Prediction of depression cases, incidence, and chronicity in a large occupational cohort using machine learning techniques: an analysis of the ELSA-Brasil study

Early diagnostic value of home video-based machine learning in autism spectrum disorder: a meta-analysis

Machine learning (ML) based on remote video has shown ideal diagnostic value in autism spectrum disorder (ASD). Here, we conducted a meta-analysis of the diagnostic value of home video-based ML in ASD. Relevant articles were systematically searched in PubMed, Cochrane, Embase, and Web of Science from inception to September 2023 with no language restriction, and the literature search was updated in September 2024. The overall risk of bias and suitability of the ML prediction models in the included studies were assessed using PROBAST. Nineteen articles involving 89 prediction models and 9959 subjects were included. The mean video duration was 5.63 ± 1.23 min, and the mean number of behavioral features during initial modeling was 23.53. Among the 19 included studies, 13 models had been trained. Seven of the 13 models were not cross-validated (c-index = 0.92, 95% CI 0.88-0.96), while 6 of the 13 models were tenfold cross-validated (c-index = 0.95, 95% CI 0.94-0.97). There were 8 validation cohorts (c-index = 0.83, 95% CI 0.77-0.89). The pooled sensitivity and specificity were 0.87 (95% CI 0.77-0.93) and 0.79 (95% CI 0.76-0.81) in the training cohort, 0.90 (95% CI 0.85-0.94) and 0.87 (95% CI 0.72-0.94) in the cross-validation, and 0.81 (95% CI 0.74-0.86) and 0.72 (95% CI 0.68-0.75) in the validation cohort, respectively. These results indicated that this model is a highly sensitive and user-friendly tool for early ASD diagnosis.

CONCLUSION

Remote video-based ML may improve clinical practice and future research, particularly by combining advanced technologies such as facial recognition. It is a potential tool for diagnosing ASD in children.

WHAT IS KNOWN

• The incidence of pediatric ASD has increased in recent years. • ML based on remote video has shown ideal early diagnostic value.

WHAT IS NEW

• The first systematic review and meta-analysis evaluating the diagnostic performance of remote video-based ML for ASD. • Home video-based ML is a valuable diagnostic tool for the early diagnosis of ASD. • Remote video-based ML is convenient and simple to utilize.

Identifying neuroimaging biomarkers in major depressive disorder using machine learning algorithms and functional near-infrared spectroscopy (fNIRS) during verbal fluency task

One of the most prevalent psychiatric disorders is major depressive disorder (MDD), which increases the probability of suicidal ideation or untimely demise. Abnormal frontal hemodynamic changes detected by functional near-infrared spectroscopy (fNIRS) during verbal fluency task (VFT) have the potential to be used as an objective indicator for assessing clinical symptoms. However, comprehensive quantitative and objective assessment instruments for individuals who exhibit symptoms suggestive of depression remain undeveloped. Drawing from a total of 467 samples in a large-scale dataset comprising 289 MDD patients and 178 healthy controls, fNIRS measurements were obtained throughout the VFT. To identify unique MDD biomarkers, this research introduced a data representation approach for extracting spatiotemporal features from fNIRS signals, which were subsequently utilized as potential predictors. Machine learning classifiers (e.g., Gradient Boosted Decision Trees (GBDT) and Multilayer Perceptron) were implemented to assess the ability to predict selected features. The mean and standard deviation of the cross-validation indicated that the GBDT model, when combined with the 180-feature pattern, distinguishes patients with MDD from healthy controls in the most effective manner. The accuracy of correct classification for the test set was 0.829 ± 0.053, with an AUC of 0.895 (95 % CI: 0.864-0.925) and a sensitivity of 0.914 ± 0.051. Channels that made the most important contribution to the identification of MDD were identified using Shapley Additive Explanations method, located in the frontopolar area and the dorsolateral prefrontal cortex, as well as pars triangularis Broca's area. Assessment of abnormal prefrontal activity during the VFT in MDD serves as an objectively measurable biomarker that could be utilized to evaluate cognitive deficits and facilitate early screening for MDD. The model suggested in this research could be applied to large-scale case-control fNIRS datasets to detect unique characteristics of MDD and offer clinicians an objective biomarker-based analytical instrument to assist in the evaluation of suspicious cases.

Early identification of children with Attention-Deficit/Hyperactivity Disorder (ADHD)

Signs and symptoms of Attention-Deficit/Hyperactivity Disorder (ADHD) are present at preschool ages and often not identified for early intervention. We aimed to use machine learning to detect ADHD early among kindergarten-aged children using population-level administrative health data and a childhood developmental vulnerability surveillance tool: Early Development Instrument (EDI). The study cohort consists of 23,494 children born in Alberta, Canada, who attended kindergarten in 2016 without a diagnosis of ADHD. In a four-year follow-up period, 1,680 children were later identified with ADHD using case definition. We trained and tested machine learning models to predict ADHD prospectively. The best-performing model using administrative and EDI data could reliably predict ADHD and achieved an Area Under the Curve (AUC) of 0.811 during cross-validation. Key predictive factors included EDI subdomain scores, sex, and socioeconomic status. Our findings suggest that machine learning algorithms that use population-level surveillance data could be a valuable tool for early identification of ADHD.

Effectiveness of artificial intelligence in detecting and managing depressive disorders: Systematic review

OBJECTIVES

This study underscores the importance of exploring AI's creative applications in treating depressive disorders to revolutionize mental health care. Through innovative integration of AI technologies, the research confirms their positive effects on preventing, diagnosing, and treating depression. The systematic review establishes an evidence base for AI in depression management, offering directions for effective interventions.

METHODS

This systematic literature review investigates the effectiveness of AI in depression management by analyzing studies from January 1, 2017, to May 31, 2022. Utilizing search engines like IEEE Xplore, PubMed, and Web of Science, the review focused on keywords such as Depression/Mental Health, Machine Learning/Artificial Intelligence, and Prediction/Diagnosis. The analysis of 95 documents involved classification based on use, data type, and algorithm type.

RESULTS

The study revealed that AI in depression management excelled in accuracy, particularly in monitoring and prediction. Biomarker-derived data demonstrated the highest accuracy, with the CNN algorithm proving most effective. The findings affirm the therapeutic benefits of AI, including treatment, detection, and disease prediction, highlighting its potential in analyzing monitored data for depression management.

LIMITATIONS

This study exclusively examined the application of AI in individuals with depressive disorders. Interpretation should be cautious due to the limited scope of subjects to this specific population.

CONCLUSIONS

To introduce digital healthcare and therapies for ongoing depression management, it's crucial to present empirical evidence on the medical fee payment system, safety, and efficacy. These findings support enhanced medical accessibility through digital healthcare, offering personalized disease management for patients seeking non-face-to-face treatment.

Predicting depression in old age: Combining life course data with machine learning

With ageing populations, understanding life course factors that raise the risk of depression in old age may help anticipate needs and reduce healthcare costs in the long run. We estimate the risk of depression in old age by combining adult life course trajectories and childhood conditions in supervised machine learning algorithms. Using data from the Survey of Health, Ageing and Retirement in Europe (SHARE), we implement and compare the performance of six alternative machine learning algorithms. We analyse the performance of the algorithms using different life-course data configurations. While we obtain similar predictive abilities between algorithms, we achieve the highest predictive performance when employing semi-structured representations of life courses using sequence data. We use the Shapley Additive Explanations method to extract the most decisive predictive patterns. Age, health, childhood conditions, and low education predict most depression risk later in life, but we identify new predictive patterns in indicators of life course instability and low utilization of dental care services.

Prediction of depression onset risk among middle-aged and elderly adults using machine learning and Canadian Longitudinal Study on Aging cohort

BACKGROUND

Early identification of the middle-aged and elderly people with high risk of developing depression disorder in the future and the full characterization of the associated risk factors are crucial for early interventions to prevent depression among the aging population.

METHODS

Canadian Longitudinal Study on Aging (CLSA) has collected comprehensive information, including psychological scales and other non-psychological measures, i.e., socioeconomic, environmental, health, lifestyle, cognitive function, personality, about its participants (30,097 subjects aged from 45 to 85) at baseline phase in 2012-2015. We applied machine learning models for the prediction of these participants' risk of depression onset approximately three years later using information collected at baseline phase.

RESULTS

Individual-level risk for future depression onset among CLSA participants can be accurately predicted, with an area under receiver operating characteristic curve (AUC) 0.791 ± 0.016, using all baseline information. We also found the 10-item Center for Epidemiological Studies Depression Scale coupled with age and sex information could achieve similar performance (AUC 0.764 ± 0.016). Furthermore, we identified existing subthreshold depression symptoms, emotional instability, low levels of life satisfaction, perceived health, and social support, and nutrition risk as the most important predictors for depression onset independent from psychological scales.

LIMITATIONS

Depression was based on self-reported doctor diagnosis and depression screening tool.

CONCLUSIONS

The identified risk factors will further improve our understanding of the depression onset among middle-aged and elderly population and the early identification of high-risk subjects is the first step for successful early interventions.

Predicting Future Depressive Episodes from Resting-State fMRI with Generative Embedding

After a first episode of major depressive disorder (MDD), there is substantial risk for a long-term remitting-relapsing course. Prevention and early interventions are thus critically important. Various studies have examined the feasibility of detecting at-risk individuals based on out-of-sample predictions about the future occurrence of depression. However, functional magnetic resonance imaging (MRI) has received very little attention for this purpose so far. Here, we explored the utility of generative models (i.e. different dynamic causal models, DCMs) as well as functional connectivity (FC) for predicting future episodes of depression in never-depressed adults, using a large dataset (N=906) of task-free ("resting state") fMRI data from the UK Biobank. Connectivity analyses were conducted using timeseries from pre-computed spatially independent components of different dimensionalities. Over a three year period, 50% of participants showed indications of at least one depressive episode, while the other 50% did not. Using nested cross-validation for training and a held-out test set (80/20 split), we systematically examined the combination of 8 connectivity feature sets and 17 classifiers. We found that a generative embedding procedure based on combining regression DCM (rDCM) with a support vector machine (SVM) enabled the best predictions, both on the training set (0.63 accuracy, 0.66 area under the curve, AUC) and the test set (0.62 accuracy, 0.64 AUC; p<0.001). However, on the test set, rDCM was only slightly superior to predictions based on FC (0.59 accuracy, 0.61 AUC). Interpreting model predictions based on SHAP (SHapley Additive exPlanations) values suggested that the most predictive connections were widely distributed and not confined to specific networks. Overall, our analyses suggest (i) ways of improving future fMRI-based generative embedding approaches for the early detection of individuals at-risk for depression and that (ii) achieving accuracies of clinical utility may require combination of fMRI with other data modalities.

Prevalence and risk factors of psychiatric symptoms and diagnoses before and during the COVID-19 pandemic: findings from the ELSA-Brasil COVID-19 mental health cohort

BACKGROUND

There is mixed evidence on increasing rates of psychiatric disorders and symptoms during the coronavirus disease 2019 (COVID-19) pandemic in 2020. We evaluated pandemic-related psychopathology and psychiatry diagnoses and their determinants in the Brazilian Longitudinal Study of Health (ELSA-Brasil) São Paulo Research Center.

METHODS

Between pre-pandemic ELSA-Brasil assessments in 2008-2010 (wave-1), 2012-2014 (wave-2), 2016-2018 (wave-3) and three pandemic assessments in 2020 (COVID-19 waves in May-July, July-September, and October-December), rates of common psychiatric symptoms, and depressive, anxiety, and common mental disorders (CMDs) were compared using the Clinical Interview Scheduled-Revised (CIS-R) and the Depression Anxiety Stress Scale-21 (DASS-21). Multivariable generalized linear models, adjusted by age, gender, educational level, and ethnicity identified variables associated with an elevated risk for mental disorders.

RESULTS

In 2117 participants (mean age 62.3 years, 58.2% females), rates of CMDs and depressive disorders did not significantly change over time, oscillating from 23.5% to 21.1%, and 3.3% to 2.8%, respectively; whereas rate of anxiety disorders significantly decreased (2008-2010: 13.8%; 2016-2018: 9.8%; 2020: 8%). There was a decrease along three wave-COVID assessments for depression [β = -0.37, 99.5% confidence interval (CI) -0.50 to -0.23], anxiety (β = -0.37, 99.5% CI -0.48 to -0.26), and stress (β = -0.48, 99.5% CI -0.64 to -0.33) symptoms (all ps < 0.001). Younger age, female sex, lower educational level, non-white ethnicity, and previous psychiatric disorders were associated with increased odds for psychiatric disorders, whereas self-evaluated good health and good quality of relationships with decreased risk.

CONCLUSION

No consistent evidence of pandemic-related worsening psychopathology in our cohort was found. Indeed, psychiatric symptoms slightly decreased along 2020. Risk factors representing socioeconomic disadvantages were associated with increased odds of psychiatric disorders.

Prediction of depressive symptoms onset and long-term trajectories in home-based older adults using machine learning techniques

OBJECTIVES

Our aim was to explore the possibility of using machine learning (ML) in predicting the onset and trajectories of depressive symptom in home-based older adults over a 7-year period.

METHODS

Depressive symptom data (collected in the year 2011, 2013, 2015 and 2018) of home-based older Chinese (n = 2650) recruited in the China Health and Retirement Longitudinal Study (CHARLS) were included in the current analysis. The latent class growth modeling (LCGM) and growth mixture modeling (GMM) were used to classify different trajectory classes. Based on the identified trajectory patterns, three ML classification algorithms (i.e. gradient boosting decision tree, support vector machine and random forest) were evaluated with a 10-fold cross-validation procedure and a metric of the area under the receiver operating characteristic curve (AUC).

RESULTS

Four trajectories were identified for the depressive symptoms: no symptoms (63.9%), depressive symptoms onset {incident increasing symptoms [new-onset increasing (16.8%)], chronic symptoms [slowly decreasing (12.5%), persistent high (6.8%)]}. Among the analyzed baseline variables, the 10-item Center for Epidemiologic Studies Depression Scale (CESD-10) score, cognition, sleep time, self-reported memory were the top five important predictors across all trajectories. The mean AUCs of the three predictive models had a range from 0.661 to 0.892.

CONCLUSIONS

ML techniques can be robust in predicting depressive symptom onset and trajectories over a 7-year period with easily accessible sociodemographic and health information.

Supplemental data for this article is available online at http://dx.doi.org/10.1080/13607863.2022.2031868.

A hybrid machine learning model of depression estimation in home-based older adults: a 7-year follow-up study

BACKGROUND

Our aim was to explore whether a two-step hybrid machine learning model has the potential to discover the onset of depression in home-based older adults.

METHODS

Depression data (collected in the year 2011, 2013, 2015 and 2018) of home-based older Chinese (n = 2,548) recruited in the China Health and Retirement Longitudinal Study were included in the current analysis. The long short-term memory network (LSTM) was applied to identify the risk factors of participants in 2015 utilizing the first 2 waves of data. Based on the identified predictors, three ML classification algorithms (i.e., gradient boosting decision tree, support vector machine and random forest) were evaluated with a 10-fold cross-validation procedure and a metric of the area under the receiver operating characteristic curve (AUROC) to estimate the depressive outcome.

RESULTS

Time-varying predictors of the depression were successfully identified by LSTM (mean squared error =0.8). The mean AUCs of the three predictive models had a range from 0.703 to 0.749. Among the prediction variables, self-reported health status, cognition, sleep time, self-reported memory and ADL (activities of daily living) disorder were the top five important variables.

CONCLUSIONS

A two-step hybrid model based on "LSTM+ML" framework can be robust in predicting depression over a 5-year period with easily accessible sociodemographic and health information.

The association between diabetes mellitus and incidence of depressive episodes is different based on sex: insights from ELSA-Brasil

OBJECTIVE

To investigate the association between diabetes mellitus (DM) and incidence of depressive episodes among men and women.

METHODS

Data were used from 12,730 participants (5866 men and 6864 women) at baseline (2008-2010) and follow-up 1 (2012-2014) of the Longitudinal Study of Adult Health (ELSA-Brasil), a multicenter cohort of Brazilian civil servants. Participants were classified for diabetes using self-reported and clinical information, and evaluated for presence of depressive episodes by the Clinical Interview Schedule-Revised (CIS-R). Associations were estimated by means of logistic regression models (crude and adjusted for socio-demographic variables).

RESULTS

Women classified as with DM prior to the baseline were at 48% greater risk (95% confidence interval (CI) = 1.03-2.07) of depressive episodes in the crude model and 54% greater risk (95% CI = 1.06-2.19) in the final adjusted model compared to women classified as non-DM. No significant associations were observed for men. The regression models for duration of DM and incidence of depressive episodes (n = 2143 participants; 1160 men and 983 women) returned no significant associations.

CONCLUSION

In women classified as with prior DM, the greater risk of depressive episodes suggests that more frequent screening for depression may be beneficial as part of a multi-factorial approach to care for DM.

Trajectories of common mental disorders symptoms before and during the COVID-19 pandemic: findings from the ELSA-Brasil COVID-19 Mental Health Cohort

AIM

Evidence indicates most people were resilient to the impact of the COVID-19 pandemic on mental health. However, evidence also suggests the pandemic effect on mental health may be heterogeneous. Therefore, we aimed to identify groups of trajectories of common mental disorders' (CMD) symptoms assessed before (2017-19) and during the COVID-19 pandemic (2020-2021), and to investigate predictors of trajectories.

METHODS

We assessed 2,705 participants of the ELSA-Brasil COVID-19 Mental Health Cohort study who reported Clinical Interview Scheduled-Revised (CIS-R) data in 2017-19 and Depression Anxiety Stress Scale-21 (DASS-21) data in May-July 2020, July-September 2020, October-December 2020, and April-June 2021. We used an equi-percentile approach to link the CIS-R total score in 2017-19 with the DASS-21 total score. Group-based trajectory modeling was used to identify CMD trajectories and adjusted multinomial logistic regression was used to investigate predictors of trajectories.

RESULTS

Six groups of CMD symptoms trajectories were identified: low symptoms (17.6%), low-decreasing symptoms (13.7%), low-increasing symptoms (23.9%), moderate-decreasing symptoms (16.8%), low-increasing symptoms (23.3%), severe-decreasing symptoms (4.7%). The severe-decreasing trajectory was characterized by age < 60 years, female sex, low family income, sedentary behavior, previous mental disorders, and the experience of adverse events in life.

LIMITATIONS

Pre-pandemic characteristics were associated with lack of response to assessments. Our occupational cohort sample is not representative.

CONCLUSION

More than half of the sample presented low levels of CMD symptoms. Predictors of trajectories could be used to detect individuals at-risk for presenting CMD symptoms in the context of global adverse events.

Präzisionspsychiatrie und der Beitrag von Brain Imaging und anderen Biomarkern

'Precision Psychiatry' as the psychiatric variant of 'Precision Medicine' aims to provide high-level diagnosis and treatment based on robust biomarkers and tailored to the individual clinical, neurobiological, and genetic constitution of the patient. The specific peculiarity of psychiatry, in which disease entities are normatively defined based on clinical experience and are also significantly influenced by contemporary history, society and philosophy, has so far made the search for valid and reliable psychobiological connections difficult. Nevertheless, considerable progress has now been made in all areas of psychiatric research, made possible above all by the critical review and renewal of previous concepts of disease and psychopathology, the increased orientation towards neurobiology and genetics, and in particular the use of machine learning methods. Notably, modern machine learning methods make it possible to integrate high-dimensional and multimodal data sets and generate models which provide new psychobiological insights and offer the possibility of individualized, biomarker-driven single-subject prediction of diagnosis, therapy response and prognosis. The aim of the present review is therefore to introduce the concept of 'Precision Psychiatry' to the interested reader, to concisely present modern, machine learning methods required for this, and to clearly present the current state and future of biomarker-based 'precision psychiatry'.