Prognostic Strategies Research Articles

Anomaly detection and multi-step estimation based remaining useful life prediction for rolling element bearings

The prediction of the Remaining Useful Life (RUL) of rotating machinery targets the avoidance of sudden machine failures and the optimization of the maintenance schedules as well as the management of repairs and replacements. A number of statistical model-based prognostics methodologies have been proposed in recent literature but a number of open challenges still exist, blocking their integration in the industry: (i) The extraction of a high-quality Health Indicator (HI) is critical for bearings’ prognostics but till now the trend of many classic HIs is often disturbed; deviating from a monotonical increase or decrease. (ii) The detection of the Start Prediction Time (SPT) on the HI is usually required in order to improve the accuracy of the RUL estimation but it can be incorrect especially when distinct random outliers occur. (iii) The widely applied RUL estimators, e.g. the Kalman filter (KF) and the Particle filter (PF), belong to the category of single-step estimation techniques that assume that the current step estimation depends only on the state of the previous step. However, the occurrence of bearings’ damage is usually not a sudden change but an accumulated process. Therefore a novel prognostic strategy for Rolling Element Bearings (REB) is proposed in this paper, which integrates a robust anomaly detection technique, the Support Vector Data Description (SVDD), with a multi-step estimation method, the Moving Horizon Estimation (MHE). Various advanced entropy and sparsity HIs are extracted by signals filtered at different frequency bands. By comparing all the extracted HIs based on a proposed criterion, a premium prognostic HI is chosen from a specific frequency band. Moreover, the SVDD, deployed and combined with several proposed constraints, can robustly detect the occurrence of a bearing fault and decide the proper SPT. Furthermore, the MHE is combined with two popular exponential statistical models and a second-order polynomial model for bearings’ prognostics. Experimental results from fifteen degraded bearings demonstrate that the MHE outperforms the classic Kalman filter and Particle filter. Moreover, the polynomial model achieves a better RUL estimation compared to the two classic exponential models in combination with the MHE.

Clinical predictions of COVID-19 patients using deep stacking neural networks.

The coronavirus disease 2019 (COVID-19) pandemic, which emerged in late 2019, has caused millions of infections and fatalities globally, disrupting various aspects of human society, including socioeconomic, political, and educational systems. One of the key challenges during the COVID-19 pandemic is accurately predicting the clinical development and outcome of the infected patients. In response, scientists and medical professionals globally have mobilized to develop prognostic strategies such as risk scores, biomarkers, and machine learning models to predict the clinical course and outcomes of COVID-19 patients. In this contribution, we deployed a mathematical approach called matrix factorization feature selection to select the most relevant features from the anonymized laboratory biomarkers and demographic data of COVID-19 patients. Based on these features, developed a model that leverages the deep stacking neural network (DSNN) to aid in clinical care by predicting patients' mortality risk. To gauge the performance of our suggested model, performed a comparative analysis with principal component analysis plus support vector machine, deep learning, and random forest, achieving outstanding performances. The DSNN model outperformed all the other models in terms of area under the curve (96.0%), F1-score (98.1%), recall (98.5%), accuracy (99.0%), precision (97.7%), specificity (97.0%), and maximum probability of correction decision (93.4%). Our model outperforms the clinical predictive models regarding patient mortality risk and classification in the literature. Therefore, we conclude that our robust model can help healthcare professionals to manage COVID-19 patients more effectively. We expect that early prediction of COVID-19 patients and preventive interventions can reduce the mortality risk of patients.

Untangling the mechanisms of pulmonary arterial hypertension-induced right ventricular stiffening in a large animal model.

Pulmonary hypertension (PHT) is a devastating disease with low survival rates. In PHT, chronic pressure overload leads to right ventricle (RV) stiffening; thus, impeding diastolic filling. Multiple mechanisms may contribute to RV stiffening, including wall thickening, microstructural disorganization, and myocardial stiffening. The relative importance of each mechanism is unclear. Our objective is to use a large animal model to untangle these mechanisms. Thus, we induced pulmonary arterial hypertension (PAH) in sheep via pulmonary artery banding. After eight weeks, the hearts underwent anatomic and diffusion tensor MRI to characterize wall thickening and microstructural disorganization. Additionally, myocardial samples underwent histological and gene expression analyses to quantify compositional changes and mechanical testing to quantify myocardial stiffening. Finally, we used finite element modeling to disentangle the relative importance of each stiffening mechanism. We found that the RVs of PAH animals thickened most at the base and the free wall and that PAH induced excessive collagen synthesis, increased cardiomyocyte cross-sectional area, and led to microstructural disorganization, consistent with increased expression of fibrotic genes. We also found that the myocardium itself stiffened significantly. Importantly, myocardial stiffening correlated significantly with collagen synthesis. Finally, our computational models predicted that myocardial stiffness contributes to RV stiffening significantly more than other mechanisms. Thus, myocardial stiffening may be the most important predictor for PAH progression. Given the correlation between myocardial stiffness and collagen synthesis, collagen-sensitive imaging modalities may be useful for estimating myocardial stiffness and predicting PAH outcomes. STATEMENT OF SIGNIFICANCE: Ventricular stiffening is a significant contributor to pulmonary hypertension-induced right heart failure. However, the mechanisms that lead to ventricular stiffening are not fully understood. The novelty of our work lies in answering this question through the use of a large animal model in combination with spatially- and directionally sensitive experimental techniques. We find that myocardial stiffness is the primary mechanism that leads to ventricular stiffening. Clinically, this knowledge may be used to improve diagnostic, prognostic, and therapeutic strategies for patients with pulmonary hypertension.

Screening protective miRNAs and constructing novel lncRNAs/miRNAs/mRNAs networks and prognostic models for triple-negative breast cancer

Triple-negative breast cancer (TNBC) represents 10–20 % of all breast cancer (BC) cases and is characterized by poor prognosis. Given the urgent need to improve prognostication and develop specific therapies for TNBC, the identification of new molecular targets is of great importance. MicroRNA (miRNA) has been reported as a valuable and novel molecular target in the progression of TNBC. However, the expression and function of miRNAs in different tumors are heterogeneous. Herein, we first analyzed miRNA data from The Cancer Genome Atlas (TCGA) and surprisedly found that overexpressed miRNAs were associated with poor survival in all breast cancer patients, but the overexpressed miRNAs were associated with better survival in TNBC patients. Based on the heterogeneity of miRNA expression in TNBC, we conducted further analysis using univariate Cox proportional hazard regression models and identified 17 miRNAs with prognostic potential. Subsequently, a multivariate Cox model was employed to create a 3-miRNA prognostic model for predicting overall survival in TNBC patients. The diagnostic model exhibited an area under the curve (AUC) of 0.727, and multivariable Cox regression indicated that each covariate was associated with survival. These data indicate that this model is relatively accurate and robust for risk assessment, which have a certain value for clinical application. In order to explore the network behind the overexpressed miRNAs in TNBC, we established a novel network consisting of lncRNAs, miRNAs, and mRNAs through complete transcriptome data from matched samples in the TCGA database. In this network, IRS-1 appeared to be the top hub gene. Experimental results demonstrated that miR-15b-5p and miR-148a-3p effectively target IRS-1 in vitro, shedding light on the intricate regulatory mechanisms in TNBC mediated by the heterogeneous miRNAs. Besides, miR-148a-3p significantly inhibited cell migration and viability. Overall, this study may add valuable insights into the molecular landscape of TNBC based on miRNAs and have the potential to contribute to the development of targeted therapies and improved prognostic strategies of TNBC.

Coccidioidomycosis Osteoarticular Dissemination.

Valley fever or coccidioidomycosis is a pulmonary infection caused by species of Coccidioides fungi that are endemic to California and Arizona. Skeletal coccidioidomycosis accounts for about half of disseminated infections, with the vertebral spine being the preferred site of dissemination. Most cases of skeletal coccidioidomycosis progress to bone destruction or spread to adjacent structures such as joints, tendons, and other soft tissues, causing significant pain and restricting mobility. Manifestations of such cases are usually nonspecific, making diagnosis very challenging, especially in non-endemic areas. The lack of basic knowledge and research data on the mechanisms defining susceptibility to extrapulmonary infection, especially when it involves bones and joints, prompted us to survey available clinical and animal data to establish specific research questions that remain to be investigated. In this review, we explore published literature reviews, case reports, and case series on the dissemination of coccidioidomycosis to bones and/or joints. We highlight key differential features with other conditions and opportunities for mechanistic and basic research studies that can help develop novel diagnostic, prognostic, and treatment strategies.

Quantitative pupillometry for neuroprognostication in comatose post-cardiac arrest patients: A protocol for a predefined sub-study of the Blood pressure and Oxygenations Targets after Out-of-Hospital Cardiac Arrest (BOX)-trial

BackgroundResuscitation guidelines propose a multimodal prognostication strategy algorithm at ≥72 hours after the return of spontaneous circulation to evaluate neurological outcome for unconscious cardiac arrest survivors. Even though guidelines suggest quantitative pupillometry for assessing pupillary light reflex, threshold values are not yet validated.This study aims to validate pre-specified thresholds of quantitative pupillometry by quantitatively assessing the percentage reduction of pupillary size (qPLR) <4% and Neurological Pupil index (NPi) ≤2 and in predicting unfavorable neurological outcome. Both as an isolated predictor and combined with guideline-suggested neuron-specific enolase (NSE) threshold >60 μg L−1 in the current prognostication strategy algorithm. MethodsWe conduct this pre-planned diagnostic sub-study in the randomized, controlled, multicenter clinical trial “Blood Pressure and Oxygenation Targets after Out-of-Hospital Cardiac Arrest-trial”. Blinded to treating physicians and outcome assessors, measurements of qPLR and NPi are obtained from cardiac arrest survivors at time points (±6 hours) of admission, after 24, 48, and 72 hours, or until the time of awakening or death. DiscussionThis study will be the largest prospective study investigating the predictive performance of automated quantitative pupillometry in unconscious patients resuscitated from cardiac arrest. We will test specific threshold values of NPi ≤2 and qPLR <4% to predict unfavorable outcome following cardiac arrest. The validation of pupillometry alone and combined with NSE with the criteria of the current prognostication strategy algorithm will hopefully increase the level of evidence and support clinical neuroprognostication with automated quantitative pupillometry in unconscious post-cardiac arrest patients. Trial registrationRegistered March 30, 2017, at ClinicalTrials.gov (Identifier: NCT03141099).

Different states of stemness of glioblastoma stem cells sustain glioblastoma subtypes indicating novel clinical biomarkers and high-efficacy customized therapies

BackgroundGlioblastoma (GBM) is the most malignant among gliomas with an inevitable lethal outcome. The elucidation of the physiology and regulation of this tumor is mandatory to unravel novel target and effective therapeutics. Emerging concepts show that the minor subset of glioblastoma stem cells (GSCs) accounts for tumorigenicity, representing the true target for innovative therapies in GBM.MethodsHere, we isolated and established functionally stable and steadily expanding GSCs lines from a large cohort of GBM patients. The molecular, functional and antigenic landscape of GBM tissues and their derivative GSCs was highlited in a side-by-side comprehensive genomic and transcriptomic characterization by ANOVA and Fisher’s exact tests. GSCs’ physio-pathological hallmarks were delineated by comparing over time in vitro and in vivo their expansion, self-renewal and tumorigenic ability with hierarchical linear models for repeated measurements and Kaplan–Meier method. Candidate biomarkers performance in discriminating GBM patients’ classification emerged by classification tree and patients’ survival analysis.ResultsHere, distinct biomarker signatures together with aberrant functional programs were shown to stratify GBM patients as well as their sibling GSCs population into TCGA clusters. Of importance, GSCs cells were demonstrated to fully resemble over time the molecular features of their patient of origin. Furthermore, we pointed out the existence of distinct GSCs subsets within GBM classification, inherently endowed with different self-renewal and tumorigenic potential. Particularly, classical GSCs were identified by more undifferentiated biological hallmarks, enhanced expansion and clonal capacity as compared to the more mature, relatively slow-propagating mesenchymal and proneural cells, likely endowed with a higher potential for infiltration either ex vivo or in vivo. Importantly, the combination of DCX and EGFR markers, selectively enriched among GSCs pools, almost exactly predicted GBM patients’ clusters together with their survival and drug response.ConclusionsIn this study we report that an inherent enrichment of distinct GSCs pools underpin the functional inter-cluster variances displayed by GBM patients. We uncover two selectively represented novel functional biomarkers capable of discriminating GBM patients’ stratification, survival and drug response, setting the stage for the determination of patient-tailored diagnostic and prognostic strategies and, mostly, for the design of appropriate, patient-selective treatment protocols.

Causes and Prevention of Early-Onset Colorectal Cancer.

Sporadic colorectal cancer (CRC) has historically been considered a disease of the elderly. However, early-onset colorectal cancer (eoCRC) incidence and prevalence have steadily increased over the last few decades, highlighting the critical need for a comprehensive understanding of its causes and prevention. This research examines the numerous factors contributing to the increasing incidence of eoCRC. These factors include a combination of genetic predispositions and environmental effects. We also investigate the impact of modifiable lifestyle factors like obesity, physical inactivity, and an unhealthy diet on eoCRC risk. Understanding these factors is critical in developing future diagnostic, prognostic, disease monitoring, and therapy planning strategies in managing eoCRC and will help optimize guidelines for CRC screening.

Histological Alterations in Hashimoto's Disease: A Case-Series Ultrastructural Study.

Hashimoto's thyroiditis (HT) is an autoimmune disease exhibiting stromal fibrosis and follicular cell destruction due to lymphoplasmacytic infiltration. Besides deprecated analyses, histopathological approaches have not employed the use of electron microscopy adequately toward delineating subcellular-level interactions. Biopsies for ultrastructural investigations were obtained from the thyroids of five patients with HT after a thyroidectomy. Transmission electron microscopy (TEM) was utilized to study representative tissue specimens. Examination indicated interstitial extravasated blood cells and a plethora of plasma cells, based on their subcellular identity landmarks. These antibody-secreting cells were profoundly spotted near follicular cells, fibroblasts, and cell debris entrenched in collagenous areas. Pathological changes persistently affected subcellular components of the thyrocytes, including the nucleus, endoplasmic reticulum (ER), Golgi apparatus, mitochondria, lysosomes, and other intracellular vesicles. Interestingly, significant endothelial destruction was observed, specifically in the larger blood vessels, while the smaller vessels appeared comparatively unaffected. Our TEM findings highlight the immune-related alterations occurring within the thyroid stroma. The impaired vasculature component and remodeling have not been described ultrastructurally before; thus, further exploration is needed with regards to angiogenesis in HT in order to achieve successful prognostic, diagnostic, and treatment-monitoring strategies.

Designing acute kidney injury clinical trials.

Acute kidney injury (AKI) is a common clinical condition with various causes and is associated with increased mortality. Despite advances in supportive care, AKI increases not only the risk of premature death compared with the general population but also the risk of developing chronic kidney disease and progressing towards kidney failure. Currently, no specific therapy exists for preventing or treating AKI other than mitigating further injury and supportive care. To address this unmet need, novel therapeutic interventions targeting the underlying pathophysiology must be developed. New and well-designed clinical trials with appropriate endpoints must be subsequently designed and implemented to test the efficacy of such new interventions. Herein, we discuss predictive and prognostic enrichment strategies for patient selection, as well as primary and secondary endpoints that can be used in different clinical trial designs (specifically, prevention and treatment trials) to evaluate novel interventions and improve the outcomes of patients at a high risk of AKI or with established AKI.

A novel immune-related prognostic signature based on Chemoradiotherapy sensitivity predicts long-term survival in patients with esophageal squamous cell carcinoma.

There is a heterogenous clinical response following chemoradiotherapy (CRT) in esophageal squamous cell carcinoma (ESCC). Therefore, we aimed to study signaling pathway genes that affect CRT sensitivity and prognosis. Gene expression analyses were performed in the GEO and TCGA datasets. A immunohistochemistry (IHC) analysis was performed in pretreatment biopsies. MMP13 was found to be highly expressed in the "Pathologic Complete Response (pCR)" and "Complete Remission (CR)" and "Alive" groups. Th17 cells and MMP9/13 showed a negative correlation in immune infiltration analysis. In GSEA analysis, IL-4 and IL-13 signaling pathways were highly enriched in patients exhibiting high MMP expression in pCR and CR groups. IHC results suggested higher MMP13 & IL-4 and lower IL-17A & RORC expression in the CR group compared to the <CR (CR not achieved) group. Survival analyses further indicated that the prognosis was worse in the high IL-17A group (p=0.046, HR = 2.15). Next, a prognostic model was established. In the training cohort, AUCs for the 1/2/3/4/5-year OS were all greater than 0.70. In the two validation cohorts, 1-year AUCs were also >0.70, and the model could well distinguish high-risk and low-risk subgroups. The above results may provide guidance for developing novel treatment and prognostic strategies in ESCC patients.

Identification of a glycolysis-related miRNA Signature for Predicting Breast cancer Survival.

Breast cancer (BC) is a common type of cancer and has a poor prognosis. In this study, we collected the mRNA and miRNA expression profiles of BC patients were obtained from The Cancer Genome Atlas (TCGA) to explore a novel prognostic strategy for BC patients using bioinformatics tools. We found that six glycolysis-related miRNAs (GRmiRs, including hsa-mir-1247, hsa-mir148b, hsa-mir-133a-2, has-mir-1307, hsa-mir-195 and hsa-mir-1258) were correlated with prognosis of BC samples. The risk score model was established based on 6 prognosis-associated GRmiRs. The outcome of high risk group was significantly poorer. Cox regression analysis showed that risk score was an independent prognostic factor. Differentially expressed genes identified between high and low risk groups were mainly enriched in inflammation and immune-related signaling pathways. The proportion of infiltration of 12 kinds of immune cells in high and low risk groups were significantly different. Risk score was closely associated with many immune indexes. Multiple DEGRGs and miRNAs were associated with drugs. In conclusion, glycolysis-related miRNA signature effectively predicts BC prognosis.

Real Time Data Processing and Predictive Analytics Using Cloud Based Machine Learning

Lately, the expansion of constant checking frameworks and the rise of the Modern Web of Things (IIoT) have uncovered the need of creating calculations that are both adaptable and lined up to gauge mechanical disappointments and decide the excess helpful existence of assembling frameworks and the parts that make up those frameworks. Information driven approaches, for example, AI have acquired importance in the field of prognostics and wellbeing the executives (PHM), as opposed to customary model-based prognostic strategies, which need a significant perception of the actual elements of the framework and frequently rely upon specific stochastic cycles. The critical measure of preparing information that is required, then again, is a hindrance to the computational productivity of AI calculations for information driven PHM. To tackle this trouble, the reason for this study is to give a remarkable strategy to hardware prognostics that utilizes a cloud-based equal AI calculation. In particular, the expectation of hardware wear in dry processing processes is achieved by the utilization of the irregular backwoods strategy, which is a method that is generally used in the field of AI. What's more, an equal irregular woods method is built by utilizing the MapReduce structure, and it is then conveyed on the Amazon Flexible Register Cloud. It has been shown by means of the consequences of the trials that the arbitrary woodland calculation is compelling in delivering expectations that are extremely exact. Likewise, the execution of the equal irregular woods strategy brings about impressive execution gains, which gives additional proof of the calculation's true capacity for functional use in modern settings. DOI: https://doi.org/10.52783/tjjpt.v42.i4.6757

Physiological and pathological functions of circular RNAs in the nervous system.

Circular RNAs (circRNAs) are a class of covalently closed single-stranded RNAs that are expressed during the development of specific cells and tissues. CircRNAs play crucial roles in physiological and pathological processes by sponging microRNAs, modulating gene transcription, controlling the activity of certain RNA-binding proteins, and producing functional peptides. A key focus of research at present is the functionality of circRNAs in the nervous system and several advances have emerged over the last 2 years. However, the precise role of circRNAs in the nervous system has yet to be comprehensively reviewed. In this review, we first summarize the recently described roles of circRNAs in brain development, maturity, and aging. Then, we focus on the involvement of circRNAs in various diseases of the central nervous system, such as brain cancer, chronic neurodegenerative diseases, acute injuries of the nervous system, and neuropathic pain. A better understanding of the functionality of circRNAs will help us to develop potential diagnostic, prognostic, and therapeutic strategies to treat diseases of the nervous system.

Assessing the Feasibility of a Multimodal Approach to Pain Evaluation in Early Stages after Spinal Cord Injury.

This research evaluates the feasibility of a multimodal pain assessment protocol during rehabilitation following spinal cord injury (SCI). The protocol amalgamates clinical workup (CW), quantitative sensory testing (QST), and psychosocial factors (PSF) administered at 4 (T1), 12 (T2), and 24 (T3) weeks post injury and at discharge (T4). Molecular blood biomarkers (BB) were evaluated via gene expression and proteomic assays at T1 and T4. Different pain trajectories and temporal changes were identified using QST, with inflammation and pain-related biomarkers recorded. Higher concentrations of osteopontin and cystatin-C were found in SCI patients compared to healthy controls, indicating their potential as biomarkers. We observed altered inflammatory responses and a slight increase in ICAM-1 and CCL3 were noted, pointing towards changes in cellular adhesion linked with spinal injury and a possible connection with neuropathic pain. Despite a small patient sample hindering the correlation of feasibility data, descriptive statistical analyses were conducted on stress, depression, anxiety, quality of life, and pain interferences. The SCI Pain Instrument (SCIPI) was efficient in distinguishing between nociceptive and neuropathic pain, showing a progressive increase in severity over time. The findings emphasize the need for the careful consideration of recruitment setting and protocol adjustments to enhance the feasibility of multimodal pain evaluation studies post SCI. They also shed light on potential early adaptive mechanisms in SCI pathophysiology, warranting the further exploration of prognostic and preventive strategies for chronic pain in the SCI population.

Preliminary Prognostication for Good Neurological Outcomes in the Early Stage of Post-Cardiac Arrest Care

We investigated prognostic strategies for predicting good outcomes in the early stage of post-cardiac-arrest care using multiple prognostic tests that are available until 24 h after the return of spontaneous circulation (ROSC). A retrospective analysis was conducted on 138 out-of-hospital cardiac-arrest patients who underwent prognostic tests, including the gray–white-matter ratio (GWR-BG), the Glasgow Coma Scale motor (GCS-M) score before sedative administration, and the neuron-specific enolase (NSE) level measured at 24 h after the ROSC. We investigated the prognostic performances of the tests as single predictors and in various combination strategies. Classification and regression-tree analysis were used to provide a reliable model for the risk stratification. Out of all the patients, 55 (44.0%) had good outcomes. The NSE level showed the highest prognostic performance as a single prognostic test and provided improved specificities (&gt;70%) and sensitivities (&gt;98%) when used in combination strategies. Low NSE levels (≤32.1 ng/mL) and high GCS-M (≥4) scores identified good outcomes without misclassification. The overall accuracy for good outcomes was 81.8%. In comatose patients with low NSE levels or high GCS-M scores, the premature withdrawal of life-sustaining therapy should be avoided, thereby complying with the formal prognostication-strategy algorithm after at least 72 h from the ROSC.

Genomic Index of Sensitivity to Chemotherapy for Triple Negative Breast Cancer.

Patients with triple-negative breast cancer (TNBC) frequently develop resistance to chemotherapy. Studies have shown that microRNAs (miRNAs) are often aberrantly expressed in TNBC and are associated with drug resistance. However, a prognostic strategy that correlates miRNAs with chemotherapy resistance remains largely unknown. To identify breast cancer chemoresistance-associated miRNAs, the miRNA microarray dataset GSE71142 was downloaded from the Gene Expression Omnibus database. Differentially expressed miRNAs (DE-miRNAs) in chemoresistant groups were identified using the LIMMA package in R. Potential target genes were predicted using the miRTarBase 9. Functional and pathway enrichment analyses was done using WebGestalt. A protein-protein interaction network was visualized using Cytoscape software. The top six hub genes regulated by DE-miRNAs were identified using the random forest model. The chemotherapy resistance index (CRI) in TNBC was defined as sum of the median expression levels of the top six hub genes. The association of CRI with distant relapse risk was evaluated using point-biserial correlation coefficient in the validation cohorts of patients with TNBC. The correlation between CRI and cumulative hazard rate was estimated using the Cox model, and the predicted rate of distant relapse was obtained from the Breslow-type estimator of the survival function. All statistical computations were performed using Origin2019b. A total of 12 DE-miRNAs were screened, including six upregulated and six downregulated miRNAs in chemoresistant breast cancer tissues compared with chemosensitive tissues. Based on fold changes, miR-214-3p, miR-4758-3p, miR-200c-3p, miR-4254, miR-140-3p, and miR-24-3p were the top six most upregulated miRNAs, whereas miR-142-5p, miR-146-5p, miR-1268b, miR-1275, miR-4447, and miR-4472 were the top six most downregulated miRNAs. The top three hub genes for upregulated miRNAs were RAC1, MYC, and CCND1 and for downregulated miRNAs were IL-6, SOCS1, and PDGFRA. CRI was significantly associated with the risk of distant relapse. CRI predicted survival benefits with reduced hazard rate.

A digital twin framework for prognostics and health management

Despite rapid advances in modeling and analysis technology, the manufacturing industry has been slow to implement prognostic and health management strategies. A cause of this delay is the individualized focus of most health monitoring solutions, which makes it difficult to deploy and reuse modeling resources across manufacturing equipment fleets. This paper presents a digital twin-based framework that standardizes communication and organization of modeling resources used for health monitoring, a critical aspect of prognostics and health management. The framework is based on a novel, state-based model of mechanical system health that can be reused across manufacturing machines and components. A set of modular digital twin classes enables the creation of extensible digital twin hierarchies for monitoring the health of complex systems. A case study implements this framework to standardize fault detection results for the seal and bearing systems of an industrial pump. The framework’s standardized DT classes and aggregation relationships allow component-level models to be re-used and aggregated to predict faults in the pump’s bearing system.

Multi-clinical index classifier combined with AI algorithm model to predict the prognosis of gallbladder cancer.

It is significant to develop effective prognostic strategies and techniques for improving the survival rate of gallbladder carcinoma (GBC). We aim to develop the prediction model from multi-clinical indicators combined artificial intelligence (AI) algorithm for the prognosis of GBC. A total of 122 patients with GBC from January 2015 to December 2019 were collected in this study. Based on the analysis of correlation, relative risk, receiver operator characteristic curve, and importance by AI algorithm analysis between clinical factors and recurrence and survival, the two multi-index classifiers (MIC1 and MIC2) were obtained. The two classifiers combined eight AI algorithms to model the recurrence and survival. The two models with the highest area under the curve (AUC) were selected to test the performance of prognosis prediction in the testing dataset. The MIC1 has ten indicators, and the MIC2 has nine indicators. The combination of the MIC1 classifier and the "avNNet" model can predict recurrence with an AUC of 0.944. The MIC2 classifier and "glmet" model combination can predict survival with an AUC of 0.882. The Kaplan-Meier analysis shows that MIC1 and MIC2 indicators can effectively predict the median survival of DFS and OS, and there is no statistically significant difference in the prediction results of the indicators (MIC1: χ2 = 6.849, P = 0.653; MIC2: χ2 = 9.14, P = 0.519). The MIC1 and MIC2 combined with avNNet and mda models have high sensitivity and specificity in predicting the prognosis of GBC.

Cord blood cardiovascular biomarkers in tetralogy of fallot and D-transposition of great arteries.

A prospective cohort study (2014-2019), including fetuses with isolated ToF and D-TGA and healthy controls, was conducted at two tertiary referral centers for CHD in Barcelona. Obstetric ultrasound and fetal echocardiography were performed in the third trimester and cord blood was obtained at delivery. Cord blood concentrations of N-terminal precursor of B-type natriuretic peptide, Troponin I, transforming growth factorβ (TGFβ), placental growth factor, and soluble fms-like tyrosine kinase-1 were determined. Thirty-four fetuses with conotruncal-CHD (22 ToF and 12 D-TGA) and 36 controls were included. ToF-fetuses showed markedly increased cord blood TGFβ (24.9 ng/ml (15.6-45.3) vs. normal heart 15.7 ng/ml (7.2-24.3) vs. D-TGA 12.6 ng/ml (8.7-37.9); P = 0.012). These results remained statistically significant even after adjusting for maternal body mass index, birth weight and mode of delivery. TGFß levels showed a negative correlation with the pulmonary valve diameter z-score at fetal echocardiography (r = -0.576, P = 0.039). No other differences were found in the rest of cord blood biomarkers among the study populations. Likewise, no other significant correlations were identified between cardiovascular biomarkers, fetal echocardiography and perinatal outcome. This study newly describes increased cord blood TGFβ concentrations in ToF compared to D-TGA and normal fetuses. We also demonstrate that TGFβ levels correlate with the severity of right ventricle outflow obstruction. These novel findings open a window of research opportunities on new prognostic and potential preventive strategies.