Predicting the diagnosis of various mental disorders in a mixed cohort using blood-based multi-protein model: a machine learning approach

Chen, Suzhen; Chen, Gang; Li, Yinghui; Yue, Yingying; Zhu, Zengwei; Li, Lei; Jiang, Wenhao; Shen, Zhongxia; Wang, Tianyu; Hou, Zhenghua; Xu, Zhi; Shen, Xinhua; Yuan, Yonggui

doi:10.1007/s00406-022-01540-3

Cited by 6 publications

(5 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Of these, 31 articles were selected for full‐text assessment. Finally, 12 articles met the inclusion criteria and were included (An et al., 2019 ; Carlino et al., 2015 ; Chen et al., 2022 , 2017 ; Chu et al., 2022 ; Kim et al., 2019 ; Kobayashi et al., 2005 ; Li et al., 2023 ; Maron et al., 2009 ; Molendijk et al., 2012 ; Ströhle et al., 2010 ; Wang et al., 2020 ) (see Figure 1 for the PRISMA flow diagram).…”

Section: Resultsmentioning

confidence: 99%

“…Recent studies reported lower BDNF protein levels in individuals with panic disorder compared to healthy controls (Chu et al., 2022 ; Li et al., 2023 ; Wang et al., 2020 ). However, there were some discrepancies among the findings, with some studies reporting no significant differences (An et al., 2019 ; Carlino et al., 2015 ; Chen et al., 2022 , 2017 ; Kim et al., 2019 ; Kobayashi et al., 2005 ; Molendijk et al., 2012 ) or even higher BDNF levels in individuals with panic disorder (Maron et al., 2009 ). Several studies also examined the relationship between BDNF levels and panic disorder severity, suggesting a potential association between lower BDNF levels and more severe symptoms.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Brain‐derived neurotrophic factor (BDNF) levels in panic disorder: A systematic review and meta‐analysis

Shafiee,

Jafarabady,

Mohammadi

et al. 2023

Brain and Behavior

View full text Add to dashboard Cite

BackgroundThe existing literature on the association between brain‐derived neurotrophic factor (BDNF) protein levels and panic disorder presents inconsistent findings. This systematic review and meta‐analysis aim to synthesize the available evidence and determine the overall effect of BDNF protein levels in individuals diagnosed with panic disorder.MethodsA comprehensive literature search was conducted using electronic databases (PubMed, Embase, Scopus, PsycINFO, and Web of Science) from inception to April 21, 2023. The search strategy included relevant keywords and medical subject headings terms related to BDNF, panic disorder, and protein levels. A random‐effects model was used for the meta‐analysis, and subgroup analyses were performed to explore heterogeneity. Publication bias was assessed using funnel plots and statistical tests.ResultsA total of 12 studies met the inclusion criteria. The meta‐analysis demonstrated a significant decrease in BDNF protein levels in individuals with panic disorder (SMD = −.53, 95% CI: −1.02 to −.04, p < .001; I2: 92%). The results of subgroup and meta‐regression analyses were not statistically significant. No significant publication bias was observed based on the results of Egger's regression test (p‐value = .3550).ConclusionThis systematic review and meta‐analysis provide evidence of lower BDNF protein levels in individuals diagnosed with panic disorder compared to healthy controls. The findings suggest a potential role for BDNF dysregulation in the pathophysiology of panic disorder. Further research is warranted to elucidate the underlying mechanisms and potential therapeutic implications.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Brain‐derived neurotrophic factor (BDNF) levels in panic disorder: A systematic review and meta‐analysis

Shafiee,

Jafarabady,

Mohammadi

et al. 2023

Brain and Behavior

View full text Add to dashboard Cite

show abstract

“…The majority of studies, including ML, evaluated cortisol levels as an outcome, not a feature [ 54 ]. However, few studies included cortisol levels in ML algorithms able to predict different diseases, such as mental disorders [ 55 ], stress and dietary intake [ 56 ], and quality of life [ 57 ].…”

Section: Discussionmentioning

confidence: 99%

Machine Learning-Based Routine Laboratory Tests Predict One-Year Cognitive and Functional Decline in a Population Aged 75+ Years

et al. 2023

View full text Add to dashboard Cite

Background: Cognitive and functional decline are common problems in older adults, especially in those 75+ years old. Currently, there is no specific plasma biomarker able to predict this decline in healthy old-age people. Machine learning (ML) is a subarea of artificial intelligence (AI), which can be used to predict outcomes Aim: This study aimed to evaluate routine laboratory variables able to predict cognitive and functional impairment, using ML algorithms, in a cohort aged 75+ years, in a one-year follow-up study. Method: One hundred and thirty-two older adults aged 75+ years were selected through a community-health public program or from long-term-care institutions. Their functional and cognitive performances were evaluated at baseline and one year later using a functional activities questionnaire, Mini-Mental State Examination, and the Brief Cognitive Screening Battery. Routine laboratory tests were performed at baseline. ML algorithms—random forest, support vector machine (SVM), and XGBoost—were applied in order to describe the best model able to predict cognitive and functional decline using routine tests as features. Results: The random forest model showed better accuracy than other algorithms and included triglycerides, glucose, hematocrit, red cell distribution width (RDW), albumin, hemoglobin, globulin, high-density lipoprotein cholesterol (HDL-c), thyroid-stimulating hormone (TSH), creatinine, lymphocyte, erythrocyte, platelet/leucocyte (PLR), and neutrophil/leucocyte (NLR) ratios, and alanine transaminase (ALT), leukocyte, low-density lipoprotein cholesterol (LDL-c), cortisol, gamma-glutamyl transferase (GGT), and eosinophil as features to predict cognitive decline (accuracy = 0.79). For functional decline, the most important features were platelet, PLR and NLR, hemoglobin, globulin, cortisol, RDW, glucose, basophil, B12 vitamin, creatinine, GGT, ALT, aspartate transferase (AST), eosinophil, hematocrit, erythrocyte, triglycerides, HDL-c, and monocyte (accuracy = 0.92). Conclusions: Routine laboratory variables could be applied to predict cognitive and functional decline in oldest-old populations using ML algorithms.

show abstract

“…CRP was shown to be related to the development of mental disorders. 18 , 19 A host of studies showed that elevated CRP level was associated with the risk of dementia. 20–23 In addition, increased CRP level could predict delirium in critically ill patients, 24 elderly patients, 25 and surgical patients.…”

Section: Introductionmentioning

confidence: 99%

Postoperative C-Reactive Protein Predicts Postoperative Delirium in Colorectal Cancer Following Surgery

Sun¹,

Peng²,

Wu³

2023

CIA

View full text Add to dashboard Cite

Background: Postoperative delirium (POD) is a common complication in operative patients. Neuroinflammation has been reported to be a potential mechanism associated with the development of POD. Identifying available inflammatory markers such as C-reactive protein (CRP) would aid clinicians in early detection of POD. Previous studies have demonstrated that CRP may be a promising predictive marker for POD. Thus, this study aimed to explore the association between CRP and POD among those elderly colorectal cancer (CRC) patients. Methods: 643 patients with CRC were included in this study. CRP levels were measured before operation and on postoperative day 1. The univariate and multivariate regression analyses were used to identify risk factors for POD. Results: Of 643 patients with CRC, 112 cases (17.4%) had POD. CRC patients with POD showed older age, higher CRP level on postoperative day 1, and higher percentage of smoking, diabetes mellitus, and chronic obstructive pulmonary disease (COPD) than CRC patients without POD. Preoperative CRP level was not associated with the POD. Univariate and multivariate regression analyses showed that older age (> 70 years), diabetes mellitus, COPD, and higher CRP level on postoperative day 1 (> 48 mg/L) were risk factors for POD in CRC patients. Conclusion:Postoperative CRP level is an independent indicator for POD among CRC patients, suggesting the predictive role of postoperative CRP levels for POD in elderly CRC patients undergoing surgery.

show abstract

Predicting the diagnosis of various mental disorders in a mixed cohort using blood-based multi-protein model: a machine learning approach

Cited by 6 publications

References 76 publications

Brain‐derived neurotrophic factor (BDNF) levels in panic disorder: A systematic review and meta‐analysis

Brain‐derived neurotrophic factor (BDNF) levels in panic disorder: A systematic review and meta‐analysis

Machine Learning-Based Routine Laboratory Tests Predict One-Year Cognitive and Functional Decline in a Population Aged 75+ Years

Postoperative C-Reactive Protein Predicts Postoperative Delirium in Colorectal Cancer Following Surgery

Contact Info

Product

Resources

About