Spectral fusion-based machine learning classifiers for discriminating membrane breakage in multiple scenarios.

Membrane breakage can lead to filtration failure, which allows harmful substances to enter the effluent, posing potential hazards to human health and the environment. This study is an innovative combination of fluorescence and ultraviolet-visible (UV-Vis) spectroscopy to identify membrane breakage. It aims to unravel more comprehensive information, improve detection sensitivity and selectivity, and enable real-time monitoring capabilities. Fluorescence and UV-Vis data are extracted through variance partitioning analysis (VPA) and integrated through a decision tree algorithm to form a superior system with enhanced discrimination capabilities. VPA improves discrimination efficiency by extracting key information from spectral data and eliminating redundancy. The decision tree algorithm, on the other hand, can process large amounts of data simultaneously. In addition, the method has a wide range of applications and can be used in various scenarios accurately. The scenarios include domestic sewage, micropollutant water, aquaculture wastewater, and secondary treated sewage. The experimental results validate the application of machine learning classifiers in membrane breakage detection with an accuracy rate of 96.8 % to 97.4 %.

Efficient Functionalization of Organosulfones via Photoredox Catalysis: Direct Incorporation of α-Carbonyl Alkyl Side Chains into α-Allyl-ß-Ketosulfones.

A novel and efficient method for functionalizing organosulfones has been established, utilizing a visible-light-driven intermolecular radical cascade cyclization of α-allyl-ß-ketosulfones. This process employs fac-Ir(ppy)3 as the photoredox catalyst and α-carbonyl alkyl bromide as the oxidizing agent. Via this approach, the substrates experience intermolecular addition of α-carbonyl alkyl radicals to the alkene bonds, initiating a sequence of C-C bond formations that culminate in the production of organosulfone derivatives. Notably, this technique features gentle reaction conditions and an exceptional compatibility with a wide array of functional groups, making it a versatile and valuable addition to the field of organic synthesis.

Personalized venlafaxine dose prediction using artificial intelligence technology: a retrospective analysis based on real-world data.

BACKGROUND: Venlafaxine dose regimens vary considerably between individuals, requiring personalized dosing. AIM: This study aimed to identify dose-related influencing factors of venlafaxine through real-world data analysis and to construct a personalized dose model using advanced artificial intelligence techniques. METHOD: We conducted a retrospective study on patients with depression treated with venlafaxine. Significant variables were selected through a univariate analysis. Subsequently, the predictive performance of seven models (XGBoost, LightGBM, CatBoost, GBDT, ANN, TabNet, and DT) was compared. The algorithm that demonstrated optimal performance was chosen to establish the dose prediction model. Model validation used confusion matrices and ROC analysis. Additionally, a dose subgroup analysis was conducted. RESULTS: A total of 298 patients were included. TabNet was selected to establish the venlafaxine dose prediction model, which exhibited the highest performance with an accuracy of 0.80. The analysis identified seven crucial variables correlated with venlafaxine daily dose, including blood venlafaxine concentration, total protein, lymphocytes, age, globulin, cholinesterase, and blood platelet count. The area under the curve (AUC) for predicting venlafaxine doses of 75 mg, 150 mg, and 225 mg were 0.90, 0.85, and 0.90, respectively. CONCLUSION: We successfully developed a TabNet model to predict venlafaxine doses using real-world data. This model demonstrated substantial predictive accuracy, offering a personalized dosing regimen for venlafaxine. These findings provide valuable guidance for the clinical use of the drug.

Association between primary angle closure glaucoma and uric acid levels in serum and aqueous humor.

Purpose: To evaluate abnormalities in serum and aqueous humor uric acid (UA) levels in primary angle closure glaucoma (PACG). Methods: Patients with PACG and age-similar and gender-similar controls (patients scheduled for cataract extraction) were enrolled prospectively. Serum UA levels were determined by enzymatic colorimetry; aqueous humor UA levels by Enzyme-Linked ImmunoSorbent Assay. A t-test was used to compare UA levels between PACG patients and controls, with one-way ANOVA used to compare levels across PACG subgroups with differing disease severity. Comparisons between PACG patients and controls were adjusted for systemic and ocular confounding factors using binary logistic regression. Results: In all, 131 PACG patients and 112 controls were included. The serum UA level was 266 ± 69 µmol/L in the PACG group and 269 ± 73 µmol/L in the control group (p = 0.71). The aqueous humor UA level was 35.4 ± 8.2 µmol/L in the PACG group and 53.9 ± 18.6 µmol/L in the control group (p < 0.001). This difference remained significant after adjusting for age, gender, systolic blood pressure, diastolic blood pressure, body mass index, axial length, central corneal thickness, anterior chamber depth, lens thickness, white-to-white distance, corneal endothelial cell density, and serum UA level (odds ratio: 0.88, 95 % confidence interval: 0.83-0.93, p < 0.001). Conclusion: Aqueous humor UA levels differ between PACG patients and controls, but serum UA levels do not. This indicates that local UA plays a role in the pathogenesis of PACG, but systemic UA does not.

New insight into molecular mechanisms of different polyphenols affecting Sirtuin 3 deacetylation activity.

Multiple phenolic substances have been shown to promote SIRT3 expression, however, few studies have focused on the effects of these phenolics on SIRT3 enzyme activity. This study constructed a variety of reaction systems to elucidate the mechanisms by which different polyphenols affect SIRT3 enzyme activity. The results showed that acP53317-320 was the most suitable substrate among the five acetylated peptide substrates (Kcat/Km = 74.85 ± 1.86 M-1•s-1). All the phenolic compounds involved in the experiment inhibited the enzymatic activity of SIRT3, and the lowest IC50 among them was quercetin (0.12 ± 0.01 mM) and the highest was piceatannol (1.29 ± 0.08 mM). Their inhibition types were mainly competitive and mixed. In addition, piceatannol was found to be a natural SIRT3 agonist by enzyme kinetic analysis and validation of deacetylation efficiency. This study will provide a useful reference for polyphenol modulation of SIRT3 dosage, as well as the development and application of polyphenol-based SIRT3 activators and agonists.

Echinacea purpurea Polysaccharide Ameliorates Dextran Sulfate Sodium-Induced Colitis by Restoring the Intestinal Microbiota and Inhibiting the TLR4-NF-κB Axis.

Ulcerative colitis (UC) is a chronic intestinal ailment which cannot be completely cured. The occurrence of UC has been on the rise in recent years, which is highly detrimental to patients. The effectiveness of conventional drug treatment is limited. The long-term usage of these agents can lead to substantial adverse effects. Therefore, the development of a safe and efficient dietary supplement is important for the prevention of UC. Echinacea purpurea polysaccharide (EPP) is one of the main bioactive substances in Echinacea purpurea. EPP has many favorable effects, such as antioxidative, anti-inflammatory, and antitumor effects. However, whether EPP can prevent or alleviate UC is still unclear. This study aims to analyze the effect and mechanism of EPP on UC in mice using a 3% dextran sulfate sodium (DSS)-induced UC model. The results showed that dietary supplementation with 200 mg/kg EPP significantly alleviated the shortening of colon length, weight loss, and histopathological damage in DSS-induced colitis mice. Mechanistically, EPP significantly inhibits the activation of the TLR4/NF-κB pathway and preserves the intestinal mechanical barrier integrity by enhancing the expression of claudin-1, ZO-1, and occludin and reducing the loss of goblet cells. Additionally, 16S rRNA sequencing revealed that EPP intervention reduced the abundance of Bacteroides, Escherichia-Shigella, and Klebsiella; the abundance of Lactobacillus increased. The results of nontargeted metabonomics showed that EPP reshaped metabolism. In this study, we clarified the effect of EPP on UC, revealed the potential function of EPP, and supported the use of polysaccharide dietary supplements for UC prevention.

Unraveling Stoichiometry Effect in Nickel-Tungsten Alloys for Efficient Hydrogen Oxidation Catalysis in Alkaline Electrolytes.

Anion-exchange membrane fuel cells provide the possibility to use platinum group metal-free catalysts, but the anodic hydrogen oxidation reaction (HOR) suffers from sluggish kinetics and its source is still debated. Here, over nickel-tungsten (Ni-W) alloy catalysts, we show that the Ni:W ratio greatly governs the HOR performance in alkaline electrolyte. Experimental and theoretical studies unravel that alloying with W can tune the unpaired electrons in Ni, tailoring the potential of zero charge and the catalytic surface to favor hydroxyl adsorption (OHad). The OHad species coordinately interact with potassium (K+) ions, which break the K+ solvation sheath to leave free water molecules, yielding an improved connectivity of hydrogen-bond networks. Consequently, the optimal Ni17W3 alloy exhibits alkaline HOR activity superior to the state-of-the-art platinum on carbon (Pt/C) catalyst and operates steadily with negligible decay after 10,000 cycles. Our findings offer new understandings of alloyed HOR catalysts and will guide rational design of next-generation catalysts for fuel cells.

Single-Cell Transcriptional Profile Construction of Rat Pituitary Glands before and after Sexual Maturation and Identification of Novel Marker Spp1 in Gonadotropes.

The mammalian pituitary gland drives highly conserved physiological processes such as somatic cell growth, pubertal transformation, fertility, and metabolism by secreting a variety of hormones. Recently, single-cell transcriptomics techniques have been used in pituitary gland research. However, more studies have focused on adult pituitary gland tissues from different species or different sexes, and no research has yet resolved cellular differences in pituitary gland tissue before and after sexual maturation. Here, we identified a total of 15 cell clusters and constructed single-cell transcriptional profiles of rats before and after sexual maturation. Furthermore, focusing on the gonadotrope cluster, 106 genes were found to be differentially expressed before and after sexual maturation. It was verified that Spp1, which is specifically expressed in gonadotrope cells, could serve as a novel marker for this cell cluster and has a promotional effect on the synthesis and secretion of follicle-stimulating hormone. The results provide a new resource for further resolving the regulatory mechanism of pituitary gland development and pituitary hormone synthesis and secretion.

Combined EEG-tDCS approach in resting state to reduce comorbid anxiety and depressive symptoms in affective disorders: A sham-controlled pilot study.

Continuous challenges have been imposed on mental health science by Anxiety and Depression disorders as the most prevalent and debilitating psychiatric conditions worldwide. Pharmacologic and cognitive behavioral therapies, either alone or in combination, have been considered as the first-line therapies, however, resistant symptomatology is prevalent in comorbid conditions with symptoms remaining after interventions. The demand for new therapeutic solutions has given space to the development of non-invasive brain stimulation techniques (NIBS), and the transmagnetic direct current stimulation (tDCS) has been reported as a safe and well-tolerated technique for the treatment of several mental health conditions, including Anxiety and Depression disorders. Relying on quantitative electroencephalography(qEEG)- tDCS approach, the current study aims to inspect the effect of tDCS intervention on patients who suffer from anxiety-depression comorbidity, in particular, the impact of tDCS intervention on qEEG spectral power activity and resting-state connectivity organization during eyes closed and eyes open protocols. QEEG data were acquired from eight patients suffering from moderate to severe anxiety-depression comorbid symptoms along with poor coping skills to manage stress and negative affect. Twelve control subjects allocated in the control group exhibiting low to moderate symptoms in both anxiety and depression conditions went also through the qEEG data acquisition. In addition, a sham-controlled study was conducted, and the patient group went through resting-state qEEG-tDCS neuromodulation once a week for ten weeks. Various-stage qEEG recordings were performed to inspect the efficacy of tDCS treatment during the modulation of brain regions involved in the regulation of affective responses. Our results demonstrated that after tDCS neuromodulation, the patients' groups exhibited decreased absolute power abnormalities over the left anterior cingulate cortex and reduced abnormal activity in the alpha band over posterior regions; improved functional connectivity indexes; decreased anxiety and depressive scores while positive affect score was improved. Besides the promising improvements, our study did not find a significant tDCS effect on perceived stress and negative affect scores. Consistently, significant differences in absolute spectral power over the left anterior cingulate cortex were detected among the patient group, as compared to the controls, as expected. Therefore, our study offers preliminary data to understand the neuroplasticity changes that potentially result from the manipulation of cortical excitability during affective regulation protocols followed by the consequent decrease of comorbid anxiety and depressive symptomatology. The pilot study was followed by prospective registration with ChiCTR2200062142.

Development and evaluation of inactivated vaccines incorporating a novel Senecavirus A strain-based Immunogen and various adjuvants in mice.

Porcine idiopathic vesicular disease (PIVD), one of several clinically indistinguishable vesicular diseases of pigs, is caused by the emerging pathogen Senecavirus A (SVA). Despite the widespread prevalence of porcine SVA infection, no effective commercial vaccines for PIVD prevention and control are available, due to high costs associated with vaccine testing in pigs, considerable SVA diversity, and SVA rapid evolution. In this study, SVA CH/JL/2022 (OP562896), a novel mutant SVA strain derived from an isolate obtained from a pig farm in Jilin Province, China, was inactivated then combined with four adjuvants, MONTANIDETM GEL02 PR (GEL 02), MONTANIDETM ISA 201 VG (ISA 201), MONTANIDETM IMG 1313 VG N (IMS1313), or Rehydragel LV (LV). The resulting inactivated SVA CH/JL/2022 vaccines were assessed for efficacy in mice and found to induce robust in vivo lymphocyte proliferation responses and strong IgG1, IgG2a, and neutralizing antibody responses with IgG2a/IgG1 ratios of <1. Furthermore, all vaccinated groups exhibited significantly higher levels of serum cytokines IL-2, IL-4, IL-6, and IFN as compared to unvaccinated mice. These results indicate that all vaccines elicited both Th1 and Th2 responses, with Th2 responses predominating. Moreover, vaccinated mice exhibited enhanced resistance to SVA infection, as evidenced by reduced viral RNA levels and SVA infection-induced histopathological changes. Collectively, our results demonstrate that the SVA-GEL vaccine induced more robust immunological responses in mice than did the other three vaccines, thus highlighting the potential of SVA-GEL to serve an effective tool for preventing and controlling SVA infection.

Quercetin ameliorates ulcerative colitis by restoring the balance of M2/M1 and repairing the intestinal barrier via downregulating cGAS‒STING pathway.

Macrophage polarization is closely associated with the pathogenesis of ulcerative colitis (UC). Quercetin, a flavonoid, has shown promise as a treatment for inflammatory diseases, but its specific mechanism of action remains unclear. This study investigates whether quercetin can regulate intestinal macrophage polarization and promote intestinal tissue repair via the cGAS-STING pathway for the treatment of UC. In vivo, mice with 3% DSS-induced UC were intraperitoneally injected with quercetin and RU.521 for 7 days, following which their general conditions and corresponding therapeutic effects were assessed. The impact of interferon-stimulated DNA (ISD) and quercetin on macrophage polarization and the cGAS-STING pathway was investigated using RAW264.7 cells and bone marrow-derived macrophages (BMDMs) in vitro. The results demonstrated that ISD induced M1 macrophage polarization and activated the cGAS-STING pathway in vitro, while quercetin reversed ISD's inflammatory effects. In vivo, quercetin suppressed the cGAS-STING pathway in the intestinal macrophages of DSS-induced UC mice, which reduced M1 macrophage polarization, increased M2 polarization, and facilitated intestinal barrier repair in UC. Taken together, these findings provide new insights into the mechanisms via which quercetin could be used to treat UC.

Brain extended and closed forms glutathione levels decrease with age and extended glutathione is associated with visuospatial memory.

During aging, the brain is subject to greater oxidative stress (OS), which is thought to play a critical role in cognitive impairment. Glutathione (GSH), as a major antioxidant in the brain, can be used to combat OS. However, how brain GSH levels vary with age and their associations with cognitive function is unclear. In this study, we combined point-resolved spectroscopy and edited spectroscopy sequences to investigate extended and closed forms GSH levels in the anterior cingulate cortex (ACC), posterior cingulate cortex (PCC), and occipital cortex (OC) of 276 healthy participants (extended form, 166 females, age range 20-70 years) and 15 healthy participants (closed form, 7 females, age range 26-56 years), and examined their relationships with age and cognitive function. The results revealed decreased extended form GSH levels with age in the PCC among 276 participants. Notably, the timecourse of extended form GSH level changes in the PCC and ACC differed between males and females. Additionally, positive correlations were observed between extended form GSH levels in the PCC and OC and visuospatial memory. Additionally, a decreased trend of closed form GSH levels with age was also observed in the PCC among 15 participants. Taken together, these findings enhance our understanding of the brain both closed and extended form GSH time course during normal aging and associations with sex and memory, which is an essential first step for understanding the neurochemical underpinnings of healthy aging.

Cryoprotective isoliquiritigenin-zein phosphatidylcholine nanoparticles inhibits breast cancer-bone metastasis by targeting JAK-STAT signaling pathways.

Breast cancer (BC) is the most common cancer in women and is known for its tendency to spread to the bones, causing significant health issues and mortality. In this study, we aimed to investigate whether cryoprotective isoliquiritigenin-zein phosphatidylcholine nanoparticles (ISL@ZLH NPs) could inhibit BC-induced bone destruction and tumor metastasis in both in vitro and animal models. To evaluate the potential of ISL@ZLH NPs, we conducted various experiments. First, we assessed cell viability, colony formation, transwell migration, and wound healing assays to determine the impact of ISL@ZLH NPs on BC cell behavior. Western blotting, TRAP staining and ALP activity were performed to examine the effects of ISL@ZLH NPs on osteoclast formation induced by MDA-MB-231 cell-conditioned medium and RANKL treated RAW 264.7 cells. Furthermore, we assessed the therapeutic impact of ISL@ZLH NPs on tumor-induced bone destruction using a mouse model of BC bone metastasis. Treatment with ISL@ZLH NPs effectively suppressed BC cell proliferation, colony formation, and motility, reducing their ability to metastasize. ISL@ZLH NPs significantly inhibited osteoclast formation and the expression of factors associated with bone destruction in BC cells. Additionally, ISL@ZLH NPs suppressed JAK-STAT signaling in RAW264.7 cells. In the BCBM mouse model, ISL@ZLH NPs led to a significant reduction in osteolytic bone lesions compared to the control group. Histological analysis and TRAP staining confirmed that ISL@ZLH NPs preserved the integrity of bone structure, preventing invasive metastasis by confining tumor growth to the bone marrow cavity. Furthermore, ISL@ZLH NPs effectively suppressed tumor-induced osteoclastogenesis, a key process in BC-related bone destruction. Our findings demonstrate that ISL@ZLH NPs have the potential to inhibit BC-induced bone destruction and tumor metastasis by targeting JAK-STAT signaling pathways and suppressing tumor-induced osteoclastogenesis. These results underscore the therapeutic promise of ISL@ZLH NPs in managing BC metastasis to the bones.

Low-intensity pulsed ultrasound protects from inflammatory dilated cardiomyopathy through inciting extracellular vesicles.

AIMS: CD4+ T cells are activated during inflammatory dilated cardiomyopathy (iDCM) development to induce immunogenic responses that damage the myocardium. Low-intensity pulsed ultrasound (LIPUS), a novel physiotherapy for cardiovascular diseases, has recently been shown to modulate inflammatory responses. However, its efficacy in iDCM remains unknown. Here, we investigated whether LIPUS could improve the severity of iDCM by orchestrating immune responses and explored its therapeutic mechanisms. METHODS AND RESULTS: In iDCM mice, LIPUS treatment reduced cardiac remodelling and dysfunction. Additionally, CD4+ T cell inflammatory responses were suppressed. LIPUS increased Treg cells while decreasing Th17 cells. LIPUS mechanically stimulates endothelial cells, resulting in increased secretion of extracellular vesicles (EVs), which are taken up by CD4+ T cells and alter their differentiation and metabolic patterns. Moreover, EVs selectively loaded with microRNA (miR)-99a are responsible for the therapeutic effects of LIPUS. The hnRNPA2B1 translocation from the nucleus to the cytoplasm and binding to caveolin-1 and miR-99a confirmed the upstream mechanism of miR-99a transport. This complex is loaded into EVs and taken up by CD4+ T cells, which further suppress mTOR and TRIB2 expression to modulate cellular differentiation. CONCLUSION: Our findings revealed that LIPUS uses an EV-dependent molecular mechanism to protect against iDCM progression. Therefore, LIPUS is a promising new treatment option for iDCM.

Understanding the Novel Approach of Nanoferroptosis for Cancer Therapy.

As a new form of regulated cell death, ferroptosis has unraveled the unsolicited theory of intrinsic apoptosis resistance by cancer cells. The molecular mechanism of ferroptosis depends on the induction of oxidative stress through excessive reactive oxygen species accumulation and glutathione depletion to damage the structural integrity of cells. Due to their high loading and structural tunability, nanocarriers can escort the delivery of ferro-therapeutics to the desired site through enhanced permeation or retention effect or by active targeting. This review shed light on the necessity of iron in cancer cell growth and the fascinating features of ferroptosis in regulating the cell cycle and metastasis. Additionally, we discussed the effect of ferroptosis-mediated therapy using nanoplatforms and their chemical basis in overcoming the barriers to cancer therapy.

Aberrant auditory metabolite levels and topological properties are associated with cognitive decline in presbycusis patients.

Presbycusis has been reported as related to cognitive decline, but its underlying neurophysiological mechanism is still unclear. This study aimed to investigate the relationship between metabolite levels, cognitive function, and node characteristics in presbycusis based on graph theory methods. Eighty-four elderly individuals with presbycusis and 63 age-matched normal hearing controls underwent magnetic resonance spectroscopy, functional magnetic resonance imaging scans, audiological assessment, and cognitive assessment. Compared with the normal hearing group, presbycusis patients exhibited reduced gamma-aminobutyric acid and glutamate levels in the auditory region, increased nodal characteristics in the temporal lobe and precuneus, as well as decreased nodal characteristics in the superior occipital gyrus and medial orbital. The right gamma-aminobutyric acid levels were negatively correlated with the degree centrality in the right precuneus and the executive function. Degree centrality in the right precuneus exhibited significant correlations with information processing speed and executive function, while degree centrality in the left medial orbital demonstrated a negative association with speech recognition ability. The degree centrality and node efficiency in the superior occipital gyrus exhibited a negative association with hearing loss and speech recognition ability, respectively. These observed changes indicate alterations in metabolite levels and reorganization patterns at the brain network level after auditory deprivation.

Effects of short-term moderate intensity exercise on the serum metabolome in older adults: a pilot randomized controlled trial.

BACKGROUND: We previously reported changes in the serum metabolome associated with impaired myocardial relaxation in an asymptomatic older community cohort. In this prospective parallel-group randomized control pilot trial, we subjected community adults without cardiovascular disease to exercise intervention and evaluated the effects on serum metabolomics. METHODS: Between February 2019 to November 2019, thirty (83% females) middle-aged adults (53 ± 4 years) were randomized with sex stratification to either twelve weeks of moderate-intensity exercise training (Intervention) (n = 15) or Control (n = 15). The Intervention group underwent once-weekly aerobic and strength training sessions for 60 min each in a dedicated cardiac exercise laboratory for twelve weeks (ClinicalTrials.gov: NCT03617653). Serial measurements were taken pre- and post-intervention, including serum sampling for metabolomic analyses. RESULTS: Twenty-nine adults completed the study (Intervention n = 14; Control n = 15). Long-chain acylcarnitine C20:2-OH/C18:2-DC was reduced in the Intervention group by a magnitude of 0.714 but increased in the Control group by a magnitude of 1.742 (mean difference -1.028 age-adjusted p = 0.004). Among Controls, alanine correlated with left ventricular mass index (r = 0.529, age-adjusted p = 0.018) while aspartate correlated with Lateral e' (r = -764, age-adjusted p = 0.016). C20:3 correlated with E/e' ratio fold-change in the Intervention group (r = -0.653, age-adjusted p = 0.004). Among Controls, C20:2/C18:2 (r = 0.795, age-adjusted p = 0.005) and C20:2-OH/C18:2-DC fold-change (r = 0.742, age-adjusted p = 0.030) correlated with change in E/A ratio. CONCLUSIONS: Corresponding relationships between serum metabolites and cardiac function in response to exercise intervention provided pilot observations. Future investigations into cellular fuel oxidation or central carbon metabolism pathways that jointly impact the heart and related metabolic systems may be critical in preventive trials.

Prior studies have found changes in cellular biological processes in both cardiac aging and heart failure suggesting a common underlying mechanism. I has also been shown that exercise in healthy participants can reverse the signs of early cardiac aging. In this experimental study, we examined the effects of exercise on biological markers and cardiac function among healthy community older adults. After twelve weeks of exercise, there were changes in biological components associated with cardiac function. These findings highlight the potential of exercise as a strategy to target biological alterations in early cardiac aging and potentially prevent it.

Developing a machine learning model for predicting venlafaxine active moiety concentration: a retrospective study using real-world evidence.

BACKGROUND: Venlafaxine is frequently prescribed for patients with depression. To control the concentration of venlafaxine within the therapeutic window for the best treatment effect, a model to predict venlafaxine concentration is necessary. AIM: Our objective was to develop a prediction model for venlafaxine concentration using real-world evidence based on machine learning and deep learning techniques. METHOD: Patients who underwent venlafaxine treatment between November 2019 and August 2022 were included in the study. Important variables affecting venlafaxine concentration were identified using a combination of univariate analysis, sequential forward selection, and machine learning techniques. Predictive performance of nine machine learning and deep learning algorithms were assessed, and the one with the optimal performance was selected for modeling. The final model was interpreted using SHapley Additive exPlanations. RESULTS: A total of 330 eligible patients were included. Five influential variables that affect venlafaxine concentration were venlafaxine daily dose, sex, age, hyperlipidemia, and adenosine deaminase. The venlafaxine concentration prediction model was developed using the eXtreme Gradient Boosting algorithm (R2 = 0.65, mean absolute error = 77.92, root mean square error = 93.58). In the testing cohort, the accuracy of the predicted concentration within ± 30% of the actual concentration was 73.49%. In the subgroup analysis, the prediction accuracy was 69.39% within the recommended therapeutic range of venlafaxine concentration within ± 30% of the actual value. CONCLUSION: The XGBoost model for predicting blood concentration of venlafaxine using real-world evidence was developed, guiding the adjustment of regimen in clinical practice.