An artificial intelligence method for predicting postoperative urinary incontinence based on multiple anatomic parameters of MRI.

Background: Deep learning methods are increasingly applied in the medical field; however, their lack of interpretability remains a challenge. Captum is a tool that can be used to interpret neural network models by computing feature importance weights. Although Captum is an interpretable model, it is rarely used to study medical problems, and there is a scarcity of data regarding MRI anatomical measurements for patients with prostate cancer after undergoing Robotic-Assisted Radical Prostatectomy (RARP). Consequently, predictive models for continence that use multiple types of anatomical MRI measurements are limited. Methods: We explored the energy efficiency of deep learning models for predicting continence by analyzing MRI measurements. We analyzed and compared various statistical models and provided reference examples for the clinical application of interpretable deep-learning models. Patients who underwent RARP at our institution between July 2019 and December 2020 were included in this study. A series of clinical MRI anatomical measurements from these patients was used to discover continence features, and their impact on continence was primarily evaluated using a series of statistical methods and computational models. Results: Age and six other anatomical measurements were identified as the top seven features of continence by the proposed model UINet7 with an accuracy of 0.97, and the first four of these features were also found by primary statistical analysis. Conclusions: This study fills the gaps in the in-depth investigation of continence features after RARP due to the limitations of clinical data and applicable models. We provide a pioneering example of the application of deep-learning models to clinical problems. The interpretability analysis of deep learning models has the potential for clinical applications.

Attenuated iron stress and oxidative stress may participate in anti-seizure and neuroprotective roles of xenon in pentylenetetrazole-induced epileptogenesis.

The previous studies have demonstrated the excellent neuroprotective effects of xenon. In this study, we verified the anti-seizure and neuroprotective roles of xenon in epileptogenesis and evaluated the involvement of oxidative stress and iron accumulation in the protective roles of xenon. Epileptogenesis was induced by pentylenetetrazole (PTZ) treatment in Sprague-Dawley rats. During epileptogenesis, we found increased levels of iron and oxidative stress accompanied by elevated levels of divalent metal transporter protein 1 and iron regulatory protein 1, which are closely associated with iron accumulation. Meanwhile, the levels of autophagy and mitophagy increased, alongside significant neuronal damage and cognitive deficits. Xenon treatment reversed these effects: oxidative stress and iron stress were reduced, neuronal injury and seizure severity were attenuated, and learning and memory deficits were improved. Thus, our results confirmed the neuroprotective and anti-seizure effects of xenon treatment in PTZ-induced epileptogenesis. The reduction in oxidative and iron stress may be the main mechanisms underlying xenon treatment. Thus, this study provides a potential intervention strategy for epileptogenesis.

Modeling the Virus Infection at the Population Level.

As pointed out by many researchers in the last few decades, differential equations with fractional (non-integer) order differential operators, in comparison with classical integer order ones, have apparent advantages in modeling. A Caputo fractional order system of ordinary differential equations is introduced to model the virus infection at the population level in this chapter. As well known, there are two main methods to study the dynamics of a model: qualitative analysis and numerical modeling. Here the qualitative analysis, including uniqueness, invariant set, and stability, is first presented with intuitive derivation. Then the famous genetic algorithm is introduced to numerically model the dynamics of virus infection, i.e. to adjust the parameters of the Caputo fractional model such that its solution can properly fit real data and predict future.

Biomarkers discovery for endometrial cancer: A graph convolutional sample network method.

BACKGROUND: Endometrial carcinoma is the sixth most common cancer in women worldwide. Importantly, endometrial cancer is among the few types of cancers with patient mortality that is still increasing, which indicates that the improvement in its diagnosis and treatment is still urgent. Moreover, biomarker discovery is essential for precise classification and prognostic prediction of endometrial cancer. METHODS: A novel graph convolutional sample network method was used to identify and validate biomarkers for the classification of endometrial cancer. The sample networks were first constructed for each sample, and the gene pairs with high frequencies were identified to construct a subtype-specific network. Putative biomarkers were then screened using the highest degrees in the subtype-specific network. Finally, simplified sample networks are constructed using the biomarkers for the graph convolutional network (GCN) training and prediction. RESULTS: Putative biomarkers (23) were identified using the novel bioinformatics model. These biomarkers were then rationalised with functional analyses and were found to be correlated to disease survival with network entropy characterisation. These biomarkers will be helpful in future investigations of the molecular mechanisms and therapeutic targets of endometrial cancers. CONCLUSIONS: A novel bioinformatics model combining sample network construction with GCN modelling is proposed and validated for biomarker discovery in endometrial cancer. The model can be generalized and applied to biomarker discovery in other complex diseases.

MIKB: A manually curated and comprehensive knowledge base for myocardial infarction.

Myocardial infarction knowledge base (MIKB; http://www.sysbio.org.cn/mikb/; latest update: December 31, 2020) is an open-access and manually curated database dedicated to integrating knowledge about MI to improve the efficiency of translational MI research. MIKB is an updated and expanded version of our previous MI Risk Knowledge Base (MIRKB), which integrated MI-related risk factors and risk models for providing help in risk assessment or diagnostic prediction of MI. The updated MIRKB includes 9701 records with 2054 single factors, 209 combined factors, 243 risk models, 37 MI subtypes and 3406 interactions between single factors and MIs collected from 4817 research articles. The expanded functional module, i.e. MIGD, is a database including not only MI associated genetic variants, but also the other multi-omics factors and the annotations for their functional alterations. The goal of MIGD is to provide a multi-omics level understanding of the molecular pathogenesis of MI. MIGD includes 1782 omics factors, 28 MI subtypes and 2347 omics factor-MI interactions as well as 1253 genes and 6 chromosomal alterations collected from 2647 research articles. The functions of MI associated genes and their interaction with drugs were analyzed. MIKB will be continuously updated and optimized to provide precision and comprehensive knowledge for the study of heterogeneous and personalized MI.

Designing Highly Luminescent Cellulose Nanocrystals with Modulated Morphology for Multifunctional Bioimaging Materials.

Spherical cellulose nanocrystals (SCNs) and rod-shaped cellulose nanocrystals (RCNs) were extracted from different cellulose materials. The two shape forms of cellulose nanocrystals (CNs) were designed with a combination of isothiocyanate (FITC), and both the obtained FITC-SCNs and FITC-RCNs exhibited high fluorescence brightness. The surfaces of SCNs and RCNs were subjected to a secondary imino group by a Schiff reaction and then covalently bonded to the isothiocyanate group of FITC through a secondary imino group to obtain fluorescent cellulose nanocrystals (FITC-CNs). The absolute ζ-potential and dispersion stability of FITC-CNs (FITC-SCNs and FITC-RCNs) were improved, which also promoted the increase in the fluorescence quantum yield. FITC-RCNs had a fluorescence quantum yield of 30.7%, and FITC-SCNs had a morphological advantage (better dispersion, etc.), resulting in a higher fluorescence quantum yield of 35.9%. Cell cytotoxicity experiments demonstrated that the process of FITC-CNs entering mouse osteoblasts (MC3T3) did not destroy the cell membrane, showing good biocompatibility. On the other hand, FITC-CNs with good dispersibility can significantly enhance poly(vinyl alcohol) (PVA) and poly(lactic acid) (PLA); their mechanical properties were improved (the highest sample reached to 243%) and their fluorescent properties were imparted. This study provides a simple surface functionalization method to produce high-luminance fluorescent materials for bioimaging, multifunctional nanoenhancement/dispersion marking, and anticounterfeiting materials.

Extracting predictors for lung adenocarcinoma based on Granger causality test and stepwise character selection.

BACKGROUND: Lung adenocarcinoma is the most common type of lung cancer, with high mortality worldwide. Its occurrence and development were thoroughly studied by high-throughput expression microarray, which produced abundant data on gene expression, DNA methylation, and miRNA quantification. However, the hub genes, which can be served as bio-markers for discriminating cancer and healthy individuals, are not well screened. RESULT: Here we present a new method for extracting gene predictors, aiming to obtain the least predictors without losing the efficiency. We firstly analyzed three different expression microarrays and constructed multi-interaction network, since the individual expression dataset is not enough for describing biological behaviors dynamically and systematically. Then, we transformed the undirected interaction network to directed network by employing Granger causality test, followed by the predictors screened with the use of the stepwise character selection algorithm. Six predictors, including TOP2A, GRK5, SIRT7, MCM7, EGFR, and COL1A2, were ultimately identified. All the predictors are the cancer-related, and the number is very small fascinating diagnosis. Finally, the validation of this approach was verified by robustness analyses applied to six independent datasets; the precision is up to 95.3% ∼ 100%. CONCLUSION: Although there are complicated differences between cancer and normal cells in gene functions, cancer cells could be differentiated in case that a group of special genes expresses abnormally. Here we presented a new, robust, and effective method for extracting gene predictors. We identified as low as 6 genes which can be taken as predictors for diagnosing lung adenocarcinoma.

High Aspect Ratio Carboxylated Cellulose Nanofibers Cross-linked to Robust Aerogels for Superabsorption-Flocculants: Paving Way from Nanoscale to Macroscale.

Charged nanocellulose (NC) with a high aspect ratio (larger than 100) extracted from animal or bacterial cellulose and chemical cross-linked NC aerogels have great promising applicability in material science, but facile fabrication of such NC aerogels from plant cellulose by physical cross-linking still remains a major challenge. In this work, carboxylated cellulose nanofiber (CNF) with the highest aspect ratio of 144 was extracted from wasted ginger fibers by a simple one-step acid hydrolysis. Our approach could easily make the carboxylated CNF assemble into robust bulk aerogels with tunable densities and desirable shapes on a large scale (3D macropores to mesopores) by hydrogen bonds. Excitingly, these CNF aerogels had better compression mechanical properties (99.5 kPa at 80% strain) and high shape recovery. Moreover, the CNF aerogels had strong coagulation-flocculation ability (87.1%), removal efficiency of MB dye uptake (127.73 mg/g), and moderate Cu2+ absorption capacity (45.053 mg/g), which were due to assistance mechanisms of charge neutralization, network capture effect, and chain bridging of high aspect ratio carboxylated CNF. This provided a novel physical cross-linking method to design robust aerogels with modulated networked structures to be a general substrate material for industrial applications such as superabsorbent, flocculation, oil-water separation, and potential electrical energy storage materials.