Deep Learning and Geriatric Mental Health.

The goal of this overview is to help clinicians develop basic proficiency with the terminology of deep learning and understand its fundamentals and early applications. We describe what machine learning and deep learning represent and explain the underlying data science principles. We also review current promising applications and identify ethical issues that bear consideration. Deep Learning is a new type of machine learning that is remarkably good at finding patterns in data, and in some cases generating realistic new data. We provide insights into how deep learning works and discuss its relevance to geriatric psychiatry.

Review of Management Considerations for Excoriation Disorder in Older Adults.

Excoriation disorder (ED) is defined as compulsive skin picking that results in skin damage and emotional distress. Optimal management of ED includes individualized treatment plans consisting of psychotherapies, behavioral and pharmacologic interventions. Compared with younger populations, older adults are at increased risk for poor outcomes, such as infection and hospitalization, and require unique management considerations. Risk factors that contribute to disease burden include age-related changes to the skin and underlying medical and psychiatric comorbidities. A literature review was conducted on ED yielding limited evidence exclusive to older adults. The authors suggest a therapeutic approach to ED in older adults based on available evidence and experience from inpatient and outpatient psychiatric settings. Finally, opportunities for future research are highlighted.

Returning Individual Research Results from Digital Phenotyping in Psychiatry.

Psychiatry is rapidly adopting digital phenotyping and artificial intelligence/machine learning tools to study mental illness based on tracking participants' locations, online activity, phone and text message usage, heart rate, sleep, physical activity, and more. Existing ethical frameworks for return of individual research results (IRRs) are inadequate to guide researchers for when, if, and how to return this unprecedented number of potentially sensitive results about each participant's real-world behavior. To address this gap, we convened an interdisciplinary expert working group, supported by a National Institute of Mental Health grant. Building on established guidelines and the emerging norm of returning results in participant-centered research, we present a novel framework specific to the ethical, legal, and social implications of returning IRRs in digital phenotyping research. Our framework offers researchers, clinicians, and Institutional Review Boards (IRBs) urgently needed guidance, and the principles developed here in the context of psychiatry will be readily adaptable to other therapeutic areas.

Effects of lithium on serum Brain-Derived Neurotrophic Factor in Alzheimer's patients with agitation.

BACKGROUND: There is ample evidence in animal models that lithium increases Brain-Derived Neurotrophic Factor (BDNF) with supporting evidence in human studies. Little is known, however, about the effects of lithium on BDNF in Alzheimer's Dementia (AD). In one study of patients with Mild Cognitive Impairment, serum BDNF increased after treatment with lithium. These patients also showed mild improvement in cognitive function. OBJECTIVES: To evaluate low-dose lithium treatment of agitation in Alzheimer's disease (AD). METHOD: We measured levels of BDNF in patients treated with lithium prior to and after a 12-week randomized placebo-controlled trial. RESULTS: BDNF levels did not change significantly and were not associated with improvement in overall neuropsychiatric symptoms or in cognitive function. CONCLUSIONS: More research is needed to understand the potential effects of lithium on BDNF in AD including whether its use might be dependent on the stage of cognitive decline and dementia.

Technology-guided assessment of vocalisations and their diagnostic value as pain indicators for people living with dementia.

BACKGROUND: during pain assessment in persons unable to self-report, such as people living with dementia, vocalisations are commonly used as pain indicators. However, there is a lack of evidence from clinical practice regarding their diagnostic value and relationship with pain. We aimed to explore vocalisations and pain in people with dementia undergoing pain assessments in clinical practice settings. METHODS: a total of 22,194 pain assessments were reviewed in people with dementia (n = 3,144) from 34 different Australian aged care homes and two dementia specific programs. Pain assessments were conducted by 389 purposely trained health care professionals and cares using PainChek pain assessment tool. Vocalised expressions were determined based on nine vocalisation features included in the tool. Linear mixed models were used to examine the relationship of pain scores with vocalisation features. Using a single pain assessment for each of the 3,144 people with dementia, additional data analysis was conducted via Receiver Operator Characteristic (ROC) analysis and Principal Component Analysis. RESULTS: vocalisation scores increased with increasing pain intensity. High pain scores were more likely with the presence of sighing and screaming (8 times). The presence of vocalisation features varied depending on the intensity of pain. The ROC optimal criterion for the voice domain yielded a cut-off score of ≥2.0 with a Youden index of 0.637. The corresponding sensitivity and specificity were 79.7% [confidence interval (CI): 76.8-82.4%] and 84.0% (CI: 82.5-85.5%), respectively. CONCLUSION: we describe vocalisation features during presence of different levels of pain in people with dementia unable to self-report, therefore providing evidence in regard to their diagnostic value in clinical practice.

Monitoring Behaviors of Patients With Late-Stage Dementia Using Passive Environmental Sensing Approaches: A Case Series.

OBJECTIVE: To show the feasibility of using different unobtrusive activity-sensing technologies to provide objective behavioral markers of persons with dementia (PwD). DESIGN: Monitored the behaviors of two PwD living in memory care unit using the Oregon Center for Aging & Technology (ORCATECH) platform, and the behaviors of two PwD living in assisted living facility using the Emerald device. SETTING: A memory care unit in Portland, Oregon and an assisted living facility in Framingham, Massachusetts. PARTICIPANTS: A 63-year-old male with Alzheimer's disease (AD), and an 80-year-old female with frontotemporal dementia, both lived in a memory care unit in Portland, Oregon. An 89-year-old woman with a diagnosis of AD, and an 85-year-old woman with a diagnosis of major neurocognitive disorder, Alzheimer's type with behavioral symptoms, both resided at an assisted living facility in Framingham, Massachusetts. MEASUREMENTS: These include: sleep quality measured by the bed pressure mat; number of transitions between spaces and dwell times in different spaces measured by the motion sensors; activity levels measured by the wearable actigraphy device; and couch usage and limb movements measured by the Emerald device. RESULTS: Number of transitions between spaces can identify the patient's episodes of agitation; activity levels correlate well with the patient's excessive level of agitation and lack of movement when the patient received potentially inappropriate medication and neared the end of life; couch usage can detect the patient's increased level of apathy; and periodic limb movements can help detect risperidone-induced side effects. This is the first demonstration that the ORCATECH platform and the Emerald device can measure such activities. CONCLUSION: The use of technologies for monitoring behaviors of PwD can provide more objective and intensive measurements of PwD behaviors.

Low Dose Lithium Treatment of Behavioral Complications in Alzheimer's Disease: Lit-AD Randomized Clinical Trial.

BACKGROUND: A case series suggested efficacy for lithium to treat agitation in dementia, but no placebo-controlled trials have been conducted. OBJECTIVES: To evaluate low-dose lithium treatment of agitation in Alzheimer's disease (AD). METHOD: In a four-site trial, patients with AD and agitation/aggression score ≥4 on the Neuropsychiatric Inventory (NPI) were randomized, double-blind, to lithium carbonate 150-600 mg daily or placebo for 12 weeks. Primary efficacy outcome was change in NPI agitation/aggression; secondary efficacy outcome was treatment response (30% reduction in NPI score for agitation/aggression plus psychosis and a Clinical Global Impression (CGI) score of much or very much improved). Safety profile of lithium was assessed. RESULTS: Fifty-eight of 77 patients (75.3%) completed the trial. In linear mixed effects model analyses, lithium was not significantly superior to placebo for agitation/aggression. Proportion of responders was 31.6% on lithium and 17.9% on placebo (χ2=1.26, p = 0.26). Moderate or marked improvement (CGI) was greater on lithium (10/38=36.8%) than placebo (0/39=0%, Fisher's exact test p <0.001). In exploratory analyses, improvement on lithium was greater than placebo on NPI delusions and irritability/lability (p's<0.05). Lithium showed greater reduction than placebo in patients with high Young Mania Rating Scale scores (ß=5.06; 95%CI,1.18 to 8.94, p = 0.01). Oral dose and serum levels demonstrated similar associations with efficacy outcomes. Lithium did not differ significantly from placebo on safety outcomes. CONCLUSIONS: Low-dose lithium was not efficacious in treating agitation but was associated with global clinical improvement and excellent safety. A larger trial may be warranted of likely lithium-responsive behavioral symptoms that overlap with mania.

Virtual reality and mental health in older adults: a systematic review.

IMPORTANCE: Virtual reality (VR) is a promising tool with the potential to enhance care of cognitive and affective disorders in the aging population. VR has been implemented in clinical settings with adolescents and children; however, it has been less studied in the geriatric population. OBJECTIVE: The objective of this study is to determine the existing levels of evidence for VR use in clinical settings and identify areas where more evidence may guide translation of existing VR interventions for older adults. DESIGN AND MEASUREMENTS: We conducted a systematic review in PubMed and Web of Science in November 2019 for peer-reviewed journal articles on VR technology and its applications in older adults. We reviewed article content and extracted the number of study participants, study population, goal of the investigation, the level of evidence, and categorized articles based on the indication of the VR technology and the study population. RESULTS: The database search yielded 1554 total results, and 55 articles were included in the final synthesis. The most represented study design was cross-sectional, and the most common study population was subjects with cognitive impairment. Articles fell into three categories for VR Indication: Testing, Training, and Screening. There was a wide variety of VR environments used across studies. CONCLUSIONS: Existing evidence offers support for VR as a screening and training tool for cognitive impairment in older adults. VR-based tasks demonstrated validity comparable to some paper-based assessments of cognition, though more work is needed to refine diagnostic specificity. The variety of VR environments used shows a need for standardization before comparisons can be made across VR simulations. Future studies should address key issues such as usability, data privacy, and confidentiality. Since most literature was generated from high-income countries (HICs), it remains unclear how this may be translated to other parts of the world.

Brain Health Living Labs.

We call on geriatric brain health care providers, executives and entrepreneurs to embrace our Brain Health Living Lab model-a user-centered, iterative ecosystem, integrating concurrent clinical care, research and innovation processes.

The role of intraindividual cognitive variability in posttraumatic stress syndromes and cognitive aging: a literature search and proposed research agenda.

OBJECTIVES: Cognitive impairments are directly related to severity of symptoms and are a primary cause for functional impairment. Intraindividual cognitive variability likely plays a role in both risk and resiliency from symptoms. In fact, such cognitive variability may be an earlier marker of cognitive decline and emergent psychiatric symptoms than traditional psychiatric or behavioral symptoms. Here, our objectives were to survey the literature linking intraindividual cognitive variability, trauma, and dementia and to suggest a potential research agenda. DESIGN: A wide body of literature suggests that exposure to major stressors is associated with poorer cognitive performance, with intraindividual cognitive variability in particular linked to the development of posttraumatic stress disorder (PTSD) in the aftermath of severe trauma. MEASUREMENTS: In this narrative review, we survey the empirical studies to date that evaluate the connection between intraindividual cognitive variability, PTSD, and pathological aging including dementia. RESULTS: The literature suggests that reaction time (RT) variability within an individual may predict future cognitive impairment, including premature cognitive aging, and is significantly associated with PTSD symptoms. CONCLUSIONS: Based on our findings, we argue that intraindividual RT variability may serve as a common pathological indicator for trauma-related dementia risk and should be investigated in future studies.

Approaches to assessing the impact of robotics in geriatric mental health care: a scoping review.

The goals of this scoping literature review are to (1) aggregate the current research involving socially assistive robots in the setting of geriatric psychiatry and (2) examine the outcome measures used in these studies and determine where the gaps and needs are. In light of the global COVID-19 pandemic, the geriatric psychiatric population in particular is vulnerable to both the physical and mental toll COVID-19 may cause. Recently, socially assistive robots have gained attention for their ability to aid in the care of the geriatric psychiatry population and are being explored as a realistic way to deliver certain elements of psychiatric care that have the potential to be safe even in the setting of COVID-19. The results of this review indicate that robots are in the early stages of clinical applicability, they display usability for a range of psychiatric indications, and their impact on clinical care is notable. We project that in the next few years, robotic applications will be tailored to address clinical outcomes with a greater degree of precision and efficacy.

Radio Signal Sensing and Signal Processing to Monitor Behavioral Symptoms in Dementia: A Case Study.

OBJECTIVES: Alzheimer's Disease (AD)-related behavioral symptoms (i.e. agitation and/or pacing) develop in nearly 90% of AD patients. In this N = 1 study, we provide proof-of-concept of detecting changes in movement patterns that may reflect underlying behavioral symptoms using a highly novel radio sensor and identifying environmental triggers. METHODS: The Emerald device is a Wi-Fi-like box without on-body sensors, which emits and processes radio-waves to infer patient movement, spatial location and activity. It was installed for 70 days in the room of patient 'E', exhibiting agitated behaviors. RESULTS: Daily motion episode aggregation revealed motor activity fluctuation throughout the data collection period which was associated with potential socio-environmental triggers. We did not detect any adverse events attributable to the use of the device. CONCLUSION: This N-of-1 study suggests the Emerald device is feasible to use and can potentially yield actionable data regarding behavioral symptom management. No active or potential device risks were encountered.

Combinatorial Pharmacogenomic Testing Improves Outcomes for Older Adults With Depression.

OBJECTIVE: Evaluate the clinical utility of combinatorial pharmacogenomic testing for informing medication selection among older adults who have experienced antidepressant medication failure for major depressive disorder (MDD). DESIGN: Post hoc analysis of data from a blinded, randomized controlled trial comparing two active treatment arms. SETTING: Psychiatry specialty and primary care clinics across 60 U.S. community and academic sites. PARTICIPANTS: Adults age 65 years or older at baseline (n = 206), diagnosed with MDD and inadequate response to at least one medication on the combinatorial pharmacogenomic test report during the current depressive episode. INTERVENTION: Combinatorial pharmacogenomic testing to inform medication selection (guided-care), compared with treatment as usual (TAU). OUTCOMES: Mean percent symptom improvement, response rate, and remission rateat week 8, measured using the 17-item Hamilton Depression Rating Scale; medication switching; and comorbidity moderator analysis. RESULTS: At week 8, symptom improvement was not significantly different for guided-care than for TAU (∆ = 8.1%, t = 1.64, df = 187; p = 0.102); however, guided-care showed significantly improved response (∆ = 13.6%, t = 2.16, df = 187; p = 0.032) and remission (∆ = 12.7%, t = 2.49, df = 189; p = 0.014) relative to TAU. By week 8, more than twice as many patients in guided-care than in TAU were on medications predicted to have no gene-drug interactions (χ2 = 19.3, df = 2; p <0.001). Outcomes in the guided-care arm showed consistent improvement through the end of the open-design 24-week trial, indicating durability of the effect. Differences in outcomes between arms were not significantly impacted by comorbidities. CONCLUSIONS: Combinatorial pharmacogenomic test-informed medication selection improved outcomes over TAU among older adults with depression.

Brain health INnovation Diplomacy: a model binding diverse disciplines to manage the promise and perils of technological innovation.

BACKGROUND: Brain health diplomacy aims to influence the global policy environment for brain health (i.e. dementia, depression, and other mind/brain disorders) and bridges the disciplines of global brain health, international affairs, management, law, and economics. Determinants of brain health include educational attainment, diet, access to health care, physical activity, social support, and environmental exposures, as well as chronic brain disorders and treatment. Global challenges associated with these determinants include large-scale conflicts and consequent mass migration, chemical contaminants, air quality, socioeconomic status, climate change, and global population aging. Given the rapidly advancing technological innovations impacting brain health, it is paramount to optimize the benefits and mitigate the drawbacks of such technologies. OBJECTIVE: We propose a working model of Brain health INnovation Diplomacy (BIND). METHODS: We prepared a selective review using literature searches of studies pertaining to brain health technological innovation and diplomacy. RESULTS: BIND aims to improve global brain health outcomes by leveraging technological innovation, entrepreneurship, and innovation diplomacy. It acknowledges the key role that technology, entrepreneurship, and digitization play and will increasingly play in the future of brain health for individuals and societies alike. It strengthens the positive role of novel solutions, recognizes and works to manage both real and potential risks of digital platforms. It is recognition of the political, ethical, cultural, and economic influences that brain health technological innovation and entrepreneurship can have. CONCLUSIONS: By creating a framework for BIND, we can use this to ensure a systematic model for the use of technology to optimize brain health.

A Future Research Agenda for Digital Geriatric Mental Healthcare.

The proliferation of mobile, online, and remote monitoring technologies in digital geriatric mental health has the potential to lead to the next major breakthrough in mental health treatments. Unlike traditional mental health services, digital geriatric mental health has the benefit of serving a large number of older adults, and in many instances, does not rely on mental health clinics to offer real-time interventions. As technology increasingly becomes essential in the everyday lives of older adults with mental health conditions, these technologies will provide a fundamental service delivery strategy to support older adults' mental health recovery. Although ample research on digital geriatric mental health is available, fundamental gaps in the scientific literature still exist. To begin to address these gaps, we propose the following recommendations for a future research agenda: 1) additional proof-of-concept studies are needed; 2) integrating engineering principles in methodologically rigorous research may help science keep pace with technology; 3) studies are needed that identify implementation issues; 4) inclusivity of people with a lived experience of a mental health condition can offer valuable perspectives and new insights; and 5) formation of a workgroup specific for digital geriatric mental health to set standards and principles for research and practice. We propose prioritizing the advancement of digital geriatric mental health research in several areas that are of great public health significance, including 1) simultaneous and integrated treatment of physical health and mental health conditions; 2) effectiveness studies that explore diagnostics and treatment of social determinants of health such as "social isolation" and "loneliness;" and 3) tailoring the development and testing of innovative strategies to minority older adult populations.

Incorporating Information From Electronic and Social Media Into Psychiatric and Psychotherapeutic Patient Care: Survey Among Clinicians.

BACKGROUND: Obtaining collateral information from a patient is an essential component of providing effective psychiatric and psychotherapeutic care. Research indicates that patients' social and electronic media contains information relevant to their psychotherapy and clinical care. However, it remains unclear to what degree this content is being actively utilized by clinicians as a part of diagnosis or therapy. Moreover, clinicians' attitudes around this practice have not been well characterized. OBJECTIVE: This survey aimed to establish the current attitudes and behaviors of outpatient clinicians regarding the incorporation of patients' social and electronic media into psychotherapy. METHODS: A Web-based survey was sent to outpatient psychotherapists associated with McLean Hospital in Belmont, Massachusetts. The survey asked clinicians to indicate to what extent and with which patients they reviewed patients' social and electronic media content as part of their clinical practice, as well as their reasons for or against doing so. RESULTS: Of the total 115 respondents, 71 (61.7%) indicated that they had viewed at least one patient's social or electronic media as part of psychotherapy, and 65 of those 71 (92%) endorsed being able to provide more effective treatment as a result of this information. The use of either short message service text messages or email was significantly greater than the use of other electronic media platforms (χ21=24.1, n=115, P<.001). Moreover, the analysis of survey responses found patterns of use associated with clinicians' years of experience and patient demographics, including age and primary diagnosis. CONCLUSIONS: The incorporation of patients' social and electronic media into therapy is currently common practice among clinicians at a large psychiatric teaching hospital. The results of this survey have informed further questions about whether reviewing patient's media impacts the quality and efficacy of clinical care.