A Machine Learning Approach to Predicting New-onset Depression in a Military Population
Ontology highlight
ABSTRACT: Objective:
Depression is one of the most common mental disorders in the United States in both civilian and military populations, but few prospective studies assess a wide range of predictors across multiple domains for new-onset (incident) depression in adulthood. Supervised machine learning methods can identify predictors of incident depression out of many different candidate variables, without some of the assumptions and constraints that underlie traditional regression analyses. The objectives of this study were to identify predictors of incident depression across 5 years of follow-up using machine learning, and to assess prediction accuracy of the algorithms. Methods:
Data were from a cohort of Army National Guard members free of history of depression at baseline (n = 1951 men and 298 women), interviewed once per year for probable depression. Classification trees and random forests were constructed and cross-validated, using 84 candidate predictors from the baseline interviews. Results:
Stressors and traumas such as emotional mistreatment and adverse childhood experiences, demographics such as being a parent or student, and military characteristics including paygrade and deployment location were predictive of probable depression. Cross-validated random forest algorithms were moderately accurate (68% for women and 73% for men). Conclusions:
Events and characteristics throughout the life course, both in and outside of deployment, predict incident depression in adulthood among military personnel. Although replication studies are needed, these results may help inform potential intervention targets to reduce depression incidence among military personnel. Future research should further refine and explore interactions between identified variables.
SUBMITTER: Sampson L
PROVIDER: S-EPMC8562467 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:IntroductionPost-stroke depression (PSD) is a serious mental disorder after ischemic stroke. Early detection is important for clinical practice. This research aims to develop machine learning models to predict new-onset PSD using real-world data.MethodsWe collected data for ischemic stroke patients from multiple medical institutions in Taiwan between 2001 and 2019. We developed models from 61,460 patients and used 15,366 independent patients to test the models' performance by evaluating their specificities and sensitivities. The predicted targets were whether PSD occurred at 30, 90, 180, and 365 days post-stroke. We ranked the important clinical features in these models.ResultsIn the study's database sample, 1.3% of patients were diagnosed with PSD. The average specificity and sensitivity of these four models were 0.83-0.91 and 0.30-0.48, respectively. Ten features were listed as important features related to PSD at different time points, namely old age, high height, low weight post-stroke, higher diastolic blood pressure after stroke, no pre-stroke hypertension but post-stroke hypertension (new-onset hypertension), post-stroke sleep-wake disorders, post-stroke anxiety disorders, post-stroke hemiplegia, and lower blood urea nitrogen during stroke.DiscussionMachine learning models can provide as potential predictive tools for PSD and important factors are identified to alert clinicians for early detection of depression in high-risk stroke patients.
| S-EPMC10315461 | biostudies-literature
Project description:Diagnostic heterogeneity within and across psychotic and affective disorders challenges accurate treatment selection, particularly in the early stages. Delineation of shared and distinct illness features at the phenotypic and brain levels may inform the development of more precise differential diagnostic tools. We aimed to identify prototypes of depression and psychosis to investigate their heterogeneity, with common, comorbid transdiagnostic symptoms. Analyzing clinical/neurocognitive and grey matter volume (GMV) data from the PRONIA database, we generated prototypic models of recent-onset depression (ROD) vs. recent-onset psychosis (ROP) by training support-vector machines to separate patients with ROD from patients with ROP, who were selected for absent comorbid features (pure groups). Then, models were applied to patients with comorbidity, ie, ROP with depressive symptoms (ROP+D) and ROD participants with sub-threshold psychosis-like features (ROD+P), to measure their positions within the affective-psychotic continuum. All models were independently validated in a replication sample. Comorbid patients were positioned between pure groups, with ROP+D patients being more frequently classified as ROD compared to pure ROP patients (clinical/neurocognitive model: χ2 = 14.874; P < .001; GMV model: χ2 = 4.933; P = .026). ROD+P patient classification did not differ from ROD (clinical/neurocognitive model: χ2 = 1.956; P = 0.162; GMV model: χ2 = 0.005; P = .943). Clinical/neurocognitive and neuroanatomical models demonstrated separability of prototypic depression from psychosis. The shift of comorbid patients toward the depression prototype, observed at the clinical and biological levels, suggests that psychosis with affective comorbidity aligns more strongly to depressive rather than psychotic disease processes. Future studies should assess how these quantitative measures of comorbidity predict outcomes and individual responses to stratified therapeutic interventions.
| S-EPMC8266654 | biostudies-literature
Project description:BackgroundMachine learning (ML) offers vigorous statistical and probabilistic techniques that can successfully predict certain clinical conditions using large volumes of data. A review of ML and big data research analytics in maternal depression is pertinent and timely, given the rapid technological developments in recent years.ObjectiveThis study aims to synthesize the literature on ML and big data analytics for maternal mental health, particularly the prediction of postpartum depression (PPD).MethodsWe used a scoping review methodology using the Arksey and O'Malley framework to rapidly map research activity in ML for predicting PPD. Two independent researchers searched PsycINFO, PubMed, IEEE Xplore, and the ACM Digital Library in September 2020 to identify relevant publications in the past 12 years. Data were extracted from the articles' ML model, data type, and study results.ResultsA total of 14 studies were identified. All studies reported the use of supervised learning techniques to predict PPD. Support vector machine and random forest were the most commonly used algorithms in addition to Naive Bayes, regression, artificial neural network, decision trees, and XGBoost (Extreme Gradient Boosting). There was considerable heterogeneity in the best-performing ML algorithm across the selected studies. The area under the receiver operating characteristic curve values reported for different algorithms were support vector machine (range 0.78-0.86), random forest method (0.88), XGBoost (0.80), and logistic regression (0.93).ConclusionsML algorithms can analyze larger data sets and perform more advanced computations, which can significantly improve the detection of PPD at an early stage. Further clinical research collaborations are required to fine-tune ML algorithms for prediction and treatment. ML might become part of evidence-based practice in addition to clinical knowledge and existing research evidence.
| S-EPMC8663566 | biostudies-literature
Project description:Introduction: Mitral stenosis is associated with an atrial cardiomyopathic process, leading to abnormal atrial electrophysiology, manifesting as prolonged P-wave duration (PWD), larger P-wave area, increased P-wave dispersion (PWDmax-PWDmin), and/or higher P-wave terminal force on lead V1 (PTFV1) on the electrocardiogram. Methods: This was a single-center retrospective study of Chinese patients, diagnosed with mitral stenosis in sinus rhythm at baseline, between November 2009 and October 2016. Automated ECG measurements from raw data were determined. The primary outcome was incident atrial fibrillation (AF). Results: A total 59 mitral stenosis patients were included (age 59 [54-65] years, 13 (22%) males). New onset AF was observed in 27 patients. Age (odds ratio [OR]: 1.08 [1.01-1.16], P = 0.017), systolic blood pressure (OR: 1.03 [1.00-1.07]; P = 0.046), mean P-wave area in V3 (odds ratio: 3.97 [1.32-11.96], P = 0.014) were significant predictors of incident AF. On multivariate analysis, age (OR: 1.08 [1.00-1.16], P = 0.037) and P-wave area in V3 (OR: 3.64 [1.10-12.00], P = 0.034) remained significant predictors of AF. Receiver-operating characteristic (ROC) analysis showed that the optimum cut-off for P-wave area in V3 was 1.45 Ashman units (area under the curve: 0.65) for classification of new onset AF. A decision tree learning model with individual and non-linear interaction variables with age achieved the best performance for outcome prediction (accuracy = 0.84, precision = 0.84, recall = 0.83, F-measure = 0.84). Conclusion: Atrial electrophysiological alterations in mitral stenosis can detected on the electrocardiogram. Age, systolic blood pressure, and P-wave area in V3 predicted new onset AF. A decision tree learning model significantly improved outcome prediction.
| S-EPMC7243705 | biostudies-literature
Project description:BackgroundThe Centers for Medicare and Medicaid Services projects that health care costs will continue to grow over the next few years. Rising readmission costs contribute significantly to increasing health care costs. Multiple areas of health care, including readmissions, have benefited from the application of various machine learning algorithms in several ways.ObjectiveWe aimed to identify suitable models for predicting readmission charges billed by hospitals. Our literature review revealed that this application of machine learning is underexplored. We used various predictive methods, ranging from glass-box models (such as regularization techniques) to black-box models (such as deep learning-based models).MethodsWe defined readmissions as readmission with the same major diagnostic category (RSDC) and all-cause readmission category (RADC). For these readmission categories, 576,701 and 1,091,580 individuals, respectively, were identified from the Nationwide Readmission Database of the Healthcare Cost and Utilization Project by the Agency for Healthcare Research and Quality for 2013. Linear regression, lasso regression, elastic net, ridge regression, eXtreme gradient boosting (XGBoost), and a deep learning model based on multilayer perceptron (MLP) were the 6 machine learning algorithms we tested for RSDC and RADC through 10-fold cross-validation.ResultsOur preliminary analysis using a data-driven approach revealed that within RADC, the subsequent readmission charge billed per patient was higher than the previous charge for 541,090 individuals, and this number was 319,233 for RSDC. The top 3 major diagnostic categories (MDCs) for such instances were the same for RADC and RSDC. The average readmission charge billed was higher than the previous charge for 21 of the MDCs in the case of RSDC, whereas it was only for 13 of the MDCs in RADC. We recommend XGBoost and the deep learning model based on MLP for predicting readmission charges. The following performance metrics were obtained for XGBoost: (1) RADC (mean absolute percentage error [MAPE]=3.121%; root mean squared error [RMSE]=0.414; mean absolute error [MAE]=0.317; root relative squared error [RRSE]=0.410; relative absolute error [RAE]=0.399; normalized RMSE [NRMSE]=0.040; mean absolute deviation [MAD]=0.031) and (2) RSDC (MAPE=3.171%; RMSE=0.421; MAE=0.321; RRSE=0.407; RAE=0.393; NRMSE=0.041; MAD=0.031). The performance obtained for MLP-based deep neural networks are as follows: (1) RADC (MAPE=3.103%; RMSE=0.413; MAE=0.316; RRSE=0.410; RAE=0.397; NRMSE=0.040; MAD=0.031) and (2) RSDC (MAPE=3.202%; RMSE=0.427; MAE=0.326; RRSE=0.413; RAE=0.399; NRMSE=0.041; MAD=0.032). Repeated measures ANOVA revealed that the mean RMSE differed significantly across models with P<.001. Post hoc tests using the Bonferroni correction method indicated that the mean RMSE of the deep learning/XGBoost models was statistically significantly (P<.001) lower than that of all other models, namely linear regression/elastic net/lasso/ridge regression.ConclusionsModels built using XGBoost and MLP are suitable for predicting readmission charges billed by hospitals. The MDCs allow models to accurately predict hospital readmission charges.
| S-EPMC9472041 | biostudies-literature
Project description:BackgroundEfforts to identify important risk factors for cognitive impairment and dementia have to date mostly relied on meta-analytic strategies. A comprehensive empirical evaluation of these risk factors within a single study is currently lacking.ObjectiveWe used a combined methodology of machine learning and semi-parametric survival analysis to estimate the relative importance of 52 predictors in forecasting cognitive impairment and dementia in a large, population-representative sample of older adults.MethodsParticipants from the Health and Retirement Study (N = 9,979; aged 50-98 years) were followed for up to 10 years (M = 6.85 for cognitive impairment; M = 7.67 for dementia). Using a split-sample methodology, we first estimated the relative importance of predictors using machine learning (random forest survival analysis), and we then used semi-parametric survival analysis (Cox proportional hazards) to estimate effect sizes for the most important variables.ResultsAfrican Americans and individuals who scored high on emotional distress were at relatively highest risk for developing cognitive impairment and dementia. Sociodemographic (lower education, Hispanic ethnicity) and health variables (worse subjective health, increasing BMI) were comparatively strong predictors for cognitive impairment. Cardiovascular factors (e.g., smoking, physical inactivity) and polygenic scores (with and without APOEɛ4) appeared less important than expected. Post-hoc sensitivity analyses underscored the robustness of these results.ConclusionsHigher-order factors (e.g., emotional distress, subjective health), which reflect complex interactions between various aspects of an individual, were more important than narrowly defined factors (e.g., clinical and behavioral indicators) when evaluated concurrently to predict cognitive impairment and dementia.
| S-EPMC7934087 | biostudies-literature
Project description:IntroductionThe study objective was to build a machine learning model to predict incident mild cognitive impairment, Alzheimer's Disease, and related dementias from structured data using administrative and electronic health record sources.MethodsA cohort of patients (n = 121,907) and controls (n = 5,307,045) was created for modeling using data within 2 years of patient's incident diagnosis date. Additional cohorts 3-8 years removed from index data are used for prediction. Training cohorts were matched on age, gender, index year, and utilization, and fit with a gradient boosting machine, lightGBM.ResultsIncident 2-year model quality on a held-out test set had a sensitivity of 47% and area-under-the-curve of 87%. In the 3-year model, the learned labels achieved 24% (71%), which dropped to 15% (72%) in year 8.DiscussionThe ability of the model to discriminate incident cases of dementia implies that it can be a worthwhile tool to screen patients for trial recruitment and patient management.
| S-EPMC6920083 | biostudies-literature
Project description:OBJECTIVE:To determine how machine learning has been applied to prediction applications in population health contexts. Specifically, to describe which outcomes have been studied, the data sources most widely used and whether reporting of machine learning predictive models aligns with established reporting guidelines. DESIGN:A scoping review. DATA SOURCES:MEDLINE, EMBASE, CINAHL, ProQuest, Scopus, Web of Science, Cochrane Library, INSPEC and ACM Digital Library were searched on 18 July 2018. ELIGIBILITY CRITERIA:We included English articles published between 1980 and 2018 that used machine learning to predict population-health-related outcomes. We excluded studies that only used logistic regression or were restricted to a clinical context. DATA EXTRACTION AND SYNTHESIS:We summarised findings extracted from published reports, which included general study characteristics, aspects of model development, reporting of results and model discussion items. RESULTS:Of 22 618 articles found by our search, 231 were included in the review. The USA (n=71, 30.74%) and China (n=40, 17.32%) produced the most studies. Cardiovascular disease (n=22, 9.52%) was the most studied outcome. The median number of observations was 5414 (IQR=16?543.5) and the median number of features was 17 (IQR=31). Health records (n=126, 54.5%) and investigator-generated data (n=86, 37.2%) were the most common data sources. Many studies did not incorporate recommended guidelines on machine learning and predictive modelling. Predictive discrimination was commonly assessed using area under the receiver operator curve (n=98, 42.42%) and calibration was rarely assessed (n=22, 9.52%). CONCLUSIONS:Machine learning applications in population health have concentrated on regions and diseases well represented in traditional data sources, infrequently using big data. Important aspects of model development were under-reported. Greater use of big data and reporting guidelines for predictive modelling could improve machine learning applications in population health. REGISTRATION NUMBER:Registered on the Open Science Framework on 17 July 2018 (available at https://osf.io/rnqe6/).
| S-EPMC7592293 | biostudies-literature
Project description:AIMS:Most cigarette smokers want to quit smoking and more than half make an attempt every year, but less than 10% remain abstinent for at least 6 months. Evidence-based tobacco use treatment improves the likelihood of quitting, but more than two-thirds of individuals relapse when provided even the most robust treatments. Identifying for whom treatment is effective will improve the success of our treatments and perhaps identify strategies for improving current approaches. METHODS:Two cohorts (training: N = 90, validation: N = 71) of cigarette smokers enrolled in group cognitive-behavioral therapy (CBT). Generalized estimating equations were used to identify baseline predictors of outcome, as defined by breath carbon monoxide and urine cotinine. Significant measures were entered as candidate variables to predict quit status. The resulting decision trees were used to predict cessation outcomes in a validation cohort. RESULTS:In the training cohort, the decision trees significantly improved on chance classification of smoking status following treatment and at 6-month follow-up. The first split of all decision trees, which was delay discounting, significantly improved on chance classification rates in both the training and validation cohort. Delay discounting emerged as the single best predictor of group CBT treatment response with an average baseline discount rate of ln(k) = -7.1, correctly predicting smoking status of 80% of participants at posttreatment and 81% of participants at follow-up. CONCLUSIONS:This study provides a first step toward personalized care for smoking cessation though future work is needed to identify individuals that are likely to be successful in treatments beyond group CBT. IMPLICATIONS:This study provides a first step toward personalized care for smoking cessation. Using a novel machine-learning approach, baseline measures of clinical and executive functioning are used to predict smoking cessation outcomes following group CBT. A decision point is recommended for the single best predictor of treatment outcomes, delay discounting, to inform future research or clinical practice in an effort to better allocate patients to treatments that are likely to work.
| S-EPMC7297111 | biostudies-literature
Project description:Objective: The brain age gap estimate (BrainAGE) is the difference between the estimated age and the individual chronological age. BrainAGE was studied primarily using MRI techniques. EEG signals in combination with machine learning (ML) approaches were not commonly used for the human age prediction, and BrainAGE. We investigated whether age-related changes are affecting brain EEG signals, and whether we can predict the chronological age and obtain BrainAGE estimates using a rigorous ML framework with a novel and extensive EEG features extraction. Methods: EEG data were obtained from 468 healthy, mood/anxiety, eating and substance use disorder participants (297 females) from the Tulsa-1000, a naturalistic longitudinal study based on Research Domain Criteria framework. Five sets of preprocessed EEG features across channels and frequency bands were used with different ML methods to predict age. Using a nested-cross-validation (NCV) approach and stack-ensemble learning from EEG features, the predicted age was estimated. The important features and their spatial distributions were deduced. Results: The stack-ensemble age prediction model achieved R2 = 0.37 (0.06), Mean Absolute Error (MAE) = 6.87(0.69) and RMSE = 8.46(0.59) in years. The age and predicted age correlation was r = 0.6. The feature importance revealed that age predictors are spread out across different feature types. The NCV approach produced a reliable age estimation, with features consistent behavior across different folds. Conclusion: Our rigorous ML framework and extensive EEG signal features allow a reliable estimation of chronological age, and BrainAGE. This general framework can be extended to test EEG association with and to predict/study other physiological relevant responses.
| S-EPMC6036180 | biostudies-literature