Currently submitted to: JMIR Aging
Date Submitted: Jun 2, 2026
Open Peer Review Period: Jun 3, 2026 - Jul 29, 2026
(currently open for review)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Aging-related innovation for older adults: patent landscape analysis using machine learning and cross-country comparison
ABSTRACT
Background:
Global population aging is accelerating, with the share of individuals aged 65 and older projected to rise from 10% in 2022 to 16% by 2050. Technological innovation plays a critical role in addressing the health, functional, and social needs of older adults, spanning domains from biotechnology and pharmaceuticals to digital health and assistive devices. Despite the breadth of aging-related innovation, a comprehensive and systematic understanding of the global innovation landscape, including how it has evolved over time and varies across countries, remains limited.
Objective:
This study aimed to identify and categorize aging-related innovations across technological domains, analyze their temporal evolution, and compare cross-national innovation patterns.
Methods:
Patent data from the United States Patent and Trademark Office (USPTO) were used as a proxy for innovation activity. A total of 15,250 aging-related patents filed between 2003 and 2022 were collected using a predefined set of search terms targeting older adult populations. Cooperative Patent Classification (CPC) codes were expanded hierarchically and processed using 2 machine learning techniques: Uniform Manifold Approximation and Projection (UMAP) for dimensionality reduction and K-means clustering (k=32) to group patents by technological similarity. Expert review was conducted to label and consolidate clusters into innovation topics and categories. Innovation trends were examined across 4 five-year periods (2003–2007, 2008–2012, 2013–2017, and 2018–2022). Country-level innovation output was normalized by gross domestic product (GDP) to enable fair cross-national comparison across the top 15 contributing countries, which collectively accounted for 92.8% of all patents.
Results:
Three major innovation categories were identified: Biotechnology and Therapeutics (A1), Pharmaceuticals and Nutrition (A2), and Medical Devices and Digital Health Technologies (A3), comprising 10 topics in total. Category A3 held the largest share across all periods (55.6% in Period 1; 43.5% in Period 4), but declined proportionally as A1and A2 showed faster growth, reflecting a shift toward upstream biological and pharmacological interventions. Patent counts in most countries outpaced GDP growth between Period 1 and Period 4, with China recording the highest absolute growth in both GDP and patents. When normalized by GDP, Switzerland ranked first in Period 4, followed by Israel and the United States. The United States contributed the largest absolute number of patents.
Conclusions:
Aging-related innovation is expanding rapidly and increasingly treated as a strategic national priority beyond welfare considerations. The shift toward biotechnology- and pharmaceutical-oriented innovation suggests growing emphasis on upstream interventions for healthy aging. Cross-national differences in innovation efficiency, shaped by R&D investment, institutional capacity, and demographic pressures, underscore the importance of targeted policy alignment to address the challenges and opportunities of global population aging.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.