Search Results (35)

Background: Heart failure (HF) ranks among the foremost causes of mortality globally, exhibiting particularly high prevalence and significant impact within intensive care units (ICUs). This study sought to develop, validate, and deploy a time-dependent machine learning model aimed at predicting the one-year all-cause mortality risk in ICU patients diagnosed with HF, thereby facilitating precise prognostic evaluation and risk stratification. Methods: This study encompassed a cohort of 8960 ICU patients with HF sourced from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database (version 3.1). This latest version of the database added data from 2020 to 2022 on the basis of version 2.2 (covering data from 2008 to 2019); therefore, data spanning 2008 to 2019 (n = 5748) were designated for the training set, while data from 2020 to 2022 (n = 3212) were reserved for the test set. The primary endpoint of interest was one-year all-cause mortality. Least Absolute Shrinkage and Selection Operator (LASSO) regression was employed to select predictive features from an initial pool of 64 candidate variables (including demographic characteristics, vital signs, comorbidities and complications, therapeutic interventions, routine laboratory data, and disease severity scores). Four predictive models were developed and compared: Cox proportional hazards, random survival forest (RSF), Cox proportional hazards deep neural network (DeepSurv), and eXtreme Gradient Boosting (XGBoost). Model performance was assessed using the concordance index (C-index) and Brier score, with model interpretability addressed through SHapley Additive exPlanations (SHAP) and time-dependent Survival SHapley Additive exPlanations (SurvSHAP(t)). Results: This study revealed a one-year mortality rate of 46.1% within the population under investigation. In the training set, LASSO effectively identified 24 features in the model. In the test set, the XGBoost model exhibited superior predictive performance, as evidenced by a C-index of 0.772 and a Brier score of 0.161, outperforming the Cox model (C-index: 0.740, Brier score: 0.175), the RSF model (C-index: 0.747, Brier score: 0.178), and the DeepSur model (C-index: 0.723, Brier score: 0.183). Decision curve analysis validated the clinical utility of the XGBoost model across a broad spectrum of risk thresholds. Feature importance analysis identified the red cell distribution width-to-albumin ratio (RAR), Charlson Comorbidity Index, Simplified Acute Physiology Score II (SAPS II), Acute Physiology Score III (APS III), and the age–bilirubin–INR–creatinine (ABIC) score as the top five predictive factors. Consequently, an online risk prediction tool based on this model has been developed and is publicly accessible. Conclusions: The time-dependent XGBoost model demonstrated robust predictive capability in evaluating the one-year all-cause mortality risk in critically ill HF patients. This model offered a useful tool for early risk identification and supported timely interventions. Full article

Complex regional pain syndrome (CRPS) is an idiopathic, highly debilitating chronic disorder with persistent regional pain accompanied by a combination of sensory, motor, and autonomic abnormalities. It is not only difficult to treat but also difficult to study. This scoping review aimed to identify the key clinical and molecular challenges encountered in CRPS research and to examine the assessment tools currently employed. A comprehensive search was conducted across PubMed/Medline, Science Direct, Scopus, Wiley Online Library, and Google Scholar using a combination of free text and MeSH terms related to CRPS, clinical and molecular aspects, neuroinflammation, biomarkers, and research challenges. We analyzed 55 original clinical research papers on CRPS and 17 studies of immunological/biochemical/molecular aspects of CRPS. A significant degree of heterogeneity was observed in the methodologies employed across the reviewed studies. The most frequently reported challenges included difficulties in participant recruitment and controlling confounding factors (reported in 62% of studies), such as the heterogeneity of the patient population, the influence of pain coping strategies and psychological factors, and the impact of sociocultural factors (reported in 62% of studies). Research into diagnostic and prognostic markers for CRPS also faces numerous challenges. Recruiting participants is difficult due to the rarity of the condition, resulting in small sample sizes for studies. In vitro models often fail to replicate the complexity of in vivo inflammation, limiting their applicability. Findings from early CRPS stages may not generalize to chronic CRPS because of differing pathophysiological mechanisms and symptom profiles. Additional obstacles include the disorder’s heterogeneity, difficulties in controlling confounding factors, variability in treatment approaches, and the lack of standardized tools and baseline comparisons. These issues hinder the development of reliable biomarkers and evidence-based treatments. Due to these difficulties, the exact cause of CRPS is still not fully understood, making it difficult to develop effective, specific treatments and conduct targeted research. Full article

Colorectal cancer (CRC) is the third most common cancer globally, with limited effective biomarkers and sensitive therapeutic targets. An increasing number of studies have highlighted the critical role of tumor microenvironment (TME) imbalances, particularly immune escape due to impaired chemokine-mediated trafficking, in tumorigenesis and progression. Notably, CC chemokines (CCLs) have been shown to either promote or inhibit angiogenesis, metastasis, and immune responses in tumors, thereby influencing cancer development and patient outcomes. However, the diagnostic and prognostic significance of CCLs in CRC remains unclear. In this study, multiple online tools for bioinformatics analyses were utilized. The findings revealed that the mRNA expression levels of CCL3, CCL4, and CCL26 were significantly elevated in CRC tissues compared to normal tissues, whereas CCL2, CCL5, CCL11, CCL21, and CCL28 mRNA levels were markedly downregulated. Additionally, dysregulation of CCL4, CCL5, and CCL21 was strongly associated with clinical staging, and elevated levels of CCL4, CCL11, and CCL28 were linked to significantly prolonged survival in CRC patients. Functional enrichment analysis indicated that the cellular roles of CCLs were predominantly associated with the chemokine, Wnt, and Toll-like receptor signaling pathways, as well as protein kinase activity. Furthermore, transcriptional regulation of most CCLs involved RELA and NFKB1. Key downstream targets included members of the SRC family of tyrosine kinases (HCK, LYN, and LCK), serine/threonine kinases (ATR and ATM), and others such as CSNK1G2, NEK2, and CDK2. Moreover, CCLs (CCL2, CCL3, CCL4, CCL5, CCL11, CCL21, and CCL28) exhibited strong correlations with major infiltration-related immune cells, including B cells, CD8⁺ T cells, CD4⁺ T cells, macrophages, neutrophils, and dendritic cells. In conclusion, our study provides novel insights into the potential utility of CCLs as biomarkers and therapeutic targets for CRC prevention and immunotherapy. Full article

Cell division cycle 20 homolog (CDC20) is a well-known regulator of cell cycle progression. Abnormal expression of CDC20 leads to mitotic defects, which play a significant role in cancer development. In breast cancer (BC), CDC20 has been identified as a biomarker that has been linked to poor patient outcomes. In this study, we investigated the association of CDC20 with BC prognosis and immune cell infiltration by using multiple online databases, including UALCAN, KM plotter, TIMER2.0, HPA, TNM-plot, bc-GenExMiner, LinkedOmics, STRING, and GEPIA. The results demonstrate that BC patients have an elevated CDC20 expression in tumor tissues compared with the adjacent normal tissue. In addition, BC patients with overexpressed CDC20 had a median survival of 63.6 months compared to 169.2 months in patients with low CDC20 expression. Prognostic analysis of the examined data indicated that elevated expression of CDC20 was associated with poor prognosis and a reduction of overall survival in BC patients. These findings were even more prevalent in chemoresistance triple-negative breast cancer (TNBC) patients. Furthermore, the Gene Set Enrichment Analysis tool indicated that CDC20 regulates BC cells’ cell cycle and apoptosis. CDC20 also significantly correlates with increased infiltrating B cells, CD4+ T cells, neutrophils, and dendritic cells in BC. In conclusion, the findings of this study suggest that CDC20 may be involved in immunomodulating the tumor microenvironment and provide evidence that CDC20 inhibition may serve as a potential therapeutic approach for the treatment of BC patients. In addition, the data indicates that CDC20 can be a reliable prognostic biomarker for BC. Full article

(1) Background: Although MRI is a well-established tool in Multiple Sclerosis (MS) diagnosis and management, neuroradiological reports often lack standardization and/or quantitative information, with possible consequences in clinical care. The aim of this study was to evaluate the impact of information provided by neuroradiological reports and different reporting systems on the clinical management of MS patients. (2) Methods: An online questionnaire was proposed to neurologists working in Italian tertiary care level MS centers. Questions assessed the impact of different MRI-derived biomarkers on clinical choices, the preferred way of receiving radiological information, and the neurologists’ opinions about different reporting systems and the use of automated software in clinical practice. (3) Results: The online survey was completed by 62 neurologists. New/enlarging (100%) lesions, the global T2w/FLAIR lesion load (96.8%), and contrast-enhancing (95.2%) lesions were considered the most important biomarkers for therapeutic decision, while new/enlarging lesions (98.4%), global T2w/FLAIR lesion load (96.8%), and cerebral atrophy (90.3%) were relevant to prognostic evaluations. Almost all participants (98.4%) considered software for medical imaging quantification helpful in clinical management, mostly in relation to prognostic evaluations. (4) Conclusions: These data highlight the impact of providing accurate and reliable data in neuroradiological reports. The use of software for medical imaging quantification in MS can be helpful to standardize radiological reports and to provide useful clinical information to neurologists. Full article

Background and Objectives: Heart failure (HF) is a prevalent and debilitating condition that imposes a significant burden on healthcare systems and adversely affects the quality of life of patients worldwide. Comorbidities such as chronic kidney disease (CKD), arterial hypertension, and diabetes mellitus (DM) are common among HF patients, as they share similar risk factors. This study aimed to identify the prognostic significance of multiple factors and their correlation with disease prognosis and outcomes in a Jordanian cohort. Materials and Methods: Data from the Jordanian Heart Failure Registry (JoHFR) were analyzed, encompassing medical records from acute and chronic HF patients attending public and private cardiology clinics and hospitals across Jordan. An online form was utilized for data collection, focusing on three kidney function tests, estimated glomerular filtration rate (eGFR), blood urea nitrogen (BUN), and creatinine levels, with the eGFR calculated using the Cockcroft–Gault formula. We also built six machine learning models to predict mortality in our cohort. Results: From the JoHFR, 2151 HF patients were included, with 644, 1799, and 1927 records analyzed for eGFR, BUN, and creatinine levels, respectively. Age negatively impacted all measures (p ≤ 0.001), while smokers surprisingly showed better results than non-smokers (p ≤ 0.001). Males had more normal eGFR levels compared to females (p = 0.002). Comorbidities such as hypertension, diabetes, arrhythmias, and implanted devices were inversely related to eGFR (all with p-values <0.05). Higher BUN levels were associated with chronic HF, dyslipidemia, and ASCVD (p ≤ 0.001). Higher creatinine levels were linked to hypertension, diabetes, dyslipidemia, arrhythmias, and previous HF history (all with p-values <0.05). Low eGFR levels were associated with increased mechanical ventilation needs (p = 0.049) and mortality (p ≤ 0.001), while BUN levels did not significantly affect these outcomes. Machine learning analysis employing the Random Forest Classifier revealed that length of hospital stay and creatinine >115 were the most significant predictors of mortality. The classifier achieved an accuracy of 90.02% with an AUC of 80.51%, indicating its efficacy in predictive modeling. Conclusions: This study reveals the intricate relationship among kidney function tests, comorbidities, and clinical outcomes in HF patients in Jordan, highlighting the importance of kidney function as a predictive tool. Integrating machine learning models into clinical practice may enhance the predictive accuracy of patient outcomes, thereby supporting a more personalized approach to managing HF and related kidney dysfunction. Further research is necessary to validate these findings and to develop innovative treatment strategies for the CKD population within the HF cohort. Full article

Background: An atypical teratoid/rhabdoid tumor (AT/RT) is an uncommon and aggressive pediatric central nervous system neoplasm. However, a universal clinical consensus or reliable prognostic evaluation system for this malignancy is lacking. Our study aimed to develop a risk model based on comprehensive clinical data to assist in clinical decision-making. Methods: We conducted a retrospective study by examining data from the Surveillance, Epidemiology, and End Results (SEER) repository, spanning 2000 to 2019. The external validation cohort was sourced from the Children’s Hospital Affiliated to Chongqing Medical University, China. To discern independent factors affecting overall survival (OS) and cancer-specific survival (CSS), we applied Least Absolute Shrinkage and Selection Operator (LASSO) and Random Forest (RF) regression analyses. Based on these factors, we structured nomogram survival predictions and initiated a dynamic online risk-evaluation system. To contrast survival outcomes among diverse treatments, we used propensity score matching (PSM) methodology. Molecular data with the most common mutations in AT/RT were extracted from the Catalogue of Somatic Mutations in Cancer (COSMIC) database. Results: The annual incidence of AT/RT showed an increasing trend (APC, 2.86%; 95% CI:0.75–5.01). Our prognostic study included 316 SEER database participants and 27 external validation patients. The entire group had a median OS of 18 months (range 11.5 to 24 months) and median CSS of 21 months (range 11.7 to 29.2). Evaluations involving C-statistics, DCA, and ROC analysis underscored the distinctive capabilities of our prediction model. An analysis via PSM highlighted that individuals undergoing triple therapy (integrating surgery, radiotherapy, and chemotherapy) had discernibly enhanced OS and CSS. The most common mutations of AT/RT identified in the COSMIC database were SMARCB1, BRAF, SMARCA4, NF2, and NRAS. Conclusions: In this study, we devised a predictive model that effectively gauges the prognosis of AT/RT and briefly analyzed its genomic features, which might offer a valuable tool to address existing clinical challenges. Full article

This article analyzed the Fridays for Future (FFF) movement and its online mobilization around the Global Day of Climate Action on 25 September 2020. Due to the COVID-19 pandemic, this event is a unique opportunity to study digital activism as marchers were considered not appropriate. Using Twitter’s API with keywords “#climateStrike”, and “#FridaysForFuture”, we collected 111,844 unique tweets and retweets from 47,892 unique users. We used two typologies based on social media activism and framing literature to understand the main function of tweets (information opinion, mobilization, and blame) and their framing (diagnosis, prognosis, and motivational). We also analyzed its relationship and tested its automated classification potential. To do so we manually coded a randomly selected sample of 950 tweets that were used as input for the automated classification process (SVM algorithm with balancing classification techniques). We found that the automated classification of the COVID-19 pandemic appeared to not increase the mobilization function of tweets, as the frequencies of mobilization tweets were low. We also found a balanced diversity of framing tasks, with an important number of tweets that envisaged solutions to legislation and policy changes. COVID-related tweets were less frequently prognostically framed. We found that both typologies were not independent. Tweets with a blaming function tended to be framed in a prognostic way and therefore were related to possible solutions. The automated data classification model performed well, especially across social function typology and the “other” category. This indicated that these tools could help researchers working with social media data to process the information across categories that are currently mainly processed manually. Full article

Precision medicine approaches often rely on complex and integrative analyses of multiple biomarkers from “omics” data to generate insights that can help with either diagnostic, prognostic, or therapeutical decisions. Such insights are often made using machine learning (ML) models that perform sample classification for a particular phenotype (yes/no). Building such models is a challenge and time-consuming, requiring advanced coding skills and mathematical modelling expertise. Artificial intelligence (AI) is a methodological solution that has the potential to facilitate, optimize, and scale model development. In this work, we developed an AI-based, user-friendly, and code-free platform that fully automated the development of predictive models from quantitative “omics” data. Here, we show the application of this tool with the development of cancer survival prognostics models using real-life data from breast, lung, and renal cancer transcriptomes. In comparison to other models, our generated models rendered performances with competitive sensitivities (72–85%), specificities (76–85%), accuracies (75–85%), and Receiver Operating Characteristic curves with superior Areas Under the Curve (ROC-AUC of 77–86%). Further, we reported the associated sets of genes (biomarkers) and their expression patterns that were predictive of cancer survival. Moreover, we made our models available as online tools to generate prognostic predictions based on the gene expressions of the biomarkers. In conclusion, we demonstrated that our tool is a robust, user-friendly solution for developing bespoke predictive tools from “omics” data, which facilitate precision medicine applications to the point-of-care. Full article

Background and Objectives: The modification of histone acetylation plays a vital role in regulating tumor occurrence and development, but the interaction between histone acetylation modulator genes and the liver hepatocellular carcinoma (LIHC) microenvironment, as well as immunotherapy, has not been investigated. Materials and Methods: Analysis of all statistical data was carried out using R software (Version 4.2.0) and the online tool Sangerbox. Comprehensive bioinformatics analysis, including signature construction and validation, functional analyses, immune and genomic features analyses, and immunotherapy prediction analyses, were performed to explore the prognostic and therapeutic role of histone acetylation modulator genes in LIHC development and progression. Results: The LIHC cohort from The Cancer Genome Atlas (TCGA) database was selected as the training cohort; the GSE76427 cohort from the Gene Expression Omnibus (GEO) database and the LIRI-JP cohort from the International Cancer Genome Consortium (ICGC) database were selected as the validation cohorts. The histone acetylation modulator gene-based prognostic signature was constructed and validated successfully. Immune infiltration analysis showed that most immune cells and immune functions were enriched in patients with high histone acetylation risk scores (HARS). Additionally, high levels of checkpoint inhibitors (ICIs) and human leukocyte antigens (HLAs) were also observed in high HARS patients. Meanwhile, TIDE algorithm analysis was conducted to explore the relationship between HARS and immunotherapy response, and submap algorithm analysis was used for the verification of the results, from which we found that high HAPS patients were more likely to respond to immunotherapy. Conclusions: Our findings revealed that the histone acetylation modulator genes, particularly for KAT21, SIRT6, and HAT1, may have the potential to function as a new prognostic marker and therapeutic target for LIHC. Full article

The 3′-untranslated region (3′-UTR) of PD-L1 is significantly longer than the coding sequences (CDSs). However, its role and regulators have been little studied. We deleted whole 3′-UTR region by CRISPR-Cas9. Prognostic analysis was performed using online tools. Immune infiltration analysis was performed using the Timer and Xcell packages. Immunotherapy response prediction and Cox regression was performed using the R software. MicroRNA network analysis was conducted by the Cytoscape software. The level of PD-L1 was significantly and dramatically up-regulated in cells after deleting the 3′-UTR. Additionally, we discovered a panel of 43 RNA-binding proteins (RBPs) whose expression correlates with PD-L1 in the majority of cancer cell lines and tumor tissues. Among these RBPs, PARP14 is widely associated with immune checkpoints, the tumor microenvironment, and immune-infiltrating cells in various cancer types. We also identified 38 microRNAs whose individual expressions are associated with PD-L1 across different cancers. Notably, miR-3139, miR-4761, and miR-15a-5p showed significant associations with PD-L1 in most cancer types. Furthermore, we revealed 21 m6A regulators that strongly correlate with PD-L1. Importantly, by combining the identified RBP and m6A regulators, we established an immune signature consisting of RBMS1, QKI, ZC3HAV1, and RBM38. This signature can be used to predict the responsiveness of cancer patients to immune checkpoint blockade treatment. We demonstrated the critical role of the 3′-UTR in the regulation of PD-L1 and identified a significant number of potential PD-L1 regulators across various types of cancer. The biomarker signature generated from our findings shows promise in predicting patient prognosis. However, further biological investigation is necessary to explore the potential of these PD-L1 regulators. Full article

Background: Compared to squamous cell carcinoma, head and neck non-squamous cell carcinoma (HNnSCC) is rarer. Integrated survival prediction tools are lacking. Methods: 4458 patients of HNnSCC were collected from the SEER database. The endpoints were overall survivals (OSs) and disease-specific survivals (DSSs) of 3 and 5 years. Cases were stratified–randomly divided into the train & validation (70%) and test cohorts (30%). Tenfold cross validation was used in establishment of the model. The performance was evaluated with the test cohort by the receiver operating characteristic, calibration, and decision curves. Results: The prognostic factors found with multivariate analyses were used to establish the prediction model. The area under the curve (AUC) is 0.866 (95%CI: 0.844–0.888) for 3-year OS, 0.862 (95%CI: 0.842–0.882) for 5-year OS, 0.902 (95%CI: 0.888–0.916) for 3-year DSS, and 0.903 (95%CI: 0.881–0.925) for 5-year DSS. The net benefit of this model is greater than that of the traditional prediction methods. Among predictors, pathology, involved cervical nodes level, and tumor size are found contributing the most variance to the prediction. The model was then deployed online for easy use. Conclusions: The present study incorporated the clinical, pathological, and therapeutic features comprehensively and established a clinically effective survival prediction model for post-treatment HNnSCC patients. Full article

Lithium-ion batteries have found applications in many parts of our daily lives. Predicting their remaining useful life (RUL) is thus essential for management and prognostics. Most approaches look at early life prediction of RUL in the context of designing charging profiles or optimising cell design. While critical, said approaches are not directly applicable to the regular testing of cells used in applications. This article focuses on a class of models called ‘one-cycle’ models which are suitable for this task and characterized by versatility (in terms of online prediction frameworks and model combinations), prediction from limited input, and cells’ history independence. Our contribution is fourfold. First, we show the wider deployability of the so-called one-cycle model for a different type of battery data, thus confirming its wider scope of use. Second, reflecting on how prediction models can be leveraged within battery management cloud solutions, we propose a universal Exponential-smoothing (e-forgetting) mechanism that leverages cycle-to-cycle prediction updates to reduce prediction variance. Third, we use this new model as a second-life assessment tool by proposing a knee region classifier. Last, using model ensembling, we build a “model of models”. We show that it outperforms each underpinning model (from in-cycle variability, cycle-to-cycle variability, and empirical models). This ‘ensembling’ strategy allows coupling explainable and black-box methods, thus giving the user extra control over the final model. Full article

The PREDICT breast cancer is a well-known online calculator to estimate survival probability. We developed a new prognostic model, myBeST, due to the PREDICT tool’s limitations when applied to our patients. This study aims to compare the performance of the two models for women with breast cancer in Malaysia. A total of 532 stage I to III patient records who underwent surgical treatment were analysed. They were diagnosed between 2012 and 2016 in seven centres. We obtained baseline predictors and survival outcomes by reviewing patients’ medical records. We compare PREDICT and myBeST tools’ discriminant performance using receiver-operating characteristic (ROC) analysis. The five-year observed survival was 80.3% (95% CI: 77.0, 83.7). For this cohort, the median five-year survival probabilities estimated by PREDICT and myBeST were 85.8% and 82.6%, respectively. The area under the ROC curve for five-year survival by myBeST was 0.78 (95% CI: 0.73, 0.82) and for PREDICT was 0.75 (95% CI: 0.70, 0.80). Both tools show good performance, with myBeST marginally outperforms PREDICT discriminant performance. Thus, the new prognostic model is perhaps more suitable for women with breast cancer in Malaysia. Full article

Multiple new subtypes of breast cancer (BRCA) are identified in women each year, rendering BRCA the most common and rapidly expanding form of cancer in females globally. NUF2 has been identified as a prognostic factor in various human cancers, regulating cell apoptosis and proliferation. However, its role in BRCA prognosis has not been clarified. This study explored the role of NUF2 in breast cancer development and prognosis using informatic analysis combined with in vivo intracellular studies. Through the online website TIMER, we evaluated the transcription profile of NUF2 across a variety of different cancer types and found that NUF2 mRNA was highly expressed in BRCA patients. Its transcription level was found to be related to the subtype, pathological stage, and prognosis of BRCA. The R program analysis showed a correlation of NUF2 with cell proliferation and tumor stemness in the BRCA patient samples. Subsequently, the association between the NUF2 expression level and immune cell infiltration was analyzed using the XIANTAO and TIMER tools. The results revealed that NUF2 expression was correlated with the responses of multiple immune cells. Furthermore, we observed the effect of NUF2 expression on tumor stemness in BRCA cell lines in vivo. The experimental results illuminated that the overexpression of NUF2 statistically upregulated the proliferation and tumor stemness ability of the BRCA cell lines MCF-7 and Hs-578T. Meanwhile, the knockdown of NUF2 inhibited the abilities of both cell lines, a finding which was verified by analyzing the subcutaneous tumorigenic ability in nude mice. In summary, this study suggests that NUF2 may play a key role in the development and progression of BRCA by affecting tumor stemness. As a stemness indicator, it has the potential to be one of the markers for the diagnosis of BRCA. Full article