A Review of Deep Transfer Learning Approaches for Class-Wise Prediction of Alzheimer’s Disease Using MRI Images

This article describes the public health impact of Alzheimer's disease (AD), including incidence and prevalence, mortality and morbidity, use and costs of care, and the overall impact on family caregivers, the dementia workforce and society. The Special Report discusses consumers' and primary care physicians' perspectives on awareness, diagnosis and treatment of mild cognitive impairment (MCI), including MCI due to Alzheimer's disease. An estimated 6.5 million Americans age 65 and older are living with Alzheimer's dementia today. This number could grow to 13.8 million by 2060 barring the development of medical breakthroughs to prevent, slow or cure AD. Official death certificates recorded 121,499 deaths from AD in 2019, the latest year for which data are available. Alzheimer's disease was officially listed as the sixth-leading cause of death in the United States in 2019 and the seventh-leading cause of death in 2020 and 2021, when COVID-19 entered the ranks of the top ten causes of death. Alzheimer's remains the fifth-leading cause of death among Americans age 65 and older. Between 2000 and 2019, deaths from stroke, heart disease and HIV decreased, whereas reported deaths from AD increased more than 145%. More than 11 million family members and other unpaid caregivers provided an estimated 16 billion hours of care to people with Alzheimer's or other dementias in 2021. These figures reflect a decline in the number of caregivers compared with a decade earlier, as well as an increase in the amount of care provided by each remaining caregiver. Unpaid dementia caregiving was valued at $271.6 billion in 2021. Its costs, however, extend to family caregivers' increased risk for emotional distress and negative mental and physical health outcomes - costs that have been aggravated by COVID-19. Members of the dementia care workforce have also been affected by COVID-19. As essential care workers, some have opted to change jobs to protect their own health and the health of their families. However, this occurs at a time when more members of the dementia care workforce are needed. Average per-person Medicare payments for services to beneficiaries age 65 and older with AD or other dementias are almost three times as great as payments for beneficiaries without these conditions, and Medicaid payments are more than 22 times as great. Total payments in 2022 for health care, long-term care and hospice services for people age 65 and older with dementia are estimated to be $321 billion. A recent survey commissioned by the Alzheimer's Association revealed several barriers to consumers' understanding of MCI. The survey showed low awareness of MCI among Americans, a reluctance among Americans to see their doctor after noticing MCI symptoms, and persistent challenges for primary care physicians in diagnosing MCI. Survey results indicate the need to improve MCI awareness and diagnosis, especially in underserved communities, and to encourage greater participation in MCI-related clinical trials.

Deep learning, a state-of-the-art machine learning approach, has shown outstanding performance over traditional machine learning in identifying intricate structures in complex high-dimensional data, especially in the domain of computer vision. The application of deep learning to early detection and automated classification of Alzheimer's disease (AD) has recently gained considerable attention, as rapid progress in neuroimaging techniques has generated large-scale multimodal neuroimaging data. A systematic review of publications using deep learning approaches and neuroimaging data for diagnostic classification of AD was performed. A PubMed and Google Scholar search was used to identify deep learning papers on AD published between January 2013 and July 2018. These papers were reviewed, evaluated, and classified by algorithm and neuroimaging type, and the findings were summarized. Of 16 studies meeting full inclusion criteria, 4 used a combination of deep learning and traditional machine learning approaches, and 12 used only deep learning approaches. The combination of traditional machine learning for classification and stacked auto-encoder (SAE) for feature selection produced accuracies of up to 98.8% for AD classification and 83.7% for prediction of conversion from mild cognitive impairment (MCI), a prodromal stage of AD, to AD. Deep learning approaches, such as convolutional neural network (CNN) or recurrent neural network (RNN), that use neuroimaging data without pre-processing for feature selection have yielded accuracies of up to 96.0% for AD classification and 84.2% for MCI conversion prediction. The best classification performance was obtained when multimodal neuroimaging and fluid biomarkers were combined. Deep learning approaches continue to improve in performance and appear to hold promise for diagnostic classification of AD using multimodal neuroimaging data. AD research that uses deep learning is still evolving, improving performance by incorporating additional hybrid data types, such as—omics data, increasing transparency with explainable approaches that add knowledge of specific disease-related features and mechanisms.

The study aim is to explore the perceptions and expectations of seniors in regard to "smart home" technology installed and operated in their homes with the purpose of improving their quality of life and/or monitoring their health status. Three focus group sessions were conducted within this pilot study to assess older adults' perceptions of the technology and ways they believe technology can improve their daily lives. Themes discussed in these groups included participants' perceptions of the usefulness of devices and sensors in health-related issues such as preventing or detecting falls, assisting with visual or hearing impairments, improving mobility, reducing isolation, managing medications, and monitoring of physiological parameters. The audiotapes were transcribed and a content analysis was performed. A total of 15 older adults participated in three focus group sessions. Areas where advanced technologies would benefit older adult residents included emergency help, prevention and detection of falls, monitoring of physiological parameters, etc. Concerns were expressed about the user-friendliness of the devices, lack of human response and the need for training tailored to older learners. All participants had an overall positive attitude towards devices and sensors that can be installed in their homes in order to enhance their lives.