Applicability of Brassica juncea as a bioindicator for As contamination in soil near the abandoned mine area.

Soil monitoring in abandoned mine areas is important from the perspective of ecological and human health risk. Arsenic (As) is a predominant metalloid contaminant in abandoned mine area and its behavior has been influenced by various soil characteristics. Bioindicator can be a useful tool in terms of testing the extent to which they are uptaken by plants bioavailability. Eighteen soils near the mine tailings dam were collected to investigate the effect of As contamination on As absorption by Brassica juncea. The pH range of the experimental soils was between 4.90 and 8.55, and the total As concentrations were between 34 mg kg-1 and 3017 mg kg-1. The bioavailability of As was evaluated by Olsen method, and B. juncea was cultivated in eighteen soils for 3 weeks. Principal component analysis, correlation, and multiple regression analysis were performed to estimate a significant factor affecting As uptake by B. juncea. All statistical results indicated that As bioavailability in soil is the main factor affecting As uptake in root and shoot of B. juncea. Although translocation process, the amount of As in shoot was exponentially explained by As bioavailability in soil. This result suggests that the contamination and bioavailability of As can be confirmed only by analyzing the shoot of B. juncea, which is be easily found in environmental ecosystem, and implies the applicability of B. juncea as a bioindicator for the monitoring of As contamination and its behavior in soil ecosystem.

Intelligent Complementary Multi-Modal Fusion for Anomaly Surveillance and Security System.

Recently, security monitoring facilities have mainly adopted artificial intelligence (AI) technology to provide both increased security and improved performance. However, there are technical challenges in the pursuit of elevating system performance, automation, and security efficiency. In this paper, we proposed intelligent anomaly detection and classification based on deep learning (DL) using multi-modal fusion. To verify the method, we combined two DL-based schemes, such as (i) the 3D Convolutional AutoEncoder (3D-AE) for anomaly detection and (ii) the SlowFast neural network for anomaly classification. The 3D-AE can detect occurrence points of abnormal events and generate regions of interest (ROI) by the points. The SlowFast model can classify abnormal events using the ROI. These multi-modal approaches can complement weaknesses and leverage strengths in the existing security system. To enhance anomaly learning effectiveness, we also attempted to create a new dataset using the virtual environment in Grand Theft Auto 5 (GTA5). The dataset consists of 400 abnormal-state data and 78 normal-state data with clip sizes in the 8-20 s range. Virtual data collection can also supplement the original dataset, as replicating abnormal states in the real world is challenging. Consequently, the proposed method can achieve a classification accuracy of 85%, which is higher compared to the 77.5% accuracy achieved when only employing the single classification model. Furthermore, we validated the trained model with the GTA dataset by using a real-world assault class dataset, consisting of 1300 instances that we reproduced. As a result, 1100 data as the assault were classified and achieved 83.5% accuracy. This also shows that the proposed method can provide high performance in real-world environments.

Enrichment of Activated Fibroblasts as a Potential Biomarker for a Non-Durable Response to Anti-Tumor Necrosis Factor Therapy in Patients with Crohn's Disease.

We investigated whether the response to anti-tumor necrosis factor (anti-TNF) treatment varied according to inflammatory tissue characteristics in Crohn's disease (CD). Bulk RNA sequencing (RNA-seq) data were obtained from inflamed and non-inflamed tissues from 170 patients with CD. The samples were clustered based on gene expression profiles using principal coordinate analysis (PCA). Cellular heterogeneity was inferred using CiberSortx, with bulk RNA-seq data. The PCA results displayed two clusters of CD-inflamed samples: one close to (Inflamed_1) and the other far away (Inflamed_2) from the non-inflamed samples. Inflamed_1 was rich in anti-TNF durable responders (DRs), and Inflamed_2 was enriched in non-durable responders (NDRs). The CiberSortx results showed that the cell fraction of activated fibroblasts was six times higher in Inflamed_2 than in Inflamed_1. Validation with public gene expression datasets (GSE16879) revealed that the activated fibroblasts were enriched in NDRs over Next, we used DRs by 1.9 times pre-treatment and 7.5 times after treatment. Fibroblast activation protein (FAP) was overexpressed in the Inflamed_2 and was also overexpressed in the NDRs in both the RISK and GSE16879 datasets. The activation of fibroblasts may play a role in resistance to anti-TNF therapy. Characterizing fibroblasts in inflamed tissues at diagnosis may help to identify patients who are likely to respond to anti-TNF therapy.

The clinical outcome of hemicortical resection in extremity malignant bone tumors.

INTRODUCTION: Hemicortical resection is challenging when a huge fungating tumor is covering the osteotomy site. We report the clinical outcome of hemicortical resection and reconstruction for primary bone tumors, especially with high-grade histology and extensive circumferential involvement. MATERIALS AND METHODS: We retrospectively reviewed 44 patients (males, n = 18; females, n = 26) who underwent hemicortical resection from 2005 to 2014. RESULTS: The median follow-up period was 46.0 (23-178) months. Disease-specific, local recurrence-free, and metastasis-free survival rates of patients in the malignant group at 5 years were 96.6%, 84.5%, and 93.6%, respectively. Among 42 patients, there were local recurrences (n = 6), metastasis (n = 2), and death (n = 1). Surgical margin was an independent prognostic factor for local recurrence (hazard ratio = 5.7; p = 0.038). The recycled autograft and strut allograft groups did not show statistical difference in bone union. Failure rate was 31.8% and local recurrence was the most frequent, followed by infection. CONCLUSION: Hemicortical resection can be a feasible option for extremity malignant bone tumors. Regarding reconstruction, there were no difference between autograft and allograft in bone union rate. Surgical margin was an independent prognostic factor for local recurrence.

Effect of bioavailable arsenic fractions on the collembolan community in an old abandoned mine waste.

Mine waste from abandoned mines poses a risk to soil ecosystems due to the dispersion of arsenic (As) in the mine waste to the nearby soil environment. Because the bioavailability of As varies depending on the As chemical fraction and exposure conditions, chemical assessment of As fractions in soil around mine waste is essential to understand their impact on soil ecosystem. Here, six sites around the mine waste were selected for investigating toxic effects of As-contaminant soil on Collembola community. To measure the As chemical fraction in soil and bioavailability, Wenzel sequential extraction employed. Meanwhile, the collembolans that live in each sampling site were identified at the species level, and the characteristics and composition of the collembola community were investigated. The mobility fraction (F1 + F2 + F3; MF) was related to the risk to the collembolan community, and the adverse impact of high MF appeared to lead to a decrease in abundance, richness, and Shannon index. According to non-metric multidimensional scaling analysis, F1, F2, F3, and pH were shown as the significant factor explaining the NMDS space. Especially, the sampling site with the highest concentration of F3 showed statistically different species composition from the other sites. In the case of As-contaminated soil around the old mine waste, the toxic effects of the remaining F3 in soil, as well as that of F1 and F2, should be fully considered. This study suggested that collembolan community could be used for understanding the impact of bioavailable As fraction in the old abandoned mine area.

Constituents from Scutellaria barbata Inhibiting Nitric Oxide Production in LPS-Stimulated Microglial Cells.

The arial parts of Scutellaria barbata D. Don (Lamiaceae) efficiently inhibited NO production in BV2 microglial cells, and the active constituents were further isolated based on activity-guided isolation using silica-gel column chromatography, RP-C18 MPLC and prep-HPLC. As the results, 2 flavonoids including 6-methoxynaringenin (1) and 6-O-methylscutellarein (5), and 6 neo-clerodane diterpenes such as scutebarbatine W (2), scutebatas B (3), scutebarbatine B (4), scutebarbatine A (6), 6-O-nicotinolylscutebarbatine G (7), and scutebarbatine X (8) were isolated. The structures of these compounds were elucidated based on NMR and MS data, and the comparison of literature values. All the compounds except compound 7 inhibited NO production efficiently with IC50 values of lower than 50 µm. Particularly, compounds 1 and 8 were the most efficient with IC50 values of 25.8 and 27.4 µm, respectively. This is the first report suggesting the potential of S. barbata on the reduction of neuroinflammation.

Sesquiterpenoids from the Rhizomes of Curcuma phaeocaulis and Their Inhibitory Effects on LPS-Induced TLR4 Activation.

Two new guaiane-type (2, 6) and one new furanogermacrane-type (11) sesquiterpenoids have been isolated along with twelve known compounds from an EtOAc-soluble extract of Curcuma phaeocaulis rhizomes. The structures of the isolated compounds were elucidated using a combination of NMR, MS, and circular dichroism (CD) spectra. The inhibitory effects of each compound on lipopolysaccharide (LPS)-induced Toll-like receptor 4 (TLR4) activation in THP-1-Blue cells were assessed, and compound 4 showed more potent inhibitory activity against LPS-stimulated TLR4 activation.

Nelumbo Nucifera leaf extract attenuated pancreatic ß-cells toxicity induced by interleukin-1ß and interferon-γ, and increased insulin secrection of pancreatic ß-cells in streptozotocin-induced diabetic rats.

OBJECTIVE: To evaluate the effect of Nelumbo Nucifera leaf water extract (NNLE) on insulinoma (RIN) cells induced by interleukin-1ß (IL-1ß) and interferon-g (IFN-γ), and injured pancreatic ß-cells induced by Streptozotocin (STZ) in rats. METHODS: The anti-oxidative effects of NNLE were assessed using 1,1-diphenyl-2-picryl hydrazyl (DPPH) and nitric oxide (NO) scavenging assays. The inhibitory effect of NNLE on α-glucosidase and DPP (dipeptidyl peptidase)-IV was measured in vitro. Pancreatic ß-cell protective and insulin secretory effects were assessed, using IL-1ß and IFN-γ-induced rat RIN cells. STZ-induced diabetic rats were treated with 50, 100, and 400 mg/kg NNLE for 4 weeks. The effects of NNLE on blood glucose (BG), body weight (BW), and lipid profiles were measured. RESULTS: NNLE inhibited DPPH, NO, α-glucosidase, and DPP-IV which were directly linked to the function of ß-cells. Furthermore, NNLE protected RIN cells from toxicity induced by IL-1ß and IFN-γ, decreased NO production, and increased insulin secretion. NNLE caused a significant reduction in blood glucose, triglyceride (TG), total cholesterol (TC), blood urea nitrogen (BUN), and creatinine in STZ-induced diabetic rats. Furthermore, it significantly decreased BW loss in STZ-induced diabetic rats. CONCLUSION: Our results suggest that NNLE reduced the toxicity in insulinoma cells and increased insulin secretion in pancreatic ß-cells in STZ-induced diabetic rats.

Loss of ERß expression in papillary thyroid carcinoma is associated with recurrence in young female.

OBJECTIVES: We investigated the expression of oestrogen receptors (ERs) in papillary thyroid cancers (PTCs) and evaluated their prognostic role. METHODS: We enrolled 81 female patients who underwent thyroid surgery and had a confirmed diagnosis of PTC between 01 January 1995 and 31 December 1996. Data on clinicopathologic parameters were obtained from patients' medical records. Tissue paraffin blocks of these 81 patients were collected for immunohistochemistry for ERα and ERß. RESULTS: ERα expression was observed in only eight patients (9·9%). In contrast, ERß expression was positive in 36 (44·4%) patients. Total thyroidectomy (84·4% vs 61·1%, P = 0·017) and cervical lymph node metastasis (62·2% vs 22·2%, P = 0·000) were more frequent in the ERß-negative group than in the ERß-positive group. Among younger female patients (<45 years), the ERß-negative group showed a tendency towards more frequent recurrent or persistent disease than the ERß-positive group (42·3% vs 13·6%, P = 0·029). In contrast, the ERα-positive group showed more recurrent or persistent disease than the ERα-negative group in older female patients (100% vs 24·1%, P = 0·024). In multivariate analysis, ERß negativity, extrathyroidal invasion and radioactive iodine treatment were risk factors for recurrence in young female patients. CONCLUSION: Loss of ERß expression was associated with recurrence in young female PTC patients. This finding suggests that oestrogen might play a protective role in the progression of PTC via ERß, especially in young female patients.

Cardioprotective effect of fimasartan, a new angiotensin receptor blocker, in a porcine model of acute myocardial infarction.

Cardioprotective effect of fimasartan, a new angiotensin receptor blocker (ARB), was evaluated in a porcine model of acute myocardial infarction (MI). Fifty swine were randomized to group 1 (sham, n=10), group 2 (no angiotensin-converting enzyme inhibitor [ACEI] or ARB, n=10), group 3 (perindopril 2 mg daily, n=10), group 4 (valsartan 40 mg daily, n=10), or group 5 (fimasartan 30 mg daily, n=10). Acute MI was induced by occlusion of the left anterior descending artery for 50 min. Echocardiography, single photon emission computed tomography (SPECT), and F-18 fluorodeoxyglucose cardiac positron emission tomography (PET) were performed at baseline, 1 week, and 4 weeks. Iodine-123 meta-iodobenzylguanidine (MIBG) scan was done at 6 weeks for visualization of cardiac sympathetic activity. Left ventricular function and volumes at 4 weeks were similar between the 5 groups. No difference was observed in groups 2 to 5 in SPECT perfusion defect, matched and mismatched segments between SPECT and PET at 1 week and 4 weeks. MIBG scan showed similar uptake between the 5 groups. Pathologic analysis showed similar infarct size in groups 2 to 5. Infarct size reduction was not observed with use of fimasartan as well as other ACEI and ARB in a porcine model of acute MI.

Influence of amendments and aided phytostabilization on metal availability and mobility in Pb/Zn mine tailings.

A greenhouse experiment was conducted to evaluate the effect of four different amendments, bone mill, bottom ash, furnace slag, and red mud, as immobilizing agents and the plant species Miscanthus sinensis and Pteridium aquilinum in aided phytostabilization of Pb/Zn mine tailings. The effects of amendments and plants on the availability and mobility of heavy metals were evaluated using single extraction, sequential extraction, pore-water analysis, and determination of heavy metal concentrations in plants. The application of Fe-rich amendments significantly reduced the amount of soluble and extractable heavy metals in the tailings (p < 0.05). Furnace slag and M. sinensis reduced CaCl2-extractable heavy metals by 56-91%, red mud and P. aquilinum treatment was the most effective at decreasing bioaccessible Pb, reducing it to 34% of the total Pb. Compared to control, water soluble Cd, Cu, Pb, and Zn were reduced by 99, 99, 98, and 99%, respectively, in the red mud and P. aquilinum tailings. M. sinensis accumulated heavy metals mainly in the root, and had lower translocation factors compared with P. aquilinum. The results of this study suggest that M. sinensis can be used in aided phytostabilization for these types of mine tailings and Fe-rich amendments are effective for the in situ immobilization of metals.

The effectiveness of spent coffee grounds and its biochar on the amelioration of heavy metals-contaminated water and soil using chemical and biological assessments.

Spent coffee grounds (SCG) and charred spent coffee grounds (SCG-char) have been widely used to adsorb or to amend heavy metals that contaminate water or soil and their success is usually assessed by chemical analysis. In this work, the effects of SCG and SCG-char on metal-contaminated water and soil were evaluated using chemical and biological assessments; a phytotoxicity test using bok choy (Brassica campestris L. ssp. chinensis Jusl.) was conducted for the biological assessment. When SCG and SCG-char were applied to acid mine drainage, the heavy metal concentrations were decreased and the pH was increased. However, for SCG, the phytotoxicity increased because a massive amount of dissolved organic carbon was released from SCG. In contrast, SCG-char did not exhibit this phenomenon because any easily released organic matter was removed during pyrolysis. While the bioavailable heavy metal content decreased in soils treated with SCG or SCG-char, the phytotoxicity only rose after SCG treatment. According to our statistical methodology, bioavailable Pb, Cu and As, as well as the electrical conductivity representing an increase in organic content, affected the phytotoxicity of soil. Therefore, applying SCG during environment remediation requires careful biological assessments and evaluations of the efficiency of this remediation technology.

Pulmonary-vein-to-pulmonary-artery ratio can be utilized to evaluate myxomatous mitral valve disease progression in dogs.

OBJECTIVE: To evaluate the diagnostic value of pulmonary-vein-to-pulmonary-artery ratio (PV:PA) in dogs with myxomatous mitral valve degeneration (MMVD), classified according to the American College of Veterinary Internal Medicine (ACVIM) consensus guidelines. ANIMALS: 80 client-owned dogs with either MMVD (n = 65) or no cardiovascular disease (control group; n = 15) between August 5, 2020, and July 19, 2023. METHODS: This is a retrospective study. Dogs with MMVD were classified according to ACVIM consensus guidelines. Echocardiograms, thoracic radiographs, and other measurements needed in this study were reviewed in all dogs. Spearman correlation was used to determine the correlation between the PV:PA and the following variables: vertebral heart size, vertebral left atrial size, left-atrium-to-aorta ratio, normalized left ventricular internal diameter, and peak transmitral early diastolic velocity. Receiver operating characteristic (ROC) curve analysis was used to evaluate the value of PV:PA in distinguishing between stages B1 and B2 and stages B2 and C. RESULTS: All conventional indices showed correlations with PV:PA. The area under the ROC curve (AUC) for stages B1 and B2 was 0.83, and the cutoff value for differentiating stage B2 was 1.52. The AUC for stages B2 and C was 0.81, and the cutoff value for differentiating stage C was 2.09. CLINICAL RELEVANCE: PV:PA was significantly different between control and the stage B1 group, stage B1 and B2 group, and stage B2 and C group. PV:PA can be an index that can be used in evaluating MMVD dogs.

Loop-mediated isothermal amplification polymerase chain reaction in place of a modified Knott test in screening dogs for heartworm (Dirofilaria immitis) infection combined with antigen detection test.

OBJECTIVE: To improve the current recommendations for the diagnosis of canine heartworm (Dirofilaria immitis) disease. ANIMALS: Blood samples collected from 35 shelter dogs in the Republic of Korea. METHODS: Samples were tested for the presence of microfilaria using the modified Knott (MK) test and D immitis DNA using species-specific loop-mediated isothermal amplification (LAMP) PCR. The blood samples were additionally assessed for the presence of heartworm antigens using the Antigen Rapid Canine Heartworm AG Test Kit 2.0 (Bionote Co). The performance of the MK test and LAMP PCR was assessed through statistical analysis, with a paired McNemar test utilized for comparison. RESULTS: The heartworm antigen was detected in 28.5% of the subjects. Of the 10 positive animals, the MK test detected microfilaria in 4 of 35 (11.4%) animals, and LAMP PCR detected D immitis DNA in 6 of 35 (17.1%). The results of this study indicate that the LAMP PCR showed more positive results in samples compared to the conventional MK test. CLINICAL RELEVANCE: The D immitis-specific LAMP PCR assay has the potential to function as an alternative to current detection methods. It could complement the existing antigen detection tests in diagnosing canine heartworm infections.

Tuning the visible colour of octahedral manganese(III) phthalocyanines via axial ligand exchange.

A series of [PcMnL2]SbF6 complexes (Pc = phthalocyanine) was synthesized and structurally characterized by stripping the chloride from PcMnCl with AgSbF6 in o-dichlorobenzene and adding a range of donor ligands (L = THF, pyridine, p-dimethylaminopyridine (DMAP), Ph3PO, N-methylimidazole (MeIm), MeCN) to the resulting solution. Addition of or exposure to water where L = heterocyclic amines yielded µ-oxo complexes of the form [PcMnL]2O, which were structurally characterized for L = DMAP and MeIm. The [PcMnL2]SbF6 complexes have an increased solubility in organic solvents, where the axial ligands inhibit the characteristic ring π-π aggregation of PcM complexes. A variety of colours were observed (blue/green to red/purple), with Q-band absorptions (excluding the µ-oxo species) spanning from 715-761 nm and LMCT-bands from 497-574 nm. The combination of the ligand-induced absorption shifts coupled with their relative intensities in the visible region is responsible for the observed colour range and illustrates that facile ligand exchange is a useful tool in producing materials with a variety of colours from PcMnCl.

Evaluating Prediction Models with Hearing Handicap Inventory for the Elderly in Chronic Otitis Media Patients.

BACKGROUND: This retrospective, cross-sectional study aimed to assess the functional hearing capacity of individuals with Chronic Otitis Media (COM) using prediction modeling techniques and the Hearing Handicap Inventory for the Elderly (HHIE) questionnaire. This study investigated the potential of predictive models to identify hearing levels in patients with COM. METHODS: We comprehensively examined 289 individuals diagnosed with COM, of whom 136 reported tinnitus and 143 did not. This study involved a detailed analysis of various patient characteristics and HHIE questionnaire results. Logistic and Random Forest models were employed and compared based on key performance metrics. RESULTS: The logistic model demonstrated a slightly higher accuracy (73.56%), area under the curve (AUC; 0.73), Kappa value (0.45), and F1 score (0.78) than the Random Forest model. These findings suggest the superior predictive performance of the logistic model in identifying hearing levels in patients with COM. CONCLUSIONS: Although the AUC for the logistic regression did not meet the benchmark, this study highlights the potential for enhanced reliability and improved performance metrics using a larger dataset. The integration of prediction modeling techniques and the HHIE questionnaire shows promise for achieving greater diagnostic accuracy and refining intervention strategies for individuals with COM.

Lipoprotein lipase mediated fatty acid delivery and its impact in diabetic cardiomyopathy.

Although cardiovascular disease is the leading cause of diabetes-related death, its etiology is still not understood. The immediate change that occurs in the diabetic heart is altered energy metabolism where in the presence of impaired glucose uptake, glycolysis, and pyruvate oxidation, the heart switches to exclusively using fatty acids (FA) for energy supply. It does this by rapidly amplifying its lipoprotein lipase (LPL-a key enzyme, which hydrolyzes circulating lipoprotein-triglyceride to release FA) activity at the coronary lumen. An abnormally high capillary LPL could provide excess fats to the heart, leading to a number of metabolic, morphological, and mechanical changes, and eventually to cardiac disease. Unlike the initial response, chronic severe diabetes "turns off" LPL, this is also detrimental to cardiac function. In this review, we describe a number of post-translational mechanisms that influence LPL vesicle formation, actin cytoskeleton rearrangement, and transfer of LPL from cardiomyocytes to the vascular lumen to hydrolyze lipoprotein-triglyceride following diabetes. Appreciating the mechanism of how the heart regulates its LPL following diabetes should allow the identification of novel targets for therapeutic intervention, to prevent heart failure. This article is part of a Special Issue entitled Triglyceride Metabolism and Disease.

Potential Oral Microbial Markers for Differential Diagnosis of Crohn's Disease and Ulcerative Colitis Using Machine Learning Models.

Although gut microbiome dysbiosis has been associated with inflammatory bowel disease (IBD), the relationship between the oral microbiota and IBD remains poorly understood. This study aimed to identify unique microbiome patterns in saliva from IBD patients and explore potential oral microbial markers for differentiating Crohn's disease (CD) and ulcerative colitis (UC). A prospective cohort study recruited IBD patients (UC: n = 175, CD: n = 127) and healthy controls (HC: n = 100) to analyze their oral microbiota using 16S rRNA gene sequencing. Machine learning models (sparse partial least squares discriminant analysis (sPLS-DA)) were trained with the sequencing data to classify CD and UC. Taxonomic classification resulted in 4041 phylotypes using Kraken2 and the SILVA reference database. After quality filtering, 398 samples (UC: n = 175, CD: n = 124, HC: n = 99) and 2711 phylotypes were included. Alpha diversity analysis revealed significantly reduced richness in the microbiome of IBD patients compared to healthy controls. The sPLS-DA model achieved high accuracy (mean accuracy: 0.908, and AUC: 0.966) in distinguishing IBD vs. HC, as well as good accuracy (0.846) and AUC (0.923) in differentiating CD vs. UC. These findings highlight distinct oral microbiome patterns in IBD and provide insights into potential diagnostic markers.

Crystallization-based upcycling of iron oxyhydroxide for efficient arsenic capture in contaminated soils.

Arsenic (As)-contaminated soil inevitably exists in nature and has become a global challenge for a sustainable future. Current processes for As capture using natural and structurally engineered nanomaterials are neither scientifically nor economically viable. Here, we established a feasible strategy to enhance As-capture efficiency and ecosystem health by structurally reorganizing iron oxyhydroxide, a natural As stabilizer. We propose crystallization to reorganize FeOOH-acetate nanoplatelets (r-FAN), which is universal for either scalable chemical synthesis or reproduction from natural iron oxyhydroxide phases. The r-FAN with wide interlayer spacing immobilizes As species through a synergistic mechanism of electrostatic intercalation and surface chemisorption. The r-FAN rehabilitates the ecological fitness of As-contaminated artificial and mine soils, as manifested by the integrated bioassay results of collembolan and plants. Our findings will serve as a cornerstone for crystallization-based material engineering for sustainable environmental applications and for understanding the interactions between soil, nanoparticles, and contaminants.

A Machine Learning-Based Diagnostic Model for Crohn's Disease and Ulcerative Colitis Utilizing Fecal Microbiome Analysis.

Recent research has demonstrated the potential of fecal microbiome analysis using machine learning (ML) in the diagnosis of inflammatory bowel disease (IBD), mainly Crohn's disease (CD) and ulcerative colitis (UC). This study employed the sparse partial least squares discriminant analysis (sPLS-DA) ML technique to develop a robust prediction model for distinguishing among CD, UC, and healthy controls (HCs) based on fecal microbiome data. Using data from multicenter cohorts, we conducted 16S rRNA gene sequencing of fecal samples from patients with CD (n = 671) and UC (n = 114) while forming an HC cohort of 1462 individuals from the Kangbuk Samsung Hospital Healthcare Screening Center. A streamlined pipeline based on HmmUFOTU was used. After a series of filtering steps, 1517 phylotypes and 1846 samples were retained for subsequent analysis. After 100 rounds of downsampling with age, sex, and sample size matching, and division into training and test sets, we constructed two binary prediction models to distinguish between IBD and HC and CD and UC using the training set. The binary prediction models exhibited high accuracy and area under the curve (for differentiating IBD from HC (mean accuracy, 0.950; AUC, 0.992) and CD from UC (mean accuracy, 0.945; AUC, 0.988)), respectively, in the test set. This study underscores the diagnostic potential of an ML model based on sPLS-DA, utilizing fecal microbiome analysis, highlighting its ability to differentiate between IBD and HC and distinguish CD from UC.