Year: 2024 Document type: Article Affiliation country: Sweden Country of publication: United States