Gene association analysis to determine the causal relationship between immune cells and juvenile idiopathic arthritis.

BACKGROUND: Juvenile idiopathic arthritis (JIA) is a type of chronic childhood arthritis with complex pathogenesis. Immunological studies have shown that JIA is an acquired self-inflammatory disease, involving a variety of immune cells, and it is also affected by genetic and environmental susceptibility. However, the precise causative relationship between the phenotype of immune cells and JIA remains unclear to date. The objective of our study is to approach this inquiry from a genetic perspective, employing a method of genetic association analysis to ascertain the causal relationship between immune phenotypes and the onset of JIA. METHODS: In this study, a two-sample Mendelian randomization (MR) analysis was used to select single nucleotide polymorphisms (SNPs) significantly associated with immune cells as instrumental variables to analyze the bidirectional causal relationship between 731 immune cells and JIA. There were four types of immune features (median fluorescence intensity (MFI), relative cellular (RC), absolute cellular (AC), and morphological parameters (MP)). Finally, the heterogeneity and horizontal reproducibility of the results were verified by sensitivity analysis, which ensured more robust results. RESULTS: We found that CD3 on CM CD8br was causally associated with JIA at the level of 0.05 significant difference (95% CI = 0.630 ~ 0.847, P = 3.33 × 10-5, PFDR = 0.024). At the significance level of 0.20, two immunophenotypes were causally associated with JIA, namely: HLA DR on CD14+ CD16- monocyte (95% CI = 0.633 ~ 0.884, P = 6.83 × 10-4, PFDR = 0.16) and HLA DR on CD14+ monocyte (95% CI = 0.627 ~ 0.882, P = 6.9 × 10-4, PFDR = 0.16). CONCLUSION: Our study assessed the causal effect of immune cells on JIA from a genetic perspective. These findings emphasize the complex and important role of immune cells in the pathogenesis of JIA and lay a foundation for further study of the pathogenesis of JIA.

A handheld isothermal fluorescence detector for duplex visualization of aquatic pathogens via enhanced one-pot LAMP-PfAgo assay.

The expansion of large-scale aquaculture has exacerbated the challenge of aquatic diseases, resulting in substantial economic losses annually. Currently, traditional laboratory-based diagnostic methods are time-consuming and costly, hindering on-site testing for individual farmers. We address this issue by developing a state-of-the-art handheld isothermal nucleic acid amplification device (WeD-1) capable of fluorescence tracking of reactions and integrating it with an enhanced one-pot Prokaryotic Argonaute based nucleic acid detection method, enabling duplex visual detection of aquatic pathogens. WeD-1 is portable, reusable, user-friendly, and cost-effective, offering real-time smartphone interaction and enabling real-time fluorescence observation during the reaction. The enhanced one-pot Loop-Mediated Isothermal Amplification (LAMP)-PfAgo method, incorporating paraffin-encapsulated lyophilized PfAgo protein, achieves precise target-specific cleavage, significantly enhancing multiplex nucleic acid detection. This innovation streamlines on-site testing, negating the need for specialized laboratory conditions while ensuring an aerosol-free system. With newly developed and highly sensitive LAMP primer sets, our compact WeD-1/LAMP-PfAgo nucleic acid rapid testing system exhibits remarkable sensitivity, readily detecting aquatic pathogens with naked eyes from rapidly prepared fish and shrimp samples within 40 min, even when the Ct values are as high as 34.

A two-branch cloud detection algorithm based on the fusion of a feature enhancement module and Gaussian mixture model.

Accurate cloud detection is an important step to improve the utilization rate of remote sensing (RS). However, existing cloud detection algorithms have difficulty in identifying edge clouds and broken clouds. Therefore, based on the channel data of the Himawari-8 satellite, this work proposes a method that combines the feature enhancement module with the Gaussian mixture model (GMM). First, statistical analysis using the probability density functions (PDFs) of spectral data from clouds and underlying surface pixels was conducted, selecting cluster features suitable for daytime and nighttime. Then, in this work, the Laplacian operator is introduced to enhance the spectral features of cloud edges and broken clouds. Additionally, enhanced spectral features are input into the debugged GMM model for cloud detection. Validation against visual interpretation shows promising consistency, with the proposed algorithm outperforming other methods such as RF, KNN and GMM in accuracy metrics, demonstrating its potential for high-precision cloud detection in RS images.

Manual Therapy for a Chronic Non-Specific Low Back Pain Rat Model.

Chronic low back pain (CLBP) is a highly prevalent condition worldwide and a major cause of disability. The majority of patients with CLBP are diagnosed with chronic non-specific low back pain (CNLBP) due to an unknown pathological cause. Manual therapy (MT) is an integral aspect of traditional Chinese medicine and is recognized as Tuina in China. It involves techniques like bone-setting and muscle relaxation manipulation. Despite its clinical efficacy in treating CNLBP, the underlying mechanisms of MT remain unclear. In animal experiments aimed at investigating these mechanisms, one of the main challenges is achieving normative MT on CNLBP model rats. Improving the stability of finger strength is a key issue in MT. To address this technical limitation, a standardized procedure for MT on CNLBP model rats is presented in this study. This procedure significantly enhances the stability of MT with the hands and alleviates common problems associated with immobilizing rats during MT. The findings of this study are of reference value for future experimental investigations of MT.

Communication-Efficient Accurate Statistical Estimation.

When the data are stored in a distributed manner, direct applications of traditional statistical inference procedures are often prohibitive due to communication costs and privacy concerns. This paper develops and investigates two Communication-Efficient Accurate Statistical Estimators (CEASE), implemented through iterative algorithms for distributed optimization. In each iteration, node machines carry out computation in parallel and communicate with the central processor, which then broadcasts aggregated information to node machines for new updates. The algorithms adapt to the similarity among loss functions on node machines, and converge rapidly when each node machine has large enough sample size. Moreover, they do not require good initialization and enjoy linear converge guarantees under general conditions. The contraction rate of optimization errors is presented explicitly, with dependence on the local sample size unveiled. In addition, the improved statistical accuracy per iteration is derived. By regarding the proposed method as a multi-step statistical estimator, we show that statistical efficiency can be achieved in finite steps in typical statistical applications. In addition, we give the conditions under which the one-step CEASE estimator is statistically efficient. Extensive numerical experiments on both synthetic and real data validate the theoretical results and demonstrate the superior performance of our algorithms.

Design, synthesis, biological evaluation of urea substituted 1,2,5-oxadiazole-3-carboximidamides as novel indoleamine 2,3-dioxygenase-1 (IDO1) inhibitors.

Indoleamine 2,3-dioxygenase-1 (IDO1) has been considered as an attractive target for oncology immunotherapy due to its immunosuppressive effects on the tumor microenvironment. The most advanced IDO1 inhibitor epacadostat in combination with anti-PD-1 antibody failed to show desirable objective response. Epacadostat is now reevaluated in phase III clinical trials, but its pharmacokinetic (PK) properties are unsatisfactory. To further unravel the antitumor efficacy of IDO1 inhibitors, we designed a series of epacadostat analogues by introducing various urea-containing side chains. In particular, the most active compound 3 showed superior inhibitory potency against recombinant hIDO1 and hIDO1 in HeLa cells induced by interferon γ (IFNγ) relative to epacadostat (3, biochemical hIDO1 IC50 = 67.4 nM, HeLa hIDO1 IC50 = 17.6 nM; epacadostat, biochemical hIDO1 IC50 = 75.9 nM, HeLa hIDO1 IC50 = 20.6 nM). Moreover, compound 3 exhibited improved physicochemical properties and rat PK profile with better oral exposure and bioavailability compared with epacadostat. Importantly, this compound exhibited comparable antitumor efficacy with epacadostat in LLC syngeneic xenograft models. Hence, compound 3 represents a promising lead compound for discovery of more effective IDO1 inhibitors.

Effectiveness and safety of acupuncture and moxibustion for chronic prostatitis: A protocol for an overview of systematic reviews and meta-analysis.

BACKGROUND: Chronic prostatitis (CP) refers to a disease characterized by local pain and discomfort, urination discomfort, and quality of life. Acupuncture (ACU) and moxibustion are widely used in the treatment of CP, and the curative effect is satisfactory. Several systematic reviews (SRs) and meta-analyzes have reported the effectiveness of ACU and moxibustion in treating patients with CP. However, the evidence is not systematically integrated. This overview aims to integrate and evaluate the reliability of these SRs and the evidence generated from the ACU and moxibustion for CP meta-analysis. METHODS: We will make a comprehensive retrieval in seven databases as following: Embase, Cochrane Library, Pubmed, Chinese databases SinoMed (previously called the Chinese Biomedical Database), Chinese National Knowledge Infrastructure (CNKI), Chinese Scientific Journals Database (VIP), and Wanfang Data (WF). The time is limited from the construction of the library to May 2021. We will use the Assessment of Multiple Systematic Reviews-2 (AMSTAR-2) tool to evaluate methodological quality. Preferred Reporting Items for Systematic Reviews and Meta-analysis Protocols (PRISMA-P) will be used in the report checklist to assess the quality of reports in the study. The GRADE will be used to evaluate the included SRs and meta-analysis. Our reviewers will conduct SRs, qualification evaluation, data extraction, methodological quality and evidence quality screening in pairs. The outcomes of interest include: NIH-Chronic Prostatitis Symptom Index (NIH-CPSI), effective rate, other CP symptom scales, EPS-WBC, and adverse events. Evidence will be combined based on patient subgroups and results where appropriate. RESULTS: The results will be published in a peer-reviewed journal. TRIAL REGISTRATION NUMBER: INPLASY202150018. CONCLUSION: This overview will provide comprehensive evidence of ACU and moxibustion for patients with CP.

Robust high dimensional factor models with applications to statistical machine learning.

Factor models are a class of powerful statistical models that have been widely used to deal with dependent measurements that arise frequently from various applications from genomics and neuroscience to economics and finance. As data are collected at an ever-growing scale, statistical machine learning faces some new challenges: high dimensionality, strong dependence among observed variables, heavy-tailed variables and heterogeneity. High-dimensional robust factor analysis serves as a powerful toolkit to conquer these challenges. This paper gives a selective overview on recent advance on high-dimensional factor models and their applications to statistics including Factor-Adjusted Robust Model selection (FarmSelect) and Factor-Adjusted Robust Multiple testing (FarmTest). We show that classical methods, especially principal component analysis (PCA), can be tailored to many new problems and provide powerful tools for statistical estimation and inference. We highlight PCA and its connections to matrix perturbation theory, robust statistics, random projection, false discovery rate, etc., and illustrate through several applications how insights from these fields yield solutions to modern challenges. We also present far-reaching connections between factor models and popular statistical learning problems, including network analysis and low-rank matrix recovery.

Factor-Adjusted Regularized Model Selection.

This paper studies model selection consistency for high dimensional sparse regression when data exhibits both cross-sectional and serial dependency. Most commonly-used model selection methods fail to consistently recover the true model when the covariates are highly correlated. Motivated by econometric and financial studies, we consider the case where covariate dependence can be reduced through the factor model, and propose a consistency strategy named Factor-Adjusted Regularized Model Selection (FarmSelect). By learning the latent factors and idiosyncratic components and using both of them as predictors, FarmSelect transforms the problem from model selection with highly correlated covariates to that with weakly correlated ones via lifting. Model selection consistency, as well as optimal rates of convergence, are obtained under mild conditions. Numerical studies demonstrate the nice finite sample performance in terms of both model selection and out-of-sample prediction. Moreover, our method is flexible in the sense that it pays no price for weakly correlated and uncorrelated cases. Our method is applicable to a wide range of high dimensional sparse regression problems. An R-package FarmSelect is also provided for implementation.

Integrated Avoid Collision Control of Autonomous Vehicle Based on Trajectory Re-Planning and V2V Information Interaction.

An integrated longitudinal-lateral control method is proposed for autonomous vehicle trajectory tracking and dynamic collision avoidance. A method of obstacle trajectory prediction is proposed, in which the trajectory of the obstacle is predicted and the dynamic solution of the reference trajectory is realized. Aiming at the lane changing scene of autonomous vehicles driving in the same direction and adjacent lanes, a trajectory re-planning motion controller with the penalty function is designed. The reference trajectory parameterized output of local reprogramming is realized by using the method of curve fitting. In the framework of integrated control, Fuzzy adaptive (proportional-integral) PI controller is proposed for longitudinal velocity tracking. The selection and control of controller and velocity are realized by logical threshold method; A model predictive control (MPC) with vehicle-to-vehicle (V2V) information interaction modular and the driver characteristics is proposed for direction control. According to the control target, the objective function and constraints of the controller are designed. The proposed method's performance in different scenarios is verified by simulation. The results show that the autonomous vehicles can avoid collision and have good stability.

Relationship between the Electrical Characteristics of Molecules and Fast Streamers in Ester Insulation Oil.

The effects of C=C, ester and ß-H groups on the ionization potential (IP) and electron affinity (EA) of molecules in natural ester insulation oil were investigated by density functional theory (DFT). The major contribution to the highest occupied molecular orbital (HOMO) comes from the carbon atoms adjacent to C=C. Thus, the IPs of triglycerides decrease as the number of C=C double bonds increases. The C=C in alkanes may also lower the IP. However, the ß-H in triglycerides has little effect on the IP, and C=C and ß-H have only a small effect on the EAs of the triglycerides because of the major contributions of atoms near the ester group in triglycerides to the lowest unoccupied molecular orbital (LUMO). This study calculated the IPs of 53 kinds of molecules in FR3, which are significantly lower compared with those of molecules in mineral oil (MO) and trimethylolpropane triester without C=C. However, the lightning impulse breakdown voltage (LI Vb) of trimethylolpropane triester is still significantly lower than that of MO at the large gap. Therefore, the transition from slow to fast streamers under low lighting impulse voltage is determined by the ester group rather than by C=C and ß-H. The ester group may attract more electrons, impacting itself more compared to alkane in MO and facilitating the transition from slow to fast streamers.

ENTRYWISE EIGENVECTOR ANALYSIS OF RANDOM MATRICES WITH LOW EXPECTED RANK.

Recovering low-rank structures via eigenvector perturbation analysis is a common problem in statistical machine learning, such as in factor analysis, community detection, ranking, matrix completion, among others. While a large variety of bounds are available for average errors between empirical and population statistics of eigenvectors, few results are tight for entrywise analyses, which are critical for a number of problems such as community detection. This paper investigates entrywise behaviors of eigenvectors for a large class of random matrices whose expectations are low-rank, which helps settle the conjecture in Abbe et al. (2014b) that the spectral algorithm achieves exact recovery in the stochastic block model without any trimming or cleaning steps. The key is a first-order approximation of eigenvectors under the ℓ ∞ norm: u k ≈ A u k * λ k * , where {u k } and { u k * } are eigenvectors of a random matrix A and its expectation E A , respectively. The fact that the approximation is both tight and linear in A facilitates sharp comparisons between u k and u k * . In particular, it allows for comparing the signs of u k and u k * even if ‖ u k - u k * ‖ ∞ is large. The results are further extended to perturbations of eigenspaces, yielding new ℓ ∞-type bounds for synchronization ( ℤ 2 -spiked Wigner model) and noisy matrix completion.

Distributed estimation of principal eigenspaces.

Principal component analysis (PCA) is fundamental to statistical machine learning. It extracts latent principal factors that contribute to the most variation of the data. When data are stored across multiple machines, however, communication cost can prohibit the computation of PCA in a central location and distributed algorithms for PCA are thus needed. This paper proposes and studies a distributed PCA algorithm: each node machine computes the top K eigenvectors and transmits them to the central server; the central server then aggregates the information from all the node machines and conducts a PCA based on the aggregated information. We investigate the bias and variance for the resulting distributed estimator of the top K eigenvectors. In particular, we show that for distributions with symmetric innovation, the empirical top eigenspaces are unbiased and hence the distributed PCA is "unbiased". We derive the rate of convergence for distributed PCA estimators, which depends explicitly on the effective rank of covariance, eigen-gap, and the number of machines. We show that when the number of machines is not unreasonably large, the distributed PCA performs as well as the whole sample PCA, even without full access of whole data. The theoretical results are verified by an extensive simulation study. We also extend our analysis to the heterogeneous case where the population covariance matrices are different across local machines but share similar top eigen-structures.

SPECTRAL METHOD AND REGULARIZED MLE ARE BOTH OPTIMAL FOR TOP-K RANKING.

This paper is concerned with the problem of top-K ranking from pairwise comparisons. Given a collection of n items and a few pairwise comparisons across them, one wishes to identify the set of K items that receive the highest ranks. To tackle this problem, we adopt the logistic parametric model - the Bradley-Terry-Luce model, where each item is assigned a latent preference score, and where the outcome of each pairwise comparison depends solely on the relative scores of the two items involved. Recent works have made significant progress towards characterizing the performance (e.g. the mean square error for estimating the scores) of several classical methods, including the spectral method and the maximum likelihood estimator (MLE). However, where they stand regarding top-K ranking remains unsettled. We demonstrate that under a natural random sampling model, the spectral method alone, or the regularized MLE alone, is minimax optimal in terms of the sample complexity - the number of paired comparisons needed to ensure exact top-K identification, for the fixed dynamic range regime. This is accomplished via optimal control of the entrywise error of the score estimates. We complement our theoretical studies by numerical experiments, confirming that both methods yield low entrywise errors for estimating the underlying scores. Our theory is established via a novel leave-one-out trick, which proves effective for analyzing both iterative and non-iterative procedures. Along the way, we derive an elementary eigenvector perturbation bound for probability transition matrices, which parallels the Davis-Kahan Θ theorem for symmetric matrices. This also allows us to close the gap between the l 2 error upper bound for the spectral method and the minimax lower limit.

Effect of Sputtering Temperature on Fluorocarbon Films: Surface Nanostructure and Fluorine/Carbon Ratio.

In this work, fluorocarbon film was deposited on silicon (P/100) substrate using polytetrafluoroethylene (PTFE) as target material at elevated sputtering temperature. Field emission scanning electron microscopy (FESEM), atomic force microscopy (AFM), Raman spectroscopy and X-ray photoelectron spectroscopy (XPS) were employed to investigate the surface morphology as well as structural and chemical compositions of the deposited film. The surface energy, as well as the polar and dispersion components, were determined by water contact angle (WCA) measurement. The experimental results indicated that increasing sputtering temperature effectively led to higher deposition rate, surface roughness and WCA of the film. It was found that the elevated temperature contributed to increasing saturated components (e.g., C-F2 and C-F3) and decreasing unsaturated components (e.g., C-C and C-CF), thus enhancing the fluorine-to-carbon (F/C) ratio. The results are expected aid in tailoring the design of fluorocarbon films for physicochemical properties.

Screening of schizophrenia associated miRNAs and the regulation of miR-320a-3p on integrin ß1.

Schizophrenia is one of the most severe chronic psychiatric disorders, which lacks of objective and effective diagnosis and observation indicators.In this work, the serum miRNA profiles of schizophrenic patients were analyzed. Targets of abnormal miRNAs, and their regulatory mechanisms were studied. A miRNA array was used to analyze the serum from 3 schizophrenic patients without treatment, 3 clinically cured patients and 3 healthy controls. The findings from the array were confirmed by real-time PCR in a larger cohort, including 59 patients and 60 healthy controls. The candidate miRNAs were analyzed using bioinformatics tools. Their potential targets were studied through in vitro cellular experiments.MiR-320a-3p and miR-320b were found to be down-regulated in patients compared with cured patients and controls in the miRNA array, which was also confirmed by real-time PCR in the larger cohort. Integrin ß1 (ITG ß1) was found to be one of the targets of miR-320a-3p. An enzyme-linked immune sorbent assay demonstrated that the ITG ß1 concentration increased significantly in the patients' serum, and the in vitro study confirmed that miR-320a-3p targeted the 3' UTR of ITG ß1 mRNA and reduced its expression.Our results demonstrated that the regulatory effect of miR-320a-3p on its target ITG ß1 might play an important role in schizophrenia pathogenesis, which could be a potential pathway for schizophrenia diagnosis and therapy.

Platelet proteomics in diagnostic differentiation of primary immune thrombocytopenia using SELDI-TOF-MS.

BACKGROUND: Primary immune thrombocytopenic purpura (pITP) is defined as isolated autoimmune thrombocytopenia with idiopathic low platelet count, normal bone marrow, and unexplained causes of thrombocytopenia. Currently there is no definite criterion for ITP diagnosis. METHODS: We conducted proteomic screen of patients with pITP, secondary immune thrombocytopenia (sITP), and healthy controls using surface-enhanced laser desorption/ionization time-of-flight mass spectrometry (SELDI-TOF-MS). The proteomic profiles were obtained from platelet lysate samples of 82 healthy adult controls, 64 pITP, and 70 sITP patients, from which we screened marker proteins with significant differences, and constructed a diagnosis model using the artificial neural network (ANN) technique. RESULTS: We identified 6 marker proteins in the platelet lysates of pITP patients. This diagnosis method differentiated pITP patients from sITP effectively with a sensitivity of 96.9% (31/32), a specificity of 71.0% (54/76), and the area under the ROC curve of 0.864 in the training set, and a sensitivity of 87.5% (28/32), a specificity of 69.7% (53/76), and a positive predictive value of 75.0% (81/108) in the test set. CONCLUSION: The artificial neural network model based on platelet protein profiling established a potential pITP diagnosis platform.

Protein Biomarkers in Serum of Patients with Schizophrenia.

This study was devised to identify potential biomarkers of schizophrenia (SP) using proteomics techniques. We obtained 44 serum specimens from patients with SP, 26 specimens from patients with depression, and 40 specimens from healthy controls. Immobilized metal affinity capture protein chips (IMAC30) and surface-enhanced laser desorption-ionization time-of-flight mass spectrometry were used to isolate and obtain mass spectrometric data of differentially expressed serum proteins. The sequences of the peaks discrepant among the study groups were obtained using matrix-assisted laser desorption/ionization mass spectrometry and proteins identified using Mascot database. In the SP group, there were 91 protein peaks that were different from other study groups at the p value of <0.05 and 54 peaks different at the p value of <0.01. Two protein peaks at the mass-to-charge ratio of 1,207.41 and 1,466.78 were markedly different among the study groups, with the lowest expression in specimens from patients with SP. The amino acid sequences were, respectively, Glu-Gly-Asp-Phe-Leu-Ala-Glu-Gly-Gly-Gly-Val-Arg (EGDFLAEGGGVR) and Asp-Ser-Gly-Glu-Gly-Asp-Phe-Leu-Ala-Glu-Gly-Gly-Gly-Val-Arg (DSGEGDFLAEGGGVR). These proteins were identified as the N-terminal fragments of fibrinogen. In conclusion, these biomarker proteins may be useful for molecular diagnosis of SP.

MicroRNAs in body fluids as biomarkers for non-small cell lung cancer: a systematic review.

Non-small cell lung cancer (NSCLC) is one of the most common life-threatening malignant tumors. A test for early diagnosis of NSCLC needs to be not too invasive and not too heavy a burden for weakened patients. A series of studies reported various microRNAs (miRNAs) could be novel serum biomarkers for NSCLC. However, the diagnostic ability of different miRNA biomarkers varies among the reports. The goal of this study was to perform a systematic review to examine the effect of miRNAs on NSCLC-related outcomes. We systematically searched The Cochrane Central Register of Controlled Trials, MEDLINE, Pub Med, EMBASE, the Chinese Biomedical Literature Database, the China Academic Journals Full-text Database, and the Chinese Scientific Journals Database for potential studies. Studies were included if they were related to miRNAs, NSCLC, and reported diagnostic outcomes. Diagnostic values analysis was used to summarize the overall test performance of miRNAs. 13 studies were included in this systematic review. The ranges of sensitivity (SEN) and specificity (SPE) of diagnosis model with miRNAs as identifying NSCLC were 0.69˜1.00 and 0.66˜1.00, respectively. The overall area under the curve (AUC) value of summary receiver operating characteristic (SROC) curve was 0.9151. The ranges of positive likelihood ratio (PLR) and negative likelihood ratio (NLR) were 2.33˜24.75 and 0.010.40, respectively. The range of diagnostic odds ratio (DOR) was 6.52˜983.38. The current evidence indicates that miRNAs in body fluids show high accuracy in identifying NSCLC, and could be a useful screening tool for diagnosing NSCLC patients.

[Diagnosis model of idiopathic thrombocytopenic purpura based on platelet differential proteome].

This study was purposed to establish a new quick and simple diagnostic method with high sensitivity and good specificity for idiopathic thrombocytopenic purpura (ITP) and to evaluate its significance. 240 platelet lysates (from patients with ITP, leukemia, MDS, and healthy adults, each of 60 cases) were randomly assigned to training set (120 cases) or validation set (120 cases), all of them were detected by surface enhanced laser desorption ionization time of flight mass spectrometry (SELDI-TOF-MS), in order to identify the differentially expressed protein, the diagnostic model was established by means of artificial neural network (ANN), and was validated by blind test with SPSS 17.0. The results showed that 5 marked proteins significantly differentially expressed (P < 0.01), m/z of highly expressed proteins were 2234.30, 3476.36, and 7526.29, m/z of low expressed proteins were 4990.02 and 5152.39, respectively. The sensitivity and specificity of diagnostic model were 80.6% and 77.3% respectively. The area under the ROC curve consisting of the output value of artificial neura1 network was 0.837. Efficacy of the model was validated by means of blinded test. It is concluded that the ANN model is useful for clinical diagnosis of ITP on the basis of platelet protein fingerprint spectrum.