RESUMO
Spatial transcriptomic (ST) clustering employs spatial and transcription information to group spots spatially coherent and transcriptionally similar together into the same spatial domain. Graph convolution network (GCN) and graph attention network (GAT), fed with spatial coordinates derived adjacency and transcription profile derived feature matrix are often used to solve the problem. Our proposed method STGIC (spatial transcriptomic clustering with graph and image convolution) is designed for techniques with regular lattices on chips. It utilizes an adaptive graph convolution (AGC) to get high quality pseudo-labels and then resorts to dilated convolution framework (DCF) for virtual image converted from gene expression information and spatial coordinates of spots. The dilation rates and kernel sizes are set appropriately and updating of weight values in the kernels is made to be subject to the spatial distance from the position of corresponding elements to kernel centers so that feature extraction of each spot is better guided by spatial distance to neighbor spots. Self-supervision realized by Kullback-Leibler (KL) divergence, spatial continuity loss and cross entropy calculated among spots with high confidence pseudo-labels make up the training objective of DCF. STGIC attains state-of-the-art (SOTA) clustering performance on the benchmark dataset of 10x Visium human dorsolateral prefrontal cortex (DLPFC). Besides, it's capable of depicting fine structures of other tissues from other species as well as guiding the identification of marker genes. Also, STGIC is expandable to Stereo-seq data with high spatial resolution.
Assuntos
Perfilação da Expressão Gênica , Transcriptoma , Humanos , Transcriptoma/genética , Benchmarking , Análise por Conglomerados , EntropiaRESUMO
For decades, it has been difficult for small-scale legged robots to conquer challenging environments. To solve this problem, we propose the introduction of a bioinspired soft spine into a small-scale legged robot. By capturing the motion mechanism of rat erector spinae muscles and vertebrae, we designed a cable-driven centrally symmetric soft spine under limited volume and integrated it into our previous robotic rat SQuRo. We called this newly updated robot SQuRo-S. Because of the coupling compliant spine bending and leg locomotion, the environmental adaptability of SQuRo-S significantly improved. We conducted a series of experiments on challenging environments to verify the performance of SQuRo-S. The results demonstrated that SQuRo-S crossed an obstacle of 1.07 body height, thereby outperforming most small-scale legged robots. Remarkably, SQuRo-S traversed a narrow space of 0.86 body width. To the best of our knowledge, SQuRo-S is the first quadruped robot of this scale that is capable of traversing a narrow space with a width smaller than its own width. Moreover, SQuRo-S demonstrated stable walking on mud-sand, pipes, and slopes (20°), and resisted strong external impact and repositioned itself in various body postures. This work provides a new paradigm for enhancing the flexibility and adaptability of small-scale legged robots with spine in challenging environments, and can be easily generalized to the design and development of legged robots with spine of different scales.
Assuntos
Procedimentos Cirúrgicos Robóticos , Robótica , Animais , Ratos , Locomoção/fisiologia , Caminhada , Coluna VertebralRESUMO
Sleep staging is crucial for assessing sleep quality and diagnosing sleep disorders. Recent advances in deep learning methods with electroencephalogram (EEG) signals have shown remarkable success in automatic sleep staging. However, the use of deeper neural networks may lead to the issues of gradient disappearance and explosion, while the non-stationary nature and low signal-to-noise ratio of EEG signals can negatively impact feature representation. To overcome these challenges, we proposed a novel lightweight sequence-to-sequence deep learning model, 1D-ResNet-SE-LSTM, to classify sleep stages into five classes using single-channel raw EEG signals. Our proposed model consists of two main components: a one-dimensional residual convolutional neural network with a squeeze-and-excitation module to extract and reweight features from EEG signals, and a long short-term memory network to capture the transition rules among sleep stages. In addition, we applied the weighted cross-entropy loss function to alleviate the class imbalance problem. We evaluated the performance of our model on two publicly available datasets; Sleep-EDF Expanded consists of 153 overnight PSG recordings collected from 78 healthy subjects and ISRUC-Sleep includes 100 PSG recordings collected from 100 subjects diagnosed with various sleep disorders, and obtained an overall accuracy rate of 86.39% and 81.97%, respectively, along with corresponding macro average F1-scores of 81.95% and 79.94%. Our model outperforms existing sleep staging models in terms of overall performance metrics and per-class F1-scores for several sleep stages, particularly for the N1 stage, where it achieves F1-scores of 59.00% and 55.53%. The kappa coefficient is 0.812 and 0.766 for the Sleep-EDF Expanded and ISRUC-Sleep datasets, respectively, indicating strong agreement with certified sleep experts. We also investigated the effect of different weight coefficient combinations and sequence lengths of EEG epochs used as input to the model on its performance. Furthermore, the ablation study was conducted to evaluate the contribution of each component to the model's performance. The results demonstrate the effectiveness and robustness of the proposed model in classifying sleep stages, and highlights its potential to reduce human clinicians' workload, making sleep assessment and diagnosis more effective. However, the proposed model is subject to several limitations. Firstly, the model is a sequence-to-sequence network, which requires input sequences of EEG epochs. Secondly, the weight coefficients in the loss function could be further optimized to balance the classification performance of each sleep stage. Finally, apart from the channel attention mechanism, incorporating more advanced attention mechanisms could enhance the model's effectiveness.
RESUMO
In this paper, we make full advantage of the information correlation of subaperture images and propose a new super-resolution (SR) reconstruction method based on spatiotemporal correlation to achieve SR reconstruction for light-field images. Meanwhile, the offset compensation method based on optical flow and spatial transformer network is designed to realize accurate compensation between adjacent light-field subaperture images. After that, the obtained light-field images with high resolution are combined with the self-designed system based on phase similarity and SR reconstruction to realize accurate 3D reconstruction of a structured light field. Finally, experimental results demonstrate the validity of the proposed method to perform accurate 3D reconstruction of light-field images from the SR data. Generally, our method makes full use of the redundant information between different subaperture images, hides the upsampling process in the convolution, provides more sufficient information, and reduces time-consuming procedures, which is more efficient to realize the accurate 3D reconstruction of light-field images.
RESUMO
BACKGROUND: A growing body of research suggests that the use of computerized decision support systems can better guide disease treatment and reduce the use of social and medical resources. Artificial intelligence (AI) technology is increasingly being used in medical decision-making systems to obtain optimal dosing combinations and improve the survival rate of sepsis patients. To meet the real-world requirements of medical applications and make the training model more robust, we replaced the core algorithm applied in an AI-based medical decision support system developed by research teams at the Massachusetts Institute of Technology (MIT) and IMPERIAL College London (ICL) with the deep deterministic policy gradient (DDPG) algorithm. The main objective of this study was to develop an AI-based medical decision-making system that makes decisions closer to those of professional human clinicians and effectively reduces the mortality rate of sepsis patients. METHODS: We used the same public intensive care unit (ICU) dataset applied by the research teams at MIT and ICL, i.e., the Multiparameter Intelligent Monitoring in Intensive Care III (MIMIC-III) dataset, which contains information on the hospitalizations of 38,600 adult sepsis patients over the age of 15. We applied the DDPG algorithm as a strategy-based reinforcement learning approach to construct an AI-based medical decision-making system and analyzed the model results within a two-dimensional space to obtain the optimal dosing combination decision for sepsis patients. RESULTS: The results show that when the clinician administered the exact same dose as that recommended by the AI model, the mortality of the patients reached the lowest rate at 11.59%. At the same time, according to the database, the baseline mortality rate of the patients was calculated as 15.7%. This indicates that the patient mortality rate when difference between the doses administered by clinicians and those determined by the AI model was zero was approximately 4.2% lower than the baseline patient mortality rate found in the dataset. The results also illustrate that when a clinician administered a different dose than that recommended by the AI model, the patient mortality rate increased, and the greater the difference in dose, the higher the patient mortality rate. Furthermore, compared with the medical decision-making system based on the Deep-Q Learning Network (DQN) algorithm developed by the research teams at MIT and ICL, the optimal dosing combination recommended by our model is closer to that given by professional clinicians. Specifically, the number of patient samples administered by clinicians with the exact same dose recommended by our AI model increased by 142.3% compared with the model based on the DQN algorithm, with a reduction in the patient mortality rate of 2.58%. CONCLUSIONS: The treatment plan generated by our medical decision-making system based on the DDPG algorithm is closer to that of a professional human clinician with a lower mortality rate in hospitalized sepsis patients, which can better help human clinicians deal with complex conditional changes in sepsis patients in an ICU. Our proposed AI-based medical decision-making system has the potential to provide the best reference dosing combinations for additional drugs.
Assuntos
Inteligência Artificial , Sepse , Adulto , Humanos , Algoritmos , Cuidados Críticos/métodos , Unidades de Terapia Intensiva , Sepse/tratamento farmacológicoRESUMO
Background: Cardiovascular disease (CVD) is the leading course of disease-related death in both developed and developing countries. Atherosclerosis is main pathology of CVD, and its severity is thought to be related to trimethylamine N-oxide (TMAO) level in plasma. Therefore, it is necessary to deeply understand the synergistic patterns between TMAO and other contribution variables to atherosclerosis, allowing for effective and timely monitoring or intervention. Methods: A total of 359 participants were recruited in our study, including 190 atherosclerosis patients, 82 MI or stroke patients, 68 non-atherosclerosis controls and 19 healthy controls. Information on their risk associated with atherosclerosis and plasma TMAO concentration were collected. LASSO regression, multivariate analysis and univariate analysis were then performed to confirm the correlation between TMAO level and risk factors of atherosclerosis. Results: Compared to patients and non-atherosclerosis controls, healthy participants had a normal BMI range (lower than 24), lower triglyceride concentration, and healthy lifestyle habits (no smoking and low salt diet). However, under backgrounds of statins treatment and balanced dietary preferences, TMAO levels were not significantly different among patients, non-atherosclerosis controls and healthy controls. Using LASSO regression model, four indicators was identified to have contribution to TMAO levels, including diabetes, atherosclerosis, low-density lipoprotein and total cholesterol. Subsequent univariate analysis further confirmed that the presence or absence of diabetes had a decisive effect on patients' plasma TMAO levels, even though they had been taking statin lipid-lowering drugs for a long time. Conclusion: Diabetics have abnormally high plasma TMAO levels even under continuous statins treatment, which may contribute to the development and progression of atherosclerosis. Therefore, it is necessary to focus on monitoring TMAO levels in diabetic patients to reduce adverse cardiovascular events in diabetic patients.
RESUMO
RESEARCH QUESTION: Can models based on artificial intelligence predict embryonic ploidy status or implantation potential of euploid transferred embryos? Can the addition of clinical features into time-lapse monitoring (TLM) parameters as input data improve their predictive performance? DESIGN: A single academic fertility centre, retrospective cohort study. A total of 773 high-grade euploid and aneuploid blastocysts from 212 patients undergoing preimplantation genetic testing (PGT) between July 2016 and July 2021 were studied for ploidy prediction. Among them, 170 euploid embryos were single-transferred and included for implantation analysis. Five machine learning models and two types of deep learning networks were used to develop the predictive algorithms. The predictive performance was measured using the area under the receiver operating characteristic curve (AUC), in addition to accuracy, precision, recall and F1 score. RESULTS: The most predictive model for ploidy prediction had an AUC, accuracy, precision, recall and F1 score of 0.70, 0.64, 0.64, 0.50 and 0.56, respectively. The DNN-LSTM model showed the best predictive performance with an AUC of 0.78, accuracy of 0.77, precision of 0.79, recall of 0.86 and F1 score of 0.83. The predictive power was improved after the addition of clinical features for the algorithms in ploidy prediction and implantation prediction. CONCLUSION: Our findings emphasize that clinical features can largely improve embryo prediction performance, and their combination with TLM parameters is robust to predict high-grade euploid blastocysts. The models for ploidy prediction, however, were not highly predictive, suggesting they cannot replace preimplantation genetic testing currently.
Assuntos
Inteligência Artificial , Diagnóstico Pré-Implantação , Aneuploidia , Blastocisto , Implantação do Embrião , Feminino , Humanos , Ploidias , Gravidez , Estudos Retrospectivos , Imagem com Lapso de TempoRESUMO
Light field imaging plays an increasingly important role in the field of three-dimensional (3D) reconstruction because of its ability to quickly obtain four-dimensional information (angle and space) of the scene. In this paper, a 3D reconstruction method of light field based on phase similarity is proposed to increase the accuracy of depth estimation and the scope of applicability of epipolar plane image (EPI). The calibration method of the light field camera was used to obtain the relationship between disparity and depth, and the projector calibration was removed to make the experimental procedure more flexible. Then, the disparity estimation algorithm based on phase similarity was designed to effectively improve the reliability and accuracy of disparity calculation, in which the phase information was used instead of the structure tensor, and the morphological processing method was used to denoise and optimize the disparity map. Finally, 3D reconstruction of the light field was realized by combining disparity information with the calibrated relationship. The experimental results showed that the reconstruction standard deviation of the two objects was 0.3179 mm and 0.3865 mm compared with the ground truth of the measured objects, respectively. Compared with the traditional EPI method, our method can not only make EPI perform well in a single scene or blurred texture situations but also maintain good reconstruction accuracy.
RESUMO
In this paper, a novel method, to the best of our knowledge, of structured light fields based on point cloud adaptive repair is proposed to realize 3D reconstruction for highly reflective surfaces. We have designed and built a focused light field camera whose spatial and angular resolution can be flexibly adjusted as required. Then the subaperture image extraction algorithm based on image mosaic is deduced and presented to obtain multidirectional images. After that, the 3D reconstruction of structured light field imaging based on point cloud adaptive repair is presented to accurately reconstruct for highly reflective surfaces. In addition, a method based on smoothness and repair rate is also proposed to objectively evaluate the performance of the 3D reconstruction. Experimental results demonstrate the validity of the proposed method to perform high-quality depth reconstruction for highly reflective surfaces. Generally, our method takes advantage of the multidirectional imaging of the light field camera and can ensure good modulation effect of structured light while avoiding hardware complexity, which makes it application more convenient.
RESUMO
Minimal inhibitory concentration (MIC) is defined as the lowest concentration of an antimicrobial agent that can inhibit the visible growth of a particular microorganism after overnight incubation. Clinically, antibiotic doses for specific infections are determined according to the fraction of MIC. Therefore, credible assessment of MICs will provide a physician valuable information on the choice of therapeutic strategy. Early and precise usage of antibiotics is the key to an infection therapy. Compared with the traditional culture-based method, the approach of whole genome sequencing to identify MICs can shorten the experimental time, thereby improving clinical efficacy. Klebsiella pneumoniae is one of the most significant members of the genus Klebsiella in the Enterobacteriaceae family and also a common non-social pathogen. Meropenem is a broad-spectrum antibacterial agent of the carbapenem family, which can produce antibacterial effects of most Gram-positive and -negative bacteria. In this study, we used single-nucleotide polymorphism (SNP) information and nucleotide k-mers count based on metagenomic data to predict MICs of meropenem against K. pneumoniae. Then, features of 110 sequenced K. pneumoniae genome data were combined and modeled with XGBoost algorithm and deep neural network (DNN) algorithm to predict MICs. We first use the XGBoost classification model and the XGBoost regression model. After five runs, the average accuracy of the test set was calculated. The accuracy of using nucleotide k-mers to predict MICs of the XGBoost classification model and XGBoost regression model was 84.5 and 89.1%. The accuracy of SNP in predicting MIC was 80 and 81.8%, respectively. The results show that XGBoost regression is better than XGBoost classification in both nucleotide k-mers and SNPs to predict MICs. We further selected 40 nucleotide k-mers and 40 SNPs with the highest correlation with MIC values as features to retrain the XGBoost regression model and DNN regression model. After 100 and 1,000 runs, the results show that the accuracy of the two models was improved. The accuracy of the XGBoost regression model for k-mers, SNPs, and k-mers & SNPs was 91.1, 85.2, and 91.3%, respectively. The accuracy of the DNN regression model was 91.9, 87.1, and 91.8%, respectively. Through external verification, some of the selected features were found to be related to drug resistance.
RESUMO
Computational ghost imaging is difficult to apply under low sampling rate. We propose high-speed computational ghost imaging based on an auto-encoder network to reconstruct images with high quality under low sampling rate. The auto-encoder convolutional neural network is designed, and the object images can be reconstructed accurately without labeled images. Experimental results show that our method can greatly improve the peak signal-to-noise ratio and structural similarity of the test samples, which are up to 18 and 0.7, respectively, under low sampling rate. Our method only needs 1/10 of traditional deep learning samples to achieve fast and high-quality image reconstruction, and the network also has a certain generalization to the gray-scale images.
RESUMO
In this paper, a novel, to the best of our knowledge, iterative approach for highlight removal is proposed using lenselet-based plenoptic cameras without multiple exposures. An unsupervised k-means clustering approach that relates unsaturated pixels to chromatic dispersion based on the intrinsic decomposition and dichromatic reflection model is proposed to recover unsaturated highlights. Meanwhile, an adaptive direction method along with a Gaussian probability distribution model is designed to recover the saturated highlights. Finally, a method that combines the specular residual ratio with information entropy is built to quantitatively evaluate the quality of highlight removal. Generally, our method not only fully removes specular highlights, but also has low spatial complexity of image acquisition, more stability, and outstanding restoration for complex scenes.
RESUMO
Background: Coronary artery disease (CAD) is the leading cause of death worldwide, which has a long asymptomatic period of atherosclerosis. Thus, it is crucial to develop efficient strategies or biomarkers to assess the risk of CAD in asymptomatic individuals. Methods: A total of 356 consecutive CAD patients and 164 non-CAD controls diagnosed using coronary angiography were recruited. Blood lipids, other baseline characteristics, and clinical information were investigated in this study. In addition, low-density lipoprotein cholesterol (LDL-C) subfractions were classified and quantified using the Lipoprint system. Based on these data, we performed comprehensive analyses to investigate the risk factors for CAD development and to predict CAD risk. Results: Triglyceride, LDLC-3, LDLC-4, LDLC-5, LDLC-6, and total small and dense LDL-C were significantly higher in the CAD patients than those in the controls, whereas LDLC-1 and high-density lipoprotein cholesterol (HDL-C) had significantly lower levels in the CAD patients. Logistic regression analysis identified male [odds ratio (OR) = 2.875, P < 0.001], older age (OR = 1.018, P = 0.025), BMI (OR = 1.157, P < 0.001), smoking (OR = 4.554, P < 0.001), drinking (OR = 2.128, P < 0.016), hypertension (OR = 4.453, P < 0.001), and diabetes mellitus (OR = 8.776, P < 0.001) as clinical risk factors for CAD development. Among blood lipids, LDLC-3 (OR = 1.565, P < 0.001), LDLC-4 (OR = 3.566, P < 0.001), and LDLC-5 (OR = 6.866, P < 0.001) were identified as risk factors. To predict CAD risk, six machine learning models were constructed. The XGboost model showed the highest AUC score (0.945121), which could distinguish CAD patients from the controls with a high accuracy. LDLC-4 played the most important role in model construction. Conclusions: The established models showed good performance for CAD risk prediction, which can help screen high-risk CAD patients in asymptomatic population, so that further examination and prevention treatment might be taken before any sudden or serious event.
RESUMO
Early recurrence after surgery could affect cancerous patients' prognosis, but the definition of early recurrence and its risk factors for esophageal squamous cell carcinoma (ESCC) patients are still unclear. This study analyzed the clinical data of 468 post-surgery recurrent ESCC patients retrospectively. A minimum p-value approach was used to evaluate the optimal cut-off value of recurrence free survival (RFS) to define early recurrence. Risk factors of early recurrence were developed based on a Cox model. The optimal cut-off value of RFS to distinguish early recurrence was 21 months (p <0.001). Independent risk factors for early recurrence included tumor locations (HR=0.562, p <0.001), pathological T stage (HR=1.829, p <0.001), tumor diameter (HR=1.344, p = 0.039), positive lymph nodes (HR=1.361, p <0.001), and total resected lymph nodes (HR=1.271, p = 044). For the late recurrent patients, there was a much more significant survival advantage for recurrence after concurrent chemoradiotherapy than that after sequential chemoradiotherapy and radiotherapy alone (p = 0.0066). In conclusion, this study defined 21 months of RFS as early recurrence and also identified its risk factors. Concurrent chemoradiotherapy was suggested as preferred post-relapse treatment for late recurrent ESCC patients.
RESUMO
BACKGROUND: Neoadjuvant chemotherapy may benefit patients with pancreatic ductal adenocarcinoma with resectable and borderline disease. Inappropriate use of neoadjuvant therapy, however, may lead to the loss of therapeutic opportunities. Until an effective prediction model of individual drug sensitivity is established, no accurate model exists to help surgeons decide on the appropriate use of neoadjuvant chemotherapy. We hypothesized that early recurrence in patients undergoing upfront, early resection may be an indication for neoadjuvant chemotherapy. Therefore, we aimed to use preoperative clinical parameters to establish a model of early recurrence to select patients at high risk for neoadjuvant chemotherapy. METHODS: Patients who underwent resection for pancreatic ductal adenocarcinoma between January 2014 and November 2017 were analyzed retrospectively. After the minimum P-value approach, the patients were divided into three groups: early recurrence, middle recurrence, and late/non-recurrence. Preoperative clinicopathologic factors that could predict early recurrence were included in a Cox proportional hazards regression model for univariate and multivariate analyses. The factors related to early recurrence were included to establish nomogram and decision tree models, which were then validated in 68 patients. RESULTS: We found that 235 (72.5%) of 324 patients had recurrence with a median recurrence-free survival of 210 days. The early recurrence, middle recurrence, and late/non-recurrence groups differed in preoperative carbohydrate antigen 19-9 and carcinoembryonic antigen levels, "resectability" on cross-sectional imaging, resection requiring a vascular resection, T stage, tumor size, and adjuvant chemotherapy. The best cutoff value of early recurrence was the first 162 days postoperatively. Univariate and multivariate analyses showed that selected preoperative chief complaints, lymph node enlargement and resectability on cross-sectional imaging, preoperative carbohydrate antigen 19-9 levels >210 kU/L, and a neutrophil/lymphocyte ratio >4.2 were independent predictors for early recurrence. CONCLUSION: We have successfully built a prediction model of early recurrence of patients with pancreatic ductal adenocarcinoma with the optimal cutoff early-recurrence value of 162 days. Our nomogram and decision tree models may be used to select those at high risk for early recurrence to guide preoperative decision-making concerning the use of neoadjuvant therapy in those patients who have "resectable" disease and not only the more classic criteria of borderline resectability.
Assuntos
Carcinoma Ductal Pancreático/terapia , Terapia Neoadjuvante , Recidiva Local de Neoplasia/epidemiologia , Nomogramas , Pancreatectomia , Neoplasias Pancreáticas/terapia , Idoso , Antígeno CA-19-9 , Carcinoma Ductal Pancreático/sangue , Carcinoma Ductal Pancreático/diagnóstico , Carcinoma Ductal Pancreático/mortalidade , Quimioterapia Adjuvante , Tomada de Decisão Clínica/métodos , Intervalo Livre de Doença , Feminino , Seguimentos , Humanos , Contagem de Linfócitos , Linfócitos , Imageamento por Ressonância Magnética , Masculino , Pessoa de Meia-Idade , Recidiva Local de Neoplasia/prevenção & controle , Estadiamento de Neoplasias , Neutrófilos , Pâncreas/diagnóstico por imagem , Pâncreas/patologia , Pâncreas/cirurgia , Neoplasias Pancreáticas/sangue , Neoplasias Pancreáticas/diagnóstico , Neoplasias Pancreáticas/mortalidade , Seleção de Pacientes , Período Pré-Operatório , Estudos Retrospectivos , Medição de Risco/métodos , Tomografia Computadorizada por Raios XRESUMO
BACKGROUND: Chronic obstructive pulmonary disease (COPD) is a major public health problem and cause of mortality worldwide. However, COPD in the early stage is usually not recognized and diagnosed. It is necessary to establish a risk model to predict COPD development. METHODS: A total of 441 COPD patients and 192 control subjects were recruited, and 101 single-nucleotide polymorphisms (SNPs) were determined using the MassArray assay. With 5 clinical features as well as SNPs, 6 predictive models were established and evaluated in the training set and test set by the confusion matrix AU-ROC, AU-PRC, sensitivity (recall), specificity, accuracy, F1 score, MCC, PPV (precision) and NPV. The selected features were ranked. RESULTS: Nine SNPs were significantly associated with COPD. Among them, 6 SNPs (rs1007052, OR = 1.671, P = 0.010; rs2910164, OR = 1.416, P < 0.037; rs473892, OR = 1.473, P < 0.044; rs161976, OR = 1.594, P < 0.044; rs159497, OR = 1.445, P < 0.045; and rs9296092, OR = 1.832, P < 0.045) were risk factors for COPD, while 3 SNPs (rs8192288, OR = 0.593, P < 0.015; rs20541, OR = 0.669, P < 0.018; and rs12922394, OR = 0.651, P < 0.022) were protective factors for COPD development. In the training set, KNN, LR, SVM, DT and XGboost obtained AU-ROC values above 0.82 and AU-PRC values above 0.92. Among these models, XGboost obtained the highest AU-ROC (0.94), AU-PRC (0.97), accuracy (0.91), precision (0.95), F1 score (0.94), MCC (0.77) and specificity (0.85), while MLP obtained the highest sensitivity (recall) (0.99) and NPV (0.87). In the validation set, KNN, LR and XGboost obtained AU-ROC and AU-PRC values above 0.80 and 0.85, respectively. KNN had the highest precision (0.82), both KNN and LR obtained the same highest accuracy (0.81), and KNN and LR had the same highest F1 score (0.86). Both DT and MLP obtained sensitivity (recall) and NPV values above 0.94 and 0.84, respectively. In the feature importance analyses, we identified that AQCI, age, and BMI had the greatest impact on the predictive abilities of the models, while SNPs, sex and smoking were less important. CONCLUSIONS: The KNN, LR and XGboost models showed excellent overall predictive power, and the use of machine learning tools combining both clinical and SNP features was suitable for predicting the risk of COPD development.
Assuntos
Aprendizado de Máquina , Doença Pulmonar Obstrutiva Crônica , China , Humanos , Polimorfismo de Nucleotídeo Único/genética , Doença Pulmonar Obstrutiva Crônica/diagnóstico , Doença Pulmonar Obstrutiva Crônica/genéticaRESUMO
INTRODUCTION: Age-related macular degeneration (AMD) is the main cause of visual impairment and the most important cause of blindness in older people. However, there is currently no effective treatment for this disease, so it is necessary to establish a risk model to predict AMD development. METHODS: This study included a total of 202 subjects, comprising 82 AMD patients and 120 control subjects. Sixty-six single-nucleotide polymorphisms (SNPs) were identified using the MassArray assay. Considering 14 independent clinical variables as well as SNPs, four predictive models were established in the training set and evaluated by the confusion matrix, area under the receiver operating characteristic (ROC) curve (AUROC). The difference distributions of the 14 independent clinical features between the AMD and control groups were tested using the chi-squared test. Age and diabetes were adjusted using logistic regression analysis and the "genomic-control" method was used for multiple testing correction. RESULTS: Three SNPs (rs10490924, OR = 1.686, genomic-control corrected p-value (GC) = 0.030; rs2338104, OR = 1.794, GC = 0.025 and rs1864163, OR = 2.125, GC = 0.038) were significant risk factors for AMD development. In the training set, four models obtained AUROC values above 0.72. CONCLUSIONS: We believe machine learning tools will be useful for the early prediction of AMD and for the development of relevant intervention strategies.
RESUMO
BACKGROUND: This study aimed to explore the associations of common inflammatory cytokine levels with restenosis and rapid angiographic stenotic progression (RASP) risk in coronary artery disease (CAD) patients underwent percutaneous coronary intervention (PCI) with drug-eluting stents (DES). METHODS: Two hundred and ten CAD patients underwent PCI with DES were consecutively recruited, then pre-operative serum levels of TNF-α, IL-1ß, IL-4, IL-6, IL-8, IL-10, IL-17A, IL-21, and IL-23 were determined by ELISA. The 12-month in-stent restenosis and RASP of non-intervened lesion were assessed by quantitative coronary angiography analysis. RESULTS: The pre-operative TNF-α, IL-6, IL-17A, and IL-23 expressions were increased while IL-4 expression was decreased in restenosis patients compared with non-restenosis patients. Further analysis revealed that IL-6, IL-8, hypercholesteremia, diabetes mellitus, and HsCRP could independently predict restenosis risk, and subsequent ROC curve revealed that their combination was able to differentiate restenosis patients from non-restenosis patients with an AUC of 0.951 (95%CI: 0.925-0.978). Meanwhile, the pre-operative TNF-α, IL-6, IL-17A, IL-21, and IL-23 expressions were increased whereas IL-4 level was decreased in RASP patients compared with non-RASP patients. Further analysis revealed that TNF-α, IL-6, IL-23, hypercholesteremia, SUA, HsCRP, and multivessel artery lesions could independently predict RASP risk, and subsequent ROC curve disclosed that their combination could discriminate RASP patients from non-RASP patients with an AUC of 0.886 (95%CI: 0.841-0.931). CONCLUSIONS: This study unveils the potentiality of pre-operative circulating inflammatory cytokines as markers for predicting restenosis and RASP risk in CAD patients underwent PCI with DES.
Assuntos
Doença da Artéria Coronariana/sangue , Doença da Artéria Coronariana/cirurgia , Reestenose Coronária/sangue , Citocinas/sangue , Progressão da Doença , Stents Farmacológicos , Mediadores da Inflamação/sangue , Intervenção Coronária Percutânea , Angiografia Coronária , Doença da Artéria Coronariana/diagnóstico por imagem , Reestenose Coronária/diagnóstico por imagem , Feminino , Humanos , Modelos Logísticos , Masculino , Pessoa de Meia-Idade , Curva ROC , Fatores de RiscoRESUMO
Obesity and type 2 diabetes (T2D) are both complicated endocrine disorders resulting from an interaction between multiple predisposing genes and environmental triggers, while diet and exercise have key influence on metabolic disorders. Previous reports demonstrated that 2-aminoadipic acid (2-AAA), an intermediate metabolite of lysine metabolism, could modulate insulin secretion and predict T2D, suggesting the role of 2-AAA in glycolipid metabolism. Here, we showed that treatment of diet-induced obesity (DIO) mice with 2-AAA significantly reduced body weight, decreased fat accumulation and lowered fasting glucose. Furthermore, Dhtkd1-/- mice, in which the substrate of DHTKD1 2-AAA increased to a significant high level, were resistant to DIO and obesity-related insulin resistance. Further study showed that 2-AAA induced higher energy expenditure due to increased adipocyte thermogenesis via upregulating PGC1α and UCP1 mediated by ß3AR activation, and stimulated lipolysis depending on enhanced expression of hormone-sensitive lipase (HSL) through activating ß3AR signaling. Moreover, 2-AAA could alleviate the diabetic symptoms of db/db mice. Our data showed that 2-AAA played an important role in regulating glycolipid metabolism independent of diet and exercise, implying that improving the level of 2-AAA in vivo could be developed as a strategy in the treatment of obesity or diabetes.
Assuntos
Ácido 2-Aminoadípico/farmacologia , Peso Corporal/efeitos dos fármacos , Diabetes Mellitus Tipo 2/metabolismo , Obesidade/metabolismo , Ácido 2-Aminoadípico/metabolismo , Células 3T3-L1 , Tecido Adiposo/citologia , Tecido Adiposo/efeitos dos fármacos , Tecido Adiposo/metabolismo , Animais , Glicemia/metabolismo , Diabetes Mellitus Tipo 2/fisiopatologia , Dieta Hiperlipídica/efeitos adversos , Cetona Oxirredutases/genética , Cetona Oxirredutases/metabolismo , Metabolismo dos Lipídeos/efeitos dos fármacos , Camundongos , Camundongos Endogâmicos C57BL , Camundongos Knockout , Obesidade/etiologia , Obesidade/fisiopatologia , Substâncias Protetoras/farmacologia , Receptores Adrenérgicos beta 3/metabolismo , Transdução de Sinais/efeitos dos fármacos , Termogênese/efeitos dos fármacosRESUMO
Background. With the development of massively parallel sequencing (MPS), noninvasive prenatal diagnosis using maternal cell-free DNA is fast becoming the preferred method of fetal chromosomal abnormality detection, due to its inherent high accuracy and low risk. Typically, MPS data is parsed to calculate a risk score, which is used to predict whether a fetal chromosome is normal or not. Although there are several highly sensitive and specific MPS data-parsing algorithms, there are currently no tools that implement these methods. Results. We developed an R package, detection of autosomal abnormalities for fetus (DASAF), that implements the three most popular trisomy detection methods-the standard Z-score (STDZ) method, the GC correction Z-score (GCCZ) method, and the internal reference Z-score (IRZ) method-together with one subchromosome abnormality identification method (SCAZ). Conclusions. With the cost of DNA sequencing declining and with advances in personalized medicine, the demand for noninvasive prenatal testing will undoubtedly increase, which will in turn trigger an increase in the tools available for subsequent analysis. DASAF is a user-friendly tool, implemented in R, that supports identification of whole-chromosome as well as subchromosome abnormalities, based on maternal cell-free DNA sequencing data after genome mapping.