EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep learning to predict rapid progression of Alzheimer’s disease from pooled clinical trials: A retrospective study

Xiaotian Ma iD, Madison Shyer iD, Kristofer Harris iD, Dulin Wang, Yu-Chun Hsu, Christine Farrell, Nathan Goodwin, Sahar Anjum, Avram S Bukhbinder, Sarah Dean, Tanveer Khan, David Hunter und 3 weitere

PLOS Digital Health · 10.04.2024 · 3 (4) · e0000479

DOI: 10.1371/journal.pdig.0000479 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Digital Health, online erschienen am 10.04.2024. Verfasst von Xiaotian Ma und 14 weiteren Autor:innen. Beteiligte Einrichtung: Department of Health Data Science and Artificial Intelligence, McWilliams School of Biomedical Informatics, The University of Texas Health Science Ce…. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIA NIH HHS, NHGRI NIH HHS, NCI NIH HHS.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rate of progression of Alzheimer’s disease (AD) differs dramatically between patients. Identifying the most is critical because when their numbers differ between treated and control groups, it distorts the outcome, making it impossible to tell whether the treatment was beneficial. Much recent effort, then, has gone into identifying RPs. We pooled de-identified placebo-arm data of three randomized controlled trials (RCTs), EXPEDITION, EXPEDITION 2, and EXPEDITION 3, provided by Eli Lilly and Company. After processing, the data included 1603 mild-to-moderate AD patients with 80 weeks of longitudinal observations on neurocognitive health, brain volumes, and amyloid-beta (Aβ) levels. RPs were defined by changes in four neurocognitive/functional health measures. We built deep learning models using recurrent neural networks with attention mechanisms to predict RPs by week 80 based on varying observation periods from baseline (e.g., 12, 28 weeks). Feature importance scores for RP prediction were computed and temporal feature trajectories were compared between RPs and non-RPs. Our evaluation and analysis focused on models trained with 28 weeks of observation. The models achieved robust internal validation area under the receiver operating characteristic (AUROCs) ranging from 0.80 (95% CI 0.79–0.82) to 0.82 (0.81–0.83), and the area under the precision-recall curve (AUPRCs) from 0.34 (0.32–0.36) to 0.46 (0.44–0.49). External validation AUROCs ranged from 0.75 (0.70–0.81) to 0.83 (0.82–0.84) and AUPRCs from 0.27 (0.25–0.29) to 0.45 (0.43–0.48). Aβ plasma levels, regional brain volumetry, and neurocognitive health emerged as important factors for the model prediction. In addition, the trajectories were stratified between predicted RPs and non-RPs based on factors such as ventricular volumes and neurocognitive domains. Our findings will greatly aid clinical trialists in designing tests for new medications, representing a key step toward identifying effective new AD therapies.

Autor:innen und Institutionen

  • Department of Health Data Science and Artificial Intelligence, McWilliams School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, Texas, United States of America.
  • Department of Neurology, McGovern Medical School, The University of Texas Health Science Center at Houston, Houston, Texas, United States of America.
  • Division of Pediatric Neurology, Massachusetts General Hospital, Boston, Massachusetts, United States of America.

ORCID-Profile: Xiaotian Ma, Madison Shyer, Kristofer Harris

Förderung

  • NIA NIH HHS
  • NHGRI NIH HHS
  • NCI NIH HHS
  • NCATS NIH HHS
  • NLM NIH HHS
  • NIH HHS
  • Cancer Prevention and Research Institute of Texas
  • National Science Foundation

Zitieren

APA

Ma, X., Shyer, M., Harris, K., Wang, D., Hsu, Y. C., Farrell, C., Goodwin, N., Anjum, S., Bukhbinder, A. S., Dean, S., Khan, T., Hunter, D., Schulz, P. E., Jiang, X., & Kim, Y. (2024). Deep learning to predict rapid progression of Alzheimer’s disease from pooled clinical trials: A retrospective study. PLOS Digital Health, 3(4), e0000479. https://doi.org/10.1371/journal.pdig.0000479

Vancouver

Ma X, Shyer M, Harris K, Wang D, Hsu YC, Farrell C, et al. Deep learning to predict rapid progression of Alzheimer’s disease from pooled clinical trials: A retrospective study. PLOS Digital Health. 2024;3(4):e0000479. doi:10.1371/journal.pdig.0000479

BibTeX
@article{Ma2024,
  author = {Ma, Xiaotian and Shyer, Madison and Harris, Kristofer and Wang, Dulin and Hsu, Yu-Chun and Farrell, Christine and Goodwin, Nathan and Anjum, Sahar and Bukhbinder, Avram S and Dean, Sarah and Khan, Tanveer and Hunter, David and Schulz, Paul E and Jiang, Xiaoqian and Kim, Yejin},
  title = {Deep learning to predict rapid progression of Alzheimer’s disease from pooled clinical trials: A retrospective study},
  journal = {PLOS Digital Health},
  year = {2024},
  volume = {3},
  number = {4},
  pages = {e0000479},
  doi = {10.1371/journal.pdig.0000479}
}
Kostenlos starten →