An in-depth analysis of machine learning approaches to predict depression

Zulfiker, Md. Sabab; Kabir, Nasrin; Biswas, Al Amin; Nazneen, Tahmina; Uddin, Mohammad Shorif

doi:10.1016/j.crbeha.2021.100044

Cited by 94 publications

(49 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Feature selection represents a step in the process in which a subset of variables (features) is selected to most accurately predict the targeted variable. Among the more popular approaches are the clustering (e.g., K-means or its variations), particle swarm optimization (PSO), RELIEFF, multivariate processing, and Boruta algorithm approaches [ 69 ]. The K-best approach is a K-nearest neighbor-based clustering feature selection technique.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Scoping Review on the Multimodal Classification of Depression and Experimental Study on Existing Multimodal Models

et al. 2022

View full text Add to dashboard Cite

Depression is a prevalent comorbidity in patients with severe physical disorders, such as cancer, stroke, and coronary diseases. Although it can significantly impact the course of the primary disease, the signs of depression are often underestimated and overlooked. The aim of this paper was to review algorithms for the automatic, uniform, and multimodal classification of signs of depression from human conversations and to evaluate their accuracy. For the scoping review, the PRISMA guidelines for scoping reviews were followed. In the scoping review, the search yielded 1095 papers, out of which 20 papers (8.26%) included more than two modalities, and 3 of those papers provided codes. Within the scope of this review, supported vector machine (SVM), random forest (RF), and long short-term memory network (LSTM; with gated and non-gated recurrent units) models, as well as different combinations of features, were identified as the most widely researched techniques. We tested the models using the DAIC-WOZ dataset (original training dataset) and using the SymptomMedia dataset to further assess their reliability and dependency on the nature of the training datasets. The best performance was obtained by the LSTM with gated recurrent units (F1-score of 0.64 for the DAIC-WOZ dataset). However, with a drop to an F1-score of 0.56 for the SymptomMedia dataset, the method also appears to be the most data-dependent.

show abstract

Section: Resultsmentioning

confidence: 99%

“…The K-best approach is a K-nearest neighbor-based clustering feature selection technique. It is non-parametric and univariate in nature [ 69 ]. It is used to select K-best features from the feature set using an univariate statistical test.…”

Section: Resultsmentioning

confidence: 99%

Scoping Review on the Multimodal Classification of Depression and Experimental Study on Existing Multimodal Models

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Feature/label selection : here we assessed the capabilities of two different approaches, namely “SelectKBest” [45, 46] and decision tree-based ensemble learning algorithms [47] to select a set of clinical labels from the pool of original clinical data. The SelectKBest algorithm uses statistical measures to score input features based on their relation to outputs and chooses the most effective features, accordingly.…”

Section: Methods and Computational Approachmentioning

confidence: 99%

“…In the current study, an optimal number of required components in the PCA was found by using various numbers of extracted features. The output datasets from PCA were then fed into seven conventional classifiers including, SVM [38], MLP [46], KNN [47], random forest [48], gradient boosting [49], Gaussian naïve bayes [50], and XGBoost [51] to assess which number of feature-sets could lead to an optimal performance. This was accordingly found to be associated with a set of 25 components.…”

Section: Dimension Reductionmentioning

confidence: 99%

Visual Transformer and Deep CNN Prediction of High-risk COVID-19 Infected Patients using Fusion of CT Images and Clinical Data

Abbasi

Tehrani

Zarvani³

et al. 2022

Preprint

View full text Add to dashboard Cite

Despite the globally reducing hospitalization rates and the much lower risks of Covid-19 mortality, accurate diagnosis of the infection stage and prediction of outcomes are clinically of interest. Advanced current technology can facilitate automating the process and help identifying those who are at higher risks of developing severe illness. Deep-learning schemes including Visual Transformer and Convolutional Neural Networks (CNNs), in particular, are shown to be powerful tools for predicting clinical outcomes when fed with either CT scan images or clinical data of patients. This paper demonstrates how a novel 3D data fusion approach through concatenating CT scan images with patients clinical data can remarkably improve the performance of Visual Transformer and CNN models in predicting Covid-19 infection outcomes. Here, we explore and represent comprehensive research on the efficiency of Video Swin Transformers and a number of CNN models fed with fusion datasets and CT scans only vs a set of conventional classifiers fed with patients clinical data only. A relatively large clinical dataset from 380 Covid-19 diagnosed patients was used to train/test the models. Results show that the 3D Video Swin Transformers fed with the fusion datasets of 64 sectional CT scans+67 (or 30 selected) clinical labels outperformed all other approaches for predicting outcomes in Covid-19-infected patients amongst all techniques (i.e., TPR=0.95, FPR=0.40, F0.5 score=0.82, AUC=0.77, Kappa=0.6). Results indicate possibilities of predicting the severity of outcome using patients CT images and clinical data collected at the time of admission to hospital.

show abstract

“…This is achieved through different feature selection procedures which are compared during model training to select a method which can produce the most optimal features. The feature selection methods which have been used in healthcare prediction [6], sequential feature selection [3], optimizer [7] and SelectKBest [8]. Expert judgement can also be used by experienced personnel to select features but the automated methods have proved to give better performance [4].…”

Section: Feature Selection and ML Algorithmsmentioning

confidence: 99%

Machine Learning Prediction Models for Postpartum Depression, a Review of Literature

Kimwomi¹,

Mgala²,

Mwakondo³

et al. 2022

IJCATR

View full text Add to dashboard Cite

Postpartum depression is a medical condition which continue to affect many mothers after delivery even though the disease can be prevented. It consequently exposes mothers and family members to illness and even death. Families, governments and other stakeholders incur heavy expenditure in the management of the disease. Research studies have been done to develop machine learning models for prediction of mothers at risk of postpartum depression during pregnancy for preventive measures. This paper presents a literature review of the machine learning prediction models which have been developed for the condition with specific focus on feature selection methods, algorithms used and the resulting performance. Literature review was done with google scholar integrated to an online institutional account for e-resources from e-databases accessed by subscription or free access. Inclusion involved all articles with the key words “machine learning, prediction model, postpartum depression” in the articles dated from 2018 to 2022 and sorted by relevance. A total of 3430 articles were listed while only 17 which were accessible with full text were eligible and therefore selected for the study. Analyzes were done using Microsoft Excel and descriptive analysis. Findings and conclusions will inform scientists on the status of research in the area to guide new studies, and inform the market on the potential benefits of integrating machine learning models in their systems.

show abstract

An in-depth analysis of machine learning approaches to predict depression

Cited by 94 publications

References 24 publications

Scoping Review on the Multimodal Classification of Depression and Experimental Study on Existing Multimodal Models

Scoping Review on the Multimodal Classification of Depression and Experimental Study on Existing Multimodal Models

Visual Transformer and Deep CNN Prediction of High-risk COVID-19 Infected Patients using Fusion of CT Images and Clinical Data

Machine Learning Prediction Models for Postpartum Depression, a Review of Literature

Contact Info

Product

Resources

About