Search

The Artificial Intelligence (AI) technology holds immense potential in the realm of automated diagnosis for Major Depressive Disorder (MDD), yet it is not without potential shortcomings. This paper systematically reviews the research progresses of integrating AI technology with depression diagnosis and provides a comprehensive analysis of existing research findings. In this context, we observe that the knowledge-driven first-generation of depression diagnosis methods could only address deterministic issues in structured information, with the selection of depression-related features directly influencing identification outcomes. The data-driven second-generation of depression diagnosis methods achieved automatic learning of features but required substantial high-quality clinical data, and the results were often obtained solely from the black-box models which lack sufficient explainability. In an effort to overcome the limitations of the preceding approaches, the third-generation of depression diagnosis methods combined the strengths of knowledge-driven and data-driven approaches. Through the fusion of information, the diagnostic accuracy is greatly enhanced, but the interpretability remains relatively weak. In order to enhance interpretability and introduce diagnostic criteria, this paper offers a new approach using Large Language Models (LLMs) as AI agents for assisting the depression diagnosis. Finally, we also discuss the potential advantages and challenges associated with this approach. This newly proposed innovative approach has the potential to offer new perspectives and solutions in the diagnosis of depression.

BackgroundsTobacco smoking is an important risk factor for coronary artery disease (CAD), but the genetic mechanisms linking smoking to CAD remain largely unknown.MethodsWe analyzed summary data from the genome-wide association study (GWAS) of the UK Biobank for CAD, plasma lipid concentrations (n = 184,305), and smoking (n = 337,030) using different biostatistical methods, which included LD score regression and Mendelian randomization (MR).ResultsWe identified SNPs shared by CAD and at least one smoking behavior, the genes where these SNPs are located were found to be significantly enriched in the processes related to lipoprotein metabolic, chylomicron-mediated lipid transport, lipid digestion, mobilization, and transport. The MR analysis revealed a positive correlation between smoking cessation and decreased risk for CAD when smoking cessation was considered as exposure (p = 0.001), and a negative correlation between the increased risk for CAD and smoking cessation when CAD was considered as exposure (p = 2.95E-08). This analysis further indicated that genetic liability for smoking cessation increased the risk of CAD.ConclusionThese findings inform the concomitant conditions of CAD and smoking and support the idea that genetic liabilities for smoking behaviors are strongly associated with the risk of CAD.

Although various susceptibility genes have been revealed to influence tobacco smoking, the underlying regulatory mechanisms between genetic variants and smoking are poorly understood. In this study, we investigated cis-expression quantitative trait loci (cis-eQTLs) and methylation quantitative trait loci (mQTLs) for 56 candidate smoking-linked genes using the BrainCloud cohort samples. An eQTL was revealed to significantly affect EGLN2 expression in the European sample and two mQTLs were respectively detected in CpG sites in NRXN1 and CYP2A7. Interestingly, we found for the first time that the minor allele of the single nucleotide polymorphism (SNP) rs3745277 located in CYP2A7P1 (downstream of CYP2B6) significantly decreased methylation at the CpG site for CYP2A7 (cg25427638; P = 5.31 × 10–7), reduced expression of CYP2B6 (P = 0.03), and lowered the percentage of smokers (8.8% vs. 42.3%; Odds Ratio (OR) = 0.14, 95% Confidence Interval (CI): 0.02–0.62; P = 4.47 × 10–3) in a dominant way for the same cohort sample. Taken together, our findings resulted from analyzing genetic variation, DNA methylation, mRNA expression, and smoking status together using the same participants revealed a regulatory mechanism linking mQTLs to the smoking phenotype. Moreover, we demonstrated the presence of different regulatory effects of low-frequency and common variants on mRNA expression and DNA methylation.

Smoking is a complex behavior with a heritability as high as 50%. Given such a large genetic contribution, it provides an opportunity to prevent those individuals who are susceptible to smoking dependence from ever starting to smoke by predicting their inherited predisposition with their genomic profiles. Although previous studies have identified many susceptibility variants for smoking, they have limited power to predict smoking behavior. We applied the support vector machine (SVM) and random forest (RF) methods to build prediction models for smoking behavior. We first used 1,431 smokers and 1,503 non-smokers of African origin for model building with a 10-fold cross-validation and then tested the prediction models on an independent dataset consisting of 213 smokers and 224 non-smokers. The SVM model with 500 top single nucleotide polymorphisms (SNPs) selected using logistic regression (p

AimsAlthough it is known that there is a high smoking prevalence among Chinese, key issues such as social and environmental factors impacting smoking initiation and persistence, the percentage of smokers considered nicotine dependence (ND), and the availability and use of ND treatments have rarely been investigated.MethodsTo address these issues, from 2012 to 2014, we conducted a large-scale study in the Zhejiang and Shanxi provinces of China using the Fagerström Test for Nicotine Dependence and other validated questionnaires.ResultsOf the 17,057 subjects, consisting of 13,476 males and 3,581 females aged 15 years or older, the prevalence of male smoking was 66.1% [95% confidence interval (CI) 65.5%, 66.9%] and that of female smoking was 3.2% (95% CI 3.0%, 3.8%). Among males, 25.8% (95% CI 25.0%, 26.5%) were low-to-moderate ND, and 11.8% (95% CI 11.2%, 12.3%) were high ND (H-ND), persons who have significant difficulty quitting without treatment. The degrees of ND were related to age, extent of education, and annual family income. The social–environmental factors examined conveyed a higher risk for smoking initiation, which is particularly true for the influence of smoking by friends. Furthermore, current smokers had a significantly higher risk of suffering respiratory and digestive symptoms.ConclusionThese data not only show a high smoking prevalence in Chinese men but also reveal that a relatively large number of smokers are H-ND. Considering that few Chinese smokers seek ND treatment, a comprehensive smoking prevention and treatment program designed specifically for Chinese is greatly needed.

BackgroundTopiramate (TPM) is suggested to be a promising medication for treatment of methamphetamine (METH) dependence, but the molecular basis remains to be elucidated.MethodsAmong 140 METH-dependent participants randomly assigned to receive either TPM (N = 69) or placebo (N = 71) in a previously conducted randomized controlled trial, 50 TPM- and 49 placebo-treated participants had a total 212 RNA samples available at baseline, week 8, and week 12 time points. Following our primary analysis of gene expression data, we reanalyzed the microarray expression data based on a latent class analysis of binary secondary outcomes during weeks 1–12 that provided a classification of 21 responders and 31 non-responders with consistent responses at both time points.ResultsBased on secondary outcomes, 1,381, 576, 905, and 711 differentially expressed genes at nominal P values

AimsPersonality characteristics are linked to nicotine dependence (ND). It remains unclear whether these factors differ across African-American (AA) and European-American (EA) male and female smokers. This study was aimed to determine the relationship between personality traits and smoking status, as well as the degree of ND, in AA and EA male and female samples.MethodsA total of 5,040 participants (AA: N = 3,737, female = 54.31%; EA: N = 1,313, female = 64.51%) were included in this study, with 2,474 smokers and 2,566 non-smokers. The measures used in this study included five dimensions of personality by the NEO-personality inventory-revised (neuroticism, extraversion, agreeableness, openness to experience, and conscientiousness), Fagerström test for ND, and drive subscale of the ND Syndrome Scale (NDSS).ResultsIn the AA sample, neuroticism was significantly associated with a higher risk of smoking [odds ratio (OR) = 1.057; 95% confidence interval (CI) 1.032, 1.083; p

Previous human and animal studies demonstrate that acute nicotine exposure has complicated influences on the function of the nervous system, which may lead to long-lasting effects on the behavior and physiology of the subject. To determine the genes and pathways that might account for long-term changes after acute nicotine exposure, a pathway-focused oligoarray specifically designed for drug addiction research was used to assess acute nicotine effect on gene expression in the neuron-like SH-SY5Y cells. Our results showed that 295 genes involved in various biological functions were differentially regulated by 1 hour of nicotine treatment. Among these genes, the expression changes of 221 were blocked by mecamylamine, indicating that the majority of nicotine-modulated genes were altered through the nAChRs-mediated signaling process. We further identified 14 biochemical pathways enriched among the nicotine-modulated genes, among which were those involved in neural development/synaptic plasticity, neuronal survival/death, immune response, or cellular metabolism. In the genes significantly regulated by nicotine but blocked by mecamylamine, 13 enriched pathways were detected. Nine of these pathways were shared with those enriched in the genes regulated by nicotine, including neuronal function-related pathways such as glucocorticoid receptor signaling, p38 MAPK signaling, PI3K/AKT signaling, and PTEN signaling, implying that nAChRs play important roles in the regulation of these biological processes. Together, our results not only provide insights into the mechanism underlying the acute response of neuronal cells to nicotine but also provide clues to how acute nicotine exposure exerts long-term effects on the nervous system.

Early-onset methamphetamine use increases the lifetime prevalence of methamphetamine dependence. An earlier onset of methamphetamine use leads to greater damage to the terminal ends of serotonin neurons, more reduction in serotonin transporter (5-HTT) density, and an increased propensity toward further methamphetamine use. Because genetic variation within the promoter region of the 5-HTT gene (the 5-HTT-linked polymorphic region; 5′-HTTLPR) leads to differential expression of the 5-HTT, we examined, for the first time, whether this could be a candidate site associated with predisposition toward early-onset methamphetamine use. We sought to determine whether there is a differential association between the long (L) and short (S) polymorphic variants of the 5′-HTTLPR and the age of first methamphetamine use. The study included 36 of 150 methamphetamine-dependent subjects enrolled in a multi-site, double-blind, randomized, placebo-controlled clinical trial. DNA was extracted from the blood samples of 36 subjects who consented to this genetic study. Diagnosis of methamphetamine dependence and age of first methamphetamine use were collected using structured questionnaires. Genotype in the 5′-HTTLPR was determined individually for each subject, and their associations with the age of onset of methamphetamine use were analyzed. Individuals with the LL genotype compared with S-carriers in the 5′-HTTLPR had more than a 3 times greater risk of an earlier onset of methamphetamine use (hazard ratio=3.27; 95% confidence interval=1.26–8.50; p=0.01), where onset occurred about 5 years earlier (p=0.04). LL genotype in the 5′-HTTLPR may be associated with an increased risk of early-onset methamphetamine use among methamphetamine-dependent individuals.

We previously reported that catechol-O-methyltransferase (COMT) is significantly associated with nicotine dependence (ND) in humans. In this study, we examined whether there exists any difference in the extent of methylation of CpG dinucleotides in the promoter region of COMT in smokers and nonsmokers by analyzing the methylation status of cytosines at 33 CpG sites through direct sequencing of bisulfite-treated DNA (N = 50 per group). The cytosine was methylated at 13 of 33 CpG sites, and two of these sites showed significant differences between smokers and matched nonsmoker controls. Specifically, in the -193 CpG site, the degree of methylation was 19.1% in smokers and 13.2% in nonsmokers (P < 0.01). This finding was confirmed by methylation-specific PCR using an additional 100 smoker and 100 nonsmoker control samples, which showed the degree of methylation to be 22.2% in smokers and 18.3% in nonsmokers (P < 0.01). For the -39 CpG site, the degree of methylation was 9.2% in smokers, whereas no methylation was found in nonsmoker controls. Together, our findings provide the first molecular explanation at the epigenetic level for the association of ND with methylation of the COMT promoter, implying that methylation plays a role in smoking dependence.