Dataset Information

Machine learning approaches for integrating clinical and imaging features in late-life depression classification and response prediction.

ABSTRACT: Currently, depression diagnosis relies primarily on behavioral symptoms and signs, and treatment is guided by trial and error instead of evaluating associated underlying brain characteristics. Unlike past studies, we attempted to estimate accurate prediction models for late-life depression diagnosis and treatment response using multiple machine learning methods with inputs of multi-modal imaging and non-imaging whole brain and network-based features.Late-life depression patients (medicated post-recruitment) (n?=?33) and older non-depressed individuals (n?=?35) were recruited. Their demographics and cognitive ability scores were recorded, and brain characteristics were acquired using multi-modal magnetic resonance imaging pretreatment. Linear and nonlinear learning methods were tested for estimating accurate prediction models.A learning method called alternating decision trees estimated the most accurate prediction models for late-life depression diagnosis (87.27% accuracy) and treatment response (89.47% accuracy). The diagnosis model included measures of age, Mini-mental state examination score, and structural imaging (e.g. whole brain atrophy and global white mater hyperintensity burden). The treatment response model included measures of structural and functional connectivity.Combinations of multi-modal imaging and/or non-imaging measures may help better predict late-life depression diagnosis and treatment response. As a preliminary observation, we speculate that the results may also suggest that different underlying brain characteristics defined by multi-modal imaging measures-rather than region-based differences-are associated with depression versus depression recovery because to our knowledge this is the first depression study to accurately predict both using the same approach. These findings may help better understand late-life depression and identify preliminary steps toward personalized late-life depression treatment.

SUBMITTER: Patel MJ

PROVIDER: S-EPMC4683603 | biostudies-literature | 2015 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning approaches for integrating clinical and imaging features in late-life depression classification and response prediction.

Patel Meenal J MJ Andreescu Carmen C Price Julie C JC Edelman Kathryn L KL Reynolds Charles F CF Aizenstein Howard J HJ

International journal of geriatric psychiatry 20150217 10

<h4>Objective</h4>Currently, depression diagnosis relies primarily on behavioral symptoms and signs, and treatment is guided by trial and error instead of evaluating associated underlying brain characteristics. Unlike past studies, we attempted to estimate accurate prediction models for late-life depression diagnosis and treatment response using multiple machine learning methods with inputs of multi-modal imaging and non-imaging whole brain and network-based features.<h4>Methods</h4>Late-life de ...[more]

PMID: 25689482

Similar Datasets

Project description:Background: Recent evidence suggests that integration of multi-modal data improves performance in machine learning prediction of depression treatment outcomes. Here, we compared the predictive performance of three machine learning classifiers using differing combinations of sociodemographic characteristics, baseline clinical self-reports, cognitive tests, and structural magnetic resonance imaging (MRI) features to predict treatment outcomes in late-life depression (LLD). Methods: Data were combined from two clinical trials conducted with depressed adults aged 60 and older, including response to escitalopram (N = 32, NCT01902004) and Tai Chi (N = 35, NCT02460666). Remission was defined as a score of 6 or less on the 24-item Hamilton Rating Scale for Depression (HAMD) at the end of 24 weeks of treatment. Features subsets were constructed from baseline sociodemographic and clinical features, gray matter volumes (GMVs), or both. Three classification algorithms were compared: (1) Support Vector Machine-Radial Bias Function (SVMRBF), (2) Random Forest (RF), and (3) Logistic Regression (LR). A repeated 5-fold cross-validation approach with a wrapper-based feature selection method was used for model fitting. Model performance metrics included Area under the ROC Curve (AUC) and Matthews correlation coefficient (MCC). Cross-validated performance significance was tested by permutation analysis. Classifiers were compared by Cochran's Q and post-hoc pairwise comparisons using McNemar's Chi-Square test with Bonferroni correction. Results: For the RF and SVMRBF algorithms, the combined feature set outperformed the clinical and GMV feature sets with a final cross-validated AUC of 0.83 ± 0.11 and 0.80 ± 0.11, respectively. Both classifiers passed permutation analysis. The LR algorithm performed best using GMV features alone (AUC 0.79 ± 0.14) but failed to pass permutation analysis using any feature set. Performance of the three classifiers differed significantly for all three features sets. Important predictive features of treatment response included anterior and posterior cingulate volumes, depression characteristics, and self-reported health-related quality scores. Conclusion: This preliminary exploration into the use of ML and multi-modal data to identify predictors of general treatment response in LLD indicates that integration of clinical and structural MRI features significantly increases predictive capability. Identified features are among those previously implicated in geriatric depression, encouraging future work in this arena.

Project description:Objective: Late-life depression (LLD) is associated with development of different types of dementia. Identification of LLD patients, who will develop cognitive decline, i.e., the early stage of dementia would help to implement interventions earlier. The purpose of this study was to assess whether structural brain magnetic resonance imaging (MRI) in LLD patients can predict mild cognitive impairment (MCI) or dementia 1 year prior to the diagnosis. Methods: LLD patients underwent brain MRI at baseline and repeated clinical assessment after 1-year. Structural brain measurements were obtained using Freesurfer software (v. 5.1) from the T1W brain MRI images. MRI-based Random Forest classifier was used to discriminate between LLD who developed MCI or dementia after 1-year follow-up and cognitively stable LLD. Additionally, a previously established Random Forest model trained on 185 patients with Alzheimer's disease (AD) vs. 225 cognitively normal elderly from the Alzheimer's disease Neuroimaging Initiative was tested on the LLD data set (ADNI model). Results: MCI and dementia diagnoses were predicted in LLD patients with 76%/68%/84% accuracy/sensitivity/specificity. Adding the baseline Mini-Mental State Examination (MMSE) scores to the models improved accuracy/sensitivity/specificity to 81%/75%/86%. The best model predicted MCI status alone using MRI and baseline MMSE scores with accuracy/sensitivity/specificity of 89%/85%/90%. The most important region for all the models was right ventral diencephalon, including hypothalamus. Its volume correlated negatively with the number of depressive episodes. ADNI model trained on AD vs. Controls using SV could predict MCI-DEM patients with 67% accuracy. Conclusion: LDD patients developing MCI and dementia can be discriminated from LLD patients remaining cognitively stable with good accuracy based on baseline structural MRI alone. Baseline MMSE score improves prediction accuracy. Ventral diencephalon, including the hypothalamus might play an important role in preservation of cognitive functions in LLD.

Dataset Information

Machine learning approaches for integrating clinical and imaging features in late-life depression classification and response prediction.

Publications

Machine learning approaches for integrating clinical and imaging features in late-life depression classification and response prediction.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets