Fusing Data Mining, Machine Learning and Traditional Statistics to Detect Biomarkers Associated with Depression

Machine learning-based predictive modelling of mental health in Rwandan Youth

Globally, mental disorders are a significant burden, particularly in low- and middle-income countries, with high prevalence in Rwanda, especially among survivors of the 1994 genocide against Tutsi. Machine learning offers promise in predicting mental health outcomes by identifying patterns missed by traditional methods. However, its application in Rwanda remains under-explored. The study aims to apply machine learning techniques to predict mental health and identify its associated risk factors among Rwandan youth. Mental health data from Rwanda Biomedical Center, collected through the recent Rwanda mental health cross-sectional study and with youth sample of 5221 was used. We used four machine learning models namely logistic regression, Support Vector Machine, Random Forest and Gradient boosting to predict mental health vulnerability among youth. The research findings indicate that the random forest model is the most effective with an accuracy of 88.8% in modeling and predicting factors contributing to mental health vulnerability and 75 % in predicting mental disorders comorbidity. Exposure to traumatic events and violence, heavy drinking and a family history of mental health emerged as the most significant risk factors contributing to the development of mental disorders. While trauma experience, violence experience, affiliation to pro-social group and family history of mental disorders are the main comorbidity drivers. These findings indicate that machine learning can provide insightful results in predicting factors associated with mental health and confirm the role of social and biological factors in mental health. Therefore, it is crucial to consider biological and social factors particularly experience of violence and exposure to traumatic events, when developing mental health interventions and policies in Rwanda. Potential initiatives should prioritize the youth who experience social hardship to strengthen intervention efforts.

An historical overview of artificial intelligence for diagnosis of major depressive disorder

The Artificial Intelligence (AI) technology holds immense potential in the realm of automated diagnosis for Major Depressive Disorder (MDD), yet it is not without potential shortcomings. This paper systematically reviews the research progresses of integrating AI technology with depression diagnosis and provides a comprehensive analysis of existing research findings. In this context, we observe that the knowledge-driven first-generation of depression diagnosis methods could only address deterministic issues in structured information, with the selection of depression-related features directly influencing identification outcomes. The data-driven second-generation of depression diagnosis methods achieved automatic learning of features but required substantial high-quality clinical data, and the results were often obtained solely from the black-box models which lack sufficient explainability. In an effort to overcome the limitations of the preceding approaches, the third-generation of depression diagnosis methods combined the strengths of knowledge-driven and data-driven approaches. Through the fusion of information, the diagnostic accuracy is greatly enhanced, but the interpretability remains relatively weak. In order to enhance interpretability and introduce diagnostic criteria, this paper offers a new approach using Large Language Models (LLMs) as AI agents for assisting the depression diagnosis. Finally, we also discuss the potential advantages and challenges associated with this approach. This newly proposed innovative approach has the potential to offer new perspectives and solutions in the diagnosis of depression.

Replicable and robust cellular and biochemical blood marker signatures of depression and depressive symptoms

BACKGROUND

Identification of replicable and robust peripheral blood-based markers associated with depression remains elusive, given that studies frequently identify potential biomarkers that ultimately fail to replicate in other studies, impeding progress in psychiatric research. Peripheral biochemical and cellular markers (PBCs; e.g., albumin) may play an important role in depression.

METHODS

Using a test-replication design including participants from the NHANES community cohort (ntest=17,450, nreplication=17,449), we examined 42 PBCs to identify PBCs that were both replicably and robustly associated with either overall depression severity or individual symptoms of depression across both cohorts across a wide range of possible combinations of analytic decisions (n's = 17,000+).

RESULTS

We found that a small set of PBCs (e.g., bilirubin) were robustly and replicably associated with overall depression severity, with unique signatures of PBCs linked with individual symptoms of depression when stratified by gender. A varying degree of correlation was found between measures of replicability.

CONCLUSIONS

We identified replicable and robust cellular biochemical blood marker signatures associated with both overall depression severity and individual symptoms of depression. Our findings can be used to enhance other researchers' abilities to better understand factors associated with depression and potentially drive the development of effective treatments for depression.

Bilirubin and postpartum depression: an observational and Mendelian randomization study

Background

Postpartum depression (PPD) is one of the most common complications of delivery and is usually disregarded. Several risk factors of PPD have been identified, but its pathogenesis has not been completely understood. Serum bilirubin has been found to be a predictor of depression, whose relationship with PPD has not been investigated.

Methods

Observational research was performed followed by a two-sample Mendelian randomization (MR) analysis. From 2017 to 2020, the clinical data of pregnant women were retrospectively extracted. Logistic regression and random forest algorithm were employed to assess the risk factors of PPD, including the serum levels of total bilirubin and direct bilirubin. To further explore their potential causality, univariable and multivariable Mendelian randomization (MVMR) were conducted. Sensitivity analyses for MR were performed to test the robustness of causal inference.

Results

A total of 1,810 patients were included in the PPD cohort, of which 631 (34.87%) were diagnosed with PPD. Compared with the control group, PPD patients had a significantly lower level of total bilirubin (9.2 μmol/L, IQR 7.7, 11.0 in PPD; 9.7 μmol/L, IQR 8.0, 12.0 in control, P < 0.001) and direct bilirubin (2.0 μmol/L, IQR 1.6, 2.6 in PPD; 2.2 μmol/L, IQR 1.7, 2.9 in control, P < 0.003). The prediction model identified eight independent predictive factors of PPD, in which elevated total bilirubin served as a protective factor (OR = 0.94, 95% CI 0.90-0.99, P = 0.024). In the MR analyses, genetically predicted total bilirubin was associated with decreased risk of PPD (IVW: OR = 0.86, 95% CI 0.76-0.97, P = 0.006), which remained consistent after adjusting educational attainment, income, and gestational diabetes mellitus. Conversely, there is a lack of solid evidence to support the causal relationship between PPD and bilirubin.

Conclusion

Our results suggested that decreased total bilirubin was associated with the incidence of PPD. Future studies are warranted to investigate its potential mechanisms and illuminate the pathogenesis of PPD.

Machine learning research based on diffusion tensor images to distinguish between anorexia nervosa and bulimia nervosa

Background

Anorexia nervosa (AN) and bulimia nervosa (BN), two subtypes of eating disorders, often present diagnostic challenges due to their overlapping symptoms. Machine learning has proven its capacity to improve group classification without requiring researchers to specify variables. The study aimed to distinguish between AN and BN using machine learning models based on diffusion tensor images (DTI).

Methods

This is a cross-sectional study, drug-naive females diagnosed with anorexia nervosa (AN) and bulimia nervosa (BN) were included. Demographic data and DTI were collected for all patients. Features for machine learning included Fractional anisotropy (FA), axial diffusivity (AD), radial diffusivity (RD), and mean diffusivity (MD). Support vector machine was constructed by LIBSVM, MATLAB2013b, and FSL5.0.9 software.

Results

A total of 58 female patients (24 AN, 34 BN) were included in this study. Statistical analysis revealed no significant differences in age, years of education, or course of illness between the two groups. AN patients had significantly lower BMI than BN patients. The AD model exhibited an area under the curve was 0.793 (accuracy: 75.86%, sensitivity: 66.67%, specificity: 88.23%), highlighting the left middle temporal gyrus (MTG_L) and the left superior temporal gyrus (STG_L) as differentiating brain regions. AN patients exhibited lower AD features in the STG_L and MTG_L than BN. Machine learning analysis indicated no significant differences in FA, MD, and RD values between AN and BN groups (p > 0.001).

Conclusion

Machine learning based on DTI could effectively distinguish between AN and BN, with MTG_L and STG_L potentially serving as neuroimaging biomarkers.

Artificial intelligence in psychiatry research, diagnosis, and therapy

Psychiatric disorders are now responsible for the largest proportion of the global burden of disease, and even more challenges have been seen during the COVID-19 pandemic. Artificial intelligence (AI) is commonly used to facilitate the early detection of disease, understand disease progression, and discover new treatments in the fields of both physical and mental health. The present review provides a broad overview of AI methodology and its applications in data acquisition and processing, feature extraction and characterization, psychiatric disorder classification, potential biomarker detection, real-time monitoring, and interventions in psychiatric disorders. We also comprehensively summarize AI applications with regard to the early warning, diagnosis, prognosis, and treatment of specific psychiatric disorders, including depression, schizophrenia, autism spectrum disorder, attention-deficit/hyperactivity disorder, addiction, sleep disorders, and Alzheimer's disease. The advantages and disadvantages of AI in psychiatry are clarified. We foresee a new wave of research opportunities to facilitate and improve AI technology and its long-term implications in psychiatry during and after the COVID-19 era.

Predicting Depression during the COVID-19 Pandemic Using Interpretable TabNet: A Case Study in South Korea

COVID-19 has further aggravated problems by compelling people to stay indoors and limit social interactions, leading to a worsening of the depression situation. This study aimed to construct a TabNet model combined with SHapley Additive exPlanations (SHAP) to predict depression in South Korean society during the COVID-19 pandemic. We used a tabular dataset extracted from the Seoul Welfare Survey with a total of 3027 samples. The TabNet model was trained on this dataset, and its performance was compared to that of several other machine learning models, including Random Forest, eXtreme Gradient Boosting, Light Gradient Boosting, and CatBoost. According to the results, the TabNet model achieved an Area under the receiver operating characteristic curve value (AUC) of 0.9957 on the training set and an AUC of 0.9937 on the test set. Additionally, the study investigated the TabNet model’s local interpretability using SHapley Additive exPlanations (SHAP) to provide post hoc global and local explanations for the proposed model. By combining the TabNet model with SHAP, our proposed model might offer a valuable tool for professionals in social fields, and psychologists without expert knowledge in the field of data analysis can easily comprehend the decision-making process of this AI model.

Blood Inflammatory Biomarkers Differentiate Inpatient and Outpatient Coronavirus Disease 2019 From Influenza

Background

The ongoing circulation of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) poses a diagnostic challenge because symptoms of coronavirus disease 2019 (COVID-19) are difficult to distinguish from other respiratory diseases. Our goal was to use statistical analyses and machine learning to identify biomarkers that distinguish patients with COVID-19 from patients with influenza.

Methods

Cytokine levels were analyzed in plasma and serum samples from patients with influenza and COVID-19, which were collected as part of the Centers for Disease Control and Prevention's Hospitalized Adult Influenza Vaccine Effectiveness Network (inpatient network) and the US Flu Vaccine Effectiveness (outpatient network).

Results

We determined that interleukin (IL)-10 family cytokines are significantly different between COVID-19 and influenza patients. The results suggest that the IL-10 family cytokines are a potential diagnostic biomarker to distinguish COVID-19 and influenza infection, especially for inpatients. We also demonstrate that cytokine combinations, consisting of up to 3 cytokines, can distinguish SARS-CoV-2 and influenza infection with high accuracy in both inpatient (area under the receiver operating characteristics curve [AUC] = 0.84) and outpatient (AUC = 0.81) groups, revealing another potential screening tool for SARS-CoV-2 infection.

Conclusions

This study not only reveals prospective screening tools for COVID-19 infections that are independent of polymerase chain reaction testing or clinical condition, but it also emphasizes potential pathways involved in disease pathogenesis that act as potential targets for future mechanistic studies.

Digital health technologies supporting the application of comprehensive geriatric assessments in long-term care settings or community care: A systematic review

Objective

To provide high-quality elderly care, digital health technologies (DHTs) can potentially assist in reaching the full capacity of comprehensive geriatric assessments (CGAs) to improve communication and data transfer on patients' medical and treatment plan information and health decision-making. This systematic review aimed to describe the evidence on the feasibility and usability, efficacy and effectiveness, and implementation outcomes of DHTs developed to facilitate the administration of CGAs for long-term care settings or community care and to describe their technical features and components.

Methods

A search strategy was conducted in three databases, targeting studies evaluating the DHTs facilitating the administration of CGAs used in long-term care settings or community care. Studies in English and Spanish published up to 5 April 2023 were considered.

Results

Four DHTs supporting the administration of the CGAs were identified. Limited information was found on the technical features and required hardware. Some of the barriers identified regarding usability can be overcome with novel technologies; however, training of health professionals on the assessments and staff knowledge regarding the purpose of the data collected are not technology related and need to be addressed.

Conclusions

Barriers regarding usability were related to experienced difficulties navigating the software, unstable network connectivity, and length of the assessment. Feasibility obstacles were associated with the lack of training to use the DHT, availability and accessibility to hardware (e.g. laptops), and lack of insight into the clinical benefits of collected data. Further research must focus on these areas to improve the implementation and usefulness of these DHTs.

Psychometric characteristics of comprehensive geriatric assessments (CGAs) for long-term care facilities and community care: A systematic review

BACKGROUND

Comprehensive Geriatric Assessments (CGAs) have been incorporated as an integrated care approach effective to face the challenges associated to uncoordinated care, risk of hospitalization, unmet needs, and care planning experienced in older adult care. As they assessed different dimensions, is important to inform about the content and psychometric properties to guide the decisions when selecting and implementing them in practice. This systematic review provides a comprehensive insight on the strengths and weaknesses of the CGAs used in long-term care settings and community care.

METHODS

A systematic search was conducted in PubMed, CINAHL, and Web of Science Core Collection. Studies published up to July 13, 2021, were considered. Quality appraisal was performed for the included studies.

RESULTS

A total of 10 different CGAs were identified from 71 studies included. Three instruments were reported for long-term care settings, and seven for community care. The content was not homogenous and differed in terms of the detail and clearness of the areas being evaluated. Evidence for good to excellent validity and reliability was reported for various instruments.

CONCLUSIONS

Setting more specific and clear domains, associated to the special needs of the care setting, could improve informed decisions at the time of selecting and implementing a CGA. Considering the amount and quality of the evidence, the instrument development trajectory, the validation in different languages, and availability in different care settings, we recommend the interRAI LTCF and interRAI HC to be used for long-term facilities and community care.

Prospects and Pitfalls of Machine Learning in Nutritional Epidemiology

Nutritional epidemiology employs observational data to discover associations between diet and disease risk. However, existing analytic methods of dietary data are often sub-optimal, with limited incorporation and analysis of the correlations between the studied variables and nonlinear behaviours in the data. Machine learning (ML) is an area of artificial intelligence that has the potential to improve modelling of nonlinear associations and confounding which are found in nutritional data. These opportunities notwithstanding, the applications of ML in nutritional epidemiology must be approached cautiously to safeguard the scientific quality of the results and provide accurate interpretations. Given the complex scenario around ML, judicious application of such tools is necessary to offer nutritional epidemiology a novel analytical resource for dietary measurement and assessment and a tool to model the complexity of dietary intake and its relation to health. This work describes the applications of ML in nutritional epidemiology and provides guidelines to avoid common pitfalls encountered in applying predictive statistical models to nutritional data. Furthermore, it helps unfamiliar readers better assess the significance of their results and provides new possible future directions in the field of ML in nutritional epidemiology.

iHealth: The ethics of artificial intelligence and big data in mental healthcare

The concept of intelligent health (iHealth) in mental healthcare integrates artificial intelligence (AI) and Big Data analytics. This article is an attempt to outline ethical aspects linked to iHealth by focussing on three crucial elements that have been defined in the literature: self-monitoring, ecological momentary assessment (EMA), and data mining. The material for the analysis was obtained by a database search. Studies and reviews providing outcome data for each of the three elements were analyzed. An ethical framing of the results was conducted that shows the chances and challenges of iHealth. The synergy between self-monitoring, EMA, and data mining might enable the prevention of mental illness, the prediction of its onset, the personalization of treatment, and the participation of patients in the treatment process. Challenges arise when it comes to the autonomy of users, privacy and data security of users, and potential bias.

Clinical and Biological Factors Are Associated with Treatment-Resistant Depression

Background: Treatment-resistant depression (TRD) is a debilitating condition associated with unmet clinical needs. Few studies have explored clinical characteristics and serum biomarkers associated with TRD. Aims: We investigated whether there were differences in clinical and biochemical variables between patients affected by TRD than those without. Methods: We recruited 343 patients (165 males and 178 females) consecutively hospitalized for MDD to the inpatient clinics affiliated to the Fondazione IRCCS Policlinico, Milan, Italy (n = 234), and ASST Monza, Italy (n = 109). Data were obtained through a screening of the clinical charts and blood analyses conducted during the hospitalization. Results: TRD versus non-TRD patients resulted to be older (p = 0.001), to have a longer duration of illness (p < 0.001), to be more currently treated with a psychiatric poly-therapy (p < 0.001), to have currently more severe depressive symptoms as showed by the Hamilton Depression Rating Scale (HAM-D) scores (p = 0.016), to have lower bilirubin plasma levels (p < 0.001). In addition, more lifetime suicide attempts (p = 0.035), more antidepressant treatments before the current episode (p < 0.001), and a lower neutrophil to lymphocyte ratio at borderline statistically significant level (p = 0.060) were all associated with the TRD group. Conclusion: We identified candidate biomarkers associated with TRD such as bilirubin plasma levels and NLR, to be confirmed by further studies. Moreover, TRD seems to be associated with unfavorable clinical factors such as a predisposition to suicidal behaviors. Future research should replicate these results to provide robust data in support of the identification of new targets of treatment and implementation of prevention strategies for TRD.

Using CatBoost algorithm to identify middle-aged and elderly depression, national health and nutrition examination survey 2011-2018

Depression is one of the most common mental health problems in middle-aged and elderly people. The establishment of risk factor-based depression risk assessment model is conducive to early detection and early treatment of high-risk groups of depression. Five machine learning models (logistic regression (LR); back propagation (BP); random forest (RF); support vector machines (SVM); category boosting (CatBoost) were used to evaluate the depression among 8374 middle-aged people and 4636 elderly people in the NHANES database from 2011 to 2018. In the 2011-2018 cycle, the estimated prevalence of depression was 8.97% in the middle-aged participants and 8.02% in the elderly participants. Among the middle-aged and elderly participants, CatBoost was the best model to identify depression, and its area under the working characteristic curve (AUC) reaches the highest. The second is LR model and SVM model, while the performance of BP and RF model was slightly worse. The primary influencing factor of depression in middle-aged male is alanine aminotransferase. All five machine learning models can identify the occurrence of depression in the NHANES data set through social demographics, lifestyle, laboratory data and other data of middle-aged and elderly people, and among five models, the CatBoost model performed best.

Precision Psychiatry: Machine learning as a tool to find new pharmacological targets

There is an increasing amount of data arising from neurobehavioral sciences and medical records that cannot be adequately analyzed by traditional research methods. New drugs develop at a slow rate and seem unsatisfactory for the majority of neurobehavioral disorders. Machine learning (ML) techniques, instead, can incorporate psychopathological, computational, cognitive, and neurobiological underpinning knowledge leading to a refinement of detection, diagnosis, prognosis, treatment, research, and support. Machine and deep learning methods are currently used to accelerate the process of discovering new pharmacological targets and drugs.

OBJECTIVE

The present work reviews current evidence regarding the contribution of machine learning to the discovery of new drug targets.

METHODS

Scientific articles from PubMed, SCOPUS, EMBASE, and Web of Science Core Collection published until May 2021 were included in this review.

RESULTS

The most significant areas of research are schizophrenia, depression and anxiety, Alzheimer´s disease, and substance use disorders. ML techniques have pinpointed target gene candidates and pathways, new molecular substances, and several biomarkers regarding psychiatric disorders. Drug repositioning studies using ML have identified multiple drug candidates as promising therapeutic agents.

CONCLUSION

Next-generation ML techniques and subsequent deep learning may power new findings regarding the discovery of new pharmacological agents by bridging the gap between biological data and chemical drug information.

Red Blood Cell Indices in Relation to Post-stroke Psychiatric Disorders: A Longitudinal Study in a Follow-up Stroke Clinic

BACKGROUND

Depression and anxiety after stroke are common conditions that are likely to be neglected. Abnormal red blood cell (RBC) indices may be associated with neuropsychiatric disorders. However, the association of RBC indices with post-stroke depression (PSD) and poststroke anxiety (PSA) has not been sufficiently investigated.

METHODS

We aimed to investigate the trajectory of post-stroke depression and anxiety in our follow- up stroke clinic at 1, 3, and 6 months, and the association of RBC indices with these. One hundred and sixty-two patients with a new diagnosis of ischemic stroke were followed up at 1, 3, and 6 months, and underwent Patient Health Questionnaire-9 (PHQ-9) and the general anxiety disorder 7-item (GAD-7) questionnaire for evaluation of depression and anxiety, respectively. First, we used Kaplan-Meier analysis to investigate the accumulated incidences of post-stroke depression and post-stroke anxiety. Next, to explore the association of RBC indices with psychiatric disorders after an ischemic stroke attack, we adjusted for demographic and vascular risk factors using multivariate Cox regression analysis.

RESULTS

Of the 162 patients with new-onset of ischemic stroke, we found the accumulated incidence rates of PSD (1.2%, 17.9%, and 35.8%) and PSA (1.2%, 13.6%, and 15.4%) at 1, 3, and 6 months, respectively. The incident PSD and PSA increased 3 months after a stroke attack. Multivariate Cox regression analysis indicated independent positive associations between PSD risk and higher mean corpuscular volume (MCV) (OR=1.42, 95% CI=1.16-1.76), older age (OR=2.63, 95% CI=1.16-5.93), and a negative relationship between male sex (OR=0.95, 95% CI=0.91-0.99) and PSA.

CONCLUSION

The risks of PSD and PSA increased substantially 3 months beyond stroke onset. Of the RBC indices, higher MCV, showed an independent positive association with PSD.

Machine Learning-Based Behavioral Diagnostic Tools for Depression: Advances, Challenges, and Future Directions

The psychiatric diagnostic procedure is currently based on self-reports that are subject to personal biases. Therefore, the diagnostic process would benefit greatly from data-driven tools that can enhance accuracy and specificity. In recent years, many studies have achieved promising results in detecting and diagnosing depression based on machine learning (ML) analysis. Despite these favorable results in depression diagnosis, which are primarily based on ML analysis of neuroimaging data, most patients do not have access to neuroimaging tools. Hence, objective assessment tools are needed that can be easily integrated into the routine psychiatric diagnostic process. One solution is to use behavioral data, which can be easily collected while still maintaining objectivity. The current paper summarizes the main ML-based approaches that use behavioral data in diagnosing depression and other psychiatric disorders. We classified these studies into two main categories: (a) laboratory-based assessments and (b) data mining, the latter of which we further divided into two sub-groups: (i) social media usage and movement sensors data and (ii) demographic and clinical information. The paper discusses the advantages and challenges in this field and suggests future research directions and implementations. The paper's overarching aim is to serve as a first step in synthetizing existing knowledge about ML-based behavioral diagnosis studies in order to develop interventions and individually tailored treatments in the future.

Convolutional Neural Network Models for Automatic Preoperative Severity Assessment in Unilateral Cleft Lip

BACKGROUND

Despite the wide range of cleft lip morphology, consistent scales to categorize preoperative severity do not exist. Machine learning has been used to increase accuracy and efficiency in detection and rating of multiple conditions, yet it has not been applied to cleft disease. The authors tested a machine learning approach to automatically detect and measure facial landmarks and assign severity grades using preoperative photographs.

METHODS

Preoperative images were collected from 800 unilateral cleft lip patients, manually annotated for cleft-specific landmarks, and rated using a previously validated severity scale by eight expert reviewers. Five convolutional neural network models were trained for landmark detection and severity grade assignment. Mean squared error loss and Pearson correlation coefficient for cleft width ratio, nostril width ratio, and severity grade assignment were calculated.

RESULTS

All five models performed well in landmark detection and severity grade assignment, with the largest and most complex model, Residual Network, performing best (mean squared error, 24.41; cleft width ratio correlation, 0.943; nostril width ratio correlation, 0.879; severity correlation, 0.892). The mobile device-compatible network, MobileNet, also showed a high degree of accuracy (mean squared error, 36.66; cleft width ratio correlation, 0.901; nostril width ratio correlation, 0.705; severity correlation, 0.860).

CONCLUSIONS

Machine learning models demonstrate the ability to accurately measure facial features and assign severity grades according to validated scales. Such models hold promise for the creation of a simple, automated approach to classifying cleft lip morphology. Further potential exists for a mobile telephone-based application to provide real-time feedback to improve clinical decision making and patient counseling.

Body Mass Index Variable Interpolation to Expand the Utility of Real-world Administrative Healthcare Claims Database Analyses

INTRODUCTION

Administrative claims data provide an important source for real-world evidence (RWE) generation, but incomplete reporting, such as for body mass index (BMI), limits the sample sizes that can be analyzed to address certain research questions. The objective of this study was to construct models by implementing machine-learning (ML) algorithms to predict BMI classifications (≥ 30, ≥ 35, and ≥ 40 kg/m²) in administrative healthcare claims databases, and then internally and externally validate them.

METHODS

Five advanced ML algorithms were implemented for each BMI classification on a random sampling of BMI readings from the Optum PanTher Electronic Health Record database (2%) and the Optum Clinformatics Date of Death (20%) database, while incorporating baseline demographic and clinical characteristics. Sensitivity analyses with oversampling ratios were conducted. Model performance was validated internally and externally.

RESULTS

Models trained on the Super Learner ML algorithm (SLA) yielded the best BMI classification predictive performance. SLA model 1 utilized sociodemographic and clinical characteristics, including baseline BMI values; the area under the receiver operating characteristic curve (ROC AUC) was approximately 88% for the prediction of BMI classifications of ≥ 30, ≥ 35, and ≥ 40 kg/m² (internal validation), while accuracy ranged from 87.9% to 92.8% and specificity ranged from 91.8% to 94.7%. SLA model 2 utilized sociodemographic information and clinical characteristics, excluding baseline BMI values; ROC AUC was approximately 73% for the prediction of BMI classifications of ≥ 30, ≥ 35, and ≥ 40 kg/m² (internal validation), while accuracy ranged from 73.6% to 80.0% and specificity ranged from 71.6% to 85.9%. The external validation on the MarketScan Commercial Claims and Encounters database yielded relatively consistent results with slightly diminished performance.

CONCLUSION

This study demonstrated the feasibility and validity of using ML algorithms to predict BMI classifications in administrative healthcare claims data to expand the utility for RWE generation.

Application of Artificial Intelligence in Pharmaceutical and Biomedical Studies

BACKGROUND

Artificial intelligence (AI) is the way to model human intelligence to accomplish certain tasks without much intervention of human beings. The term AI was first used in 1956 with The Logic Theorist program, which was designed to simulate problem-solving ability of human beings. There have been a significant amount of research works using AI in order to determine the advantages and disadvantages of its applicabication and, future perspectives that impact different areas of society. Even the remarkable impact of AI can be transferred to the field of healthcare with its use in pharmaceutical and biomedical studies crucial for the socioeconomic development of the population in general within different studies, we can highlight those that have been conducted with the objective of treating diseases, such as cancer, neurodegenerative diseases, among others. In parallel, the long process of drug development also requires the application of AI to accelerate research in medical care.

METHODS

This review is based on research material obtained from PubMed up to Jan 2020. The search terms include "artificial intelligence", "machine learning" in the context of research on pharmaceutical and biomedical applications.

RESULTS

This study aimed to highlight the importance of AI in the biomedical research and also recent studies that support the use of AI to generate tools using patient data to improve outcomes. Other studies have demonstrated the use of AI to create prediction models to determine response to cancer treatment.

CONCLUSION

The application of AI in the field of pharmaceutical and biomedical studies has been extensive, including cancer research, for diagnosis as well as prognosis of the disease state. It has become a tool for researchers in the management of complex data, ranging from obtaining complementary results to conventional statistical analyses. AI increases the precision in the estimation of treatment effect in cancer patients and determines prediction outcomes.

Factors Associated with E-Cigarette Use in U.S. Young Adult Never Smokers of Conventional Cigarettes: A Machine Learning Approach

E-cigarette use is increasing among young adult never smokers of conventional cigarettes, but the awareness of the factors associated with e-cigarette use in this population is limited. The goal of this work was to use machine learning (ML) algorithms to determine the factors associated with current e-cigarette use among US young adult never cigarette smokers. Young adult (18-34 years) never cigarette smokers from the 2016 and 2017 Behavioral Risk Factor Surveillance System (BRFSS) who reported current or never e-cigarette use were used for the analysis (n = 79,539). Variables associated with current e-cigarette use were selected by two ML algorithms (Boruta and Least absolute shrinkage and selection operator (LASSO)). Odds ratios were calculated to determine the association between e-cigarette use and the variables selected by the ML algorithms, after adjusting for age, gender and race/ethnicity and incorporating the BRFSS complex design. The prevalence of e-cigarette use varied across states. Factors previously reported in the literature, such as age, race/ethnicity, alcohol use, depression, as well as novel factors associated with e-cigarette use, such as disabilities, obesity, history of diabetes and history of arthritis were identified. These results can be used to generate further hypotheses for research, increase public awareness and help provide targeted e-cigarette education.

Risk and Protective Factors of Current Opioid Use Among Youth Living on or Near American Indian Reservations: An Application of Machine Learning

Opioid use among youth, particularly among American Indian (AI) youth, is rising, resulting in a large number of accidental overdoses and deaths. In order to develop effective prevention strategies, we need to use exploratory data analysis to identify previously unknown predictors of opioid use among youth living on or near reservations. The present study is an application of Machine Learning, a type of exploratory data analysis, to the Our Youth, Our Future epidemiological survey (N = 6482) to determine salient risk and protective factors for past 30-day opioid use. The Machine Learning algorithm identified 11 salient risk and protective factors. Importantly, highest risk was conferred for those reporting recent cocaine use, having ever tried a narcotic other than heroin, and identifying as American Indian. Protective factors included never having tried opioids other than heroin, infrequent binge drinking, having fewer friends pressuring you to use illicit drugs, initiating alcohol use at a later age, and being older. This model explained 61% of the variance in the training sample and, on average, 24% of the variance in the bootstrapped samples. Taken together, this model identifies known predictors of 30-day opioid use, for example, recent substance use, as well as unknown predictors including being AI, Snapchat use, and peer encouragement for use. Notably, recent cocaine use was a more salient predictor of recent opioid use than lifetime opioid use.

Improving Diagnosis of Depression With XGBOOST Machine Learning Model and a Large Biomarkers Dutch Dataset (n = 11,081)

Machine Learning has been on the rise and healthcare is no exception to that. In healthcare, mental health is gaining more and more space. The diagnosis of mental disorders is based upon standardized patient interviews with defined set of questions and scales which is a time consuming and costly process. Our objective was to apply the machine learning model and to evaluate to see if there is predictive power of biomarkers data to enhance the diagnosis of depression cases. In this research paper, we aimed to explore the detection of depression cases among the sample of 11,081 Dutch citizen dataset. Most of the earlier studies have balanced datasets wherein the proportion of healthy cases and unhealthy cases are equal but in our study, the dataset contains only 570 cases of self-reported depression out of 11,081 cases hence it is a class imbalance classification problem. The machine learning model built on imbalance dataset gives predictions biased toward majority class hence the model will always predict the case as no depression case even if it is a case of depression. We used different resampling strategies to address the class imbalance problem. We created multiple samples by under sampling, over sampling, over-under sampling and ROSE sampling techniques to balance the dataset and then, we applied machine learning algorithm “Extreme Gradient Boosting” (XGBoost) on each sample to classify the mental illness cases from healthy cases. The balanced accuracy, precision, recall and F1 score obtained from over-sampling and over-under sampling were more than 0.90.

Evaluation of machine learning methodology for the prediction of healthcare resource utilization and healthcare costs in patients with critical limb ischemia-is preventive and personalized approach on the horizon?

Background

Critical limb ischemia (CLI) is a severe stage of peripheral arterial disease and has a substantial disease and economic burden not only to patients and families, but also to the society and healthcare systems. We aim to develop a personalized prediction model that utilizes baseline patient characteristics prior to CLI diagnosis to predict subsequent 1-year all-cause hospitalizations and total annual healthcare cost, using a novel Bayesian machine learning platform, Reverse Engineering Forward Simulation™ (REFS™), to support a paradigm shift from reactive healthcare to Predictive Preventive and Personalized Medicine (PPPM)-driven healthcare.

Methods

Patients ≥ 50 years with CLI plus clinical activity for a 6-month pre-index and a 12-month post-index period or death during the post-index period were included in this retrospective cohort of the linked Optum-Humedica databases. REFS™ built an ensemble of 256 predictive models to identify predictors of all-cause hospitalizations and total annual all-cause healthcare costs during the 12-month post-index interval.

Results

The mean age of 3189 eligible patients was 71.9 years. The most common CLI-related comorbidities were hypertension (79.5%), dyslipidemia (61.4%), coronary atherosclerosis and other heart disease (42.3%), and type 2 diabetes (39.2%). Post-index CLI-related healthcare utilization included inpatient services (14.6%) and ≥ 1 outpatient visits (32.1%). Median annual all-cause and CLI-related costs per patient were $30,514 and $2196, respectively. REFS™ identified diagnosis of skin and subcutaneous tissue infections, cellulitis and abscess, use of nonselective beta-blockers, other aftercare, and osteoarthritis as high confidence predictors of all-cause hospitalizations. The leading predictors for total all-cause costs included region of residence and comorbid health conditions including other diseases of kidney and ureters, blindness of vision defects, chronic ulcer of skin, and chronic ulcer of leg or foot.

Conclusions

REFS™ identified baseline predictors of subsequent healthcare resource utilization and costs in CLI patients. Machine learning and model-based, data-driven medicine may complement physicians' evidence-based medical services. These findings also support the PPPM framework that a paradigm shift from post-diagnosis disease care to early management of comorbidities and targeted prevention is warranted to deliver a cost-effective medical services and desirable healthcare economy.

Alpha-hydroxybutyrate dehydrogenase as a biomarker for predicting systemic lupus erythematosus with liver injury

PURPOSE

To explore potential biomarkers for identifying systemic lupus erythematosus (SLE) with liver injury.

METHODS

This retrospective study examined the records of 158 SLE cases. The Apriori algorithm of association rules was employed to identify laboratory indexes related to liver injury in SLE patients.

RESULTS

The ratio of albumin to globulin; levels of alpha-hydroxybutyrate dehydrogenase (α-HBDH), calcium, hemoglobin, urine protein, total cholesterol; absolute value of lymphocytes; red cell distribution width and hematocrit were identified by the Apriori algorithm from SLE-related liver injury patients. α-HBDH was identified as an independent risk factor for SLE-related liver injury. There were more SLE patients with liver injury in high-α-HBDH group than in low-α-HBDH group (64.63% vs. 21.05%; P < 0.001). In high-α-HBDH group, levels of aspartate aminotransferase (AST), alanine aminotransferase (ALT), lactate dehydrogenase (LDH), and gamma-glutamyl transpeptidase (GGT), and the AST/ALT ratio were significantly higher, and albumin and complement 3 (C3) were markedly lower. Moreover, α-HBDH level was significantly higher in the SLE-related liver injury patients than in the non-SLE-related liver injury patients. In addition, α-HBDH was positively correlated with levels of AST and LDH, the AST/ALT ratio, and the SLE Disease Activity Index 2000, and it was negatively correlated with albumin and C3. The optimal cutoff value of α-HBDH for distinguishing SLE patients with and without liver injury was 258.50 U/L, which provided a 60.94% sensitivity and a 94.67% specificity.

CONCLUSION

α-HBDH could be used to evaluate the disease activity of SLE-related liver injury, and it may be a potential biomarker for diagnosing SLE-related liver injury.

Identifying depression in the National Health and Nutrition Examination Survey data using a deep learning algorithm

BACKGROUND

As depression is the leading cause of disability worldwide, large-scale surveys have been conducted to establish the occurrence and risk factors of depression. However, accurately estimating epidemiological factors leading up to depression has remained challenging. Deep-learning algorithms can be applied to assess the factors leading up to prevalence and clinical manifestations of depression.

METHODS

Customized deep-neural-network and machine-learning classifiers were assessed using survey data from 19,725 participants from the NHANES database (from 1999 through 2014) and 4949 from the South Korea NHANES (K-NHANES) database in 2014.

RESULTS

A deep-learning algorithm showed area under the receiver operating characteristic curve (AUCs) of 0.91 and 0.89 for detecting depression in NHANES and K-NHANES, respectively. The deep-learning algorithm trained with serial datasets (NHANES, from 1999 to 2012), predicted the prevalence of depression in the following two years of data (NHANES, 2013 and 2014) with an AUC of 0.92. Machine learning classifiers trained with NHANES could further predict depression in K-NHANES. There, logistic regression had the highest performance (AUC, 0.77) followed by deep learning algorithm (AUC, 0.74).

CONCLUSIONS

Deep neural-networks managed to identify depression well from other health and demographic factors in both the NHANES and K-NHANES datasets. The deep-learning algorithm was also able to predict depression relatively well on new data set-cross temporally and cross nationally. Further research can delineate the clinical implications of machine learning and deep learning in detecting disease prevalence and progress as well as other risk factors for depression and other mental illnesses.

Machine learning and big data: Implications for disease modeling and therapeutic discovery in psychiatry

INTRODUCTION

Machine learning capability holds promise to inform disease models, the discovery and development of novel disease modifying therapeutics and prevention strategies in psychiatry. Herein, we provide an introduction on how machine learning/Artificial Intelligence (AI) may instantiate such capabilities, as well as provide rationale for its application to psychiatry in both research and clinical ecosystems.

METHODS

Databases PubMed and PsycINFO were searched from 1966 to June 2016 for keywords:Big Data, Machine Learning, Precision Medicine, Artificial Intelligence, Mental Health, Mental Disease, Psychiatry, Data Mining, RDoC, and Research Domain Criteria. Articles selected for review were those that were determined to be aligned with the objective of this particular paper.

RESULTS

Results indicate that AI is a viable option to build useful predictors of outcome while offering objective and comparable accuracy metrics, a unique opportunity, particularly in mental health research. The approach has also consistently brought notable insight into disease models through processing the vast amount of already available multi-domain, semi-structured medical data. The opportunity for AI in psychiatry, in addition to disease-model refinement, is in characterizing those at risk, and it is likely also relevant to personalizing and discovering therapeutics.

CONCLUSIONS

Machine learning currently provides an opportunity to parse disease models in complex, multi-factorial disease states (e.g. mental disorders) and could possibly inform treatment selection with existing therapies and provide bases for domain-based therapeutic discovery.

Machine learning in mental health: a scoping review of methods and applications

BACKGROUND

This paper aims to synthesise the literature on machine learning (ML) and big data applications for mental health, highlighting current research and applications in practice.

METHODS

We employed a scoping review methodology to rapidly map the field of ML in mental health. Eight health and information technology research databases were searched for papers covering this domain. Articles were assessed by two reviewers, and data were extracted on the article's mental health application, ML technique, data type, and study results. Articles were then synthesised via narrative review.

RESULTS

Three hundred papers focusing on the application of ML to mental health were identified. Four main application domains emerged in the literature, including: (i) detection and diagnosis; (ii) prognosis, treatment and support; (iii) public health, and; (iv) research and clinical administration. The most common mental health conditions addressed included depression, schizophrenia, and Alzheimer's disease. ML techniques used included support vector machines, decision trees, neural networks, latent Dirichlet allocation, and clustering.

CONCLUSIONS

Overall, the application of ML to mental health has demonstrated a range of benefits across the areas of diagnosis, treatment and support, research, and clinical administration. With the majority of studies identified focusing on the detection and diagnosis of mental health conditions, it is evident that there is significant room for the application of ML to other areas of psychology and mental health. The challenges of using ML techniques are discussed, as well as opportunities to improve and advance the field.

Risk Assessment Tools and Data-Driven Approaches for Predicting and Preventing Suicidal Behavior

Risk assessment of suicidal behavior is a time-consuming but notoriously inaccurate activity for mental health services globally. In the last 50 years a large number of tools have been designed for suicide risk assessment, and tested in a wide variety of populations, but studies show that these tools suffer from low positive predictive values. More recently, advances in research fields such as machine learning and natural language processing applied on large datasets have shown promising results for health care, and may enable an important shift in advancing precision medicine. In this conceptual review, we discuss established risk assessment tools and examples of novel data-driven approaches that have been used for identification of suicidal behavior and risk. We provide a perspective on the strengths and weaknesses of these applications to mental health-related data, and suggest research directions to enable improvement in clinical practice.

Data Mining Algorithms and Techniques in Mental Health: A Systematic Review

Data Mining in medicine is an emerging field of great importance to provide a prognosis and deeper understanding of disease classification, specifically in Mental Health areas. The main objective of this paper is to present a review of the existing research works in the literature, referring to the techniques and algorithms of Data Mining in Mental Health, specifically in the most prevalent diseases such as: Dementia, Alzheimer, Schizophrenia and Depression. Academic databases that were used to perform the searches are Google Scholar, IEEE Xplore, PubMed, Science Direct, Scopus and Web of Science, taking into account as date of publication the last 10 years, from 2008 to the present. Several search criteria were established such as 'techniques' AND 'Data Mining' AND 'Mental Health', 'algorithms' AND 'Data Mining' AND 'dementia' AND 'schizophrenia' AND 'depression', etc. selecting the papers of greatest interest. A total of 211 articles were found related to techniques and algorithms of Data Mining applied to the main Mental Health diseases. 72 articles have been identified as relevant works of which 32% are Alzheimer's, 22% dementia, 24% depression, 14% schizophrenia and 8% bipolar disorders. Many of the papers show the prediction of risk factors in these diseases. From the review of the research articles analyzed, it can be said that use of Data Mining techniques applied to diseases such as dementia, schizophrenia, depression, etc. can be of great help to the clinical decision, diagnosis prediction and improve the patient's quality of life.

Genetic and Psychosocial Predictors of Aggression: Variable Selection and Model Building With Component-Wise Gradient Boosting

Rationale: Given datasets with a large or diverse set of predictors of aggression, machine learning (ML) provides efficient tools for identifying the most salient variables and building a parsimonious statistical model. ML techniques permit efficient exploration of data, have not been widely used in aggression research, and may have utility for those seeking prediction of aggressive behavior.

Objectives: The present study examined predictors of aggression and constructed an optimized model using ML techniques. Predictors were derived from a dataset that included demographic, psychometric and genetic predictors, specifically FK506 binding protein 5 (FKBP5) polymorphisms, which have been shown to alter response to threatening stimuli, but have not been tested as predictors of aggressive behavior in adults.

Methods: The data analysis approach utilized component-wise gradient boosting and model reduction via backward elimination to: (a) select variables from an initial set of 20 to build a model of trait aggression; and then (b) reduce that model to maximize parsimony and generalizability.

Results: From a dataset of N = 47 participants, component-wise gradient boosting selected 8 of 20 possible predictors to model Buss-Perry Aggression Questionnaire (BPAQ) total score, with R² = 0.66. This model was simplified using backward elimination, retaining six predictors: smoking status, psychopathy (interpersonal manipulation and callous affect), childhood trauma (physical abuse and neglect), and the FKBP5_13 gene (rs1360780). The six-factor model approximated the initial eight-factor model at 99.4% of R².

Conclusions: Using an inductive data science approach, the gradient boosting model identified predictors consistent with previous experimental work in aggression; specifically psychopathy and trauma exposure. Additionally, allelic variants in FKBP5 were identified for the first time, but the relatively small sample size limits generality of results and calls for replication. This approach provides utility for the prediction of aggression behavior, particularly in the context of large multivariate datasets.

Getting RID of the blues: Formulating a Risk Index for Depression (RID) using structural equation modeling

OBJECTIVE

While risk factors for depression are increasingly known, there is no widely utilised depression risk index. Our objective was to develop a method for a flexible, modular, Risk Index for Depression using structural equation models of key determinants identified from previous published research that blended machine-learning with traditional statistical techniques.

METHODS

Demographic, clinical and laboratory variables from the National Health and Nutrition Examination Study (2009-2010, N = 5546) were utilised. Data were split 50:50 into training:validation datasets. Generalised structural equation models, using logistic regression, were developed with a binary outcome depression measure (Patient Health Questionnaire-9 score ⩾ 10) and previously identified determinants of depression: demographics, lifestyle-environs, diet, biomarkers and somatic symptoms. Indicative goodness-of-fit statistics and Areas Under the Receiver Operator Characteristic Curves were calculated and probit regression checked model consistency.

RESULTS

The generalised structural equation model was built from a systematic process. Relative importance of the depression determinants were diet (odds ratio: 4.09; 95% confidence interval: [2.01, 8.35]), lifestyle-environs (odds ratio: 2.15; 95% CI: [1.57, 2.94]), somatic symptoms (odds ratio: 2.10; 95% CI: [1.58, 2.80]), demographics (odds ratio:1.46; 95% CI: [0.72, 2.95]) and biomarkers (odds ratio:1.39; 95% CI: [1.00, 1.93]). The relationships between demographics and lifestyle-environs and depression indicated a potential indirect path via somatic symptoms and biomarkers. The path from diet was direct to depression. The Areas under the Receiver Operator Characteristic Curves were good (logistic:training = 0.850, validation = 0.813; probit:training = 0.849, validation = 0.809).

CONCLUSION

The novel Risk Index for Depression modular methodology developed has the flexibility to add/remove direct/indirect risk determinants paths to depression using a structural equation model on datasets that take account of a wide range of known risks. Risk Index for Depression shows promise for future clinical use by providing indications of main determinant(s) associated with a patient's predisposition to depression and has the ability to be translated for the development of risk indices for other affective disorders.

Biomarkers for depression: recent insights, current challenges and future prospects

A plethora of research has implicated hundreds of putative biomarkers for depression, but has not yet fully elucidated their roles in depressive illness or established what is abnormal in which patients and how biologic information can be used to enhance diagnosis, treatment and prognosis. This lack of progress is partially due to the nature and heterogeneity of depression, in conjunction with methodological heterogeneity within the research literature and the large array of biomarkers with potential, the expression of which often varies according to many factors. We review the available literature, which indicates that markers involved in inflammatory, neurotrophic and metabolic processes, as well as neurotransmitter and neuroendocrine system components, represent highly promising candidates. These may be measured through genetic and epigenetic, transcriptomic and proteomic, metabolomic and neuroimaging assessments. The use of novel approaches and systematic research programs is now required to determine whether, and which, biomarkers can be used to predict response to treatment, stratify patients to specific treatments and develop targets for new interventions. We conclude that there is much promise for reducing the burden of depression through further developing and expanding these research avenues.

The Necessity of Data Mining in Clinical Emergency Medicine; A Narrative Review of the Current Literatrue

Clinical databases can be categorized as big data, include large quantities of information about patients and their medical conditions. Analyzing the quantitative and qualitative clinical data in addition with discovering relationships among huge number of samples using data mining techniques could unveil hidden medical knowledge in terms of correlation and association of apparently independent variables. The aim of this research is using predictive algorithm for prediction of trauma patients on admission to hospital to be able to predict the necessary treatment for patients and provided the necessary measures for the trauma patients who are before entering the critical situation. This study provides a review on data mining in clinical medicine. The relevant, recently-published studies of data mining on medical data with a focus on emergency medicine were investigated to tackle pros and cons of such approaches. The results of this study can be used in prediction of trauma patient’s status at six hours after admission to hospital.

Into the Bowels of Depression: Unravelling Medical Symptoms Associated with Depression by Applying Machine-Learning Techniques to a Community Based Population Sample

Background

Depression is commonly comorbid with many other somatic diseases and symptoms. Identification of individuals in clusters with comorbid symptoms may reveal new pathophysiological mechanisms and treatment targets. The aim of this research was to combine machine-learning (ML) algorithms with traditional regression techniques by utilising self-reported medical symptoms to identify and describe clusters of individuals with increased rates of depression from a large cross-sectional community based population epidemiological study.

Methods

A multi-staged methodology utilising ML and traditional statistical techniques was performed using the community based population National Health and Nutrition Examination Study (2009–2010) (N = 3,922). A Self-organised Mapping (SOM) ML algorithm, combined with hierarchical clustering, was performed to create participant clusters based on 68 medical symptoms. Binary logistic regression, controlling for sociodemographic confounders, was used to then identify the key clusters of participants with higher levels of depression (PHQ-9≥10, n = 377). Finally, a Multiple Additive Regression Tree boosted ML algorithm was run to identify the important medical symptoms for each key cluster within 17 broad categories: heart, liver, thyroid, respiratory, diabetes, arthritis, fractures and osteoporosis, skeletal pain, blood pressure, blood transfusion, cholesterol, vision, hearing, psoriasis, weight, bowels and urinary.

Results

Five clusters of participants, based on medical symptoms, were identified to have significantly increased rates of depression compared to the cluster with the lowest rate: odds ratios ranged from 2.24 (95% CI 1.56, 3.24) to 6.33 (95% CI 1.67, 24.02). The ML boosted regression algorithm identified three key medical condition categories as being significantly more common in these clusters: bowel, pain and urinary symptoms. Bowel-related symptoms was found to dominate the relative importance of symptoms within the five key clusters.

Conclusion

This methodology shows promise for the identification of conditions in general populations and supports the current focus on the potential importance of bowel symptoms and the gut in mental health research.

Why so GLUMM? Detecting depression clusters through graphing lifestyle-environs using machine-learning methods (GLUMM)

BACKGROUND

Key lifestyle-environ risk factors are operative for depression, but it is unclear how risk factors cluster. Machine-learning (ML) algorithms exist that learn, extract, identify and map underlying patterns to identify groupings of depressed individuals without constraints. The aim of this research was to use a large epidemiological study to identify and characterise depression clusters through "Graphing lifestyle-environs using machine-learning methods" (GLUMM).

METHODS

Two ML algorithms were implemented: unsupervised Self-organised mapping (SOM) to create GLUMM clusters and a supervised boosted regression algorithm to describe clusters. Ninety-six "lifestyle-environ" variables were used from the National health and nutrition examination study (2009-2010). Multivariate logistic regression validated clusters and controlled for possible sociodemographic confounders.

RESULTS

The SOM identified two GLUMM cluster solutions. These solutions contained one dominant depressed cluster (GLUMM5-1, GLUMM7-1). Equal proportions of members in each cluster rated as highly depressed (17%). Alcohol consumption and demographics validated clusters. Boosted regression identified GLUMM5-1 as more informative than GLUMM7-1. Members were more likely to: have problems sleeping; unhealthy eating; ≤2 years in their home; an old home; perceive themselves underweight; exposed to work fumes; experienced sex at ≤14 years; not perform moderate recreational activities. A positive relationship between GLUMM5-1 (OR: 7.50, P<0.001) and GLUMM7-1 (OR: 7.88, P<0.001) with depression was found, with significant interactions with those married/living with partner (P=0.001).

CONCLUSION

Using ML based GLUMM to form ordered depressive clusters from multitudinous lifestyle-environ variables enabled a deeper exploration of the heterogeneous data to uncover better understandings into relationships between the complex mental health factors.

Association between completed suicide and environmental temperature in a Mexican population, using the Knowledge Discovery in Database approach

BACKGROUND AND OBJECTIVE

Suicide is a worldwide health problem and climatological characteristics have been associated with suicide behavior. However, approaches such as the Knowledge Discovery in Database are not frequently used to search for an association between climatological characteristics and suicide. The aim of the present study was to assess the association between weather data and suicide in a Mexican population.

METHODS

We used the information of 1357 patients who completed suicide from 2005 to 2012. Alternatively, weather data were provided by the National Water Commission. We used the Knowledge Discovery in Database approach with an Apriori algorithm and the data analyses were performed with the Waikato Environment for Knowledge Analysis software. One hundred rules of association were generated with a confidence of 0.86 and support of 1.

RESULTS

We found an association between environmental temperature and suicide: days with no rain and temperatures between 30 °C and 40 °C (86-104 °F) were related to males completing suicide by hanging.

CONCLUSIONS

In the prevention of suicidal behavior, the Knowledge Discovery in Database could be used to establish climatological characteristics and their association with suicide. This approach must be considered in future prevention strategies.