Identifying neuroanatomical signatures of anorexia nervosa: a multivariate machine learning approach

2015 ◽  
Vol 45 (13) ◽  
pp. 2805-2812 ◽  
Author(s):  
L. Lavagnino ◽  
F. Amianto ◽  
B. Mwangi ◽  
F. D'Agata ◽  
A. Spalatro ◽  
...  
Keyword(s):  
Machine Learning ◽  
Anorexia Nervosa ◽  
Predictive Accuracy ◽  
Third Ventricle ◽  
Healthy Controls ◽  
Drive For Thinness ◽  
Individual Subject ◽  
Machine Learning Approach ◽  
Scan Data ◽  
Selection Operator

BackgroundThere are currently no neuroanatomical biomarkers of anorexia nervosa (AN) available to make clinical inferences at an individual subject level. We present results of a multivariate machine learning (ML) approach utilizing structural neuroanatomical scan data to differentiate AN patients from matched healthy controls at an individual subject level.MethodStructural neuroimaging scans were acquired from 15 female patients with AN (age = 20, s.d. = 4 years) and 15 demographically matched female controls (age = 22, s.d. = 3 years). Neuroanatomical volumes were extracted using the FreeSurfer software and input into the Least Absolute Shrinkage and Selection Operator (LASSO) multivariate ML algorithm. LASSO was ‘trained’ to identify ‘novel’ individual subjects as either AN patients or healthy controls. Furthermore, the model estimated the probability that an individual subject belonged to the AN group based on an individual scan.ResultsThe model correctly predicted 25 out of 30 subjects, translating into 83.3% accuracy (sensitivity 86.7%, specificity 80.0%) (p < 0.001; χ2 test). Six neuroanatomical regions (cerebellum white matter, choroid plexus, putamen, accumbens, the diencephalon and the third ventricle) were found to be relevant in distinguishing individual AN patients from healthy controls. The predicted probabilities showed a linear relationship with drive for thinness clinical scores (r = 0.52, p < 0.005) and with body mass index (BMI) (r = −0.45, p = 0.01).ConclusionsThe model achieved a good predictive accuracy and drive for thinness showed a strong neuroanatomical signature. These results indicate that neuroimaging scans coupled with ML techniques have the potential to provide information at an individual subject level that might be relevant to clinical outcomes.

scholarly journals Overcoming limitations of self-report: an assessment of fear of weight gain in anorexia nervosa and healthy controls using implicit association tests

2021 ◽  
Vol 9 (1) ◽  
Author(s):  
Tiana Borgers ◽  
Nathalie Krüger ◽  
Silja Vocks ◽  
Jennifer J. Thomas ◽  
Franziska Plessow ◽  
...  
Keyword(s):  
Anorexia Nervosa ◽  
Weight Gain ◽  
Normal Weight ◽  
Self Report ◽  
Healthy Controls ◽  
Drive For Thinness ◽  
Implicit Association ◽  
Association Tests ◽  
Implicit Assessment ◽  
Fear Of Weight Gain

Abstract Background Fear of weight gain is a characteristic feature of anorexia nervosa (AN), and reducing this fear is often a main target of treatment. However, research shows that 20% of individuals with AN do not report fear of weight gain. Studies are needed that evaluate the centrality of fear of weight gain for AN with a method less susceptible to deception than self-report. Methods We approximated implicit fear of weight gain by measuring implicit drive for thinness using implicit association tests (IATs). We asked 64 participants (35 AN, 29 healthy controls [HCs]) to categorize statements as pro-dieting vs. non-dieting and true vs. false in a questionnaire-based IAT, and pictures of underweight vs. normal-weight models and positive vs. negative words in a picture-based IAT using two response keys. We tested for associations between implicit drive for thinness and explicitly reported psychopathology within AN as well as group differences between AN and HC groups. Results Correlation analyses within the AN group showed that higher implicit drive for thinness was associated with more pronounced eating disorder-specific psychopathology. Furthermore, the AN group showed a stronger implicit drive for thinness than HCs in both IATs. Conclusion The results highlight the relevance of considering fear of weight gain as a continuous construct. Our implicit assessment captures various degrees of fear of weight gain in AN, which might allow for more individually tailored interventions in the future.

scholarly journals A machine learning approach for gait speed estimation using skin-mounted wearable sensors: From healthy controls to individuals with multiple sclerosis

PLoS ONE ◽  
2017 ◽  
Vol 12 (6) ◽  
pp. e0178366 ◽  
Author(s):  
Ryan S. McGinnis ◽  
Nikhil Mahadevan ◽  
Yaejin Moon ◽  
Kirsten Seagers ◽  
Nirav Sheth ◽  
...  
Keyword(s):  
Machine Learning ◽  
Multiple Sclerosis ◽  
Gait Speed ◽  
Wearable Sensors ◽  
Learning Approach ◽  
Speed Estimation ◽  
Healthy Controls ◽  
Machine Learning Approach

Comparative analysis of a deep learning approach with various classification techniques for credit score computation

2020 ◽  
Vol 13 ◽  
Author(s):  
Arvind Pandey ◽  
Shipra Shukla ◽  
Krishna Kumar Mohbey
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Comparative Analysis ◽  
Predictive Accuracy ◽  
Credit Scoring ◽  
Gradient Boosting ◽  
Learning Approach ◽  
Probit Regression ◽  
Credit Score ◽  
Machine Learning Approach

Background: Large financial companies are perpetually creating and updating customer scoring techniques. From a risk management view, this research for the predictive accuracy of probability is of vital importance than the traditional binary result of classification, i.e., non-credible and credible customers. The customer's default payment in Taiwan is explored for the case study. Objective: The aim is to audit the comparison between the predictive accuracy of the probability of default with various techniques of statistics and machine learning. Method: In this paper, nine predictive models are compared from which the results of the six models are taken into consideration. Deep learning-based H2O, XGBoost, logistic regression, gradient boosting, naïve Bayes, logit model, and probit regression comparative analysis is performed. The software tools such as R and SAS (university edition) is employed for machine learning and statistical model evaluation. Results: Through the experimental study, we demonstrate that XGBoost performs better than other AI and ML algorithms. Conclusion: Machine learning approach such as XGBoost effectively used for credit scoring, among other data mining and statistical approaches.

scholarly journals Integration of Machine Learning and Computational Fluid Dynamics to Develop Turbulence Models for Improved Turbine Wake Mixing Prediction

2020 ◽  
Author(s):  
Harshal D. Akolekar ◽  
Yaomin Zhao ◽  
Richard D. Sandberg ◽  
Roberto Pacciani
Keyword(s):  
Machine Learning ◽  
Predictive Accuracy ◽  
Model Development ◽  
Learning Approach ◽  
Near Wake ◽  
Machine Learning Approach ◽  
Non Linear ◽  
Turbulence Closures ◽  
Unsteady Rans ◽  
Turbine Wake

Abstract This paper presents development of accurate turbulence closures for wake mixing prediction by integrating a machine-learning approach with Reynolds Averaged Navier-Stokes (RANS)-based computational fluid dynamics (CFD). The data-driven modeling framework is based on the gene expression programming (GEP) approach previously shown to generate non-linear RANS models with good accuracy. To further improve the performance and robustness of the data-driven closures, here we exploit that GEP produces tangible models to integrate RANS in the closure development process. Specifically, rather than using as cost function a comparison of the GEP-based closure terms with a frozen high-fidelity dataset, each GEP model is instead automatically implemented into a RANS solver and the subsequent calculation results compared with reference data. By first using a canonical turbine wake with inlet conditions prescribed based on high-fidelity data, we demonstrate that the CFD-driven machine-learning approach produces non-linear turbulence closures that are physically correct, i.e. predict the right downstream wake development and maintain an accurate peak wake loss throughout the domain. We then extend our analysis to full turbine-blade cases and show that the model development is sensitive to the training region due to the presence of deterministic unsteadiness in the near wake region. Models developed including this region have artificially large diffusion coefficients to over-compensate for the vortex shedding steady RANS cannot capture. In contrast, excluding the near wake region in the model development produces the correct physical model behavior, but predictive accuracy in the near-wake remains unsatisfactory. We show that this can be remedied by using the physically consistent models in unsteady RANS, implying that the non-linear closure producing the best predictive accuracy depends on whether it will be deployed in RANS or unsteady RANS calculations. Overall, the models developed with the CFD-assisted machine learning approach were found to be robust and capture the correct physical behavior across different operating conditions.

scholarly journals A Multimodality Machine Learning Approach to Differentiate Severe and Nonsevere COVID-19: Model Development and Validation

10.2196/23948 ◽  
2021 ◽  
Vol 23 (4) ◽  
pp. e23948
Author(s):  
Yuanfang Chen ◽  
Liu Ouyang ◽  
Forrest S Bao ◽  
Qian Li ◽  
Lei Han ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Laboratory Test ◽  
Predictive Accuracy ◽  
Learning Approach ◽  
Test Results ◽  
Laboratory Test Results ◽  
Machine Learning Approach ◽  
Forest Models ◽  
Random Forest Models

Background Effectively and efficiently diagnosing patients who have COVID-19 with the accurate clinical type of the disease is essential to achieve optimal outcomes for the patients as well as to reduce the risk of overloading the health care system. Currently, severe and nonsevere COVID-19 types are differentiated by only a few features, which do not comprehensively characterize the complicated pathological, physiological, and immunological responses to SARS-CoV-2 infection in the different disease types. In addition, these type-defining features may not be readily testable at the time of diagnosis. Objective In this study, we aimed to use a machine learning approach to understand COVID-19 more comprehensively, accurately differentiate severe and nonsevere COVID-19 clinical types based on multiple medical features, and provide reliable predictions of the clinical type of the disease. Methods For this study, we recruited 214 confirmed patients with nonsevere COVID-19 and 148 patients with severe COVID-19. The clinical characteristics (26 features) and laboratory test results (26 features) upon admission were acquired as two input modalities. Exploratory analyses demonstrated that these features differed substantially between two clinical types. Machine learning random forest models based on all the features in each modality as well as on the top 5 features in each modality combined were developed and validated to differentiate COVID-19 clinical types. Results Using clinical and laboratory results independently as input, the random forest models achieved >90% and >95% predictive accuracy, respectively. The importance scores of the input features were further evaluated, and the top 5 features from each modality were identified (age, hypertension, cardiovascular disease, gender, and diabetes for the clinical features modality, and dimerized plasmin fragment D, high sensitivity troponin I, absolute neutrophil count, interleukin 6, and lactate dehydrogenase for the laboratory testing modality, in descending order). Using these top 10 multimodal features as the only input instead of all 52 features combined, the random forest model was able to achieve 97% predictive accuracy. Conclusions Our findings shed light on how the human body reacts to SARS-CoV-2 infection as a unit and provide insights on effectively evaluating the disease severity of patients with COVID-19 based on more common medical features when gold standard features are not available. We suggest that clinical information can be used as an initial screening tool for self-evaluation and triage, while laboratory test results should be applied when accuracy is the priority.

scholarly journals Multimodal assessment of communicative-pragmatic features in schizophrenia: a machine learning approach

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Alberto Parola ◽  
Ilaria Gabbatore ◽  
Laura Berardinelli ◽  
Rogerio Salvini ◽  
Francesca M. Bosco
Keyword(s):  
Machine Learning ◽  
Decision Tree ◽  
Decision Tree Model ◽  
Learning Approach ◽  
Healthy Controls ◽  
Tree Model ◽  
Communicative Acts ◽  
Multimodal Assessment ◽  
Machine Learning Approach ◽  
Tone Of Voice

AbstractAn impairment in pragmatic communication is a core feature of schizophrenia, often associated with difficulties in social interactions. The pragmatic deficits regard various pragmatic phenomena, e.g., direct and indirect communicative acts, deceit, irony, and include not only the use of language but also other expressive means such as non-verbal/extralinguistic modalities, e.g., gestures and body movements, and paralinguistic cues, e.g., prosody and tone of voice. The present paper focuses on the identification of those pragmatic features, i.e., communicative phenomena and expressive modalities, that more reliably discriminate between individuals with schizophrenia and healthy controls. We performed a multimodal assessment of communicative-pragmatic ability, and applied a machine learning approach, specifically a Decision Tree model, with the aim of identifying the pragmatic features that best separate the data into the two groups, i.e., individuals with schizophrenia and healthy controls, and represent their configuration. The results indicated good overall performance of the Decision Tree model, with mean Accuracy of 82%, Sensitivity of 76%, and Precision of 91%. Linguistic irony emerged as the most relevant pragmatic phenomenon in distinguishing between the two groups, followed by violation of the Gricean maxims, and then extralinguistic deceitful and sincere communicative acts. The results are discussed in light of the pragmatic theoretical literature, and their clinical relevance in terms of content and design of both assessment and rehabilitative training.

scholarly journals A mixed-methods approach to conceptualizing friendships in anorexia nervosa

PLoS ONE ◽  
2021 ◽  
Vol 16 (9) ◽  
pp. e0254110
Author(s):  
Nandini Datta ◽  
Molly Foukal ◽  
Savannah Erwin ◽  
Hannah Hopkins ◽  
Kate Tchanturia ◽  
...  
Keyword(s):  
Anorexia Nervosa ◽  
Mixed Methods ◽  
Attachment Styles ◽  
Negative Evaluation ◽  
Self Report ◽  
Healthy Controls ◽  
Care Seeking ◽  
Drive For Thinness ◽  
Attachment Figure ◽  
Mixed Methods Approach

Background Individuals with anorexia nervosa have reported feelings of loneliness, social anhedonia, and interpersonal difficulties. This study sought to clarify the nature of interpersonal relationships in adults with anorexia, which may help improve existing interventions while also facilitating the attainment of something that might compete with the drive for thinness: friendships. Methods The present study used a mixed-methods approach to investigate friendship experiences in three groups: anorexia (n = 27), participants with a history of anorexia who are weight restored (n = 20), and healthy controls (n = 24). Thematic analysis was used to isolate the most prevalent themes that emerged from an open-ended interview of experiencing friendships in a subset of participants. Three self-report questionnaires investigating friendship valuation and attachment styles were also administered. Results 11 unique themes emerged in the data: social comparison, reciprocity, trust, fear of negative evaluation, perceived skills deficit, logistical barriers, reliability, identity issue, low interest, similarity, and conflict avoidance. Only 17% of those with anorexia reported experiencing friendships as positive, relative to 82% of healthy controls and 52% of weight restored participants. Lastly, on self-report measures, participants with anorexia reported greater reliance on themselves versus others, greater use of care-seeking behaviors, and more fear/anger at the thought of losing an attachment figure (p < .05 in all cases). Conclusion Results suggest that individuals with anorexia have particular challenges which interfere with the formation and maintenance of friendships, such as viewing friendships negatively and struggling with social comparisons in friendships. Assessing and addressing barriers to intimacy may motivate those with anorexia to relinquish dangerous symptoms that maintain the illness.

scholarly journals Alterations of white matter abnormalities in Parkinson’s disease: a machine learning approach

2021 ◽  
Author(s):  
long qian ◽  
chaoyong xiao ◽  
Sidong Liu ◽  
zaixu cui ◽  
xiao hu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
White Matter ◽  
Rating Scale ◽  
Mean Diffusivity ◽  
Learning Approach ◽  
Healthy Controls ◽  
White Matter Tracts ◽  
Machine Learning Approach

Abstract The inter-tract/region dependencies of white-matter in Parkinson’s disease are usually ignored by standard statistical tests. Moreover, it remains unclear whether the disruption of white-matter tracts/regions suffices to identify Parkinson’s disease patients from healthy controls. A machine learning approach was applied to capture the interdependencies between white-matter tracts/regions and to differentiate PD patients from healthy controls. First, the mean regional white-matter profiles, including white-matter volume, fractional anisotropy, mean diffusivity, axial diffusivity, and radial diffusivity, were extracted as features in Parkinson’s disease patients (N = 78) and in healthy controls (N = 91). Then, the feature selection and classification were performed using t-test and linear support vector machine, respectively. Last, the relationships between clinical variables and regional magnetic resonance indices were estimated. Our results showed the combined features (white-matter volume, fractional anisotropy, mean diffusivity, axial diffusivity, and radial diffusivity) had the best performance with an accuracy of 75.15% and area under curve of 0.8171, respectively. The most discriminative white-matter features were centered on the association fibers, commissural fibers, projection fibers, and striatal fibers. The discriminative regions of right anterior limb of internal capsule had positive association trends with the Unified Parkinson Disease Rating Scale III score; while the genu of corpus callosum and right retrolenticular part of internal capsule had positively association trends with the Hamilton Depression Rating Scale score. Our finding showed the multivariate machine learning approach is a promising tool to detect abnormal white-matter tracts/regions in Parkinson’s disease, and provides us a multidimensional means for neuroimaging classification.

scholarly journals Utility of Machine Learning Approach with Neuropsychological Tests in Predicting Functional Impairment of Alzheimer’s Disease

2021 ◽  
pp. 1-16
Author(s):  
Seyul Kwak ◽  
Dae Jong Oh ◽  
Yeong-Ju Jeon ◽  
Da Young Oh ◽  
Su Mi Park ◽  
...  
Keyword(s):  
Machine Learning ◽  
Functional Impairment ◽  
Linear Models ◽  
Predictive Accuracy ◽  
Nonlinear Models ◽  
Learning Approach ◽  
High Complexity ◽  
Neuropsychological Battery ◽  
Machine Learning Approach ◽  
Summary Index

Background: In assessing the levels of clinical impairment in dementia, a summary index of neuropsychological batteries has been widely used in describing the overall functional status. Objective: It remains unexamined how complex patterns of the test performances can be utilized to have specific predictive meaning when the machine learning approach is applied. Methods: In this study, the neuropsychological battery (CERAD-K) and assessment of functioning level (Clinical Dementia Rating scale and Instrumental Activities of Daily Living) were administered to 2,642 older adults with no impairment (n = 285), mild cognitive impairment (n = 1,057), and Alzheimer’s disease (n = 1,300). Predictive accuracy on functional impairment level with the linear models of the single total score or multiple subtest scores (Model 1, 2) and support vector regression with low or high complexity (Model 3, 4) were compared across different sample sizes. Results: The linear models (Model 1, 2) showed superior performance with relatively smaller sample size, while nonlinear models with low and high complexity (Model 3, 4) showed an improved accuracy with a larger dataset. Unlike linear models, the nonlinear models showed a gradual increase in the predictive accuracy with a larger sample size (n >  500), especially when the model training is allowed to exploit complex patterns of the dataset. Conclusion: Our finding suggests that nonlinear models can predict levels of functional impairment with a sufficient dataset. The summary index of the neuropsychological battery can be augmented for specific purposes, especially in estimating the functional status of dementia.

Sign in / Sign up

Export Citation Format

Share Document