A clinical support system for classification and prediction of depression using machine learning methods

Benfares, Chaymae; Akhrif, Ouidad; Idrissi, Younès El Bouzekri El; Hamid, Karim

doi:10.1111/coin.12377

Cited by 5 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A study has developed a clinical decision support system that assists clinicians and mental health practitioners in classifying and characterizing patients with depression intelligently, by analysing patient data based on their represented symptoms. In order to make relevant decisions, classification models based on online health information resources from within an electronic medical record system are used [ 37 ]. Therefore, the algorithm developed and presented here may potentially be useful as a fall risk prediction tool where the clinician is just required to enter the necessary parameters and the algorithm will automatically assign the older adult to a cluster.…”

Section: Discussionmentioning

confidence: 99%

Development of an effective clustering algorithm for older fallers

et al. 2022

View full text Add to dashboard Cite

Falls are common and often lead to serious physical and psychological consequences for older persons. The occurrence of falls are usually attributed to the interaction between multiple risk factors. The clinical evaluation of falls risks is time-consuming as a result, hence limiting its availability. The purpose of this study was, therefore, to develop a clustering-based algorithm to determine falls risk. Data from the Malaysian Elders Longitudinal Research (MELoR), comprising 1411 subjects aged ≥55 years, were utilized. The proposed algorithm was developed through the stages of: data pre-processing, feature identification and extraction with either t-Distributed Stochastic Neighbour Embedding (t-SNE) or principal component analysis (PCA)), clustering (K-means clustering, Hierarchical clustering, and Fuzzy C-means clustering) and characteristics interpretation with statistical analysis. A total of 1279 subjects and 9 variables were selected for clustering after the data pre-possessing stage. Using feature extraction with the t-SNE and the K-means clustering algorithm, subjects were clustered into low, intermediate A, intermediate B and high fall risk groups which corresponded with fall occurrence of 13%, 19%, 21% and 31% respectively. Slower gait, poorer balance, weaker muscle strength, presence of cardiovascular disorder, poorer cognitive performance, and advancing age were the key variables identified. The proposed fall risk clustering algorithm grouped the subjects according to features. Such a tool could serve as a case identification or clinical decision support tool for clinical practice to enhance access to falls prevention efforts.

show abstract

Section: Discussionmentioning

confidence: 99%

Development of an effective clustering algorithm for older fallers

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In psychometrics as in medicine, the application of the ROC curve is widely used in the comparison of diagnostic performance between instruments and allows to study the variation of sensitivity and specificity for different cutoff values in the dimensional diagnostic approach (TRIPEPI et al, 2009;KRZANOWSKI;HAND, 2009;QI et al, 2018;ZHU;ZENG;WANG, 2010;BENFARES et al, 2021).…”

Section: Roc Curve and Area Under Curve (Auc)mentioning

confidence: 99%

Random Forest multiclasse: a diagnostic study of mathematical learning difficulties

Augusto

View full text Add to dashboard Cite

This work is dedicated to all mothers, heroines in their homes, fighters for their families and their children. To the mothers who multiply themselves in daily activities, who build inexplicable relationships of affection, which are the basis of their home, but who never stop dreaming, believing that they are capable of, in addition to the glory of motherhood, still realizing personal dreams and desires to collaborate. I do thank my family, specially my husband Renato and my kids Rebecca and Giovani, for the support and for understanding the absent hours. My thanks for my mother Neusa that ever inspired me with her strength for living. I also thank to MSc. Giulia Paiva, from UFMG, for sharing her experience, work and knowledge without what this work could not be done. A special thank for Professor Dr.José Augusto Baranauskas, for all orientation and corrections that improved my work and comprehension. I would also like to thank Professor Dr.Vitor Geraldi Haase, from UFMG, for leading me to Giulia, becoming possible the partnership for this work, and therefore for all background transferred by publications I have read. Futhermore, I would like to thank Professor Dr. Galera from Psicobiology Departament -USP, who was responsible to connect me to UFMG colleagues. I kindly thank for docent group from DCM -USP who taught and lead me to new concepts and a whole new world of opportunities. I also thanks for all staff support.

show abstract

Unravelling the complexities of depression with medical intelligence: exploring the interplay of genetics, hormones, and brain function

Heyat,

Akhtar,

Munir

et al. 2024

Complex Intell. Syst.

View full text Add to dashboard Cite

Depression is a multifactorial disease with unknown etiology affecting globally. It’s the second most significant reason for infirmity in 2020, affecting about 50 million people worldwide, with 80% living in developing nations. Recently, a surge in depression research has been witnessed, resulting in a multitude of emerging techniques developed for prediction, evaluation, detection, classification, localization, and treatment. The main purpose of this study is to determine the volume of depression research conducted on different aspects such as genetics, proteins, hormones, oxidative stress, inflammation, mitochondrial dysfunction, and associations with other mental disorders like anxiety and stress using traditional and medical intelligence (medical with AI). In addition, it also designs a comprehensive survey on detection, treatment planning, and genetic predisposition, along with future recommendations. This work is designed through different methods, including a systematic mapping process, literature review, and network visualization. In addition, we also used VOSviewer software and some authentic databases such as Google Scholar, Scopus, PubMed, and Web of Science for data collection, analysis, and designing comprehensive picture of the study. We analyzed 60 articles related to medical intelligence, including 47 from machine learning with 513,767 subjects (mean ± SD = 10,931.212 ± 35,624.372) and 13 from deep learning with 37,917 subjects (mean ± SD = 3159.75 ± 6285.57). Additionally, we also found that stressors impact the brain's cognitive and autonomic functioning, resulting in increased production of catecholamine, decreased cholinergic and glucocorticoid activity, with increased cortisol. These factors lead to chronic inflammation and hinder the brain's normal functioning, leading to depression, anxiety, and cardiovascular disorders. In the brain, reactive oxygen species (ROS) production is increased by IL-6 stimulation and mitochondrial cytochrome c oxidase is inhibited by nitric oxide, a potent inhibitor. Proteins, lipids, oxidative phosphorylation enzymes, and mtDNA are further disposed to oxidative impairment in the mitochondria. Consequently, mitochondrial dysfunction exacerbates oxidative stress, impairs mitochondrial DNA (mtDNA) or deletions of mtDNA, increases intracellular Ca2+ levels, changes in fission/fusion and mitochondrial morphology, and lastly leads to neuronal death. This study highlights the multidisciplinary approaches to depression with different aspects using traditional and medical intelligence. It will open a new way for depression research through new emerging technologies.

show abstract

A clinical support system for classification and prediction of depression using machine learning methods

Cited by 5 publications

References 17 publications

Development of an effective clustering algorithm for older fallers

Development of an effective clustering algorithm for older fallers

Random Forest multiclasse: a diagnostic study of mathematical learning difficulties

Unravelling the complexities of depression with medical intelligence: exploring the interplay of genetics, hormones, and brain function

Contact Info

Product

Resources

About