Deep Learning for Depression Detection Using Twitter Data

Intelligent Automation & Soft Computing, Год журнала: 2023, Номер 36(2), С. 1301 - 1313

Опубликована: Янв. 1, 2023

Today social media became a communication line among people to share their happiness, sadness, and anger with end-users. It is necessary know people’s emotions are very important identify depressed from messages. Early depression detection helps save lives other dangerous mental diseases. There many intelligent algorithms for predicting high accuracy, but they lack the definition of such cases. Several machine learning methods help people. But accuracy existing was not satisfactory. To overcome this issue, deep method used in proposed detection. In paper, novel Deep Learning Multi-Aspect Depression Detection Hierarchical Attention Network (MDHAN) classifying data. Initially, Twitter data preprocessed by tokenization, punctuation mark removal, stop word stemming, lemmatization. The Adaptive Particle grey Wolf optimization feature selection. MDHAN classifies predicts non-depressed users. Finally, compared as Convolutional Neural (CNN), Support Vector Machine (SVM), Minimum Description Length (MDL), MDHAN. suggested MDH-PWO architecture gains 99.86% more significant than frequency-based models, lower false-positive rate. experimental result shows that achieves better precision, recall, F1-measure. also minimizes execution time.

Язык: Английский

---

Attention-Enabled Ensemble Deep Learning Models and Their Validation for Depression Detection: A Domain Adoption Paradigm

Diagnostics, Год журнала: 2023, Номер 13(12), С. 2092 - 2092

Опубликована: Июнь 16, 2023

Depression is increasingly prevalent, leading to higher suicide risk. detection and sentimental analysis of text inputs in cross-domain frameworks are challenging. Solo deep learning (SDL) ensemble (EDL) models not robust enough. Recently, attention mechanisms have been introduced SDL. We hypothesize that attention-enabled EDL (aeEDL) architectures superior compared attention-not-enabled SDL (aneSDL) or aeSDL models. designed EDL-based with blocks build eleven kinds model five on four domain-specific datasets. scientifically validated our by comparing "seen" "unseen" paradigms (SUP). benchmarked results against the SemEval (2016) dataset established reliability tests. The mean increase accuracy for over their corresponding components was 4.49%. Regarding effect block, (AUC) aneSDL 2.58% (1.73%), aeEDL aneEDL 2.76% (2.80%). When vs. non-attention attention, greater than 4.82% (3.71%), 5.06% (4.81%). For benchmarking (SemEval), best-performing (ALBERT+BERT-BiLSTM) best (BERT-BiLSTM) 3.86%. Our scientific validation design showed a difference only 2.7% SUP, thereby meeting regulatory constraints. all hypotheses further demonstrated very effective generalized method detecting symptoms depression settings.

Язык: Английский

---

A Comparative Study and Systematic Analysis of XAI Models and their Applications in Healthcare

Archives of Computational Methods in Engineering, Год журнала: 2024, Номер unknown

Опубликована: Апрель 16, 2024

Язык: Английский

---

Mental stress detection from ultra-short heart rate variability using explainable graph convolutional network with network pruning and quantisation

Machine Learning, Год журнала: 2024, Номер 113(8), С. 5467 - 5494

Опубликована: Янв. 22, 2024

Язык: Английский

---

XAI-Based Clinical Decision Support Systems: A Systematic Review

Applied Sciences, Год журнала: 2024, Номер 14(15), С. 6638 - 6638

Опубликована: Июль 30, 2024

With increasing electronic medical data and the development of artificial intelligence, clinical decision support systems (CDSSs) assist clinicians in diagnosis prescription. Traditional knowledge-based CDSSs follow an accumulated knowledgebase a predefined rule system, which clarifies decision-making process; however, maintenance cost issues exist quality control standardization processes. Non-knowledge-based utilize vast amounts algorithms to effectively make decisions; deep learning black-box problem causes unreliable results. EXplainable Artificial Intelligence (XAI)-based provide valid rationales explainable These ensure trustworthiness transparency by showing recommendation prediction result process using techniques. However, existing have limitations, such as scope utilization lack explanatory power AI models. This study proposes new XAI-based CDSS framework address these issues; introduces resources, datasets, models that can be utilized; provides foundation model various disease domains. Finally, we propose future directions for technology highlight societal need addressed emphasize potential future.

Язык: Английский

---

Advances in Machine Learning and Explainable Artificial Intelligence for Depression Prediction

International Journal of Advanced Computer Science and Applications, Год журнала: 2023, Номер 14(6)

Опубликована: Янв. 1, 2023

There is a growing interest in applying AI technology the field of mental health, particularly as an alternative to complement limitations human analysis, judgment, and accessibility health assessments treatments. The current treatment service faces gap which individuals who need help are not receiving it due negative perceptions treatment, lack professional manpower, physical limitations. To overcome these difficulties, there for new approach, being explored potential solution. Explainable artificial intelligence (X-AI) with both accuracy interpretability can improve expert decision-making, increase services, solve psychological problems high-risk groups depression. In this review, we examine use X-AI As result reviewing 6 studies that used discriminate depression, various algorithms such SHAP (SHapley Additive exPlanations) Local Interpretable Model-Agnostic Explanation (LIME) were predicting psychiatry, crucial ensure prediction justifications clear transparent. Therefore, ensuring models will be important future research.

Язык: Английский

---

A BERT-encoded ensembled CNN model for suicide risk identification in social media posts

Neural Computing and Applications, Год журнала: 2024, Номер 36(18), С. 10955 - 10970

Опубликована: Март 28, 2024

Язык: Английский

---

Integrating metaheuristics and artificial intelligence for healthcare: basics, challenging and future directions

Artificial Intelligence Review, Год журнала: 2024, Номер 57(8)

Опубликована: Июль 12, 2024

Abstract Accurate and rapid disease detection is necessary to manage health problems early. Rapid increases in data amount dimensionality caused challenges many disciplines, with the primary issues being high computing costs, memory low accuracy performance. These will arise since Machine Learning (ML) classifiers are mostly used these fields. However, noisy irrelevant features have an impact on ML accuracy. Therefore, choose best subset of decrease data, Metaheuristics (MHs) optimization algorithms applied Feature Selection (FS) using various modalities medical imaging or datasets different dimensions. The review starts by giving a general overview approaches AI algorithms, followed MH for healthcare applications, analysis MHs boosted wide range research databases as source access numerous field publications. final section this discusses facing application development.

Язык: Английский

---

Federated Learning of XAI Models in Healthcare: A Case Study on Parkinson’s Disease

Cognitive Computation, Год журнала: 2024, Номер 16(6), С. 3051 - 3076

Опубликована: Авг. 28, 2024

Abstract Artificial intelligence (AI) systems are increasingly used in healthcare applications, although some challenges have not been completely overcome to make them fully trustworthy and compliant with modern regulations societal needs. First of all, sensitive health data, essential train AI systems, typically stored managed several separate medical centers cannot be shared due privacy constraints, thus hindering the use all available information learning models. Further, transparency explainability such becoming urgent, especially at a time when “opaque” or “black-box” models commonly used. Recently, technological algorithmic solutions these investigated: on one hand, federated (FL) has proposed as paradigm for collaborative model training among multiple parties without any disclosure private raw data; other research eXplainable (XAI) aims enhance either through interpretable by-design approaches post-hoc explanation techniques. In this paper, we focus case study, namely predicting progression Parkinson’s disease, assume that data originate from different collection centralized is precluded limitations. We aim investigate how FL XAI can allow achieving good level accuracy trustworthiness. Cognitive biologically inspired adopted our analysis: an fuzzy rule-based system neural network explained using version SHAP technique. analyze accuracy, interpretability, two approaches, also varying degree heterogeneity across distribution scenarios. Although generally more accurate, results show achieves competitive performance setting presents desirable properties terms interpretability transparency.

Язык: Английский

---

Enhancing explainability in predicting mental health disorders using human–machine interaction

Multimedia Tools and Applications, Год журнала: 2024, Номер unknown

Опубликована: Фев. 23, 2024

Язык: Английский

---