GLORIA

GEOMAR Library Ocean Research Information Access

X

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
Filter
  • Wiley  (2)
  • English  (2)
Material
Publisher
  • Wiley  (2)
Person/Organisation
Language
  • English  (2)
Years
  • 1
    Online Resource
    Online Resource
    Predicting future amyloid biomarkers in dementia patients with machine learning to improve clinical trial patient selection
    Wiley ; 2021
    In:  Alzheimer's & Dementia: Translational Research & Clinical Interventions Vol. 7, No. 1 ( 2021-01)
    Details
    In: Alzheimer's & Dementia: Translational Research & Clinical Interventions, Wiley, Vol. 7, No. 1 ( 2021-01)
    Abstract: In Alzheimer's disease, asymptomatic patients may have amyloid deposition, but predicting their progression rate remains a substantial challenge with implications for clinical trial enrollment. Here, we demonstrate an artificial intelligence approach to use baseline clinical information and images to predict changes in quantitative biomarkers of brain pathology on future images. Methods Patients from the Alzheimer's Disease Neuroimaging Initiative (ADNI) who underwent positron emission tomography (PET) with the amyloid radiotracer 18F‐AV45 (florbetapir) were included. We identified important baseline PET image features using a deep convolutional neural network based on ResNet. These were combined with eight clinical, demographic, and genetic markers using a gradient‐boosted decision tree (GBDT) algorithm to predict future quantitative standardized uptake value ratio (SUVR), an established biomarker of brain amyloid deposition. We used this model to better identify individuals with the highest positive change in amyloid deposition on future images and compared this to typical inclusion criteria for clinical trials. We also compared the model's performance to other methods such as multivariate linear regression and GBDT without imaging features. Findings Using 2577 PET scans from 1224 unique individuals, we showed that the GBDT with deep image features was significantly more accurate than the other approaches, reaching a root mean squared error of 0.0339 ± 0.0027 for future SUVR prediction. Using this approach, we could identify individuals with the highest 10% SUVR accumulation at rates 2‐ to 4‐fold higher than by random pick or existing inclusion criteria. Discussion Predicting quantitative biomarkers on future images using machine learning methods consisting of deep image features combined with clinical data may allow better targeting of treatments or enrollment in clinical trials.
    Type of Medium: Online Resource
    ISSN: 2352-8737 , 2352-8737
    URL: Issue
    URL: Article
    DOI: 10.1002/trc2.v7.1
    DOI: 10.1002/trc2.12212
    Language: English
    Publisher: Wiley
    Publication Date: 2021
    detail.hit.zdb_id: 2832891-7
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 2
    Online Resource
    Online Resource
    A Novel PowderMEMS Technique for Fabrication of Low‐Cost High‐Power‐Factor Thermoelectric Films and Micro‐Patterns
    Wiley ; 2023
    In:  Advanced Engineering Materials Vol. 25, No. 9 ( 2023-05)
    Details
    In: Advanced Engineering Materials, Wiley, Vol. 25, No. 9 ( 2023-05)
    Abstract: Thermoelectric (TE) films, which are normally fabricated by MicroElectroMechanical‐Systems (MEMS) technology, are crucial for the development of micro‐TE devices (e.g., Peltier coolers for hot‐spot cooling, TE generators). However, achieving a significant TE property (e.g., high power factor) of TE films and a low‐cost fabrication process is challenging. A novel fabrication technique named PowderMEMS to fabricate high‐performance, low‐cost TE films, and micro‐patterns is presented in this article. The TE film is based on agglomeration of micro‐sized N‐type (BTS) powders with stoichiometric composition by the molten binder bismuth (Bi). The influence of the key process parameters (e.g., the weight ratio between the TE powder and the binder, the hot‐pressing duration, and pressure) on the TE performance is investigated. The TE film exhibits a maximum power factor of 1.7  at room temperature, which is the highest value reported so far for the state‐of‐the‐art TE thick film (thickness  〉  10 μm). Besides, the PowderMEMS‐based TE films are successfully patterned to the micro‐pillar array, which opens up a new MEMS‐compatible approach for manufacturing micro‐TE devices.
    Type of Medium: Online Resource
    ISSN: 1438-1656 , 1527-2648
    URL: Issue
    URL: Article
    DOI: 10.1002/adem.v25.9
    DOI: 10.1002/adem.202201546
    Language: English
    Publisher: Wiley
    Publication Date: 2023
    detail.hit.zdb_id: 2016980-2
    detail.hit.zdb_id: 1496512-4
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...