ABSTRACT
PURPOSE: To develop and validate a model for predicting suboptimal debulking surgery (SDS) of serous ovarian carcinoma (SOC) using radiomics method, clinical and MRI features. METHODS: 228 patients eligible from institution A (randomly divided into the training and internal validation cohorts) and 45 patients from institution B (external validation cohort) were collected and retrospectively analyzed. All patients underwent abdominal pelvic enhanced MRI scan, including T2-weighted imaging fat-suppressed fast spin-echo (T2FSE), T1-weighted dual-echo magnetic resonance imaging (T1DEI), diffusion weighted imaging (DWI), and T1 with contrast enhancement (T1CE). We extracted, selected and eliminated highly correlated radiomic features for each sequence. Then, Radiomic models were made by each single sequence, dual-sequence (T1CE + T2FSE), and all-sequence, respectively. Univariate and multivariate analyses were performed to screen the clinical and MRI independent predictors. The radiomic model with the highest area under the curve (AUC) was used to combine the independent predictors as a combined model. RESULTS: The optimal radiomic model was based on dual sequences (T2FSE + T1CE) among the five radiomic models (AUC = 0.720, P < 0.05). Serum carbohydrate antigen 125, the relationship between sigmoid colon/rectum and ovarian mass or mass implanted in Douglas' pouch, diaphragm nodules, and peritoneum/mesentery nodules were considered independent predictors. The AUC of the radiomic-clinical-radiological model was higher than either the optimal radiomic model or the clinical-radiological model in the training cohort (AUC = 0.908 vs. 0.720/0.854). CONCLUSIONS: The radiomic-clinical-radiological model has an overall algorithm reproducibility and may help create individualized treatment programs and improve the prognosis of patients with SOC.
ABSTRACT
BACKGROUND AND PURPOSE: Intracranial hemorrhage (ICH) in leukemia patients progresses rapidly with high mortality. Limited data are available on imaging studies in this population. The study aims to develop prediction models for 7-day and short-term mortality risk based on the non-contrast computed tomography (NCCT) image features. METHODS: The NCCT image features of ICH in 135 leukemia patients between 2007-2023 were retrospectively extracted using manual assessment and radiomics methods. After multiple imputation of missing laboratory data, univariate logistic regression and least absolute shrinkage and selection operator (LASSO) were used for feature selection. Random forest models were built with comprehensive evaluation and ranking of feature importance. RESULT: 135 and 129 patients were included in the studies for 7-day and short-term prognostic models, respectively. The median age of all enrolled patients was 35 years, and there were 86 male patients (63.7 %). Clinical models (validation: AUC [area under the curve] = 0.78, AUPRC [area under the precision-recall curve] = 0.73; AUC = 0.84, AUPRC = 0.86), radiomics models (validation: AUC = 0.82, AUPRC = 0.78; AUC = 0.75, AUPRC = 0.77), and the combined models (validation: AUC = 0.84, AUPRC = 0.83; AUC = 0.87, AUPRC = 0.89) predicted 7-day and short-term mortality with good predictive efficacy. Clinical decision curve analysis showed that the combined models predicted 7-day and 30-day risk of death would be more beneficial than other models. Shape features contributed significantly more than semantic features in both radiomics models and combined models (93.3 %, 52.1 %, as well as 85.2 %,37.4 %, respectively) for 7-day and 30-day mortality. CONCLUSIONS: Combined models constructed based on NCCT perform well in predicting the risk of 7-day and short-term mortality in ICH patients with leukemia. Shape features extracted by radiomics are important markers for modeling the prognosis.
Subject(s)
Cerebral Hemorrhage , Leukemia , Machine Learning , Tomography, X-Ray Computed , Humans , Male , Female , Adult , Tomography, X-Ray Computed/methods , Cerebral Hemorrhage/diagnostic imaging , Cerebral Hemorrhage/mortality , Cerebral Hemorrhage/complications , Leukemia/complications , Leukemia/diagnostic imaging , Retrospective Studies , Prognosis , Middle Aged , Predictive Value of Tests , Aged , AdolescentABSTRACT
PURPOSE: To develop and validate an end-to-end model for automatically predicting hematoma expansion (HE) after spontaneous intracerebral hemorrhage (sICH) using a novel deep learning framework. METHODS: This multicenter retrospective study collected cranial noncontrast computed tomography (NCCT) images of 490 patients with sICH at admission for model training (n = 236), internal testing (n = 60), and external testing (n = 194). A HE-Mind model was designed to predict HE, which consists of a densely connected U-net for segmentation process, a multi-instance learning strategy for resolving label ambiguity and a Siamese network for classification process. Two radiomics models based on support vector machine or logistic regression and two deep learning models based on residual network or Swin transformer were developed for performance comparison. Reader experiments including physician diagnosis mode and artificial intelligence mode were conducted for efficiency comparison. RESULTS: The HE-Mind model showed better performance compared to the comparative models in predicting HE, with areas under the curve of 0.849 and 0.809 in the internal and external test sets respectively. With the assistance of the HE-Mind model, the predictive accuracy and work efficiency of the emergency physician, junior radiologist, and senior radiologist were significantly improved, with accuracies of 0.768, 0.789, and 0.809 respectively, and reporting times of 7.26 s, 5.08 s, and 3.99 s respectively. CONCLUSIONS: The HE-Mind model could rapidly and automatically process the NCCT data and predict HE after sICH within three seconds, indicating its potential to assist physicians in the clinical diagnosis workflow of HE.
Subject(s)
Cerebral Hemorrhage , Hematoma , Tomography, X-Ray Computed , Humans , Cerebral Hemorrhage/diagnostic imaging , Cerebral Hemorrhage/complications , Male , Tomography, X-Ray Computed/methods , Retrospective Studies , Hematoma/diagnostic imaging , Female , Middle Aged , Aged , Deep Learning , Support Vector Machine , Disease Progression , Predictive Value of TestsABSTRACT
PURPOSE: To evaluate the diagnostic efficacy of a developed artificial intelligence (AI) platform incorporating deep learning algorithms for the automated detection of intracranial aneurysms in time-of-flight (TOF) magnetic resonance angiography (MRA). METHOD: This retrospective study encompassed 3D TOF MRA images acquired between January 2023 and June 2023, aiming to validate the presence of intracranial aneurysms via our developed AI platform. The manual segmentation results by experienced neuroradiologists served as the "gold standard". Following annotation of MRA images by neuroradiologists using InferScholar software, the AI platform conducted automatic segmentation of intracranial aneurysms. Various metrics including accuracy (ACC), balanced ACC, area under the curve (AUC), sensitivity (SE), specificity (SP), F1 score, Brier Score, and Net Benefit were utilized to evaluate the generalization of AI platform. Comparison of intracranial aneurysm identification performance was conducted between the AI platform and six radiologists with experience ranging from 3 to 12 years in interpreting MR images. Additionally, a comparative analysis was carried out between radiologists' detection performance based on independent visual diagnosis and AI-assisted diagnosis. Subgroup analyses were also performed based on the size and location of the aneurysms to explore factors impacting aneurysm detectability. RESULTS: 510 patients were enrolled including 215 patients (42.16 %) with intracranial aneurysms and 295 patients (57.84 %) without aneurysms. Compared with six radiologists, the AI platform showed competitive discrimination power (AUC, 0.96), acceptable calibration (Brier Score loss, 0.08), and clinical utility (Net Benefit, 86.96 %). The AI platform demonstrated superior performance in detecting aneurysms with an overall SE, SP, ACC, balanced ACC, and F1 score of 91.63 %, 92.20 %, 91.96 %, 91.92 %, and 90.57 % respectively, outperforming the detectability of the two resident radiologists. For subgroup analysis based on aneurysm size and location, we observed that the SE of the AI platform for identifying tiny (diameterï¼3mm), small (3 mm ≤ diameterï¼5mm), medium (5 mm ≤ diameterï¼7mm) and large aneurysms (diameter ≥ 7 mm) was 87.80 %, 93.14 %, 95.45 %, and 100 %, respectively. Furthermore, the SE for detecting aneurysms in the anterior circulation was higher than that in the posterior circulation. Utilizing the AI assistance, six radiologists (i.e., two residents, two attendings and two professors) achieved statistically significant improvements in mean SE (residents: 71.40 % vs. 88.37 %; attendings: 82.79 % vs. 93.26 %; professors: 90.07 % vs. 97.44 %; P < 0.05) and ACC (residents: 85.29 % vs. 94.12 %; attendings: 91.76 % vs. 97.06 %; professors: 95.29 % vs. 98.82 %; P < 0.05) while no statistically significant change was observed in SP. Overall, radiologists' mean SE increased by 11.40 %, mean SP increased by 1.86 %, and mean ACC increased by 5.88 %, mean balanced ACC promoted by 6.63 %, mean F1 score grew by 7.89 %, and Net Benefit rose by 12.52 %, with a concurrent decrease in mean Brier score declined by 0.06. CONCLUSIONS: The deep learning algorithms implemented in the AI platform effectively detected intracranial aneurysms on TOF-MRA and notably enhanced the diagnostic capabilities of radiologists. This indicates that the AI-based auxiliary diagnosis model can provide dependable and precise prediction to improve the diagnostic capacity of radiologists.
Subject(s)
Deep Learning , Intracranial Aneurysm , Magnetic Resonance Angiography , Humans , Intracranial Aneurysm/diagnostic imaging , Intracranial Aneurysm/diagnosis , Magnetic Resonance Angiography/methods , Female , Male , Middle Aged , Retrospective Studies , Adult , Imaging, Three-Dimensional/methods , Aged , Sensitivity and Specificity , Brain/diagnostic imagingABSTRACT
RATIONALE AND OBJECTIVES: We examined the effectiveness of computed tomography (CT)-based deep learning (DL) models in differentiating benign and malignant solid pulmonary nodules (SPNs) ≤ 8 mm. MATERIALS AND METHODS: The study patients (n = 719) were divided into internal training, internal validation, and external validation cohorts; all had small SPNs and had undergone preoperative chest CTs and surgical resection. We developed five DL models incorporating features of the nodule and five different peri-nodular regions with the Multiscale Dual Attention Network (MDANet) to differentiate benign and malignant SPNs. We selected the best-performing model, which was then compared to four conventional algorithms (VGG19, ResNet50, ResNeXt50, and DenseNet121). Furthermore, another five DL models were constructed using MDANet to distinguish benign tumors from inflammatory nodules and the one performed best was selected out. RESULTS: Model 4, which incorporated the nodule and 15 mm peri-nodular region, best differentiated benign and malignant SPNs. The model had an area under the curve (AUC), accuracy, recall, precision, and F1-score of 0.730, 0.724, 0.711, 0.705, and 0.707 in the external validation cohort. Model 4 also performed better than the other four conventional algorithms. Model 8, which incorporated the nodule and 10 mm peri-nodular region, was the best model for distinguishing benign tumors from inflammatory nodules. The model had an AUC, accuracy, recall, precision, and F1-score of 0.871, 0.938, 0.863, 0.904, and 0.882 in the external validation cohort. CONCLUSION: The study concludes that CT-based DL models built with MDANet can accurately discriminate among small benign and malignant SPNs, benign tumors and inflammatory nodules.
ABSTRACT
PURPOSE: To investigate the value of a computed tomography (CT)-based deep learning (DL) model to predict the presence of micropapillary or solid (M/S) growth pattern in invasive lung adenocarcinoma (ILADC). MATERIALS AND METHODS: From June 2019 to October 2022, 617 patients with ILADC who underwent preoperative chest CT scans in our institution were randomly placed into training and internal validation sets in a 4:1 ratio, and 353 patients with ILADC from another institution were included as an external validation set. Then, a self-paced learning (SPL) 3D Net was used to establish two DL models: model 1 was used to predict the M/S growth pattern in ILADC, and model 2 was used to predict that pattern in ≤ 2-cm-diameter ILADC. RESULTS: For model 1, the training cohort's area under the curve (AUC), accuracy, recall, precision, and F1-score were 0.924, 0.845, 0.851, 0.842, and 0.843; the internal validation cohort's were 0.807, 0.744, 0.756, 0.750, and 0.743; and the external validation cohort's were 0.857, 0.805, 0.804, 0.806, and 0.804, respectively. For model 2, the training cohort's AUC, accuracy, recall, precision, and F1-score were 0.946, 0.858, 0.881,0.844, and 0.851; the internal validation cohort's were 0.869, 0.809, 0.786, 0.794, and 0.790; and the external validation cohort's were 0.831, 0.792, 0.789, 0.790, and 0.790, respectively. The SPL 3D Net model performed better than the ResNet34, ResNet50, ResNeXt50, and DenseNet121 models. CONCLUSION: The CT-based DL model performed well as a noninvasive screening tool capable of reliably detecting and distinguishing the subtypes of ILADC, even in small-sized tumors.
Subject(s)
Adenocarcinoma of Lung , Deep Learning , Lung Neoplasms , Tomography, X-Ray Computed , Humans , Lung Neoplasms/diagnostic imaging , Lung Neoplasms/pathology , Female , Male , Tomography, X-Ray Computed/methods , Adenocarcinoma of Lung/diagnostic imaging , Adenocarcinoma of Lung/pathology , Middle Aged , Aged , Retrospective Studies , Neural Networks, Computer , Neoplasm Invasiveness , Imaging, Three-Dimensional/methods , Predictive Value of TestsABSTRACT
PURPOSE: To develop a deep learning (DL) model based on preoperative contrast-enhanced computed tomography (CECT) images to predict microvascular invasion (MVI) and pathological differentiation of hepatocellular carcinoma (HCC). METHODS: This retrospective study included 640 consecutive patients who underwent surgical resection and were pathologically diagnosed with HCC at two medical institutions from April 2017 to May 2022. CECT images and relevant clinical parameters were collected. All the data were divided into 368 training sets, 138 test sets and 134 validation sets. Through DL, a segmentation model was used to obtain a region of interest (ROI) of the liver, and a classification model was established to predict the pathological status of HCC. RESULTS: The liver segmentation model based on the 3D U-Network had a mean intersection over union (mIoU) score of 0.9120 and a Dice score of 0.9473. Among all the classification prediction models based on the Swin transformer, the fusion models combining image information and clinical parameters exhibited the best performance. The area under the curve (AUC) of the fusion model for predicting the MVI status was 0.941, its accuracy was 0.917, and its specificity was 0.908. The AUC values of the fusion model for predicting poorly differentiated, moderately differentiated and highly differentiated HCC based on the test set were 0.962, 0.957 and 0.996, respectively. CONCLUSION: The established DL models established can be used to noninvasively and effectively predict the MVI status and the degree of pathological differentiation of HCC, and aid in clinical diagnosis and treatment.
Subject(s)
Carcinoma, Hepatocellular , Deep Learning , Liver Neoplasms , Humans , Carcinoma, Hepatocellular/diagnostic imaging , Retrospective Studies , Liver Neoplasms/diagnostic imaging , Neoplasm Invasiveness/diagnostic imagingABSTRACT
OBJECTIVES: To develop a deep learning (DL) method that can determine the Liver Imaging Reporting and Data System (LI-RADS) grading of high-risk liver lesions and distinguish hepatocellular carcinoma (HCC) from non-HCC based on multiphase CT. METHODS: This retrospective study included 1049 patients with 1082 lesions from two independent hospitals that were pathologically confirmed as HCC or non-HCC. All patients underwent a four-phase CT imaging protocol. All lesions were graded (LR 4/5/M) by radiologists and divided into an internal (n = 886) and external cohort (n = 196) based on the examination date. In the internal cohort, Swin-Transformer based on different CT protocols were trained and tested for their ability to LI-RADS grading and distinguish HCC from non-HCC, and then validated in the external cohort. We further developed a combined model with the optimal protocol and clinical information for distinguishing HCC from non-HCC. RESULTS: In the test and external validation cohorts, the three-phase protocol without pre-contrast showed κ values of 0.6094 and 0.4845 for LI-RADS grading, and its accuracy was 0.8371 and 0.8061, while the accuracy of the radiologist was 0.8596 and 0.8622, respectively. The AUCs in distinguishing HCC from non-HCC were 0.865 and 0.715 in the test and external validation cohorts, while those of the combined model were 0.887 and 0.808. CONCLUSION: The Swin-Transformer based on three-phase CT protocol without pre-contrast could feasibly simplify LI-RADS grading and distinguish HCC from non-HCC. Furthermore, the DL model have the potential in accurately distinguishing HCC from non-HCC using imaging and highly characteristic clinical data as inputs. CLINICAL RELEVANCE STATEMENT: The application of deep learning model for multiphase CT has proven to improve the clinical applicability of the Liver Imaging Reporting and Data System and provide support to optimize the management of patients with liver diseases. KEY POINTS: ⢠Deep learning (DL) simplifies LI-RADS grading and helps distinguish hepatocellular carcinoma (HCC) from non-HCC. ⢠The Swin-Transformer based on the three-phase CT protocol without pre-contrast outperformed other CT protocols. ⢠The Swin-Transformer provide help in distinguishing HCC from non-HCC by using CT and characteristic clinical information as inputs.
Subject(s)
Carcinoma, Hepatocellular , Deep Learning , Liver Neoplasms , Humans , Carcinoma, Hepatocellular/pathology , Liver Neoplasms/pathology , Retrospective Studies , Tomography, X-Ray Computed/methods , Magnetic Resonance Imaging/methods , Contrast Media , Sensitivity and SpecificityABSTRACT
PURPOSE: Accurate prediction of outcomes for patients with acute ischemic stroke (AIS) is crucial for clinical decision-making. In this study, we developed prediction models based on non-contrast computed tomography (NCCT) radiomics and clinical features to predict the modified Rankin Scale (mRS) six months after hospital discharge. METHOD: A two-center retrospective cohort of 240 AIS patients receiving conventional treatment was included. Radiomics features of the infarct area were extracted from baseline NCCT scans. We applied Kruskal-Wallis (KW) test and recursive feature elimination (RFE) to select features for developing clinical, radiomics, and fusion models (with clinical data and radiomics features), using support vector machine (SVM) algorithm. The prediction performance of the models was assessed by accuracy, sensitivity, specificity, F1 score, and receiver operating characteristic (ROC) curve. Shapley Additive exPlanations (SHAP) was applied to analyze the interpretability and predictor importance of the model. RESULTS: A total of 1454 texture features were extracted from the NCCT images. In the test cohort, the ROC analysis showed that the radiomics model and the fusion model showed AUCs of 0.705 and 0.857, which outperformed the clinical model (0.643), with the fusion model exhibiting the best performance. Additionally, the accuracy and sensitivity of the fusion model were also the best among the models (84.8% and 93.8%, respectively). CONCLUSIONS: The model based on NCCT radiomics and machine learning has high predictive efficiency for the prognosis of AIS patients receiving conventional treatment, which can be used to assist early personalized clinical therapy.
Subject(s)
Ischemic Stroke , Humans , Retrospective Studies , Ischemic Stroke/diagnostic imaging , Ischemic Stroke/therapy , Prognosis , Tomography, X-Ray Computed/methods , Machine LearningABSTRACT
BACKGROUND: Chest radiography is the standard investigation for identifying rib fractures. The application of artificial intelligence (AI) for detecting rib fractures on chest radiographs is limited by image quality control and multilesion screening. To our knowledge, few studies have developed and verified the performance of an AI model for detecting rib fractures by using multi-center radiographs. And existing studies using chest radiographs for multiple rib fracture detection have used more complex and slower detection algorithms, so we aimed to create a multiple rib fracture detection model by using a convolutional neural network (CNN), based on multi-center and quality-normalised chest radiographs. METHODS: A total of 1080 radiographs with rib fractures were obtained and randomly divided into the training set (918 radiographs, 85%) and the testing set (162 radiographs, 15%). An object detection CNN, You Only Look Once v3 (YOLOv3), was adopted to build the detection model. Receiver operating characteristic (ROC) and free-response ROC (FROC) were used to evaluate the model's performance. A joint testing group of 162 radiographs with rib fractures and 233 radiographs without rib fractures was used as the internal testing set. Furthermore, an additional 201 radiographs, 121 with rib fractures and 80 without rib fractures, were independently validated to compare the CNN model performance with the diagnostic efficiency of radiologists. RESULTS: The sensitivity of the model in the training and testing sets was 92.0% and 91.1%, respectively, and the precision was 68.0% and 81.6%, respectively. FROC in the testing set showed that the sensitivity for whole-lesion detection reached 91.3% when the false-positive of each case was 0.56. In the joint testing group, the case-level accuracy, sensitivity, specificity, and area under the curve were 85.1%, 93.2%, 79.4%, and 0.92, respectively. At the fracture level and the case level in the independent validation set, the accuracy and sensitivity of the CNN model were always higher or close to radiologists' readings. CONCLUSIONS: The CNN model, based on YOLOv3, was sensitive for detecting rib fractures on chest radiographs and showed great potential in the preliminary screening of rib fractures, which indicated that CNN can help reduce missed diagnoses and relieve radiologists' workload. In this study, we developed and verified the performance of a novel CNN model for rib fracture detection by using radiography.
Subject(s)
Rib Fractures , Humans , Rib Fractures/diagnostic imaging , Artificial Intelligence , Feasibility Studies , Sensitivity and Specificity , Radiography , Neural Networks, Computer , Retrospective StudiesABSTRACT
Attention deficit/hyperactivity disorder (ADHD) is among the most common childhood onset psychiatric behavioral disorders, and the pathogenesis of ADHD is still unclear. Utilizing the latest genome wide association studies (GWAS) data and enhancer map, we explored the brain region related biological pathways associated with ADHD. The GWAS summary data of ADHD was driven from a published study, involving 20,183 ADHD cases and 35,191 healthy controls. The brain-related enhancer map was collected from ENCODE and Roadmap Epigenomics (ENCODEâ¯+â¯Roadmap) including 489,581 enhancers. Firstly, the chromosomal enhancer maps of four brain regions were aligned with the ADHD GWAS summary data in order to obtain enhancer SNPs. Then the significant enhancers SNPs were subjected to the gene set enrichment analysis (GSEA) for identifying ADHD associated gene sets. A total of 866 pathways and 4 brain tissues were analyzed in this study. We detected several candidate genes for ADHD, such as AHI1, ALG2 and DNM1. We also detected several candidate biological pathways associated with ADHD, such as Reactome SEMA4D in semaphorin signaling and Reactome NCAM1 interactions. Our findings may provide a novel insight into the complex genetic mechanism of ADHD.
Subject(s)
Attention Deficit Disorder with Hyperactivity/diagnostic imaging , Attention Deficit Disorder with Hyperactivity/genetics , Brain/diagnostic imaging , Genome-Wide Association Study/methods , Polymorphism, Single Nucleotide/genetics , Child , Female , Genetic Association Studies/methods , Genetic Predisposition to Disease/genetics , Humans , Male , Neural Pathways/diagnostic imagingABSTRACT
BACKGROUND: Psychiatric disorders are usually caused by the dysfunction of various brain regions. Incorporating the genetic information of brain regions into correlation analysis can provide novel clues for pathogenetic and therapeutic studies of psychiatric disorders. METHODS: The latest genome-wide association study (GWAS) summary data of schizophrenia (SCZ), bipolar disorder (BIP), autism spectrum disorder (AUT), major depression disorder (MDD), and attention-deficit/hyperactivity disorder (ADHD) were obtained from the Psychiatric GWAS Consortium (PGC). The expression quantitative trait loci (eQTLs) datasets of 10 brain regions were driven from the genotype-tissue expression (GTEx) database. The PGC GWAS summaries were first weighted by the GTEx eQTLs summaries for each brain region. Linkage disequilibrium score regression was applied to the weighted GWAS summary data to detect genetic correlation for each pair of 5 disorders. RESULTS: Without considering brain region difference, significant genetic correlations were observed for BIP vs SCZ (P = 1.68 × 10-63), MDD vs SCZ (P = 5.08 × 10-45), ADHD vs MDD (P = 1.93 × 10-44), BIP vs MDD (P = 6.39 × 10-9), AUT vs SCZ (P = .0002), and ADHD vs SCZ (P = .0002). Utilizing brain region related eQTLs weighted LD score regression, different strengths of genetic correlations were observed within various brain regions for BIP vs SCZ, MDD vs SCZ, ADHD vs MDD, and SCZ vs ADHD. For example, the most significant genetic correlations were observed at anterior cingulate cortex (P = 1.13 × 10-34) for BIP vs SCZ. CONCLUSIONS: This study provides new clues for elucidating the mechanism of genetic correlations among various psychiatric disorders.
Subject(s)
Attention Deficit Disorder with Hyperactivity/genetics , Autism Spectrum Disorder/genetics , Bipolar Disorder/genetics , Brain , Depressive Disorder, Major/genetics , Genome-Wide Association Study , Linkage Disequilibrium/genetics , Quantitative Trait Loci/genetics , Schizophrenia/genetics , Attention Deficit Disorder with Hyperactivity/physiopathology , Autism Spectrum Disorder/physiopathology , Brain/physiopathology , Depressive Disorder, Major/physiopathology , Humans , Schizophrenia/physiopathologyABSTRACT
OBJECTIVE: To explore the associations between chemical elements and attention deficit hyperactivity disorder (ADHD)/intelligence quotient (IQ). METHODS: We applied elements related gene set enrichment analysis (ERGSEA) to explore the relationships between elements and ADHD/IQ. The GWAS dataset of ADHD was derived from the Psychiatric Genomics Consortium, involving 55,374 individuals. The GWAS dataset of IQ was derived from UK Biobank web-based measure (n = 17,862), UK Biobank touchscreen measure (n = 36,257), CHIC consortium (n = 12,441) and five additional cohorts (n = 11,748). Enhancer-gene datasets of eight brain tissues consist of 935 individuals. Utilizing the published GWAS summary and eight brain region-related chromosomal enhancer maps to obtain the SNP association testing signals. The element-gene interaction datasets of 21 elements were downloaded from the comparative toxicogenomics database (CTD). RESULTS: ERGSEA observed significant associations between 4 elements and ADHD, such as Al at Hippocampus Middle (P value = 0.040), As at Angular Gyrus (P value = 0.007) and Na at Hippocampus Middle (P value = 0.026). Additionally, ERGSEA identified that 5 elements were associated with IQ, mainly including Al at Dorsolateral Prefrontal Cortex (P value = 0.017), As at Dorsolateral Prefrontal Cortex (P value = 0.004) and Pb at Germinal Matrix (P value = 0.045). CONCLUSION: Our study results provide novel clues for understanding the associations between elements and ADHD/IQ. This study also illustrated the good performance of ERGSEA approach for complex diseases.
Subject(s)
Attention Deficit Disorder with Hyperactivity/genetics , Attention Deficit Disorder with Hyperactivity/metabolism , Brain/metabolism , Chromosome Mapping , Environmental Exposure , Gene Regulatory Networks , Genome-Wide Association Study , Humans , Intelligence , Meta-Analysis as TopicABSTRACT
To identify novel susceptibility genes and gene sets for obesity, we conducted a genomewide expression association analysis of obesity via integrating genomewide association study (GWAS) and expression quantitative trait loci (eQTLs) data. GWAS summary data of body mass index (BMI) and waist-to-hip ratio (WHR) was driven from a published study, totally involving 339,224 individuals. The eQTLs dataset (containing 927,753 eQTLs) was obtained from eQTLs meta-analysis of 5,311 subjects. Integrative analysis of GWAS and eQTLs data was conducted by SMR software. The SMR single gene analysis results were further subjected to gene set enrichment analysis (GSEA) for identifying obesity associated gene sets. A total of 13,311 annotated gene sets were analyzed in this study. SMR single gene analysis identified 20 BMI associated genes (TUFM, SPI1, APOB48R, etc.). Also 3 WHR associated genes were detected (CPEB4, WARS2, and L3MBTL3). The significant association between Chr16p11 and BMI was observed by GSEA (FDR adjusted p value = 0.040). The TGCTGCT, MIR-15A, MIR-16, MIR-15B, MIR-195, MIR-424, and MIR-497 (FDR adjusted p value = 0.049) gene set appeared to be linked with WHR. Our results provide novel clues for the genetic mechanism studies of obesity. This study also illustrated the good performance of SMR for susceptibility gene mapping.
Subject(s)
Genetic Predisposition to Disease/genetics , Obesity/genetics , Quantitative Trait Loci/genetics , Body Mass Index , Chromosome Mapping/methods , Genome-Wide Association Study/methods , Humans , MicroRNAs/genetics , Molecular Sequence Annotation/methods , Waist-Hip Ratio/methodsABSTRACT
Context: Osteoporosis is a metabolic bone disease. The effect of blood metabolites on the development of osteoporosis remains elusive. Objective: To explore the relationship between blood metabolites and osteoporosis. Design and Methods: We used 2286 unrelated white subjects for the discovery samples and 3143 unrelated white subjects from the Framingham Heart Study (FHS) for the replication samples. The bone mineral density (BMD) was measured using dual-energy X-ray absorptiometry. Genome-wide single nucleotide polymorphism (SNP) genotyping was performed using Affymetrix Human SNP Array 6.0 (for discovery samples) and Affymetrix SNP 500K and 50K array (for FHS replication samples). The SNP sets significantly associated with blood metabolites were obtained from a reported whole-genome sequencing study. For each subject, the genetic risk score of the metabolite was calculated from the genotype data of the metabolite-associated SNP sets. Pearson correlation analysis was conducted to evaluate the potential effect of blood metabolites on the variations in bone phenotypes; 10,000 permutations were conducted to calculate the empirical P value and false discovery rate. Results: We analyzed 481 blood metabolites. We identified multiple blood metabolites associated with hip BMD, such as 1,5-anhydroglucitol (Pdiscovery < 0.0001; Preplication = 0.0361), inosine (Pdiscovery = 0.0018; Preplication = 0.0256), theophylline (Pdiscovery = 0.0048; Preplication = 0.0433, gamma-glutamyl methionine (Pdiscovery = 0.0047; Preplication = 0.0471), 1-linoleoyl-2-arachidonoyl-GPC (18:2/20:4n6; Pdiscovery = 0.0018; Preplication = 0.0390), and X-12127 (Pdiscovery = 0.0002; Preplication = 0.0249). Conclusions: Our results suggest a modest effect of blood metabolites on the variations of BMD and identified several candidate blood metabolites for osteoporosis.
Subject(s)
Biomarkers/blood , Osteoporosis/blood , Osteoporosis/genetics , Absorptiometry, Photon , Adult , Aged , Biomarkers/analysis , Biomarkers/metabolism , Bone Density/genetics , Female , Genetic Predisposition to Disease , Genome-Wide Association Study , Genotype , Humans , Male , Mendelian Randomization Analysis , Middle Aged , Osteoporosis/epidemiology , Osteoporosis/metabolism , Phenotype , Polymorphism, Single Nucleotide , Random AllocationABSTRACT
Genome-wide association study (GWAS)-based pathway association analysis is a powerful approach for the genetic studies of human complex diseases. However, the genetic confounding effects of environment exposure-related genes can decrease the accuracy of GWAS-based pathway association analysis of target diseases. In this study, we developed a pathway association analysis approach, named Mendelian randomization-based pathway enrichment analysis (MRPEA), which was capable of correcting the genetic confounding effects of environmental exposures, using the GWAS summary data of environmental exposures. After analyzing the real GWAS summary data of cardiovascular disease and cigarette smoking, we observed significantly improved performance of MRPEA compared with traditional pathway association analysis (TPAA) without adjusting for environmental exposures. Further, simulation studies found that MRPEA generally outperformed TPAA under various scenarios. We hope that MRPEA could help to fill the gap of TPAA and identify novel causal pathways for complex diseases.
Subject(s)
Environmental Exposure/adverse effects , Environmental Exposure/statistics & numerical data , Genome-Wide Association Study/statistics & numerical data , Cardiovascular Diseases/etiology , Cardiovascular Diseases/genetics , Computational Biology/methods , Computer Simulation , Genetic Variation , Humans , Models, Genetic , Multifactorial Inheritance , Polymorphism, Single Nucleotide , Risk Factors , Smoking/adverse effects , Smoking/geneticsABSTRACT
Schizophrenia is a serious mental disease with high heritability. To better understand the genetic basis of schizophrenia, we conducted a large scale integrative analysis of genome-wide association study (GWAS) and expression quantitative trait loci (eQTLs) data. GWAS summary data was derived from a published GWAS of schizophrenia, containing 9394 schizophrenia patients and 12,462 healthy controls. The eQTLs dataset was obtained from an eQTLs meta-analysis of 5311 subjects, containing 923,021 cis-eQTLs for 14,329 genes and 4732 trans-eQTLs for 2612 genes. Genome-wide single gene expression association analysis was conducted by SMR software. The SMR analysis results were further subjected to gene set enrichment analysis (GSEA) to identify schizophrenia associated gene sets. SMR detected 49 genes significantly associated with schizophrenia. The top five significant genes were CRELD2 (p value=1.65×10-11), DIP2B (p value=3.94×10-11), ZDHHC18 (p value=1.52×10-10) and ZDHHC5 (p value=7.45×10-10), C11ORF75 (p value=3.70×10-9). GSEA identified 80 gene sets with p values <0.01. The top five significant gene sets were COWLING_MYCN_TARGETS (p value <0.001) and CHR16P11 (p value <0.001), ACTACCT_MIR196A_MIR196B (p value=0.002), CELLULAR_COMPONENT_DISASSEMBLY (p value=0.002) and GRAESSMANN_RESPONSE_TO_MC_AND_DOXORUBICIN_DN (p value=0.002). Our results provide useful information for revealing the genetic basis of schizophrenia.
Subject(s)
Genetic Predisposition to Disease , Genome-Wide Association Study , Quantitative Trait Loci , Schizophrenia/genetics , Humans , Meta-Analysis as Topic , Polymorphism, Single Nucleotide , White People/geneticsABSTRACT
Amyotrophic lateral sclerosis (ALS) is a neurodegenerative disease with strong genetic components. To identity novel risk variants for ALS, utilizing the latest genome-wide association studies (GWAS) and eQTL study data, we conducted a genome-wide expression association analysis by summary data-based Mendelian randomization (SMR) method. Summary data were derived from a large-scale GWAS of ALS, involving 12577 cases and 23475 controls. The eQTL annotation dataset included 923,021 cis-eQTL for 14,329 genes and 4732 trans-eQTL for 2612 genes. Genome-wide single gene expression association analysis was conducted by SMR software. To identify ALS-associated biological pathways, the SMR analysis results were further subjected to gene set enrichment analysis (GSEA). SMR single gene analysis identified one significant and four suggestive genes associated with ALS, including C9ORF72 (P value = 7.08 × 10-6), NT5C3L (P value = 1.33 × 10-5), GGNBP2 (P value = 1.81 × 10-5), ZNHIT3(P value = 2.94 × 10-5), and KIAA1600(P value = 9.97 × 10-5). GSEA identified 7 significant biological pathways, such as PEROXISOME (empirical P value = 0.006), GLYCOLYSIS_GLUCONEOGENESIS (empirical P value = 0.043), and ARACHIDONIC_ACID_ METABOLISM (empirical P value = 0.040). Our study provides novel clues for the genetic mechanism studies of ALS.
Subject(s)
Amyotrophic Lateral Sclerosis/genetics , Amyotrophic Lateral Sclerosis/metabolism , Genetic Predisposition to Disease , Genome-Wide Association Study , Polymorphism, Single Nucleotide/genetics , C9orf72 Protein/genetics , Humans , Quantitative Trait Loci/genetics , Tumor Suppressor Proteins/geneticsABSTRACT
AIM: To identify novel candidate genes and gene sets for diabetes. METHODS: We performed an integrative analysis of genome-wide association studies (GWAS) and expression quantitative trait loci (eQTLs) data for diabetes. Summary data was driven from a large-scale GWAS of diabetes, totally involving 58,070 individuals. eQTLs dataset included 923,021 cis-eQTL for 14,329 genes and 4,732 trans-eQTL for 2,612 genes. Integrative analysis of GWAS and eQTLs data was conducted by summary data-based Mendelian randomization (SMR). To identify the gene sets associated with diabetes, the SMR single gene analysis results were further subjected to gene set enrichment analysis (GSEA). A total of 13,311 annotated gene sets were analyzed in this study. RESULTS: SMR analysis identified 6 genes significantly associated with fasting glucose, such as C11ORF10 (p value = 6.04 × 10-8), MRPL33 (p value = 1.24 × 10-7), and FADS1 (p value = 2.39 × 10-7). Gene set analysis identified HUANG_FOXA2_TARGETS_UP (false discovery rate = 0.047) associated with fasting glucose. CONCLUSION: Our study provides novel clues for clarifying the genetic mechanism of diabetes. This study also illustrated the good performance of SMR approach and extended it to gene set association analysis for complex diseases.