Health Information Science and Systems最新文献

Prostate cancer is the most common cancer in men worldwide and has a high mortality rate. The complex and heterogeneous development of prostate cancer has become a core obstacle in the treatment of prostate cancer. Simultaneously, the issues of overtreatment in early-stage diagnosis, oligometastasis and dormant tumor recognition, as well as personalized drug utilization, are also specific concerns that require attention in the clinical management of prostate cancer. Some typical genetic mutations have been proved to be associated with prostate cancer's initiation and progression. However, single-omic studies usually are not able to explain the causal relationship between molecular alterations and clinical phenotypes. Exploration from a systems genetics perspective is also lacking in this field, that is, the impact of gene network, the environmental factors, and even lifestyle behaviors on disease progression. At the meantime, current trend emphasizes the utilization of artificial intelligence (AI) and machine learning techniques to process extensive multidimensional data, including multi-omics. These technologies unveil the potential patterns, correlations, and insights related to diseases, thereby aiding the interpretable clinical decision making and applications, namely intelligent medicine. Therefore, there is a pressing need to integrate multidimensional data for identification of molecular subtypes, prediction of cancer progression and aggressiveness, along with perosonalized treatment performing. In this review, we systematically elaborated the landscape from molecular mechanism discovery of prostate cancer to clinical translational applications. We discussed the molecular profiles and clinical manifestations of prostate cancer heterogeneity, the identification of different states of prostate cancer, as well as corresponding precision medicine practices. Taking multi-omics fusion, systems genetics, and intelligence medicine as the main perspectives, the current research results and knowledge-driven research path of prostate cancer were summarized.

Cardiovascular disease (CVDs) has become one of the leading causes of death, posing a significant threat to human life. The development of reliable Artificial Intelligence (AI) assisted diagnosis algorithms for cardiac sounds is of great significance for early detection and treatment of CVDs. However, there is scarce research in this field. Existing research mainly faces three major challenges: (1) They mainly limited to murmur classification and cannot achieve murmur grading, but attempting both classification and grading may lead to negative effects between different multi-tasks. (2) They mostly pay attention to unstructured cardiac sound modality and do not consider the structured demographic modality, as it is difficult to balance the influence of heterogeneous modalities. (3) Deep learning methods lack interpretability, which makes it challenging to apply them clinically. To tackle these challenges, we propose a method for cardiac murmur grading and cardiac risk analysis based on heterogeneous modality adaptive multi-task learning. Specifically, a Hierarchical Multi-Task learning-based cardiac murmur detection and grading method (HMT) is proposed to prevent negative interference between different tasks. In addition, a cardiac risk analysis method based on Heterogeneous Multi-modal feature impact Adaptation (HMA) is also proposed, which transforms unstructured modality into structured modality representation, and utilizes an adaptive mode weight learning mechanism to balance the impact between unstructured modality and structured modality, thus enhancing the performance of cardiac risk prediction. Finally, we propose a multi-task interpretability learning module that incorporates an important evaluation using random masks. This module utilizes SHAP graphs to visualize crucial murmur segments in cardiac sound and employs a multi-factor risk decoupling model based on nomograms. And then we gain insights into the cardiac disease risk in both pre-decoupled multi-modality and post-decoupled single-modality scenarios, thus providing a solid foundation for AI assisted cardiac murmur grading and risk analysis. Experimental results on a large real-world CirCor DigiScope PCG dataset demonstrate that the proposed method outperforms the state-of-the-art (SOTA) method in murmur detection, grading, and cardiac risk analysis, while also providing valuable diagnostic evidence.

Counting the repetition of human exercise and physical rehabilitation is common in rehabilitation and exercise training. The existing vision-based repetition counting methods less emphasize the concurrent motions in the same video, and counting skeleton in different view angles. This work analyzed the spectrogram of the pose estimation cosine similarity to count the repetition. Besides the public datasets. This work also collected exercise videos from 11 adults to verify that the proposed method can handle concurrent motion and different view angles. The presented method was validated on the University of Idaho Physical Rehabilitation Movements Data Set (UI-PRMD) and MM-fit dataset. The overall mean absolute error (MAE) for MM-fit was 0.06 with off-by-one Accuracy (OBOA) of 0.94. As for the UI-PRMD dataset, MAE was 0.06 with OBOA 0.95. We have also tested the performance in various camera locations and concurrent motions with 57 skeleton time-series videos with an overall MAE of 0.07 and OBOA of 0.91. The proposed method provides a view-angle and motion agnostic concurrent motion counting. This method can potentially use in large-scale remote rehabilitation and exercise training with only one camera.

Supplementary information: The online version contains supplementary material available at 10.1007/s13755-023-00258-3.

As medical treatments continue to advance rapidly, minimally invasive surgery (MIS) has found extensive applications across various clinical procedures. Accurate identification of medical instruments plays a vital role in comprehending surgical situations and facilitating endoscopic image-guided surgical procedures. However, the endoscopic instrument detection poses a great challenge owing to the narrow operating space, with various interfering factors (e.g. smoke, blood, body fluids) and inevitable issues (e.g. mirror reflection, visual obstruction, illumination variation) in the surgery. To promote surgical efficiency and safety in MIS, this paper proposes a cross-layer aggregated attention detection network (CLAD-Net) for accurate and real-time detection of endoscopic instruments in complex surgical scenarios. We propose a cross-layer aggregation attention module to enhance the fusion of features and raise the effectiveness of lateral propagation of feature information. We propose a composite attention mechanism (CAM) to extract contextual information at different scales and model the importance of each channel in the feature map, mitigate the information loss due to feature fusion, and effectively solve the problem of inconsistent target size and low contrast in complex contexts. Moreover, the proposed feature refinement module (RM) enhances the network's ability to extract target edge and detail information by adaptively adjusting the feature weights to fuse different layers of features. The performance of CLAD-Net was evaluated using a public laparoscopic dataset Cholec80 and another set of neuroendoscopic dataset from Sun Yat-sen University Cancer Center. From both datasets and comparisons, CLAD-Net achieves the $A{P}_{0.5}$ of 98.9% and 98.6%, respectively, that is better than advanced detection networks. A video for the real-time detection is presented in the following link: https://github.com/A0268/video-demo.

The most prevalent malignant illness of the gastrointestinal system, colorectal cancer, is the third most prevalent cancer in males and the second most prevalent cancer in women. Importin-11 is a protein that acts as a regulator of cancer cell proliferation in colorectal tumours by conveying $\beta$-catenin to the cell nucleus. However, the IPO11 gene was found to encode a protein called Importin-11, which functions as a nucleus importer for the cell. As a result, preventing $\beta$-catenin from entering the nucleus requires blocking Importin-11. As a result, we conducted a multi-omics investigation to assess IPO11 gene potential as a therapeutic biomarker for human colorectal cancer (CC). Oncomine, GEPIA2, immunohisto-chemistry, and UALCAN databases were used to analyses the mRNA expression profiles of IPO11 in CC. The investigation has yielded clear evidence of the increase of IPO11 expression in CC subtypes, as indicated by the data acquired. Analysing CC research from the cBioPortal database, the study discovered three new missense mutations in the importin-11 protein sequence at a frequency of 0.00-1.50% copy number changes. Additionally, the Kaplan-Meier plots demonstrated a strong connection concerning IPO11 downregulation and a poorer CC patient survival rate. The co-expressed gene profile of IPO11 was likewise associated with the onset of CC. IPO11 co-expressed gene profile was also linked to CC development. Moreover, the correlation analysis using bc-GenExMiner and the UCSC Xena server identified KIF2A as the most positively co-expressed gene. The study found that KIF2A and its co-expressed genes were involved in a wide variety of cancer progression pathways using the Enrichr database. Cumulatively, this result will not only provide new information about the expression of IPO11 associated with CC progression and patient survival, but could also serve as a therapeutic biomarker for treating CC in a significant and worthwhile manner.

Supplementary information: The online version contains supplementary material available at 10.1007/s13755-023-00259-2.

Background: Lead, an environmental toxicant, accounts for 0.6% of the global burden of disease, with the highest burden in developing countries. Lead poisoning is very much preventable with adequate and timely action. Therefore, it is important to identify factors that contribute to maternal BLL and minimise them to reduce the transfer to the foetus. Literacy and awareness related to its impact are low and the clinical establishment for biological monitoring of blood lead level (BLL) is low, costly, and time-consuming. A significant contribution to an infant's BLL load is caused by maternal lead transfer during pregnancy. This acts as the first pathway to the infant's lead exposure. The social and demographic information that includes lifestyle and environmental factors are key to maternal lead exposure.

Results: We propose a novel approach to build a computational model framework that can predict lead toxicity levels in maternal blood using a set of sociodemographic features. To illustrate our proposed approach, maternal data comprising socio-demographic features and blood samples from the pregnant woman is collected, analysed, and modelled. The computational model is built that learns from the maternal data and then predicts lead level in a pregnant woman using a set of questionnaires that relate to the maternal's social and demographic information as the first point of testing. The range of features identified in the built models can estimate the underlying function and provide an understanding of the toxicity level. Following feature selection methods, the 12-feature set obtained from the Boruta algorithm gave better prediction results (kNN = 76.84%, DT = 74.70%, and NN = 73.99%).

Conclusion: The built prediction model can be beneficial in improving the point of care and hence reducing the cost and the risk involved. It is envisaged that in future, the proposed methodology will become a part of a screening process to assist healthcare experts at the point of evaluating the lead toxicity level in pregnant women. Women screened positive could be given a range of facilities including preliminary counselling to being referred to the health centre for further diagnosis. Steps could be taken to reduce maternal lead exposure; hence, it could also be possible to mitigate the infant's lead exposure by reducing transfer from the pregnant woman.

Essential proteins play a vital role in development and reproduction of cells. The identification of essential proteins helps to understand the basic survival of cells. Due to time-consuming, costly and inefficient with biological experimental methods for discovering essential proteins, computational methods have gained increasing attention. In the initial stage, essential proteins are mainly identified by the centralities based on protein-protein interaction (PPI) networks, which limit their identification rate due to many false positives in PPI networks. In this study, a purified PPI network is firstly introduced to reduce the impact of false positives in the PPI network. Secondly, by analyzing the similarity relationship between a protein and its neighbors in the PPI network, a new centrality called neighborhood similarity centrality (NSC) is proposed. Thirdly, based on the subcellular localization and orthologous data, the protein subcellular localization score and ortholog score are calculated, respectively. Fourthly, by analyzing a large number of methods based on multi-feature fusion, it is found that there is a special relationship among features, which is called dominance relationship, then, a novel model based on dominance relationship is proposed. Finally, NSC, subcellular localization score, and ortholog score are fused by the dominance relationship model, and a new method called NSO is proposed. In order to verify the performance of NSO, the seven representative methods (ION, NCCO, E_POC, SON, JDC, PeC, WDC) are compared on yeast datasets. The experimental results show that the NSO method has higher identification rate than other methods.

Finding patterns among risk factors and chronic illness can suggest similar causes, provide guidance to improve healthy lifestyles, and give clues for possible treatments for outliers. Prior studies have typically isolated data challenges from single-disease datasets. However, the predictive power of multiple diseases is more helpful in establishing a healthy lifestyle than investigating one disease. Most studies typically focus on single-disease datasets; however, to ensure that health advice is generalized and contemporary, the features that predict the likelihood of many diseases can improve health advice effectiveness when considering the patient's point of view. We construct and present a novel knowledge-based qualitative method to remove redundant features from a dataset and redefine the outliers. The results of our trials upon five annual chronic disease health surveys demonstrate that our Knowledge Graph-based feature selection, when applied to many machine learning and deep learning multi-label classifiers, can improve classification performance. Our methodology is compatible with future directions, such as graph neural networks. It provides clinicians with an efficient process to select the most relevant health survey questions and responses regarding single or many human organ systems.