Application of artificial intelligence ensemble learning model in early prediction of atrial fibrillation.

BACKGROUND: Atrial fibrillation is a paroxysmal heart disease without any obvious symptoms for most people during the onset. The electrocardiogram (ECG) at the time other than the onset of this disease is not significantly different from that of normal people, which makes it difficult to detect and diagnose. However, if atrial fibrillation is not detected and treated early, it tends to worsen the condition and increase the possibility of stroke. In this paper, P-wave morphology parameters and heart rate variability feature parameters were simultaneously extracted from the ECG. A total of 31 parameters were used as input variables to perform the modeling of artificial intelligence ensemble learning model. RESULTS: This paper applied three artificial intelligence ensemble learning methods, namely Bagging ensemble learning method, AdaBoost ensemble learning method, and Stacking ensemble learning method. The prediction results of these three artificial intelligence ensemble learning methods were compared. As a result of the comparison, the Stacking ensemble learning method combined with various models finally obtained the best prediction effect with the accuracy of 92%, sensitivity of 88%, specificity of 96%, positive predictive value of 95.7%, negative predictive value of 88.9%, F1 score of 0.9231 and area under receiver operating characteristic curve value of 0.911. CONCLUSION: In feature extraction, this paper combined P-wave morphology parameters and heart rate variability parameters as input parameters for model training, and validated the value of the proposed parameters combination for the improvement of the model's predicting effect. In the calculation of the P-wave morphology parameters, the hybrid Taguchi-genetic algorithm was used to obtain more accurate Gaussian function fitting parameters. The prediction model was trained using the Stacking ensemble learning method, so that the model accuracy had better results, which can further improve the early prediction of atrial fibrillation.

A deep learning method for counting white blood cells in bone marrow images.

BACKGROUND: Differentiating and counting various types of white blood cells (WBC) in bone marrow smears allows the detection of infection, anemia, and leukemia or analysis of a process of treatment. However, manually locating, identifying, and counting the different classes of WBC is time-consuming and fatiguing. Classification and counting accuracy depends on the capability and experience of operators. RESULTS: This paper uses a deep learning method to count cells in color bone marrow microscopic images automatically. The proposed method uses a Faster RCNN and a Feature Pyramid Network to construct a system that deals with various illumination levels and accounts for color components' stability. The dataset of The Second Affiliated Hospital of Zhejiang University is used to train and test. CONCLUSIONS: The experiments test the effectiveness of the proposed white blood cell classification system using a total of 609 white blood cell images with a resolution of 2560 × 1920. The highest overall correct recognition rate could reach 98.8% accuracy. The experimental results show that the proposed system is comparable to some state-of-art systems. A user interface allows pathologists to operate the system easily.

Prognostic Risk Model of Immune-Related Genes in Colorectal Cancer.

PURPOSE: We focused on immune-related genes (IRGs) derived from transcriptomic studies, which had the potential to stratify patients' prognosis and to establish a risk assessment model in colorectal cancer. SUMMARY: This article examined our understanding of the molecular pathways associated with intratumoral immune response, which represented a critical step for the implementation of stratification strategies toward the development of personalized immunotherapy of colorectal cancer. More and more evidence shows that IRGs play an important role in tumors. We have used data analysis to screen and identify immune-related molecular biomarkers of colon cancer. We selected 18 immune-related prognostic genes and established models to assess prognostic risks of patients, which can provide recommendations for clinical treatment and follow-up. Colorectal cancer (CRC) is a leading cause of cancer-related death in human. Several studies have investigated whether IRGs and tumor immune microenvironment (TIME) could be indicators of CRC prognoses. This study aimed to develop an improved prognostic signature for CRC based on IRGs to predict overall survival (OS) and provide new therapeutic targets for CRC treatment. Based on the screened IRGs, the Cox regression model was used to build a prediction model based on 18-IRG signature. Cox regression analysis revealed that the 18-IRG signature was an independent prognostic factor for OS in CRC patients. Then, we used the TIMER online database to explore the relationship between the risk scoring model and the infiltration of immune cells, and the results showed that the risk model can reflect the state of TIME to a certain extent. In short, an 18-IRG prognostic signature for predicting CRC patients' survival was firmly established.

Identifying Stage II Colorectal Cancer Recurrence Associated Genes by Microarray Meta-Analysis and Building Predictive Models with Machine Learning Algorithms.

BACKGROUND: Stage II colorectal cancer patients had heterogeneous prognosis, and patients with recurrent events had poor survival. In this study, we aimed to identify stage II colorectal cancer recurrence associated genes by microarray meta-analysis and build predictive models to stratify patients' recurrence-free survival. METHODS: We searched the GEO database to retrieve eligible microarray datasets. The microarray meta-analysis was used to identify universal recurrence associated genes. Total samples were randomly divided into the training set and the test set. Two survival models (lasso Cox model and random survival forest model) were trained in the training set, and AUC values of the time-dependent receiver operating characteristic (ROC) curves were calculated. Survival analysis was performed to determine whether there was significant difference between the predicted high and low risk groups in the test set. RESULTS: Six datasets containing 651 stage II colorectal cancer patients were included in this study. The microarray meta-analysis identified 479 recurrence associated genes. KEGG and GO enrichment analysis showed that G protein-coupled glutamate receptor binding and Hedgehog signaling were significantly enriched. AUC values of the lasso Cox model and the random survival forest model were 0.815 and 0.993 at 60 months, respectively. In addition, the random survival forest model demonstrated that the effects of gene expression on the recurrence-free survival probability were nonlinear. According to the risk scores computed by the random survival forest model, the high risk group had significantly higher recurrence risk than the low risk group (HR = 1.824, 95% CI: 1.079-3.084, p = 0.025). CONCLUSIONS: We identified 479 stage II colorectal cancer recurrence associated genes by microarray meta-analysis. The random survival forest model which was based on the recurrence associated gene signature could strongly predict the recurrence risk of stage II colorectal cancer patients.

An Autophagy-Related Long Noncoding RNA Signature Contributes to Poor Prognosis in Colorectal Cancer.

PURPOSE: Colorectal cancer is one of the most common malignant primary tumors, prone to metastasis, and associated with a poor prognosis. As autophagy is closely related to the development and treatment of colorectal cancer, we investigated the potential prognostic value of long noncoding RNA (lncRNA) associated with autophagy in colorectal cancer. METHODS: In this study, we acquired information on the expression of lncRNAs in colorectal cancer from the Cancer Genome Atlas (TCGA) database and found that 860 lncRNAs were associated with autophagy-related genes. Subsequently, univariate Cox regression analysis was used to investigate 32 autophagy-related lncRNAs linked to colon cancer prognosis. Subsequently, eight of the 32 autophagy-related lncRNAs (i.e., long intergenic nonprotein coding RNA 1503 [LINC01503], ZEB1 antisense RNA 1 [ZEB1-AS1], AC087481.3, AC008760.1, AC073896.3, AL138756.1, AL022323.1, and TNFRSF10A-AS1) were selected through multivariate Cox regression analysis. Based on these autophagy-related lncRNAs, a risk signature was constructed, and the patients were divided into high- and low-risk groups. RESULTS: The high-risk group's overall survival time was significantly shorter than that of the low-risk group (p < 0.0001). Receiver operating characteristic curve analysis was performed to further confirm the validity of the model (area under the curve: 0.689). Moreover, multivariate regression suggested that the risk score was a significant prognostic risk factor in colorectal cancer. Gene set enrichment analysis showed that these gene sets are significantly enriched in cancer-related pathways, such as Kirsten rat sarcoma viral oncogene homolog (KRAS) signaling. CONCLUSION: The risk signature of eight autophagy-related lncRNAs has prognostic potential for colorectal cancer. These autophagy-related lncRNAs may play a vital role in the biology of colorectal cancer.

An automated detection system for colonoscopy images using a dual encoder-decoder model.

Conventional computer-aided detection systems (CADs) for colonoscopic images utilize shape, texture, or temporal information to detect polyps, so they have limited sensitivity and specificity. This study proposes a method to extract possible polyp features automatically using convolutional neural networks (CNNs). The objective of this work aims at building up a light-weight dual encoder-decoder model structure for polyp detection in colonoscopy Images. This proposed model, though with a relatively shallow structure, is expected to have the capability of a similar performance to the methods with much deeper structures. The proposed CAD model consists of two sequential encoder-decoder networks that consist of several CNN layers and full connection layers. The front end of the model is a hetero-associator (also known as hetero-encoder) that uses backpropagation learning to generate a set of reliably corrupted labeled images with a certain degree of similarity to a ground truth image, which eliminates the need for a large amount of training data that is usually required for medical images tasks. This dual CNN architecture generates a set of noisy images that are similar to the labeled data to train its counterpart, the auto-associator (also known as auto-encoder), in order to increase the successor's discriminative power in classification. The auto-encoder is also equipped with CNNs to simultaneously capture the features of the labeled images that contain noise. The proposed method uses features that are learned from open medical datasets and the dataset of Zhejiang University (ZJU), which contains around one thousand images. The performance of the proposed architecture is compared with a state-of-the-art detection model in terms of the metrics of the Jaccard index, the DICE similarity score, and two other geometric measures. The improvements in the performance of the proposed model are attributed to the effective reduction in false positives in the auto-encoder and the generation of noisy candidate images by the hetero-encoder.

FOLFOX treatment response prediction in metastatic or recurrent colorectal cancer patients via machine learning algorithms.

Early identification of metastatic or recurrent colorectal cancer (CRC) patients who will be sensitive to FOLFOX (5-FU, leucovorin and oxaliplatin) therapy is very important. We performed microarray meta-analysis to identify differentially expressed genes (DEGs) between FOLFOX responders and nonresponders in metastatic or recurrent CRC patients, and found that the expression levels of WASHC4, HELZ, ERN1, RPS6KB1, and APPBP2 were downregulated, while the expression levels of IRF7, EML3, LYPLA2, DRAP1, RNH1, PKP3, TSPAN17, LSS, MLKL, PPP1R7, GCDH, C19ORF24, and CCDC124 were upregulated in FOLFOX responders compared with nonresponders. Subsequent functional annotation showed that DEGs were significantly enriched in autophagy, ErbB signaling pathway, mitophagy, endocytosis, FoxO signaling pathway, apoptosis, and antifolate resistance pathways. Based on those candidate genes, several machine learning algorithms were applied to the training set, then performances of models were assessed via the cross validation method. Candidate models with the best tuning parameters were applied to the test set and the final model showed satisfactory performance. In addition, we also reported that MLKL and CCDC124 gene expression were independent prognostic factors for metastatic CRC patients undergoing FOLFOX therapy.