Multimodal deep learning for Alzheimer’s disease dementia assessment

Shangran Qiu, Matthew I. Miller, Prajakta S. Joshi, Joyce C. Lee, Chonghua Xue, Yunruo Ni, Yuwei Wang, Ileana Anda-Duran, Phillip H. Hwang, Justin A. Cramer, Brigid C. Dwyer, Honglin Hao, Michelle C. Kaku, Sachin Kedar, Peter H. Lee, Asim Z. Mian, Daniel L. Murman, Sarah O’Shea, Aaron B. Paul, Marie-Helene Saint-Hilaire, E. Alton Sartor, Aneeta R. Saxena, Ludy C. Shih, Juan E. Small, Maximilian J. Smith, Arun Swaminathan, Courtney E. Takahashi, Olga Taraschenko, Hui You, Jing Yuan, Yan Zhou, Shuhan Zhu, Michael L. Alosco, Jesse Mez, Thor D. Stein, Kathleen L. Poston, Rhoda Au and Vijaya B. Kolachalama ()
Additional contact information
Shangran Qiu: Boston University School of Medicine
Matthew I. Miller: Boston University School of Medicine
Prajakta S. Joshi: Boston University School of Medicine
Joyce C. Lee: Boston University School of Medicine
Chonghua Xue: Boston University School of Medicine
Yunruo Ni: Boston University School of Medicine
Yuwei Wang: Boston University School of Medicine
Ileana Anda-Duran: Tulane University
Phillip H. Hwang: Boston University School of Medicine
Justin A. Cramer: University of Nebraska Medical Center
Brigid C. Dwyer: Boston University School of Medicine
Honglin Hao: Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences
Michelle C. Kaku: Boston University School of Medicine
Sachin Kedar: University of Nebraska Medical Center
Peter H. Lee: Lahey Hospital & Medical Center
Asim Z. Mian: Boston University School of Medicine
Daniel L. Murman: University of Nebraska Medical Center
Sarah O’Shea: Boston University School of Medicine
Aaron B. Paul: Lahey Hospital & Medical Center
Marie-Helene Saint-Hilaire: Boston University School of Medicine
E. Alton Sartor: Boston University School of Medicine
Aneeta R. Saxena: Boston University School of Medicine
Ludy C. Shih: Boston University School of Medicine
Juan E. Small: Lahey Hospital & Medical Center
Maximilian J. Smith: Lahey Hospital & Medical Center
Arun Swaminathan: University of Nebraska Medical Center
Courtney E. Takahashi: Boston University School of Medicine
Olga Taraschenko: University of Nebraska Medical Center
Hui You: Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences
Jing Yuan: Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences
Yan Zhou: Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences
Shuhan Zhu: Boston University School of Medicine
Michael L. Alosco: Boston University School of Medicine
Jesse Mez: Boston University School of Medicine
Thor D. Stein: Boston University Alzheimer’s Disease Research Center
Kathleen L. Poston: Stanford University
Rhoda Au: Boston University School of Medicine
Vijaya B. Kolachalama: Boston University School of Medicine

Nature Communications, 2022, vol. 13, issue 1, 1-17

Abstract: Abstract Worldwide, there are nearly 10 million new cases of dementia annually, of which Alzheimer’s disease (AD) is the most common. New measures are needed to improve the diagnosis of individuals with cognitive impairment due to various etiologies. Here, we report a deep learning framework that accomplishes multiple diagnostic steps in successive fashion to identify persons with normal cognition (NC), mild cognitive impairment (MCI), AD, and non-AD dementias (nADD). We demonstrate a range of models capable of accepting flexible combinations of routinely collected clinical information, including demographics, medical history, neuropsychological testing, neuroimaging, and functional assessments. We then show that these frameworks compare favorably with the diagnostic accuracy of practicing neurologists and neuroradiologists. Lastly, we apply interpretability methods in computer vision to show that disease-specific patterns detected by our models track distinct patterns of degenerative changes throughout the brain and correspond closely with the presence of neuropathological lesions on autopsy. Our work demonstrates methodologies for validating computational predictions with established standards of medical diagnosis.

Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-022-31037-5 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:13:y:2022:i:1:d:10.1038_s41467-022-31037-5

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-022-31037-5

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().