Call for Papers

Special Issue: AI-Driven Measurement in Gerontological Research: Digital Metrics, Biomarkers, and Phenotypes in Cognitive, Behavioral, and Psychological Sciences

Guest Co-Editors: Ganesh M. Babulal, PhD, OTD (Washington University School of Medicine), Maiya R. Geddes, MD, FRCPC (Montreal Neurological Institute; McGill University), and Laura Thi Germine, PhD (McLean Hospital; Harvard Medical School).

Gerontological research is experiencing unprecedented advancements in the field of artificial intelligence (AI). This includes data-centric algorithms such as machine learning (ML) and deep learning (DL), natural language processing (NLP), large language models (LLMs), and computer vision combined with digital metrics and phenotypes to identify patterns, make predictions, improve diagnosis, monitor disease progression, and assess the effectiveness of interventions. Digital metrics, including so-called digital biomarkers, are objective, quantifiable physiological, cognitive, psychological, social, and behavioral data that are collected and analyzed using devices such as wearables, smartphones, and other sensor-equipped (e.g., global positioning systems [GPS], accelerometers) technologies. These technologies hold promise for multidimensional detection and tracking of changes at the intersection of cognition functioning, affect/mood, behavior, and daily function and for analyzing large-scale, high-dimensional datasets to improve precision and move beyond group comparison valuable results. However, gerontological research must contend with some key challenges posed by the rapid development of new tools and methodological approaches:

1. Many ML models, especially complex DL architectures, are often viewed as “black boxes” with limited interpretability. Understanding how these models make predictions is crucial for translating research findings into actionable insights and informing clinical decision-making in the context of aging and neurobehavioral functioning.
2. AI integration with traditional research methods remains a challenge to ensure that ML techniques complement established methodologies in aging research.
3. Access to large, diverse, and longitudinally collected datasets that extend earlier in the lifespan is essential for training accurate ML models. However, these datasets may be limited in scope or difficult to obtain due to privacy concerns, policies around data sovereignty, and challenges in data standardization.
4. ML models may achieve high predictive accuracy, precision, and recall in identifying risk factors or early neurobehavioral markers of functional decline. However, their clinical validity and utility in real-world settings require rigorous validation and evaluation, and translation into clinically meaningful outcomes requires further development.
5. Establishing collaborative efforts between researchers, clinicians, policymakers, and industry partners is essential for translating ML findings into actionable strategies for promoting healthy aging and well-being. Improving the interpretability and transparency of ML models is essential for building trust and acceptance among researchers and clinical practitioners.

We invite researchers and scholars to submit original contributions that integrate and examine AI and specific ML approaches to provide deeper insights into the complex dynamics of aging, neurobehavioral functioning, clinical and ecological validity, precision medicine, and ethical considerations.

Topics that will be considered include but are not limited to:

• AI-based predictive analytics, prognostics, and decision support systems.
• Forecast neurobehavioral and/or functional decline, identify risk factors for prevention trials, and enhance early detection of age-related cognitive impairments.
• ML applications that address diversity, equity, inclusion, and accessibility in gerontology and aging.
• Novel applications of ML techniques in understanding cognitive aging processes, such as memory decline, attentional deficits, and executive dysfunction.
• Investigating the use of digital measures of mood and behavior for early identification and supporting mental health and well-being.
• Addressing ethical and regulatory considerations, privacy concerns, and societal impacts associated with the integration of ML approaches in gerontological research.
• Innovative AI methodologies to improve cognitive functioning, mood, neurobehavioral, and functional outcomes.

Manuscripts must be submitted via the ScholarOne submission website for the Psychological Sciences Section of The Journals of Gerontology, Series B: Psychological Sciences and Social Sciences. Authors are advised to carefully read and follow formatting directions detailed in the Instructions to Authors. Ganesh M. Babulal, PhD, OTD, Maiya R. Geddes, MD, FRCPC, and Laura Thi Germine, PhD, will serve as guest co-editors for this special issue. Manuscripts will be evaluated using the journal’s usual peer-review process.

For any questions, please contact the editorial office.

Manuscript submissions due: August 1, 2024
Issue publication date (expected): July 2025