RESUMEN
Background: Major depressive disorder (MDD) is a leading cause of disability worldwide. At present, however, there are no established biomarkers that have been validated for diagnosing and treating MDD. This study sought to assess the diagnostic and predictive potential of the differences in serum amino acid concentration levels between MDD patients and healthy controls (HCs), integrating them into interpretable machine learning models. Methods: In total, 70 MDD patients and 70 HCs matched in age, gender, and ethnicity were recruited for the study. Serum amino acid profiling was conducted by means of chromatography-mass spectrometry. A total of 21 metabolites were analysed, with 17 from a preset amino acid panel and the remaining 4 from a preset kynurenine panel. Logistic regression was applied to differentiate MDD patients from HCs. Results: The best-performing model utilised both feature selection and hyperparameter optimisation and yielded a moderate area under the receiver operating curve (AUC) classification value of 0.76 on the testing data. The top five metabolites identified as potential biomarkers for MDD were 3-hydroxy-kynurenine, valine, kynurenine, glutamic acid, and xanthurenic acid. Conclusions: Our study highlights the potential of using an interpretable machine learning analysis model based on amino acids to aid and increase the diagnostic accuracy of MDD in clinical practice.
RESUMEN
BACKGROUND: Major depressive disorder (MDD) affects a substantial number of individuals worldwide. New approaches are required to improve the diagnosis of MDD, which relies heavily on subjective reports of depression-related symptoms. AIM: Establish an objective measurement and evaluation of MDD. METHODS: Functional near-infrared spectroscopy (fNIRS) was used to investigate the brain activity of MDD patients and healthy controls (HCs). Leveraging a sizeable fNIRS dataset of 263 HCs and 251 patients with MDD, including mild to moderate MDD (mMDD; n = 139) and severe MDD (sMDD; n = 77), we developed an interpretable deep learning model for screening MDD and staging its severity. RESULTS: The proposed deep learning model achieved an accuracy of 80.9% in diagnostic classification and 78.6% in severity staging for MDD. We discerned five channels with the most significant contribution to MDD identification through Shapley additive explanations (SHAP), located in the right medial prefrontal cortex, right dorsolateral prefrontal cortex, right superior temporal gyrus, and left posterior superior frontal cortex. The findings corresponded closely to the features of haemoglobin responses between HCs and individuals with MDD, as we obtained a good discriminative ability for MDD using cortical channels that are related to the disorder, namely the frontal and temporal cortical channels with areas under the curve of 0.78 and 0.81, respectively. CONCLUSION: Our study demonstrated the potential of integrating the fNIRS system with artificial intelligence algorithms to classify and stage MDD in clinical settings using a large dataset. This approach can potentially enhance MDD assessment and provide insights for clinical diagnosis and intervention.
Asunto(s)
Aprendizaje Profundo , Trastorno Depresivo Mayor , Humanos , Trastorno Depresivo Mayor/diagnóstico por imagen , Espectroscopía Infrarroja Corta , Inteligencia Artificial , Corteza Prefrontal/diagnóstico por imagen , Imagen por Resonancia Magnética/métodosRESUMEN
Major depressive disorder (MDD) is a highly prevalent and disabling condition with a high disease burden. There are currently no validated biomarkers for the diagnosis and treatment of MDD. This study assessed serum amino acid metabolite changes between MDD patients and healthy controls (HCs) and their association with disease severity and diagnostic utility. In total, 70 MDD patients and 70 HCs matched in age, gender, and ethnicity were recruited for the study. For amino acid profiling, serum samples were analysed and quantified by liquid chromatography-mass spectrometry (LC-MS). Receiver-operating characteristic (ROC) curves were used to classify putative candidate biomarkers. MDD patients had significantly higher serum levels of glutamic acid, aspartic acid and glycine but lower levels of 3-Hydroxykynurenine; glutamic acid and phenylalanine levels also correlated with depression severity. Combining these four metabolites allowed for accurate discrimination of MDD patients and HCs, with 65.7% of depressed patients and 62.9% of HCs correctly classified. Glutamic acid, aspartic acid, glycine and 3-Hydroxykynurenine may serve as potential diagnostic biomarkers, whereas glutamic acid and phenylalanine may be markers for depression severity. To elucidate the association between these indicators and clinical features, it is necessary to conduct additional studies with larger sample sizes that involve a spectrum of depressive symptomatology.
Asunto(s)
Aminoácidos , Trastorno Depresivo Mayor , Humanos , Trastorno Depresivo Mayor/tratamiento farmacológico , Ácido Glutámico , Ácido Aspártico , Depresión , Biomarcadores , Fenilalanina/uso terapéutico , Glicina/uso terapéuticoRESUMEN
AIMS: Our study aims to explore how miRNAs can elucidate the molecular mechanisms of major depressive disorder (MDD) by comparing the miRNA levels in the blood serum of patients with depression and healthy individuals. It also explores the potential of miRNAs to differentiate between depressed patients and healthy controls. METHODS: 60 healthy controls (n = 45 females) were matched to 60 depressed patients (n = 10 unmedicated) for age (±7), sex, ethnicity, and years of education. Depression severity was measured using the Hamilton Depression Rating Scale, and venous blood was collected using PAXgene Blood RNA tubes for miRNA profiling. To further identify the depression-related biological pathways that are influenced by differentially expressed miRNAs, networks were constructed using QIAGEN Ingenuity Pathway Analysis. Receiver operating characteristic (ROC) analyses were also conducted to examine the discriminative ability of miRNAs to distinguish between depressed and healthy individuals. RESULTS: Six miRNAs (miR-542-3p, miR-181b-3p, miR-190a-5p, miR-33a-3p, miR-3690 and miR-6895-3p) showed to be considerably down-regulated in unmedicated depressed patients relative to healthy controls. miR-542-3p, in particular, also has experimentally verified mRNA targets that are predicted to be associated with MDD. ROC analyses found that a panel combining miR-542-3p, miR-181b-3p and miR-3690 produced an area under the curve value of 0.67 in distinguishing between depressed and healthy individuals. CONCLUSIONS: miRNAs - most notably, miR-542-3p, miR-181b-3p and miR-3690 - may be biomarkers with targets that are implicated in the pathophysiology of depression. They could also be used to distinguish between depressed and healthy individuals with reasonable accuracy.
Asunto(s)
Trastorno Depresivo Mayor , MicroARNs , Femenino , Humanos , Biomarcadores , Trastorno Depresivo Mayor/diagnóstico , Trastorno Depresivo Mayor/genética , Perfilación de la Expresión Génica , MicroARNs/genética , Curva ROC , MasculinoRESUMEN
OBJECTIVE: This study aimed to examine the intrapersonal, interpersonal, environmental and macrosystem influences on dietary behaviours among primary school children in Singapore. DESIGN: A qualitative interpretive approach was used in this study. Focus group discussions guided by the socio-ecological model (sem), of which transcripts were analysed deductively using the sem and inductively using thematic analysis to identify themes at each sem level. SETTING: Two co-educational public primary schools in Singapore. PARTICIPANTS: A total of 48 children (n 26 girls) took part in the semi-structured focus group discussions. Their mean age was 10·8 years (sd = 0·9, range 9-12 years), and the majority of the children were Chinese (n 36), along with some Indians (n 8) and Malays (n 4). RESULTS: Children's knowledge of healthy eating did not necessarily translate into healthy dietary practices and concern for health was a low priority. Instead, food and taste preferences were pivotal influences in their food choices. Parents had a large influence on children with regards to their accessibility to food, their attitudes and values towards food. Parental food restriction led to some children eating in secrecy. Peer influence was not frequently reported by children. Competitions in school incentivised children to consume fruits and vegetables, but reinforcements from teachers were inconsistent. The proximity of fast-food chains in the neighbourhood provided children easy access to less healthy foods. Health advertisements on social media rather than posters worked better in drawing children's attention. CONCLUSIONS: Findings highlighted important factors that should be considered in future nutrition interventions targeting children.
RESUMEN
PURPOSE: Establishing healthy lifestyle behaviours in primary school children is important, as these behaviours are likely to track into adulthood. This study aimed to explore the factors influencing physical activity (PA) in primary school children through their perspectives. APPROACH: Eleven focus group discussions and one interview were conducted with 52 children (n = 29 girls) aged 9-12 years from two primary schools in Singapore. Data analyses were conducted using thematic analysis, deductively following the socio-ecological model (SEM) and inductively for themes at each SEM level. RESULTS: At individual level, children's perceived enjoyment, health benefits and expectation of rewards motivated them to engage in PA, while time constraints and their apathy towards PA hindered PA engagement. Children's PA occasions at home were reported to be influenced by parental permission, priorities and availability, and the availability of preferred peers. Physical environmental factors such as opportunities for PA in school, access to facilities for PA and weather influenced children's time spent on PA and the types of activities they engaged in. CONCLUSION: This study summarized some factors that children have reported to influence their PA behaviour. These findings could help inform future interventions aimed at promoting PA among primary school children in Singapore.