Development and validation of a geriatric depression knowledge scale for older adults with depression.

Poor adherence to antidepressants increases the risk of suicide, while greater mental health awareness promotes seeking appropriate treatment, highlighting the urgent need to assess depression knowledge. This study aimed to develop and assess the psychometrics of a Geriatric Depression Knowledge Scale (GDKS) for older adults with depression. In phase 1, 18 items were generated through an intensive literature review and clinical experiences. Phase 2 involved assessing content and face validities of the GDKS. In phase 3, a cross-sectional study (206 older adults, 100 psychiatric professionals) determined construct validity, internal consistency, and test-retest reliability. GDKS demonstrated excellent content and face validity. Older participants scored significantly lower than psychiatric professionals, confirming excellent construct validity. Reliability was evident with a Kuder-Richardson formula 20 score of 0.72 and a 4-week test-retest reliability of 0.86 (p < 0.01). The GDKS provides a reliable tool for evaluating geriatric depression knowledge in psychiatric outpatient settings.

[Effects of Multicomponent Case Management on the Problem Behaviors of Patients With Dementia and Family Caregivers' Distress, Self-Efficacy, Depression, Burden and Health Promotion Behaviors].

BACKGROUND: Few of the interventions currently available for family caregivers (FCGs) of persons with dementia (PWDs) with long-term follow-ups have a grounding in theory and incorporate multicomponent case management formats. PURPOSE: Based on Pearlin's Caregiving and Stress Process model, this study was developed to examine the effectiveness of a family-centered case management program for PWDs with early to moderate dementia in terms of reducing PWDs behavioral problems and improve FCG outcomes, including distress, self-efficacy, depression, caregiver burden, and health-promoting behaviors. METHODS: This randomized, single-blind, parallel-controlled trial included 76 dyads of PWDs and their FCGs. The dyads were recruited from outpatient clinics at dementia centers in three district hospitals in northern Taiwan. The dyads were randomly assigned to the intervention group (IG, n = 39) and control group (CG, n = 37). The dyads in the IG received a four-month intervention with two home or clinic visits and two telephone interviews. The multi-component interventions provided assessment, education, consultations, support, and referrals to long-term care resources. The CG received routine care and two social phone calls. Data were collected upon enrollment (T0 = baseline) and at 4-,6-, and 12-months post-intervention (T1, T2, and T3, respectively). Generalized estimating equations were conducted to analyze the effects of the intervention. RESULTS: By controlling for the interaction between group and time, we made a comparison between IG and the CG. The results showed significant improvements from baseline measures in behavioral problems in the PWDs for mood, psychosis, and social engagement, and improvements in the FCGs for distress and self-efficacy for obtaining respite as well as for better control of distressing thoughts, feelings of depression, caregiver burden, and overall health promoting behaviors at T1 and T2 (p < 0.5). Significant improvements were also found in the IG for psychomotor regulation among PWDs and the self-efficacy of FCGs in managing the PWDs' disturbing behaviors and health promotion behaviors for nutrition at T1 (p < 0.5). There were no significant improvements in the outcome variables at T3. CONCLUSIONS / IMPLICATIONS FOR PRACTICE: Significant interactions between group and time were found at the 6-month assessment (T2) for improvements in problem behaviors of PWDs and depression, caregiver burden, and distress in the FCGs. Positive effects on self-efficacy and health promotion behaviors among the FCGs were also achieved. The results suggest that a multicomponent case management intervention should be referenced in dementia care policymaking for FCGs and PWDs.

Loneliness and depression dissociated on parietal-centered networks in cognitive and resting states.

BACKGROUND: Perceived loneliness, an increasingly prevalent social issue, is closely associated with major depressive disorder (MDD). However, the neural mechanisms previously implicated in key cognitive and affective processes in loneliness and MDD still remain unclear. Such understanding is critical for delineating the psychobiological basis of the relationship between loneliness and MDD. METHODS: We isolated the unique and interactive cognitive and neural substrates of loneliness and MDD among 27 MDD patients (mean age = 51.85 years, 20 females), and 25 matched healthy controls (HCs; mean age = 48.72 years, 19 females). We assessed participants' behavioral performance and neural regional and network functions on a Stroop color-word task, and their resting-state neural connectivity. RESULTS: Behaviorally, we found greater incongruence-related accuracy cost in MDD patients, but reduced incongruence effect on reaction time in lonelier individuals. When performing the Stroop task, loneliness positively predicted prefrontal-anterior cingulate-parietal connectivity across all participants, whereas MDD patients showed a decrease in connectivity compared to controls. Furthermore, loneliness negatively predicted parietal and cerebellar activities in MDD patients, but positively predicted the same activities in HCs. During resting state, MDD patients showed reduced parietal-anterior cingulate connectivity, which again positively correlated with loneliness in this group. CONCLUSIONS: We speculate the distinct neurocognitive profile of loneliness might indicate increase in both bottom-up attention and top-down executive control functions. However, the upregulated cognitive control processes in lonely individuals may eventually become exhausted, which may in turn predispose to MDD onset.

A Pilot Study on the Efficacy of Stress Relief Programs for Family Caregivers of Older People with Dementia.

The aim of this study was to evaluate the effects of stress-relief programs on positive aspects of caregiving and depression among caregivers of older people with dementia. A quasi-experimental design was employed. Participants in the experimental group received a 8-week period and 120 minutes each session cognitive-behavioral therapy. Participants in the control group received standard health education. Stress relief programs may alleviate depression and increase positive aspects of caregiving among family caregivers of older people with dementia. These findings will help health professionals to implement stress-relief strategies for family caregivers of older people with dementia, or to use those strategies to increase positive aspects of caregiving, or to alleviate depression in caregivers.

The relationships between brain structural changes and perceived loneliness in older adults suffering from late-life depression.

OBJECTIVE: Late-life depression is a significant health risk factor for older adults, part of which is perceived loneliness. In this voxel-based morphometry study, we examined the relationships between perceived loneliness and depression recurrence. METHODS: Fifty-two older adults were recruited, and they were split into 3 groups: single episode, multiple episodes, or normal control groups, according to their clinical histories. RESULTS: This result suggests the level of functioning regarding the reward system may be negatively related to the number of depressive episodes. Taken together, the findings of this study offer important insight into the neural underpinnings of the course and chronicity of late-life depression.

Development and psychometric testing of the triggers of Suicidal Ideation Inventory for assessing older outpatients in primary care settings.

OBJECTIVE: The purpose of this study was to develop an instrument for assessing triggers of suicidal ideation among older outpatients and determine its psychometrics. METHOD: Participants were recruited from older outpatients of two hospitals in northern Taiwan. The 34-item Triggers of Suicidal Ideation Inventory (TSII) was developed, and its items were validated by experts in two runs of Delphi technique survey. Pre-testing this TSII in 200 older outpatients resulted in a 12-item TSII, with three items not considered triggers but suggesting the need for further psychiatric assessment. The 9-item TSII was examined by criterion validity, construct validity, internal consistency reliability, and test-retest reliability. RESULTS: Factor analysis of the final version of TSII yielded a three-factor solution, accounting for 68.75% of the variance. Participants with depressive tendency tended to have higher TSII scores than participants with no depressive tendency (t = 8.62, p < 0.01), indicating good construct validity. TSII scores were significantly and positively correlated with Beck Scale for Suicide Ideation (r = 0.45, p < 0.01) and UCLA Loneliness (r = 0.55, p < 0.01) scores, indicating satisfactory criterion validity. The TSII had Cronbach's α and intraclass correlation coefficient of 0.70 and 0.99, respectively, indicating acceptable internal consistency reliability and excellent test-retest reliability. Receiver operating characteristic analysis revealed an area under the curve of 0.82, indicating excellent ability to detect triggers of suicidal ideation. With a cutoff point of 2, the sensitivity and specificity were 0.76 and 0.69, respectively. CONCLUSIONS: The TSII can be completed in 5 min, is perceived as easy to complete, and yielded highly acceptable parameters of validity and reliability. Copyright © 2016 John Wiley & Sons, Ltd.

Development and psychometric testing of the Protective Reasons Against Suicide Inventory for assessing older Chinese-speaking outpatients in primary care settings.

AIM: To develop and psychometrically test the Protective Reasons against Suicide Inventory among older Chinese-speaking outpatients. BACKGROUND: Tools currently exist to test reasons for living among individuals of all ages in western countries, but few are available to assess older adults' protective reasons against suicide in Asia. DESIGN: A cross-sectional survey to investigate protective reasons against suicide among older Chinese-speaking outpatients. METHODS: The Protective Reasons against Suicide Inventory was developed based on individual interviews with 83 older outpatients in Taiwan, the literature and the authors' clinical experiences. The resulting Inventory was examined in 2013 for content validity, face validity, construct validity, criterion-related validity, internal consistency reliability and test-retest reliability. RESULTS: The Inventory had excellent content validity and face validity. Factor analysis yielded a seven-factor solution, accounting for 87·7% of the variance. Scores on the global Inventory and its subscales tended to be higher in outpatients diagnosed without suicidal ideation than in outpatients diagnosed with suicidal ideation, indicating good criterion validity. Inventory reliability and the intraclass correlation coefficient were satisfactory. CONCLUSIONS: The Protective Reasons against Suicide Inventory can be completed in 5 minutes and is perceived as easy to complete. Moreover, the Inventory yielded highly acceptable parameters for validity and reliability. The Protective Reasons against Suicide Inventory can be used to assess older Chinese-speaking outpatients for factors that protect them from attempting suicide.

Triggers of suicide ideation and protective factors of actually executing suicide among first onset cases in older psychiatric outpatients: a qualitative study.

BACKGROUND: Suicide is a global issue among the elderly, but few studies have explored the experiences of suicide ideation in older Asian psychiatric outpatients. METHOD: Older psychiatric outpatients (N = 24) were recruited by convenience from one medical centre and one regional hospital in northern Taiwan. Participants were recruited if they met these inclusion criteria: 1) ≥ 65 years old, 2) without severe cognitive deficit, 3) outpatients in the psychiatric clinics at the selected hospitals, and 4) self-reported first episode of suicidal ideation within the previous year. Data were collected in individual interviews using a semi-structured guide and analysed by content analysis. RESULTS: Suicide ideation was triggered by illness and physical discomfort, conflicts with family members/friends, illness of family members, death of family members/friends, and loneliness. Participants' reasons for not executing suicide were family members' and friends' support, receiving treatment, finding a way to shift their attention, fear of increasing pressure on one's children, religious beliefs, and not knowing how to execute suicide. CONCLUSION: Understanding these identified triggers of suicide ideation may help psychiatrists open a channel for conversation with their elderly clients and more readily make their diagnosis. Understanding these identified protective factors against executing suicide can help psychiatrists not only treat depression, but also enhance protective factors for their clients.

Protective factors against suicide among young-old Chinese outpatients.

BACKGROUND: Suicide is common among the elderly worldwide. However, no literature could be found on the beliefs/expectations that protect young-old people from attempting suicide. The purpose of this study was to explore young-old outpatients' reasons for not killing themselves in Taiwan. METHOD: Data for this qualitative descriptive study were extracted from a large research series. From the 83 elderly outpatients in the original sample, 31 were chosen for this study because they were young-old (65-74 years old) and from two randomly selected medical centers in northern Taiwan. Data on participants' reasons for not killing themselves in unhappy situations were collected in individual interviews using a semi-structured guide and analyzed by content analysis. RESULTS: Analysis of interview data identified six major themes: satisfied with one's life, suicide cannot resolve problems, fear of humiliating one's children, religious beliefs, never thought about suicide, and living in harmony with nature. CONCLUSION: These identified protective factors (reasons for living) could be added to suicide-prevention programs for the elderly. Our findings may also serve as a reference for geriatric researchers in western countries with increasing numbers of elderly ethnic minority immigrants.

Perceived reasons for, opinions about, and suggestions for elders considering suicide: elderly outpatients' perspectives.

OBJECTIVES: The purposes of this study were to explore elderly outpatients' perceived reasons for, opinions of, and suggestions for elderly people considering suicide in Taiwan. METHOD: Elderly outpatients (N = 83) were recruited in 2011-2012 by convenience sampling from three randomly selected medical centers in Taiwan. Data were collected in individual interviews using a semi-structured guide and analyzed by content analysis. RESULTS: Findings revealed that most participants had heard of elderly suicide, with television news as the main source for their information. Their opinions about elderly suicide reflected judgmental attitudes, negative emotional reactions, expectations of social welfare, and could happen after losing one's meaning in life. Their suggestions for elderly people considering suicide fell into four major themes: give up suicidal ideas, seek help, enhance social welfare, and attend religious activities. CONCLUSION: Since television news was the main source for participants' information about elderly suicide, this mass medium should be used in suicide prevention to disseminate suicide knowledge, increase access to help, and strengthen suicide-protective factors among the elderly. Furthermore, no participants mentioned depression as a reason for attempted or completed suicide among older people despite depression being a well-known suicide-risk factor. Future suicide-prevention programs should emphasize the role of depression in suicide among older people. Participants also did not suggest that older people considering suicide seek help from the health system. Thus, older people should be educated about the role of the health system in suicide prevention and trained as gatekeepers to recognize signs of suicide ideation and respond appropriately.

Family caregivers' sleep disturbance and its associations with multilevel stressors when caring for patients with dementia.

OBJECTIVE: We tested a stress process model of multilevel stressors on sleep disturbance for family caregivers (FCG) of persons with dementia (PWD). METHODS: For this cross-sectional study, trained research assistants collected data from a purposive sample of 180 PWD-FCG dyads at two teaching hospitals, two local hospitals, and two community long-term care service programs in northern Taiwan. PWDs' neuropsychiatric symptoms were assessed using the Chinese Neuropsychiatric Inventory (CNPI), FCGs' distress by CNPI Caregiver Distress Scale, physical fatigue by Visual Analogue for Fatigue Scale, mental fatigue by Attentional Function Index, depressive symptoms by the Center for Epidemiological Studies Depression Scale - Short Form, and sleep disturbance by the General Sleep Disturbance Scale. RESULTS: FCGs' most prevalent sleep disturbance problems were sleep quality problems (99.4%). Hierarchical regression models revealed that FCGs' sleep disturbance was predicted by their physical fatigue, their depressive symptoms, and the synergistic effect of physical fatigue and depressive symptoms in the final model, explaining 57.8% of the variance. CONCLUSIONS: This study supports the model that development of caregivers' sleep problems may depend on their depression, fatigue, and the synergistic effects of these two variables. These findings suggest that clinicians should educate FCGs about self-care and offer strategies for dealing with a cluster of symptoms when maintaining sleep hygiene.

The N-3 polyunsaturated fatty acids supplementation to prevent depression recurrence in patients with late-life depression: A 52-week double-blind, placebo-controlled trial.

BACKGROUND: Reports on the efficacy of omega-3 fatty acids (n-3 PUFAs) for the treatment of late-life depression (LLD) are mixed, and most studies focus on the modification of depressive symptoms rather than depression prevention. The aim of the present study was to investigate the efficacy of n-3 PUFAs in preventing depressive recurrence in patients with late-life depression. In addition, we investigated the effects of n-3 PUFAs on changes in depressive and anxiety symptoms and inflammatory markers in LLD. METHODS: A 52-week, double-blind, randomized, controlled trial was conducted. We enrolled a total of 39 euthymic patients with LLD. They were randomized to receive either n-3 PUFAs (1.2 g per day of eicosapentaenoic acid and 1 g of docosahexaenoic acid) or placebo for 52 weeks. Recurrence of depression and severity of depression symptoms were assessed at baseline and weeks 4, 8, 16, 24, 32, 40, and 52. RESULTS: A total of 39 patients completed the trial with 19 in the n-3 PUFAs group and 20 in the placebo group. Cox proportional hazard regression indicated that n-3 PUFAs had significant protective effect on depression recurrence (Hazard Ratio: 0.295, 95 % Confidence Interval: 0.093-0.931, p value =0.037). But n-3 PUFAs intervention had no significant effect in reducing depressive or anxiety symptoms, inflammatory markers over the placebo group. LIMITATION: The results should be interpreted with consideration of the modest sample size. CONCLUSION: These findings suggest that n-3 PUFAs may have a prophylactic effect in currently euthymic patients with LLD.

User-Friendly Chatbot to Mitigate the Psychological Stress of Older Adults During the COVID-19 Pandemic: Development and Usability Study.

BACKGROUND: To safeguard the most vulnerable individuals during the COVID-19 pandemic, numerous governments enforced measures such as stay-at-home orders, social distancing, and self-isolation. These social restrictions had a particularly negative effect on older adults, as they are more vulnerable and experience increased loneliness, which has various adverse effects, including increasing the risk of mental health problems and mortality. Chatbots can potentially reduce loneliness and provide companionship during a pandemic. However, existing chatbots do not cater to the specific needs of older adult populations. OBJECTIVE: We aimed to develop a user-friendly chatbot tailored to the specific needs of older adults with anxiety or depressive disorders during the COVID-19 pandemic and to examine their perspectives on mental health chatbot use. The primary research objective was to investigate whether chatbots can mitigate the psychological stress of older adults during COVID-19. METHODS: Participants were older adults belonging to two age groups (≥65 years and <65 years) from a psychiatric outpatient department who had been diagnosed with depressive or anxiety disorders by certified psychiatrists according to the Diagnostic and Statistical Manual of Mental Disorders (Fifth Edition) (DSM-5) criteria. The participants were required to use mobile phones, have internet access, and possess literacy skills. The chatbot's content includes monitoring and tracking health data and providing health information. Participants had access to the chatbot for at least 4 weeks. Self-report questionnaires for loneliness, depression, and anxiety were administered before and after chatbot use. The participants also rated their attitudes toward the chatbot. RESULTS: A total of 35 participants (mean age 65.21, SD 7.51 years) were enrolled in the trial, comprising 74% (n=26) female and 26% (n=9) male participants. The participants demonstrated a high utilization rate during the intervention, with over 82% engaging with the chatbot daily. Loneliness significantly improved in the older group ≥65 years. This group also responded positively to the chatbot, as evidenced by changes in University of California Los Angeles Loneliness Scale scores, suggesting that this demographic can derive benefits from chatbot interaction. Conversely, the younger group, <65 years, exhibited no significant changes in loneliness after the intervention. Both the older and younger age groups provided good scores in relation to chatbot design with respect to usability (mean scores of 6.33 and 6.05, respectively) and satisfaction (mean scores of 5.33 and 5.15, respectively), rated on a 7-point Likert scale. CONCLUSIONS: The chatbot interface was found to be user-friendly and demonstrated promising results among participants 65 years and older who were receiving care at psychiatric outpatient clinics and experiencing relatively stable symptoms of depression and anxiety. The chatbot not only provided caring companionship but also showed the potential to alleviate loneliness during the challenging circumstances of a pandemic.

Traces of EEG-fMRI coupling reveals neurovascular dynamics on sleep inertia.

Upon emergence from sleep, individuals experience temporary hypo-vigilance and grogginess known as sleep inertia. During the transient period of vigilance recovery from prior nocturnal sleep, the neurovascular coupling (NVC) may not be static and constant as assumed by previous neuroimaging studies. Stemming from this viewpoint of sleep inertia, this study aims to probe the NVC changes as awakening time prolongs using simultaneous EEG-fMRI. The time-lagged coupling between EEG features of vigilance and BOLD-fMRI signals, in selected regions of interest, was calculated with one pre-sleep and three consecutive post-awakening resting-state measures. We found marginal changes in EEG theta/beta ratio and spectral slope across post-awakening sessions, demonstrating alterations of vigilance during sleep inertia. Time-varying EEG-fMRI coupling as awakening prolonged was evidenced by the changing time lags of the peak correlation between EEG alpha-vigilance and fMRI-thalamus, as well as EEG spectral slope and fMRI-anterior cingulate cortex. This study provides the first evidence of potential dynamicity of NVC occurred in sleep inertia and opens new avenues for non-invasive neuroimaging investigations into the neurophysiological mechanisms underlying brain state transitions.

Predicting suicidality in late-life depression by 3D convolutional neural network and cross-sample entropy analysis of resting-state fMRI.

BACKGROUND: Predicting suicide is a pressing issue among older adults; however, predicting its risk is difficult. Capitalizing on the recent development of machine learning, considerable progress has been made in predicting complex behavior such as suicide. As depression remained the strongest risk for suicide, we aimed to apply deep learning algorithms to identify suicidality in a group with late-life depression (LLD). METHODS: We enrolled 83 patients with LLD, 35 of which were non-suicidal and 48 were suicidal, including 26 with only suicidal ideation and 22 with past suicide attempts, for resting-state functional magnetic resonance imaging (MRI). Cross-sample entropy (CSE) analysis was conducted to examine the complexity of MRI signals among brain regions. Three-dimensional (3D) convolutional neural networks (CNNs) were used, and the classification accuracy in each brain region was averaged to predict suicidality after sixfold cross-validation. RESULTS: We found brain regions with a mean accuracy above 75% to predict suicidality located mostly in default mode, fronto-parietal, and cingulo-opercular resting-state networks. The models with right amygdala and left caudate provided the most reliable accuracy in all cross-validation folds, indicating their neurobiological importance in late-life suicide. CONCLUSION: Combining CSE analysis and the 3D CNN, several brain regions were found to be associated with suicidality.

Cognitive protection and brain entropy changes from omega-3 polyunsaturated fatty acids supplement in late-life depression: A 52-week randomized controlled trial.

BACKGROUND: Late-life depression (LLD) is associated with risk of dementia, yet intervention of LLD provides an opportunity to attenuate subsequent cognitive decline. Omega-3 polyunsaturated fatty acids (PUFAs) supplement is a potential intervention due to their beneficial effect in depressive symptoms and cognitive function. To explore the underlying neural mechanism, we used resting-state functional MRI (rs-fMRI) before and after omega-3 PUFAs supplement in older adults with LLD. METHODS: A 52-week double-blind randomized controlled trial was conducted. We used multi-scale sample entropy to analyze rs-fMRI data. Comprehensive cognitive tests and inflammatory markers were collected to correlate with brain entropy changes. RESULTS: A total of 20 patients completed the trial with 11 under omega-3 PUFAs and nine under placebo. While no significant global cognitive improvement was observed, a marginal enhancement in processing speed was noted in the omega-3 PUFAs group. Importantly, participants receiving omega-3 PUFAs exhibited decreased brain entropy in left posterior cingulate gyrus (PCG), multiple visual areas, the orbital part of the right middle frontal gyrus, and the left Rolandic operculum. The brain entropy changes of the PCG in the omega-3 PUFAs group correlated with improvement of language function and attenuation of interleukin-6 levels. LIMITATIONS: Sample size is small with only marginal clinical effect. CONCLUSION: These findings suggest that omega-3 PUFAs supplement may mitigate cognitive decline in LLD through anti-inflammatory mechanisms and modulation of brain entropy. Larger clinical trials are warranted to validate the potential therapeutic implications of omega-3 PUFAs for deterring cognitive decline in patients with late-life depression.

Potential Mobile Health Applications for Improving the Mental Health of the Elderly: A Systematic Review.

The rapid aging of the global population presents challenges in providing mental health care resources for older adults aged 65 and above. The COVID-19 pandemic has further exacerbated the global population's psychological distress due to social isolation and distancing. Thus, there is an urgent need to update scholarly knowledge on the effectiveness of mHealth applications to improve older people's mental health. This systematic review summarizes recent literature on chatbots aimed at enhancing mental health and well-being. Sixteen papers describing six apps or prototypes were reviewed, indicating the practicality, feasibility, and acceptance of chatbots for promoting mental health in older adults. Engaging with chatbots led to improvements in well-being and stress reduction, as well as a decrement in depressive symptoms. Mobile health applications addressing these studies are categorized for reference.

Review of EEG-based neurofeedback as a therapeutic intervention to treat depression.

Depression, or major depressive disorder, is a common mental disorder that affects individuals' behavior, mood, and physical health, and its prevalence has increased during the lockdowns implemented to curb the COVID-19 pandemic. There is an urgent need to update the treatment recommendations for mental disorders during such crises. Conventional interventions to treat depression include long-term pharmacotherapy and cognitive behavioral therapy. Electroencephalogram-neurofeedback (EEG-NF) training has been suggested as a non-invasive option to treat depression with minimal side effects. In this systematic review, we summarize the recent literature on EEG-NF training for treating depression. The 12 studies included in our final sample reported that despite several issues related to EEG-NF practices, patients with depression showed significant cognitive, clinical, and neural improvements following EEG-NF training. Given its low cost and the low risk of side effects due to its non-invasive nature, we suggest that EEG-NF is worth exploring as an augmented tool for patients who already receive standard medications but remain symptomatic, and that EEG-NF training may be an effective intervention tool that can be utilized as a supplementary treatment for depression. We conclude by providing some suggestions related to experimental designs and standards to improve current EEG-NF training practices for treating depression.

Automatic diagnosis of late-life depression by 3D convolutional neural networks and cross-sample Entropy analysis from resting-state fMRI.

Resting-state fMRI has been widely used in investigating the pathophysiology of late-life depression (LLD). Unlike the conventional linear approach, cross-sample entropy (CSE) analysis shows the nonlinear property in fMRI signals between brain regions. Moreover, recent advances in deep learning, such as convolutional neural networks (CNNs), provide a timely application for understanding LLD. Accurate and prompt diagnosis is essential in LLD; hence, this study aimed to combine CNN and CSE analysis to discriminate LLD patients and non-depressed comparison older adults based on brain resting-state fMRI signals. Seventy-seven older adults, including 49 patients and 28 comparison older adults, were included for fMRI scans. Three-dimensional CSEs with volumes corresponding to 90 seed regions of interest of each participant were developed and fed into models for disease classification and depression severity prediction. We obtained a diagnostic accuracy > 85% in the superior frontal gyrus (left dorsolateral and right orbital parts), left insula, and right middle occipital gyrus. With a mean root-mean-square error (RMSE) of 2.41, three separate models were required to predict depressive symptoms in the severe, moderate, and mild depression groups. The CSE volumes in the left inferior parietal lobule, left parahippocampal gyrus, and left postcentral gyrus performed best in each respective model. Combined complexity analysis and deep learning algorithms can classify patients with LLD from comparison older adults and predict symptom severity based on fMRI data. Such application can be utilized in precision medicine for disease detection and symptom monitoring in LLD.