Predicting posttraumatic stress disorder following a natural disaster

Speech-based recognition and estimating severity of PTSD using machine learning

BACKGROUND

Traditional methodologies for diagnosing post-traumatic stress disorder (PTSD) primarily rely on interviews, incurring considerable costs and lacking objective indices. Integrating biomarkers and machine learning techniques into this diagnostic process has the potential to facilitate accurate PTSD assessment by clinicians.

METHODS

We assembled a dataset encompassing recordings from 76 individuals diagnosed with PTSD and 60 healthy controls. Leveraging the openSmile framework, we extracted acoustic features from these recordings and employed a random forest algorithm for feature selection. Subsequently, these selected features were utilized as inputs for six distinct classification models and a regression model.

RESULTS

Classification models employing a feature set of 18 elements yielded robust binary prediction outcomes for PTSD. Notably, the RF model achieved peak accuracy at 0.975 with the highest AUC of 1.0. In terms of the regression model, it exhibited significant predictive capability for PCL-5 scores (MSE = 0.90, MAE = 0.76, R2 = 0.10, p < 0.001). Noteworthy was the correlation coefficient of 0.33 (p < 0.01) between predicted and actual values.

LIMITATIONS

Firstly, the process of feature selection may compromise the stability of models, which leads to potentially overestimating results. Secondly, it is hard to elucidate the nature of biological mechanisms behind between PTSD patients and healthy individuals. Lastly, the regression model has a limited prediction for PTSD.

CONCLUSIONS

Distinct speech patterns differentiate PTSD patients and controls. Classification models accurately discern both groups. Regression model gauges PTSD severity, but further validation on larger datasets is needed.

Surgical planning of arteriovenous fistulae in routine clinical practice: A machine learning predictive tool

BACKGROUND

Arteriovenous fistula (AVF) is the preferred vascular access (VA) for hemodialysis, but it is associated with high non-maturation and failure rates. Predicting patient-specific AVF maturation and postoperative changes in blood flow volumes (BFVs) and vessel diameters is of fundamental importance to support the choice of optimal AVF location and improve VA survival. The goal of this study was to employ machine learning (ML) in order to give physicians a fast and easy-to-use tool that provides accurate patient-specific predictions, useful to make AVF surgical planning decisions.

METHODS

We applied a set of ML approaches on a dataset of 156 patients. Both parametric and non-parametric ML approaches, taking preoperative data as input, were exploited to predict maturation, postoperative BFVs, and diameters. The best approach associated with lowest cross-validation errors between predictions and real measurements was then chosen to provide estimates and quantify prediction errors.

RESULTS

The k-NN was the best approach to predict brachial BFV, AVF maturation, and other VA variables, and it was also associated with the least computational effort. With this approach, the confusion matrices proved the high accuracy of the prediction for AVF maturation (96.8%) and the low absolute error distribution for the continuous BFV and diameter variables.

CONCLUSIONS

Our data-based approach provided accurate patient-specific predictions for different AVF configurations, requiring short computational time as compared to a physical model we previously developed. By supporting VA surgical planning, this fast computing approach could allow AVF surgical planning and help reducing the rate of non-maturation, which might ultimately have a broad impact on the management of hemodialysis patients.

Applications of artificial intelligence-machine learning for detection of stress: a critical overview

Psychological distress is a major contributor to human physiology and pathophysiology, and it has been linked to several conditions, such as auto-immune diseases, metabolic syndrome, sleep disorders, and suicidal thoughts and inclination. Therefore, early detection and management of chronic stress is crucial for the prevention of several diseases. Artificial intelligence (AI) and Machine Learning (ML) have promoted a paradigm shift in several areas of biomedicine including diagnosis, monitoring, and prognosis of disease. Here, our review aims to present some of the AI and ML applications for solving biomedical issues related to psychological stress. We provide several lines of evidence from previous studies highlighting that AI and ML have been able to predict stress and detect the brain normal states vs. abnormal states (notably, in post-traumatic stress disorder (PTSD)) with accuracy around 90%. Of note, AI/ML-driven technology applied to identify ubiquitously present stress exposure may not reach its full potential, unless future analytics focus on detecting prolonged distress through such technology instead of merely assessing stress exposure. Moving forward, we propose that a new subcategory of AI methods called Swarm Intelligence (SI) can be used towards detecting stress and PTSD. SI involves ensemble learning techniques to efficiently solve a complex problem, such as stress detection, and it offers particular strength in clinical settings, such as privacy preservation. We posit that AI and ML approaches will be beneficial for the medical and patient community when applied to predict and assess stress levels. Last, we encourage additional research to bring AI and ML into the standard clinical practice for diagnostics in the not-too-distant future.

Ranking important predictors of the need for a high-acuity psychiatry unit among 2,064 inpatients admitted to psychiatric emergency hospitals: a random forest model

Aims

In order to uphold and enhance the emergency psychiatric care system, a thorough comprehension of the characteristics of patients who require a high-acuity psychiatry unit is indispensable. We aimed to clarify the most important predictors of the need for a high-acuity psychiatry unit using a random forest model.

Methods

This cross-sectional study encompassed patients admitted to psychiatric emergency hospitals at 161 medical institutions across Japan between December 8, 2022, and January 31, 2023. Questionnaires were completed by psychiatrists, with a maximum of 30 patients assessed per medical institution. The questionnaires included psychiatrists' assessment of the patient's condition (exposure variables) and the need for a high-acuity psychiatry unit (outcome variables). The exposure variables consisted of 32 binary variables, including age, diagnoses, and clinical condition (i.e., factors on the clinical profile, emergency treatment requirements, and purpose of hospitalization). The outcome variable was the need for a high-acuity psychiatry unit, scored from 0 to 10. To identify the most important predictors of the need for a high-acuity psychiatry unit, we used a random forest model. As a sensitivity analysis, multivariate linear regression analysis was performed.

Results

Data on 2,164 patients from 81 medical institutions were obtained (response rate, 50.3%). After excluding participants with missing values, this analysis included 2,064 patients. Of the 32 items, the top-5 predictors of the need for a high-acuity psychiatry unit were the essentiality of inpatient treatment (otherwise, symptoms will worsen or linger), need for 24-hour professional care, symptom severity, safety ensured by specialized equipment, and medication management. These items were each significantly and positively associated with the need for a high-acuity psychiatry unit in linear regression analyses (p < 0.001 for all). Conversely, items on age and diagnosis were lower in the ranking and were not statistically significant in linear regression models.

Conclusion

Items related to the patient's clinical profile might hold greater importance in predicting the need for a high-acuity psychiatry unit than do items associated with age and diagnosis.

Testing the bipolar assumption of Singer-Loomis Type Deployment Inventory for Korean adults using classification and multidimensional scaling

In this study, we explored whether the Korean version of Singer Loomis Type Deployment Inventory II (K-SLTDI) captures the opposing tendencies of Jung's theory of psychological type. The types are Extroverted Sensing, Extroverted Intuition, Extroverted Feeling, Extroverted Thinking, Introverted Sensing, Introverted Intuition, Introverted Feeling, and Introverted Thinking. A nationwide online survey was conducted in South Korea. We performed multidimensional scaling and classification analyses based on 521 Korean adult profiles with eight psychological types to test the bipolarity assumption. The results showed that the Procrustes-rotated four-dimensional space successfully represented four types of opposing tendencies. Moreover, the bipolarity assumption in the four dimensions of Jungian typology was tested and compared between lower and higher psychological distress populations via cluster analysis. Lastly, we explored patterns of responses in lower and higher psychological distress populations using intersubject correlation. Both similarity analyses and classification results consistently support the theoretical considerations on the conceptualization of Jung's type in independent order that the types could be derived without bipolar assumption as Singer and Loomis expected in their Type Development Inventory. Limitations in our study include the sample being randomly selected internet users during the COVID-19 pandemic, despite excellence in the use of the internet in the general Korean population.

Identification of Psycho-Socio-Judicial Trajectories and Factors Associated With Posttraumatic Stress Disorder in People Over 15 Years of Age Who Recently Reported Sexual Assault to a Forensic Medical Center: Protocol for a Multicentric Prospective Study Using Mixed Methods and Artificial Intelligence

BACKGROUND

Sexual assault (SA) can lead to a range of adverse effects on physical, sexual, and mental health, as well as on one's social life, financial stability, and overall quality of life. However, not all people who experience SA will develop negative functional outcomes. Various risk and protective factors can influence psycho-socio-judicial trajectories. However, how these factors influence trauma adaptation and the onset of early posttraumatic stress disorder (PTSD) is not always clear.

OBJECTIVE

Guided by an ecological framework, this project has 3 primary objectives: (1) to describe the 1-year psycho-socio-judicial trajectories of individuals recently exposed to SA who sought consultation with a forensic practitioner; (2) to identify predictive factors for the development of PTSD during the initial forensic examination using artificial intelligence; and (3) to explore the perceptions, needs, and experiences of individuals who have been sexually assaulted.

METHODS

This longitudinal multicentric cohort study uses a mixed methods approach. Quantitative cohort data are collected through an initial questionnaire completed by the physician during the first forensic examination and through follow-up telephone questionnaires at 6 weeks, 3 months, 6 months, and 1 year after the SA. The questionnaires measure factors associated with PTSD, mental, physical, social, and overall functional outcomes, as well as psycho-socio-judicial trajectories. Cohort participants are recruited through their forensic examination at 1 of the 5 participating centers based in France. Eligible participants are aged 15 or older, have experienced SA in the last 30 days, are fluent in French, and can be reached by phone. Qualitative data are gathered through semistructured interviews with cohort participants, individuals who have experienced SA but are not part of the cohort, and professionals involved in their psycho-socio-judicial care.

RESULTS

Bivariate and multivariate analyses will be conducted to examine the associations between each variable and mental, physical, social, and judicial outcomes. Predictive analyses will be performed using multiple prediction algorithms to forecast PTSD. Qualitative data will be integrated with quantitative data to identify psycho-socio-judicial trajectories and enhance the prediction of PTSD. Additionally, data on the perceptions and needs of individuals who have experienced SA will be analyzed independently to gain a deeper understanding of their experiences and requirements.

CONCLUSIONS

This project will collect extensive qualitative and quantitative data that have never been gathered over such an extended period, leading to unprecedented insights into the psycho-socio-judicial trajectories of individuals who have recently experienced SA. It represents the initial phase of developing a functional artificial intelligence tool that forensic practitioners can use to better guide individuals who have recently experienced SA, with the aim of preventing the onset of PTSD. Furthermore, it will contribute to addressing the existing gap in the literature regarding the accessibility and effectiveness of support services for individuals who have experienced SA in Europe. This comprehensive approach, encompassing the entire psycho-socio-judicial continuum and taking into account the viewpoints of SA survivors, will enable the generation of innovative recommendations for enhancing their care across all stages, starting from the initial forensic examination.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/46652.

A Machine-Learning Approach to Assess Factors Associated With Hospitalization of Children and Youths in Psychiatric Crisis

OBJECTIVE

The authors used a machine-learning approach to model clinician decision making regarding psychiatric hospitalization of children and youths in crisis and to identify factors associated with the decision to hospitalize.

METHODS

Data consisted of 4,786 mobile crisis response team assessments of children and youths, ages 4.0-19.5 years (mean±SD=14.0±2.7 years, 56% female), in Nevada. The sample assessments were split into training and testing data sets. A random-forest machine-learning algorithm was used to identify variables related to the decision to hospitalize a child or youth after the crisis assessment. Results from the training sample were externally validated in the testing sample.

RESULTS

The random-forest model had good performance (area under the curve training sample=0.91, testing sample=0.92). Variables found to be important in the decision to hospitalize a child or youth were acute suicidality, followed by poor judgment or decision making, danger to others, impulsivity, runaway behavior, other risky behaviors, nonsuicidal self-injury, psychotic or depressive symptoms, sleep problems, oppositional behavior, poor functioning at home or with peers, depressive or schizophrenia spectrum disorders, and age.

CONCLUSIONS

In crisis settings, clinicians were found to mostly focus on acute factors that increased risk for danger to self or others (e.g., suicidality, poor judgment), current psychiatric symptoms (e.g., psychotic symptoms), and functioning (e.g., poor home functioning, problems with peer relationships) when deciding whether to hospitalize or stabilize a child or youth. To reduce psychiatric hospitalization, community-based services should target interventions to address these important factors associated with the need for a higher level of care among youths in psychiatric crisis.

Derivation and validation of risk prediction for posttraumatic stress symptoms following trauma exposure

BACKGROUND

Posttraumatic stress symptoms (PTSS) are common following traumatic stress exposure (TSE). Identification of individuals with PTSS risk in the early aftermath of TSE is important to enable targeted administration of preventive interventions. In this study, we used baseline survey data from two prospective cohort studies to identify the most influential predictors of substantial PTSS.

METHODS

Self-identifying black and white American women and men (n = 1546) presenting to one of 16 emergency departments (EDs) within 24 h of motor vehicle collision (MVC) TSE were enrolled. Individuals with substantial PTSS (⩾33, Impact of Events Scale - Revised) 6 months after MVC were identified via follow-up questionnaire. Sociodemographic, pain, general health, event, and psychological/cognitive characteristics were collected in the ED and used in prediction modeling. Ensemble learning methods and Monte Carlo cross-validation were used for feature selection and to determine prediction accuracy. External validation was performed on a hold-out sample (30% of total sample).

RESULTS

Twenty-five percent (n = 394) of individuals reported PTSS 6 months following MVC. Regularized linear regression was the top performing learning method. The top 30 factors together showed good reliability in predicting PTSS in the external sample (Area under the curve = 0.79 ± 0.002). Top predictors included acute pain severity, recovery expectations, socioeconomic status, self-reported race, and psychological symptoms.

CONCLUSIONS

These analyses add to a growing literature indicating that influential predictors of PTSS can be identified and risk for future PTSS estimated from characteristics easily available/assessable at the time of ED presentation following TSE.

Heart and brain traumatic stress biomarker analysis with and without machine learning: A scoping review

The enigma of post-traumatic stress disorder (PTSD) is embedded in a complex array of physiological responses to stressful situations that result in disruptions in arousal and cognitions that characterise the psychological disorder. Deciphering these physiological patterns is complex, which has seen the use of machine learning (ML) grow in popularity. However, it is unclear to what extent ML has been used with physiological data, specifically, the electroencephalogram (EEG) and electrocardiogram (ECG) to further understand the physiological responses associated with PTSD. To better understand the use of EEG and ECG biomarkers, with and without ML, a scoping review was undertaken. A total of 124 papers based on adult samples were identified comprising 19 ML studies involving EEG and ECG. A further 21 studies using EEG data, and 84 studies employing ECG meeting all other criteria but not employing ML were included for comparison. Identified studies indicate classical ML methodologies currently dominate EEG and ECG biomarkers research, with derived biomarkers holding clinically relevant diagnostic implications for PTSD. Discussion of the emerging trends, algorithms used and their success is provided, along with areas for future research.

A Review of Machine Learning and Deep Learning Approaches on Mental Health Diagnosis

Combating mental illnesses such as depression and anxiety has become a global concern. As a result of the necessity for finding effective ways to battle these problems, machine learning approaches have been included in healthcare systems for the diagnosis and probable prediction of the treatment outcomes of mental health conditions. With the growing interest in machine and deep learning methods, analysis of existing work to guide future research directions is necessary. In this study, 33 articles on the diagnosis of schizophrenia, depression, anxiety, bipolar disorder, post-traumatic stress disorder (PTSD), anorexia nervosa, and attention deficit hyperactivity disorder (ADHD) were retrieved from various search databases using the preferred reporting items for systematic reviews and meta-analysis (PRISMA) review methodology. These publications were chosen based on their use of machine learning and deep learning technologies, individually assessed, and their recommended methodologies were then classified into the various disorders included in this study. In addition, the difficulties encountered by the researchers are discussed, and a list of some public datasets is provided.

A statistical genetic investigation of psychiatric resilience

Background: Although trauma exposure (TE) is a transdiagnostic risk factor for many psychiatric disorders, not everyone who experiences TE develops a psychiatric disorder. Resilience may explain this heterogeneity; thus, it is critical to understand the etiologic underpinnings of resilience.Objective: The present study sought to examine the genetic underpinnings of psychiatric resilience using genome-wide association studies (GWAS), genome-wide complex trait analysis (GCTA), and polygenic risk score (PRS) analyses.Method: Participants were 6,634 trauma exposed college students attending a diverse, public university in the Mid Atlantic. GWAS and GCTA analyses were conducted, and using GWAS summary statistics from large genetic consortia, PRS analyses examined the shared genetic risk between resilience and various phenotypes.Results: Results demonstrate that nine single-nucleotide polymorphisms (SNPs) met the suggestive of significance threshold, heritability estimates for resilience were non-significant, and that there is genetic overlap between resilience and AD, as well as resilience and PTSD.Conclusion: Mixed findings from the present study suggest additional research to elucidate the etiological underpinnings of resilience, ideally with larger samples less biased by variables such as heterogeneity (i.e. clinical vs. population based) and population stratification. Genetic investigations of resilience have the potential to elucidate the molecular bases of stress-related psychopathology, suggesting new avenues for prevention and intervention efforts.

Breaking up with my idol: A qualitative study of the psychological adaptation process of renouncing fanship

Introduction

This study aimed to explore the psychological adaptation process of renouncing fanship due to para-loveshock in the context of fandom culture.

Methods

We adopted netnography to explore social media platforms used by fans in China (Weibo, WeChat, and Douban) as research fields for 3 years.

Results

(1) The process of "breaking up with" or renouncing an idol can be divided into three phases: the resistance phase with acute stress, the negotiation phase with bargaining, and the recovery phase with attachment reconstruction. In the resistance phase, fans displayed acute stress responses due to loveshock in psychological, physical, and behavioral aspects. In the negotiation phase, fans faced four barriers to renouncement: cognitive dissonance, emotional attachment, behavioral dependence, and social threat. They bargained within the three types of cognitive framework before deciding to "leave" or "re-follow" their idol. In the recovery phase, fans adopted two types of strategies to promote recovery: healing the past and facing the future. Healing the past involved public outcry, sharing their breakup plans, cognitive reconstruction, and seeking closure to the fan role. Facing the future involved switching environments, seeking new interests, and inhibiting the re-intrusion of trauma cues. (2) Internal factors affecting the psychological adaptation process of renouncement include the level of initiative, attribution styles, experience, attachment status and core belief systems, and alternative lifestyles; external factors include social support, peer pressure from the fan community, life stressors, and types and impact of traumatic events. (3) Based on the two dimensions of orientation and commitment, fans were classified into four types: short-term rational, short-term passionate, bounded loyal, and unconditionally loyal, corresponding to non-traumatic, stressful, accumulated, and traumatic breakup processes, respectively. (4) The post-renouncement growth of fans mainly manifested in the development of mental modes, coping skills toward trauma, emotional adaptation experience, and behavior patterns.

Implications

This investigation of the recovery process from para-loveshock after renouncement of fanship can provide theoretical and practical insights into the development of psychological resilience for fans, reduction of the psychological distress and negative outcomes, and public governance on social media platform and cyber pop culture industry.

Identifying and predicting posttraumatic stress symptom states in adults with posttraumatic stress disorder

Between-person heterogeneity of posttraumatic stress disorder (PTSD) is well established. Within-person analyses and the DSM-5 suggest that heterogeneity may also be evident within individuals across time as they move through social contexts and biological cycles. Modeling within-person symptom-level fluctuations may confirm such heterogeneity, elucidate mechanisms of disorder maintenance, and inform time- and person-specific interventions. The present study aimed to identify and predict discrete within-person disorder presentations, or symptom states, and explore group-level patterns of these states. Adults (N = 20, 60.0% male, M age = 38.25 years) with PTSD responded to symptom surveys four times per day for 30 days. We subjected each individual's dataset to Gaussian finite mixture modeling (GFMM) to uncover latent, within-person classes of symptom levels (i.e., states) and predicted those states with idiographic elastic net regularized regression using a set of time-based and behavioral predictors. Next, we conducted a GFMM of the within-person GFMM outputs and tested idiographic prediction models of these states. Multiple within-person states were revealed for 19 of 20 participants (Mdn = 4; 66 for the full sample). Prediction models were moderately successful, M AUC = .66 (d = 0.58), range: .50-1.00. The GFMM of the within-person model outputs revealed two states: one with above-average and one with below-average symptom levels. Prediction models were, again, moderately successful, M AUC = .66; range: .50-.89. The findings provide evidence for within-person heterogeneity of PTSD as well as between-person similarities and suggest that future work should incorporate additional contextual variables as symptom state predictors.

Mother’s Concern in the Family about Her Child with Post-Traumatic Due to the Tornado in Central Java, Indonesia – A Qualitative Study

BACKGROUND: Natural disasters continue to occur worldwide, influencing the economy, finances, and psychological problems. Traumatic on children is an impact of the catastrophe likely a burden on the family, especially mothers who accompany their children as caregivers. AIM: The purpose of the study was to explore children’s traumatic experiences from mothers in a family in a rural community in Indonesia. METHODS: We conducted six focus groups with mothers to explore their traumatic children’s experiences using a qualitative research design. Thirty mothers with children 3−10 years old contributed to the focus groups across all sites. We formed focus groups with six mothers and continued in-depth interviews, including nine mothers. RESULTS: The mothers had similar experiences understanding their children’s trauma due to natural tornado disasters. This study revealed three overarching themes shaping the mothers’ experience: anxiety in children, trauma trigger, and lingering distress. All themes lead to the main theme is psychological distress in the face of a child suffering from PTSD. From the hermeneutical perspective, topics can be identified as terms, including being-thrownness, being-fallenness and being-alongside. CONCLUSION: Children with post-traumatic stress disorder may impact family physiological problems, especially the mother. The study found that may place the burden of care for children on the person’s families.

Uncovering heterogeneous associations of disaster-related traumatic experiences with subsequent mental health problems: A machine learning approach

AIM

Understanding the differential mental health effects of traumatic experiences is important to identify particularly vulnerable subpopulations. We examined the heterogeneous associations between disaster-related traumatic experiences and postdisaster mental health, using a novel machine learning-based causal inference approach.

METHODS

Data were from a prospective cohort study of Japanese older adults in an area severely affected by the 2011 Great East Japan Earthquake. The baseline survey was conducted 7 months before the disaster and the 2 follow-up surveys were conducted 2.5 and 5.5 years after (n = 1150 to n = 1644 depending on the exposure-outcome combinations). As disaster-related traumatic experiences, we assessed complete home loss and loss of loved ones. Using the generalized random forest algorithm, we estimated conditional average treatment effects (CATEs) of the disaster damages on postdisaster mental health outcomes to examine the heterogeneous associations by 51 predisaster characteristics of the individuals.

RESULTS

We found that, even when there was no population average association between disaster-related trauma and subsequent mental health outcomes, some subgroups experienced severe impacts. We also identified and compared characteristics of the most and least vulnerable groups (ie, top versus bottom deciles of the estimated CATEs). While there were some unique patterns specific to each exposure-outcome combination, the most vulnerable group tended to be from lower socioeconomic backgrounds with preexisting depressive symptoms for many exposure-outcome combinations.

CONCLUSIONS

We found considerable heterogeneity in the association between disaster-related traumatic experiences and subsequent mental health problems.

Experiencing Urban Green and Blue Spaces in Urban Wetlands as a Nature-Based Solution to Promote Positive Emotions

Green and blue spaces are nature-based solutions (NBSs) that evoke positive emotions of experiencers therein. There is an impetus to optimize wetland forest landscapes by planning the geographical arrangement of metrics that promote positive emotion. The facial expressions of nature experiencers in photos, downloaded from social media databases with landscape metrics, were evaluated for emotions and given scores. Happy and sad scores were rated by FireFACE v1.0 software and positive response index (PRI) was calculated as happy score minus sad score. Spatial areas and tree height were evaluated from Landsat 8 images and digital model maps, respectively. Visitors at middle and senior ages smiled more frequently in southern parts than in northern parts, and females had higher happy scores and PRI than males. Both green- and blue-space areas had positive relationships with PRI scores, while blue spaces and their area to park area ratios had positive contributions to happy scores and PRI scores in multivariate linear regression models. Elevation had a negative relationship with positive facial emotion. Overall, based on spatial distributions of blue-space area and elevation, regional landscape was optimized so people perceived more happiness in wetlands around Zhejiang and Shanghai, while people in wetlands of Jiangxi and Hubei showed more net emotional expressions.

Predictive modeling of service discontinuation in transitional age youth with recent behavioral health service use

OBJECTIVE

To develop and test predictive models of discontinuation of behavioral health service use within 12 months in transitional age youth with recent behavioral health service use.

DATA SOURCES

Administrative claims for Medicaid beneficiaries aged 15-26 years in Connecticut.

STUDY DESIGN

We compared the performance of a decision tree, random forest, and gradient boosting machine learning algorithms to logistic regression in predicting service discontinuation within 12 months among beneficiaries using behavioral health services.

DATA EXTRACTION

We identified 33,532 transitional age youth with ≥1 claim for a primary behavioral health diagnosis in 2016 and Medicaid enrollment of ≥11 months in 2016 and ≥11 months in 2017.

PRINCIPAL FINDINGS

Classification accuracy for identifying youth who discontinued behavioral health service use was highest for gradient boosting (80%, AUC = 0.86), decision tree (79%, AUC = 0.84), and random forest (79%, AUC = 0.86), as compared with logistic regression (71%, AUC = 0.71).

CONCLUSIONS

Predictive models based on Medicaid claims can assist in identifying transitional age youth who are at risk of discontinuing from behavioral health care within 12 months, thus allowing for proactive assessment and outreach to promote continuity of care for younger persons who have behavioral health needs.

Diagnosing post-traumatic stress disorder using electronic medical record data

This study proposes a predictive model that uses structured data and unstructured narrative notes from Electronic Medical Records to accurately identify patients diagnosed with Post-Traumatic Stress Disorder (PTSD). We utilize data from primary care clinicians participating in the Manitoba Primary Care Research Network (MaPCReN) representing 154,118 patients. A reference sample of 195 patients that had their PTSD diagnosis confirmed using a manual chart review of structured data and narrative notes, and PTSD negative patients is used as the gold standard data for model training, validation and testing. We assess structured and unstructured data from eight tables in the MaPCReN namely, patient demographics, disease case, examinations, medication, billing records, health condition, risk factors, and encounter notes. Feature engineering is applied to convert data into proper representation for predictive modeling. We explore serial and parallel mixed data models that are trained on both structured and unstructured data to identify PTSD. Model performances were calculated based on a highly skewed hold-out test dataset. The serial model that uses both structured and text data as input, yielded the highest values in sensitivity (0.77), F-measure (0.76), and AUC (0.88) and the parallel model that uses both structured and text data as the input obtained the highest positive predicted value (PPV) (0.75). Diseases such as PTSD are difficult to diagnose. Information recorded in the chart note over multiple visits of the patients with the primary care physicians has higher predictive power than structured data and combining these two data types can increase the predictive capabilities of machine learning models in diagnosing PTSD. While the deep-learning model outperformed the traditional ensemble model in processing text data, the ensemble classifier obtained better results in ingesting a combination of features obtained from both data types in the serial mixed model. The study demonstrated that unstructured encounter notes enhance a model's ability to identify patients diagnosed with PTSD. These findings can enhance quality improvement, research, and disease surveillance related to PTSD in primary care populations.

Common and specific determinants of 9-year depression and anxiety course-trajectories: A machine-learning investigation in the Netherlands Study of Depression and Anxiety (NESDA)

BACKGROUND

Given the strong relationship between depression and anxiety, there is an urge to investigate their shared and specific long-term course determinants. The current study aimed to identify and compare the main determinants of the 9-year trajectories of combined and pure depression and anxiety symptom severity.

METHODS

Respondents with a 6-month depression and/or anxiety diagnosis (n=1,701) provided baseline data on 152 sociodemographic, clinical and biological variables. Depression and anxiety symptom severity assessed at baseline, 2-, 4-, 6- and 9-year follow-up, were used to identify data-driven course-trajectory subgroups for general psychological distress, pure depression, and pure anxiety severity scores. For each outcome (class-probability), a Superlearner (SL) algorithm identified an optimally weighted (minimum mean squared error) combination of machine-learning prediction algorithms. For each outcome, the top determinants in the SL were identified by determining variable-importance and correlations between each SL-predicted and observed outcome (ρ_pred) were calculated.

RESULTS

Low to high prediction correlations (ρ_pred: 0.41-0.91, median=0.73) were found. In the SL, important determinants of psychological distress were age, young age of onset, respiratory rate, participation disability, somatic disease, low income, minor depressive disorder and mastery score. For course of pure depression and anxiety symptom severity, similar determinants were found. Specific determinants of pure depression included several types of healthcare-use, and of pure-anxiety course included somatic arousal and psychological distress.

LIMITATIONS

Limited sample size for machine learning.

CONCLUSIONS

The determinants of depression- and anxiety-severity course are mostly shared. Domain-specific exceptions are healthcare use for depression and somatic arousal and distress for anxiety-severity course.

Deep learning model of fMRI connectivity predicts PTSD symptom trajectories in recent trauma survivors

Early intervention following exposure to a traumatic life event could change the clinical path from the development of post traumatic stress disorder (PTSD) to recovery, hence the interest in early detection and underlying biological mechanisms involved in the development of post traumatic sequelae. We introduce a novel end-to-end neural network that employs resting-state and task-based functional MRI (fMRI) datasets, obtained one month after trauma exposure, to predict PTSD symptoms at one-, six- and fourteen-months after the exposure. FMRI data, as well as PTSD status and symptoms, were collected from adults at risk for PTSD development, after admission to emergency room following a traumatic event. Our computational method utilized a per-region encoder to extract brain regions embedding, which were subsequently updated by applying the algorithmic technique of pairwise attention. The affinities obtained between each pair of regions were combined to create a pairwise co-activation map used to perform multi-label classification. The results demonstrate that the novel method's performance in predicting PTSD symptoms, in a prospective manner, outperforms previous analytical techniques reported in the fMRI literature, all trained on the same dataset. We further show a high predictive ability for predicting PTSD symptom clusters and PTSD persistence. To the best of our knowledge, this is the first deep learning method applied on fMRI data with respect to prospective clinical outcomes, to predict PTSD status, severity and symptom clusters. Future work could further delineate the mechanisms that underlie such a prediction, and potentially improve single patient characterization.

Effects of Autonomic Nervous System Functioning and Tornado Exposure on Long-Term Outcomes of Aggressive Children

This study examined whether pre-disaster indicators of sympathetic and parasympathetic activity moderated the relation between degree of disaster exposure from an EF-4 tornado and changes in the externalizing and internalizing behavior problems of children at-risk for aggression. Participants included 188 children in 4th-6th grades (65% male; 78% African American; ages 9-13) and their parents from predominantly low-income households who were participating in a prevention study when the tornado occurred in 2011. Fourth-grade children who exhibited elevated levels of aggressive behavior were recruited in three annual cohorts. Parent-rated externalizing and internalizing problems were assessed prior to the tornado (Wave 1; W1), and at 4-12 months (W2), 16-24 months (W3), 42-28 months (W4) and 56-60 months (W5) post-tornado. Children's pre-tornado Skin Conductance Level (SCL) reactivity and Respiratory Sinus Arrhythmia (RSA) withdrawal were assessed at W1 using SCL and RSA measured during resting baseline and during the first 5 min of the Iowa Gambling Task (IGT). Children and parents reported their exposure to tornado-related trauma and disruptions at Wave 3. Children displayed less reduction in externalizing problems if there had been higher child- or parent-reported tornado exposure and less RSA withdrawal, or if they had lower parent-reported TORTE and less SCL reactivity or lower SCL baseline. Highlighting the importance of children's pre-disaster arousal, higher levels of disaster exposure negatively affected children's level of improvement in externalizing problems when children had less vagal withdrawal, and when tornado exposure disrupted the protective effects of higher SCL reactivity and higher SCL baseline.

Prediction of the development of depression and post-traumatic stress disorder in sexually abused children using a random forest classifier

BACKGROUND

Depression and post-traumatic stress disorder (PTSD) are among the most common psychiatric disorders observed in children and adolescents exposed to sexual abuse.

OBJECTIVE

The present study aimed to investigate the effects of many factors such as the characteristics of a child, abuse, and the abuser, family type of the child, and the role of social support in the development of psychiatric disorders using machine learning techniques.

PARTICIPANTS AND SETTINGS

The records of 482 children and adolescents who were determined to have been sexually abused were examined to predict the development of depression and PTSD.

METHODS

Each child was evaluated by a child and adolescent psychiatrist in the psychiatric aspect according to the DSM-V. Through the data of both groups, a predictive model was established based on a random forest classifier.

RESULTS

The mean values and standard deviation of the 10-k cross-validated results were obtained as accuracy: 0.82% (+/- 0.19%), F1: 0.81% (+/- 0.19%), precision: 0.81% (+/- 0.19%), recall: 0.80% (+/- 0.19%) for children with depression; and accuracy: 0.72% (+/- 0.12%), F1: 0.71% (+/- 0.12%), precision: 0.72% (+/- 0.12%), recall: 0.71% (+/- 0.12%) for children with PTSD, respectively. ROC curves were drawn for both, and the AUC results were obtained as 0.88 for major depressive disorder and 0.76 for PTSD.

CONCLUSIONS

Machine learning techniques are powerful methods that can be used to predict disorders that may develop after sexual abuse. The results should be supported by studies with larger samples, which are repeated and applied to other risk groups.

Implementing Precision Psychiatry: A Systematic Review of Individualized Prediction Models for Clinical Practice

BACKGROUND

The impact of precision psychiatry for clinical practice has not been systematically appraised. This study aims to provide a comprehensive review of validated prediction models to estimate the individual risk of being affected with a condition (diagnostic), developing outcomes (prognostic), or responding to treatments (predictive) in mental disorders.

METHODS

PRISMA/RIGHT/CHARMS-compliant systematic review of the Web of Science, Cochrane Central Register of Reviews, and Ovid/PsycINFO databases from inception until July 21, 2019 (PROSPERO CRD42019155713) to identify diagnostic/prognostic/predictive prediction studies that reported individualized estimates in psychiatry and that were internally or externally validated or implemented. Random effect meta-regression analyses addressed the impact of several factors on the accuracy of prediction models.

FINDINGS

Literature search identified 584 prediction modeling studies, of which 89 were included. 10.4% of the total studies included prediction models internally validated (n = 61), 4.6% models externally validated (n = 27), and 0.2% (n = 1) models considered for implementation. Across validated prediction modeling studies (n = 88), 18.2% were diagnostic, 68.2% prognostic, and 13.6% predictive. The most frequently investigated condition was psychosis (36.4%), and the most frequently employed predictors clinical (69.5%). Unimodal compared to multimodal models (β = .29, P = .03) and diagnostic compared to prognostic (β = .84, p < .0001) and predictive (β = .87, P = .002) models were associated with increased accuracy.

INTERPRETATION

To date, several validated prediction models are available to support the diagnosis and prognosis of psychiatric conditions, in particular, psychosis, or to predict treatment response. Advancements of knowledge are limited by the lack of implementation research in real-world clinical practice. A new generation of implementation research is required to address this translational gap.

Literature review and methodological considerations for understanding circulating risk biomarkers following trauma exposure

Exposure to traumatic events is common. While many individuals recover following trauma exposure, a substantial subset develop adverse posttraumatic neuropsychiatric sequelae (APNS) such as posttraumatic stress, major depression, and regional or widespread chronic musculoskeletal pain. APNS cause substantial burden to the individual and to society, causing functional impairment and physical disability, risk for suicide, lost workdays, and increased health care costs. Contemporary treatment is limited by an inability to identify individuals at high risk of APNS in the immediate aftermath of trauma, and an inability to identify optimal treatments for individual patients. Our purpose is to provide a comprehensive review describing candidate blood-based biomarkers that may help to identify those at high risk of APNS and/or guide individual intervention decision-making. Such blood-based biomarkers include circulating biological factors such as hormones, proteins, immune molecules, neuropeptides, neurotransmitters, mRNA, and noncoding RNA expression signatures, while we do not review genetic and epigenetic biomarkers due to other recent reviews of this topic. The current state of the literature on circulating risk biomarkers of APNS is summarized, and key considerations and challenges for their discovery and translation are discussed. We also describe the AURORA study, a specific example of current scientific efforts to identify such circulating risk biomarkers and the largest study to date focused on identifying risk and prognostic factors in the aftermath of trauma exposure.

Supervised Machine Learning: A Brief Primer

Machine learning is increasingly used in mental health research and has the potential to advance our understanding of how to characterize, predict, and treat mental disorders and associated adverse health outcomes (e.g., suicidal behavior). Machine learning offers new tools to overcome challenges for which traditional statistical methods are not well-suited. This paper provides an overview of machine learning with a specific focus on supervised learning (i.e., methods that are designed to predict or classify an outcome of interest). Several common supervised learning methods are described, along with applied examples from the published literature. We also provide an overview of supervised learning model building, validation, and performance evaluation. Finally, challenges in creating robust and generalizable machine learning algorithms are discussed.

Real-Time Stress Assessment Using Sliding Window Based Convolutional Neural Network

Mental stress has been identified as a significant cause of several bodily disorders, such as depression, hypertension, neural and cardiovascular abnormalities. Conventional stress assessment methods are highly subjective and tedious and tend to lack accuracy. Machine-learning (ML)-based computer-aided diagnosis systems can be used to assess the mental state with reasonable accuracy, but they require offline processing and feature extraction, rendering them unsuitable for real-time applications. This paper presents a real-time mental stress assessment approach based on convolutional neural networks (CNNs). The CNN-based approach afforded real-time mental stress assessment with an accuracy as high as 96%, the sensitivity of 95%, and specificity of 97%. The proposed approach is compared with state-of-the-art ML techniques in terms of accuracy, time utilisation, and quality of features.

Applicability of an Automated Model and Parameter Selection in the Prediction of Screening-Level PTSD in Danish Soldiers Following Deployment: Development Study of Transferable Predictive Models Using Automated Machine Learning

BACKGROUND

Posttraumatic stress disorder (PTSD) is a relatively common consequence of deployment to war zones. Early postdeployment screening with the aim of identifying those at risk for PTSD in the years following deployment will help deliver interventions to those in need but have so far proved unsuccessful.

OBJECTIVE

This study aimed to test the applicability of automated model selection and the ability of automated machine learning prediction models to transfer across cohorts and predict screening-level PTSD 2.5 years and 6.5 years after deployment.

METHODS

Automated machine learning was applied to data routinely collected 6-8 months after return from deployment from 3 different cohorts of Danish soldiers deployed to Afghanistan in 2009 (cohort 1, N=287 or N=261 depending on the timing of the outcome assessment), 2010 (cohort 2, N=352), and 2013 (cohort 3, N=232).

RESULTS

Models transferred well between cohorts. For screening-level PTSD 2.5 and 6.5 years after deployment, random forest models provided the highest accuracy as measured by area under the receiver operating characteristic curve (AUC): 2.5 years, AUC=0.77, 95% CI 0.71-0.83; 6.5 years, AUC=0.78, 95% CI 0.73-0.83. Linear models performed equally well. Military rank, hyperarousal symptoms, and total level of PTSD symptoms were highly predictive.

CONCLUSIONS

Automated machine learning provided validated models that can be readily implemented in future deployment cohorts in the Danish Defense with the aim of targeting postdeployment support interventions to those at highest risk for developing PTSD, provided the cohorts are deployed on similar missions.

Can Hyperparameter Tuning Improve the Performance of a Super Learner?: A Case Study

BACKGROUND

Super learning is an ensemble machine learning approach used increasingly as an alternative to classical prediction techniques. When implementing super learning, however, not tuning the hyperparameters of the algorithms in it may adversely affect the performance of the super learner.

METHODS

In this case study, we used data from a Canadian electronic prescribing system to predict when primary care physicians prescribed antidepressants for indications other than depression. The analysis included 73,576 antidepressant prescriptions and 373 candidate predictors. We derived two super learners: one using tuned hyperparameter values for each machine learning algorithm identified through an iterative grid search procedure and the other using the default values. We compared the performance of the tuned super learner to that of the super learner using default values ("untuned") and a carefully constructed logistic regression model from a previous analysis.

RESULTS

The tuned super learner had a scaled Brier score (R) of 0.322 (95% [confidence interval] CI = 0.267, 0.362). In comparison, the untuned super learner had a scaled Brier score of 0.309 (95% CI = 0.256, 0.353), corresponding to an efficiency loss of 4% (relative efficiency 0.96; 95% CI = 0.93, 0.99). The previously-derived logistic regression model had a scaled Brier score of 0.307 (95% CI = 0.245, 0.360), corresponding to an efficiency loss of 5% relative to the tuned super learner (relative efficiency 0.95; 95% CI = 0.88, 1.01).

CONCLUSIONS

In this case study, hyperparameter tuning produced a super learner that performed slightly better than an untuned super learner. Tuning the hyperparameters of individual algorithms in a super learner may help optimize performance.

Posttraumatic Stress and Depression in the Aftermath of Environmental Disasters: A Review of Quantitative Studies Published in 2018

PURPOSE OF REVIEW

As interest in the mental health consequences of environmental disasters increases, this review aimed to summarize peer-reviewed studies published in 2018 on posttraumatic stress disorder (PTSD) and depression symptoms after such events.

RECENT FINDINGS

Notable trends in the past year of research included studies focusing on vulnerable populations (e.g., persons with preexisting physical health conditions), assessing the cumulative impact of exposure to multiple disasters, exploring pathway leading to PTSD and depression symptoms, and evaluating the effectiveness of post-disaster interventions. Over 100 articles were identified, focused on 40 disasters that occurred between 1982 and 2017. Prevalence estimates ranged from 0 to 70.51% for PTSD and 1.9 to 59.5% for depression. Consistent predictors of adverse outcomes included female gender, socioeconomic disadvantage, high disaster exposure, and low psychosocial resources. Further research that expands upon recent advances in the literature is critical given the large proportion of the world's population exposed to disasters and the increasing incidence of such events.

Personalized prognostic prediction of treatment outcome for depressed patients in a naturalistic psychiatric hospital setting: A comparison of machine learning approaches

OBJECTIVE

Research on predictors of treatment outcome in depression has largely derived from randomized clinical trials involving strict standardization of treatments, stringent patient exclusion criteria, and careful selection and supervision of study clinicians. The extent to which findings from such studies generalize to naturalistic psychiatric settings is unclear. This study sought to predict depression outcomes for patients seeking treatment within an intensive psychiatric hospital setting and while comparing the performance of a range of machine learning approaches.

METHOD

Depressed patients (N = 484; ages 18-72; 89% White) receiving treatment within a psychiatric partial hospital program delivering pharmacotherapy and cognitive behavioral therapy were split into a training sample and holdout sample. First, within the training sample, 51 pretreatment variables were submitted to 13 machine learning algorithms to predict, via cross-validation, posttreatment Patient Health Questionnaire-9 depression scores. Second, the best performing modeling approach (lowest mean squared error; MSE) from the training sample was selected to predict outcome in the holdout sample.

RESULTS

The best performing model in the training sample was elastic net regularization (ENR; MSE = 20.49, R2 = .28), which had comparable performance in the holdout sample (MSE = 11.26; R2 = .38). There were 14 pretreatment variables that predicted outcome. To demonstrate the translation of an ENR model to personalized prediction of treatment outcome, a patient-specific prognosis calculator is presented.

CONCLUSIONS

Informed by pretreatment patient characteristics, such predictive models could be used to communicate prognosis to clinicians and to guide treatment planning. Identified predictors of poor prognosis may suggest important targets for intervention. (PsycINFO Database Record (c) 2019 APA, all rights reserved).

The use of machine learning techniques in trauma-related disorders: a systematic review

Establishing the diagnosis of trauma-related disorders such as Acute Stress Disorder (ASD) and Posttraumatic Stress Disorder (PTSD) have always been a challenge in clinical practice and in academic research, due to clinical and biological heterogeneity. Machine learning (ML) techniques can be applied to improve classification of disorders, to predict outcomes or to determine person-specific treatment selection. We aim to review the existing literature on the use of machine learning techniques in the assessment of subjects with ASD or PTSD. We systematically searched PubMed, Embase and Web of Science for articles published in any language up to May 2019. We found 806 abstracts and included 49 studies in our review. Most of the included studies used multiple levels of biological data to predict risk factors or to identify early symptoms related to PTSD. Other studies used ML classification techniques to distinguish individuals with ASD or PTSD from other psychiatric disorder or from trauma-exposed and healthy controls. We also found studies that attempted to define outcome profiles using clustering techniques and studies that assessed the relationship among symptoms using network analysis. Finally, we proposed a quality assessment in this review, evaluating methodological and technical features on machine learning studies. We concluded that etiologic and clinical heterogeneity of ASD/PTSD patients is suitable to machine learning techniques and a major challenge for the future is to use it in clinical practice for the benefit of patients in an individual level.

Internalizing Symptoms as Predictors of School Absenteeism Severity at Multiple Levels: Ensemble and Classification and Regression Tree Analysis

School attendance problems are highly prevalent worldwide, leading researchers to investigate many different risk factors for this population. Of considerable controversy is how internalizing behavior problems might help to distinguish different types of youth with school attendance problems. In addition, efforts are ongoing to identify the point at which children and adolescents move from appropriate school attendance to problematic school absenteeism. The present study utilized ensemble and classification and regression tree analysis to identify potential internalizing behavior risk factors among youth at different levels of school absenteeism severity (i.e., 1+%, 3+%, 5+%, 10+%). Higher levels of absenteeism were also examined on an exploratory basis. Participants included 160 youth aged 6-19 years (M = 13.7; SD = 2.9) and their families from an outpatient therapy clinic (39.4%) and community (60.6%) setting, the latter from a family court and truancy diversion program cohort. One particular item relating to lack of enjoyment was most predictive of absenteeism severity at different levels, though not among the highest levels. Other internalizing items were also predictive of various levels of absenteeism severity, but only in a negatively endorsed fashion. Internalizing symptoms of worry and fatigue tended to be endorsed higher across less severe and more severe absenteeism severity levels. A general expectation that predictors would tend to be more homogeneous at higher than lower levels of absenteeism severity was not generally supported. The results help confirm the difficulty of conceptualizing this population based on forms of behavior but may support the need for early warning sign screening for youth at risk for school attendance problems.

Family Environment Variables as Predictors of School Absenteeism Severity at Multiple Levels: Ensemble and Classification and Regression Tree Analysis

School attendance problems, including school absenteeism, are common to many students worldwide, and frameworks to better understand these heterogeneous students include multiple classes or tiers of intertwined risk factors as well as interventions. Recent studies have thus examined risk factors at varying levels of absenteeism severity to demarcate distinctions among these tiers. Prior studies in this regard have focused more on demographic and academic variables and less on family environment risk factors that are endemic to this population. The present study utilized ensemble and classification and regression tree analysis to identify potential family environment risk factors among youth (i.e., children and adolescents) at different levels of school absenteeism severity (i.e., 1 + %, 3 + %, 5 + %, 10 + %). Higher levels of absenteeism were also examined on an exploratory basis. Participants included 341 youth aged 5-17 years (M = 12.2; SD = 3.3) and their families from an outpatient therapy clinic (68.3%) and community (31.7%) setting, the latter from a family court and truancy diversion program cohort. Family environment risk factors tended to be more circumscribed and informative at higher levels of absenteeism, with greater diversity at lower levels. Higher levels of absenteeism appear more closely related to lower achievement orientation, active-recreational orientation, cohesion, and expressiveness, though several nuanced results were found as well. Absenteeism severity levels of 10-15% may be associated more with qualitative changes in family functioning. These data may support a Tier 2-Tier 3 distinction in this regard and may indicate the need for specific family-based intervention goals at higher levels of absenteeism severity.

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.

Machine Learning for Prediction of Posttraumatic Stress and Resilience Following Trauma: An Overview of Basic Concepts and Recent Advances

Posttraumatic stress responses are characterized by a heterogeneity in clinical appearance and etiology. This heterogeneity impacts the field's ability to characterize, predict, and remediate maladaptive responses to trauma. Machine learning (ML) approaches are increasingly utilized to overcome this foundational problem in characterization, prediction, and treatment selection across branches of medicine that have struggled with similar clinical realities of heterogeneity in etiology and outcome, such as oncology. In this article, we review and evaluate ML approaches and applications utilized in the areas of posttraumatic stress, stress pathology, and resilience research, and present didactic information and examples to aid researchers interested in the relevance of ML to their own research. The examined studies exemplify the high potential of ML approaches to build accurate predictive and diagnostic models of posttraumatic stress and stress pathology risk based on diverse sources of available information. The use of ML approaches to integrate high-dimensional data demonstrates substantial gains in risk prediction even when the sources of data are the same as those used in traditional predictive models. This area of research will greatly benefit from collaboration and data sharing among researchers of posttraumatic stress disorder, stress pathology, and resilience.

Prediction of Return-to-original-work after an Industrial Accident Using Machine Learning and Comparison of Techniques

BACKGROUND

Many studies have tried to develop predictors for return-to-work (RTW). However, since complex factors have been demonstrated to predict RTW, it is difficult to use them practically. This study investigated whether factors used in previous studies could predict whether an individual had returned to his/her original work by four years after termination of the worker's recovery period.

METHODS

An initial logistic regression analysis of 1,567 participants of the fourth Panel Study of Worker's Compensation Insurance yielded odds ratios. The participants were divided into two subsets, a training dataset and a test dataset. Using the training dataset, logistic regression, decision tree, random forest, and support vector machine models were established, and important variables of each model were identified. The predictive abilities of the different models were compared.

RESULTS

The analysis showed that only earned income and company-related factors significantly affected return-to-original-work (RTOW). The random forest model showed the best accuracy among the tested machine learning models; however, the difference was not prominent.

CONCLUSION

It is possible to predict a worker's probability of RTOW using machine learning techniques with moderate accuracy.