Cancer Data Research Articles

Early detection of anal squamous cell carcinoma with the use of high resolution anoscopy.

In the UK, few (12%) anal squamous cell carcinomas (aSCC) are diagnosed early at stage 1 (T1N0M0). The Homerton Anogenital Neoplasia Service (HANS) is a highly specialised tertiary centre where high resolution anoscopy (HRA) is performed to diagnose and treat anal intraepithelial neoplasia (AIN), a precursor to cancer. In some cases, aSCC (here defined as anal canal cancers and perianal cancers up to 5cm from the anal verge) is found on referral for AIN; in others, aSCC may develop while undergoing AIN management. We reviewed aSCC diagnoses at our specialist unit to establish whether HRA offers added value in the early detection of aSCC in a high-risk cohort. A cross-sectional analysis was performed of all primary aSCC diagnoses at HANS between January 2016 and June 2021. Patient records, histopathology and radiology reports were reviewed to define anal cancer stage per TNM classification (AJCC version 8). Results were compared with national anal cancer data published by the Office for National Statistics (AJCC version 8). Fifty-three aSCC diagnoses were made at HANS; 35 (66%) were stage 1 (14 prevalent, 21 incident), 11 (21%) stage 2 (9 prevalent, 2 incident) and 6 (11%) stage 3 (5 prevalent, 1 incident). None were stage 4; 1 cancer was unstageable due to further management at another unit. By comparison, 5836 aSCCs were diagnosed in the UK between 2013-2017; of these, 12.0% were stage 1, 22.8% stage 2, 33.0% stage 3 and 8.46% stage 4; 23.8% were unknown or unstageable. There was a statistically significant difference in the proportion of early (i.e. stage 1) HRA-detected cancers (HDCs) compared with national statistics (p < 0.001). Our results suggest that surveillance and examination within an HRA programme may lead to detection of aSCC at an earlier stage allowing for less morbid treatment and potentially a lower mortality.

B4GALT5 a sialylation-related genes associated with patient prognosis and immune microenvironment in ovarian cancer and pan-cancer

BackgroundOvarian cancer (OC) is the predominant primary tumor in the human reproductive system. Abnormal sialylation has a significant impact on tumor development, metastasis, immune evasion, angiogenesis, and treatment resistance. B4GALT5, a gene associated with sialylation, plays a crucial role in ovarian cancer, and may potentially affect clinicopathological characteristics and prognosis.MethodsWe conducted a comprehensive search across TIMER, GEPIA2, GeneMANIA, and Metascape to obtain transcription profiling data of ovarian cancer from The Cancer Genome Atlas (TCGA). The expression of B4GALT5 was test by immunohistochemistry. To investigate the impact of B4GALT5 on growth and programmed cell death in OC cells, we performed transwell assays and western blots.ResultsThe presence of B4GALT5 was strongly associated with an unfavorable outcome in OC. B4GALT5 significantly promoted the proliferation of OC cells. Upon analyzing gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG), it was discovered that B4GALT5 played a crucial role in the extracellular matrix, particularly in collagen-containing structures, and exhibited correlations with ECM-receptor interactions, transcriptional dysregulation in cancer, as well as the interleukin-1 receptor signaling pathway. Furthermore, there is a clear link between B4GALT5 and the tumor immune microenvironment in OC. Moreover, B4GALT5 exhibits favorable expression levels across various types of cancers, including CHOL, KIRC, STAD and UCES.ConclusionIn conclusion, it is widely believed that B4GALT5 plays a pivotal role in the growth and progression of OC, with its heightened expression serving as an indicator of unfavorable outcomes. Moreover, B4GALT5 actively participates in shaping the cancer immune microenvironment within OC. This investigation has the potential to contribute significantly to a deeper understanding of the substantial involvement of B4GALT5 in human malignancies, particularly OCs.

Interactive data comics for communicating medical data to the general public: A study of engagement and ease of understanding

We are experiencing a health literacy crisis worldwide, which has alarming effects on individuals’ medical outcomes. This poses the challenge of communicating key information about health conditions and their management in a way that is easily understood by a general audience. In this paper, we propose the use of data-driven storytelling to address this challenge, in particular through interactive data comics. We developed an interactive data comic that communicates cancer data. A between-group study with 98 participants was carried out to evaluate the data comic’s ease of understanding and engagement, compared to a text medium that captures the same information. The study reveals that the data comic is perceived to be more engaging, and participants have greater recall and understanding of the data within the story, compared with the text medium.

Survival analysis for lung cancer patients: A comparison of Cox regression and machine learning models

IntroductionSurvival analysis based on cancer registry data is of paramount importance for monitoring the effectiveness of health care. As new methods arise, the compendium of statistical tools applicable to cancer registry data grows. In recent years, machine learning approaches for survival analysis were developed. The aim of this study is to compare the model performance of the well established Cox regression and novel machine learning approaches on a previously unused dataset. Material and MethodsThe study is based on lung cancer data from the Schleswig-Holstein Cancer Registry. Four survival analysis models are compared: Cox Proportional Hazard Regression (CoxPH) as the most commonly used statistical model, as well as Random Survival Forests (RSF) and two neural network architectures based on the DeepSurv and TabNet approaches. The models are evaluated using the concordance index (C-I), the Brier score and the AUC-ROC score. In addition, to gain more insight in the decision process of the models, we identified the features that have an higher impact on patient survival using permutation feature importance scores and SHAP values. ResultsUsing a dataset including the cancer stage established by the Union for International Cancer Control (UICC), the best performing model is the CoxPH (C-I: 0.698±0.005), while using a dataset which includes the tumor size, lymph node and metastasis status (TNM) leads to the RSF as best performing model (C-I: 0.703±0.004). The explainability metrics show that the models rely on the combined UICC stage and the metastasis status in the first place, which corresponds to other studies. DiscussionThe studied methods are highly relevant for epidemiological researchers to create more accurate survival models, which can help physicians make informed decisions about appropriate therapies and management of patients with lung cancer, ultimately improving survival and quality of life.

Factor-adjusted tests for generalized linear models with multimodal data: An application to breast cancer data

Factor-adjusted tests for generalized linear models with multimodal data: An application to breast cancer data

Enhanced Immunohistochemistry Interpretation with a Machine Learning-Based Expert System.

In recent decades, machine-learning (ML) technologies have advanced the management of high-dimensional and complex cancer data by developing reliable and user-friendly automated diagnostic tools for clinical applications. Immunohistochemistry (IHC) is an essential staining method that enables the identification of cellular origins by analyzing the expression of specific antigens within tissue samples. The aim of this study was to identify a model that could predict histopathological diagnoses based on specific immunohistochemical markers. The XGBoost learning model was applied, where the input variable (target variable) was the histopathological diagnosis and the predictors (independent variables influencing the target variable) were the immunohistochemical markers. Our study demonstrated a precision rate of 85.97% within the dataset, indicating a high level of performance and suggesting that the model is generally reliable in producing accurate predictions. This study demonstrated the feasibility and clinical efficacy of utilizing the probabilistic decision tree algorithm to differentiate tumor diagnoses according to immunohistochemistry profiles.

A gene selection algorithm for microarray cancer classification using an improved particle swarm optimization

Gene selection is an essential step for the classification of microarray cancer data. Gene expression cancer data (deoxyribonucleic acid microarray] facilitates in computing the robust and concurrent expression of various genes. Particle swarm optimization (PSO) requires simple operators and less number of parameters for tuning the model in gene selection. The selection of a prognostic gene with small redundancy is a great challenge for the researcher as there are a few complications in PSO based selection method. In this research, a new variant of PSO (Self-inertia weight adaptive PSO) has been proposed. In the proposed algorithm, SIW-APSO-ELM is explored to achieve gene selection prediction accuracies. This novel algorithm establishes a balance between the exploitation and exploration capabilities of the improved inertia weight adaptive particle swarm optimization. The self-inertia weight adaptive particle swarm optimization (SIW-APSO) algorithm is employed for solution explorations. Each particle in the SIW-APSO increases its position and velocity iteratively through an evolutionary process. The extreme learning machine (ELM) has been designed for the selection procedure. The proposed method has been employed to identify several genes in the cancer dataset. The classification algorithm contains ELM, K-centroid nearest neighbor, and support vector machine to attain high forecast accuracy as compared to the start-of-the-art methods on microarray cancer datasets that show the effectiveness of the proposed method.

MetDecode: methylation-based deconvolution of cell-free DNA for noninvasive multi-cancer typing.

Circulating-cell free DNA (cfDNA) is widely explored as a noninvasive biomarker for cancer screening and diagnosis. The ability to decode the cells of origin in cfDNA would provide biological insights into pathophysiological mechanisms, aiding in cancer characterization and directing clinical management and follow-up. We developed a DNA methylation signature-based deconvolution algorithm, MetDecode, for cancer tissue origin identification. We built a reference atlas exploiting de novo and published whole-genome methylation sequencing data for colorectal, breast, ovarian, and cervical cancer, and blood-cell-derived entities. MetDecode models the contributors absent in the atlas with methylation patterns learnt on-the-fly from the input cfDNA methylation profiles. In addition, our model accounts for the coverage of each marker region to alleviate potential sources of noise. In-silico experiments showed a limit of detection down to 2.88% of tumor tissue contribution in cfDNA. MetDecode produced Pearson correlation coefficients above 0.95 and outperformed other methods in simulations (P < 0.001; T-test; one-sided). In plasma cfDNA profiles from cancer patients, MetDecode assigned the correct tissue-of-origin in 84.2% of cases. In conclusion, MetDecode can unravel alterations in the cfDNA pool components by accurately estimating the contribution of multiple tissues, while supplied with an imperfect reference atlas. MetDecode is available at https://github.com/JorisVermeeschLab/MetDecode.

On the Fidelity-Privacy Tradeoff of Synthetic Cancer Registry Data.

The sharing of personal health data is highly regulated due to privacy and security concerns. An alternative to sharing personal data is to share synthetic data, because ideally it should be impossible to reconstruct real personal data from synthetic data, which is called privacy. At the same time, the structure of the synthetic data should be as similar as possible to the structure of the real data to ensure that conclusions drawn from the synthetic data are also valid for the real data, which is called fidelity. Typically, there is a tradeoff between fidelity and privacy for synthetic health data. We study the fidelity and privacy of cancer data synthesized using generative machine learning approaches. To generate synthetic cancer data, we use variational autoencoders (VAEs), generative adversarial networks (GANs), and denoising diffusion probabilistic models (DDPMs). The tabular cancer registry data studied have nine categorical variables from breast cancer patients. We find that DDPMs generate synthetic cancer data with higher fidelity; that is, the structure of the synthetic data is more similar to the real cancer data than the data generated by VAEs and GANs. At the same time, synthetic cancer data from DDPMs pose a greater privacy risk because the data are more likely to reveal information from real patients than synthetic data from VAEs and GANs.

Comparison of Imputation Methods for Categorical Real-World Prostate Cancer Data with Natural Order.

Missing values (NA) often occur in cancer research, which may be due to reasons such as data protection, data loss, or missing follow-up data. Such incomplete patient information can have an impact on prediction models and other data analyses. Imputation methods are a tool for dealing with NA. Cancer data is often presented in an ordered categorical form, such as tumour grading and staging, which requires special methods. This work compares mode imputation, k nearest neighbour (knn) imputation, and, in the context of Multiple Imputation by Chained Equations (MICE), logistic regression model with proportional odds (mice_polr) and random forest (mice_rf) on a real-world prostate cancer dataset provided by the Cancer Registry of Rhineland-Palatinate in Germany. Our dataset contains relevant information for the risk classification of patients and the time between date of diagnosis and date of death. For the imputation comparison, we use Rubin's (1974) Missing Completely At Random (MCAR) mechanism to remove 10%, 20%, 30%, and 50% observations. The results are evaluated and ranked based on the accuracy per patient. Mice_rf performs significantly best for each percentage of NA, followed by knn, and mice_polr performs significantly worst. Furthermore, our findings indicate that the accuracy of imputation methods increases with a lower number of categories, a relatively even proportion of patients in the categories, or a majority of patients in a particular category.

SexAnnoDB, a knowledgebase of sex-specific regulations from multi-omics data of human cancers

BackgroundSexual differences across molecular levels profoundly impact cancer biology and outcomes. Patient gender significantly influences drug responses, with divergent reactions between men and women to the same drugs. Despite databases on sex differences in human tissues, understanding regulations of sex disparities in cancer is limited. These resources lack detailed mechanistic studies on sex-biased molecules.MethodsIn this study, we conducted a comprehensive examination of molecular distinctions and regulatory networks across 27 cancer types, delving into sex-biased effects. Our analyses encompassed sex-biased competitive endogenous RNA networks, regulatory networks involving sex-biased RNA binding protein-exon skipping events, sex-biased transcription factor-gene regulatory networks, as well as sex-biased expression quantitative trait loci, sex-biased expression quantitative trait methylation, sex-biased splicing quantitative trait loci, and the identification of sex-biased cancer therapeutic drug target genes. All findings from these analyses are accessible on SexAnnoDB (https://ccsm.uth.edu/SexAnnoDB/).ResultsFrom these analyses, we defined 126 cancer therapeutic target sex-associated genes. Among them, 9 genes showed sex-biased at both the mRNA and protein levels. Specifically, S100A9 was the target of five drugs, of which calcium has been approved by the FDA for the treatment of colon and rectal cancers. Transcription factor (TF)-gene regulatory network analysis suggested that four TFs in the SARC male group targeted S100A9 and upregulated the expression of S100A9 in these patients. Promoter region methylation status was only associated with S100A9 expression in KIRP female patients. Hypermethylation inhibited S100A9 expression and was responsible for the downregulation of S100A9 in these female patients.ConclusionsComprehensive network and association analyses indicated that the sex differences at the transcriptome level were partially the result of corresponding sex-biased epigenetic and genetic molecules. Overall, SexAnnoDB offers a discipline-specific search platform that could potentially assist basic experimental researchers or physicians in developing personalized treatment plans.

Improving the Quality of Unstructured Cancer Data Using Large Language Models: A German Oncological Case Study.

With cancer being a leading cause of death globally, epidemiological and clinical cancer registration is paramount for enhancing oncological care and facilitating scientific research. However, the heterogeneous landscape of medical data presents significant challenges to the current manual process of tumor documentation. This paper explores the potential of Large Language Models (LLMs) for transforming unstructured medical reports into the structured format mandated by the German Basic Oncology Dataset. Our findings indicate that integrating LLMs into existing hospital data management systems or cancer registries can significantly enhance the quality and completeness of cancer data collection - a vital component for diagnosing and treating cancer and improving the effectiveness and benefits of therapies. This work contributes to the broader discussion on the potential of artificial intelligence or LLMs to revolutionize medical data processing and reporting in general and cancer care in particular.

Pan-Cancer Analysis Reveals Long Non-coding RNA (lncRNA) Embryonic Stem Cell-Related Gene (ESRG) as a Promising Diagnostic and Prognostic Biomarker.

Embryonic stem cell-related gene (ESRG; also known as HESRG) is a long non-coding RNA (lncRNA). It is involved in the regulation of human pluripotent stem cells (hPSCs) self-renewal. ESRG gene has the ability to interact with chromatins, different RNA types, and RNA binding proteins (RBP); thus making ESRG be considered an oncogenic lncRNA, where its expression is detected in various tumor tissues. This study aimed to evaluate the prospective diagnostic and prognostic values of ESRG in various human cancers. The expression of ESRG in various cancers was analyzed using the Gene Expression Profiling Interactive Analysis (GEPIA), Tumor Immune Estimation Resource (TIMER), and University of Alabama at Birmingham Cancer Data Analysis Portal (UALCAN) databases. Moreover, the correlation between the expression of ESRG and clinical pathological parameters was analyzed using UALCAN. The effect of ESRG expression on the survival outcome was evaluated using Kaplan-Meier plotter, UALCAN, GEPIA, and TIMER. The correlation between ESRG expression and immune cell infiltration was studied by TIMER. Additionally, the genetic alterations were investigated cBioportal. Our findings were validated using the GEO2R database. Our results showed ESRG to be significantly up-regulated incolon adenocarcinoma (COAD) and lung squamous cell carcinoma (LUSC) with p<0.001, in addition to rectum adenocarcinoma (READ), and uterine carcinosarcoma (UCEC) withp<0.01. Regarding pathogenic stages, there was a significant upregulation in stages 2, 3, and 4 compared to normal in COAD and stages 1, 2, and 3 for LUSC patients. The combined prognostic analysis showed that the up-regulated expression of ESRG was associated with better survival outcomes in patients with brain lower-grade glioma (LGG). Our results demonstrate a significant negative correlation between ESRG expression and the abundance of CD8+T cells in COAD, READ, LUSC, and UCEC. Additionally, ESRG was mutated in 0.77 (<1%) of the queried samples, and the most prevalent ESRG mutations are deep deletion mutations, followed by amplification. Analysis of ESRG across various cancer types elucidated its potential to be used as a diagnostic biomarker in COAD, LUSC, READ, and UCEC and a promising prognostic biomarker in LGG. Our findings provide useful insights for future research.

The Ubiquitin E3 Ligase FBXO33 Suppresses Stem Cell-Like Properties and Metastasis in Non-Small-Cell Lung Cancer by Promoting Ubiquitination and Degradation of Myc.

Non-small cell lung cancer (NSCLC) is a malignant form of lung cancer, and its prognosis could be improved by identifying key therapeutic targets. Thus, this study investigates the potential role of F-box Only Protein 33 (FBXO33) in NSCLC. The expression levels of FBXO33 in NSCLC were determined using University of Alabama at Birmingham Cancer Data Analysis Portal (UALCAN) prediction, and its correlation with overall survival (OS) was analyzed via Kaplan-Meier survival analysis. These results were validated through quantitative polymerase chain reaction (qPCR), western blot (WB), and immunofluorescence (IF). We modulated FBXO33 expression by overexpression or knockdown and analyzed its effects on cell growth, proliferation, migration, invasion, and stemness characteristics in NSCLC cell lines. Additionally, the interaction between FBXO33 and Myelocytomatosis (Myc) and its impact on Myc ubiquitination were examined. An in vivo NSCLC xenograft model was used to corroborate the in vivo experimental results. The study found an inverse correlation between FBXO33 expression in NSCLC and OS. Lower FBXO33 expression enhanced the growth, proliferation, migration, invasion, and stemness characteristics of NSCLC cell lines. FBXO33 interacted with Myc to promote its ubiquitination and subsequent degradation, which suppressed NSCLC development. FBXO33 is expressed at low levels in NSCLC and correlates with lower OS. Overexpression of FBXO33 promotes Myc ubiquitination and degradation and inhibits tumor cell proliferation, migration and stemness characteristics, thereby impeding NSCLC progression.

Clinical Significance and Potential Function of Complement Factor D in Acute Myeloid Leukemia.

Acute myeloid leukemia (AML) is a hematologic malignancy characterized by aggressive proliferation and a poor prognosis. The objective of this study is to elucidate the specific role of complement factor D (CFD) in AML, with the aim of identifying robust prognostic markers for the disease. We performed a systematic investigation on clinical significance and potential function of CFD in AML by using the R Programming Language with The Cancer Genome Atlas (TCGA), Gene Expression Omnibus (GEO), The Human Protein Atlas (HPA), The University of ALabama at Birmingham CANcer data analysis Portal (UALCAN), Gene Expression Profiling Interactive Analysis (GEPIA), Kaplan-Meier plotter, Cancer Cell Line Encyclopedia (CCLE) database, and Comprehensive Analysis on Multi-Omics of Immunotherapy in Pan-cancer (CAMOIP) database. The expression of CFD in AML patients was verified by reverse transcription-quantitative polymerase chain reaction(RT-qPCR). The expression of CFD was the highest in AML cells than in other tumor cell lines. The expression of CFD was also higher in AML patients than in the matched normal group. Compared with the low expression of the CFD group, high expression of CFD predicted better overall survival (OS) and lower tumor mutational burden (TMB) in AML patients. Moreover, a nomogram model based on CFD was successfully constructed to predict the OS of AML patients. Notably, the expression of CFD was associated with drug sensitivity and monocyte cell infiltration. CFD could serve as a potential OS prognostic biomarker and guide clinical treatment for AML.

Construction of a prognostic model for colon cancer by combining endoplasmic reticulum stress responsive genes

Endoplasmic reticulum stress may affect the occurrence and development of cancer. However, its effect on the prognosis of colon cancer (CC) patients is not clear yet. Herein, based on TCGA database, we screened 15 endoplasmic reticulum stress responsive genes (ERSRGs) associated with the prognosis of CC patients by Cox regression. By LASSO and multivariate Cox regression analyses, a prognostic risk assessment model involving 12 genes (DNAJB2, EIF4A1, YPEL4, COQ10A, IRX3, ASPHD1, NTRK2, TRIM39, XBP1, GRIN2B, LRRC59, and RORC) was built. The survival curves indicated that patients in the low-risk group had good prognosis. ROC curves demonstrated a good performance of this 12-gene prognostic model, and the Riskscore could be considered as an independent prognostic factor. Patients in low-risk group benefit more from immune checkpoint inhibitor and immune checkpoint blockade (ICB) treatment. Besides, the enrichment analysis suggested a remarkable difference in Ca2+ signaling in both groups. Finally, based on the cMAP database, we identified several potential drugs that could target high-risk groups, such as Dasatinib, GNF-2, Saracatinib, and WZ-1-84. To sum up, our research constructed an ERSRGs-characteristic prognostic model. The model is a promising biomarker for prediction of clinical outcomes and immune therapy response of CC patients. SignificanceBased on the transcriptomic data of colon cancer in the TCGA database, this study screens 12 endoplasmic reticulum stress-related genes (ERSRGs), including DNAJB2, EIF4A1, YPEL4, COQ10A, IRX3, ASPHD1, NTRK2, TRIM39, XBP1, asphD1, NTRK2. GRIN2B, LRRC59, and RORC, and a prognostic model was constructed. This model can be used as a predictor of prognosis and immunotherapy response in colon cancer patients. At the same time, model-based prediction of drugs can also be a potential option for colon cancer treatment in the future.

Target trial emulation using new comorbidity indices provided risk estimates comparable to a randomized trial

ObjectivesTo quantify the ability of two new comorbidity indices to adjust for confounding, by benchmarking a target trial emulation against the randomized controlled trial (RCT) result. Study Design and SettingObservational study including 18,316 men from Prostate Cancer data Base Sweden 5.0, diagnosed with prostate cancer between 2008 and 2019 and treated with primary radical prostatectomy (RP, n = 14,379) or radiotherapy (RT, n = 3,937). The effect on adjusted risk of death from any cause after adjustment for comorbidity by use of two new comorbidity indices, the multidimensional diagnosis-based comorbidity index and the drug comorbidity index, were compared to adjustment for the Charlson comorbidity index (CCI). ResultsRisk of death was higher after RT than RP (hazard ratio [HR] = 1.94; 95% confidence interval [CI]: 1.70–2.21). The difference decreased when adjusting for age, cancer characteristics, and CCI (HR = 1.32, 95% CI: 1.06–1.66). Adjustment for the two new comorbidity indices further attenuated the difference (HR 1.14, 95% CI 0.91–1.44). Emulation of a hypothetical pragmatic trial where also older men with any type of baseline comorbidity were included, largely confirmed these results (HR 1.10; 95% CI 0.95–1.26). ConclusionAdjustment for comorbidity using two new indices provided comparable risk of death from any cause in line with results of a RCT. Similar results were seen in a broader study population, more representative of clinical practice.

Mortality and disease burden of oral cancer in China: a time-trend analysis on the China Death Surveillance Database from 2006 to 2021

BackgroundOral cancer is one of the most common cancers in China and seriously threaten life and health of Chinese people. We analysed the trends and disparities of oral cancer mortality rates and the disease burden of oral cancer in China from 2006 to 2021 to provide a reference for its prevention and control.MethodsAnnual death data for oral cancer was gleaned from the China Death Surveillance Database. The age-standardized mortality rate (ASMR), annual percentage change (APC), and average APC (AAPC) were used to analyze the trend of mortality. Loss of life expectancy (LLE) and years of life lost (YLL) were adopted to assess disease burden.ResultsFrom 2006 to 2021, the overall ASMR of oral cancer lightly declined (AAPC: − 0.97%; 95% CI: − 1.89%, − 0.04%), and the similar trend was observed among females (AAPC: − 1.22%; 95% CI: − 1.89%, − 0.55%). The ASMR of males was 2.31–3.16 times higher than that of females per year. The median of LLE for overall, males and females caused by oral cancer from 2006 to 2021 were 0.05, 0.06 and 0.03 years, respectively. There was a decrease of standardized YLL rate from 2006 to 2021 for overall (AAPC: − 1.31%, 95% CI: − 2.24% ~ − 0.37%) and for female (AAPC: − 1.63%, 95% CI: − 2.30% ~ − 0.95%). ASMR in urban areas was 1.02–1.28 times higher than that in rural areas from 2006 to2011, but 0.85–0.97 times lower in urban areas than that in rural areas from 2018 to 2021. The disease burden was higher in urban areas than in rural areas in 2006, whereas the reverse was observed in 2021.ConclusionsThere are severe health gaps and disparities in trends between sexes and different areas in China. Males and rural populations need to be focused on targeted interventions for the main influencing factors.

The Multicollinearity Effect on the Performance of Machine Learning Algorithms: Case Examples in Healthcare Modelling

Background: The data extracted from various fields inherently consists of extremely correlated measurements in parallel with the exponential increase in the size of the data that need to be interpreted owing to the technological advances. This problem, called the multicollinearity, influences the performance of both statistical and machine learning algorithms. Statistical models proposed as a potential remedy to this problem have not been sufficiently evaluated in the literature. Therefore, a comprehensive comparison of statistical and machine learning models is required for addressing the multicollinearity problem. Methods: Statistical models (including Ridge, Liu, Lasso and Elastic Net regression) and the eight most important machine learning algorithms (including Cart, Knn, Mlp, MARS, Cubist, Svm, Bagging and XGBoost) are comprehensively compared by using two different healthcare datasets (including Body Fat and Cancer) having multicollinearity problem. The performance of the models is assessed through cross validation methods via root mean square error, mean absolute error and r-squared criteria. Results: The results of the study revealed that statistical models outperformed machine learning models in terms of root mean square error, mean absolute error and r-squared criteria in both training and testing performance. Particularly the Liu regression often achieved better relative performance (up to 7.60% to 46.08% for Body Fat data set and up to 1.55% to 21.53% for Cancer data set on training performance and up to 1.56% to 38.08% for Body Fat data set and up to 3.50% to 23.29% for Cancer data set on testing performance) among regression methods as well as compared to machine algorithms. Conclusions: Liu regression is mostly disregarded in the machine learning literature, but since it outperforms the most powerful and widely used machine learning algorithms, it appears to be a promising tool in almost all fields, especially for regression-based studies including data with multicollinearity problem.

-KIDS: A novel feature evaluation in the ultrahigh-dimensional right-censored setting, with application to Head and Neck Cancer.

Recent advances in sequencing technologies have allowed collection of massive genome-wide information that substantially enhances the diagnosis and prognosis of head and neck cancer. Identifying predictive markers for survival time is crucial for devising prognostic systems, and learning the underlying molecular driver of the cancer course. In this paper, we introduce -KIDS, a model-free feature screening procedure with false discovery rate (FDR) control for ultrahigh dimensional right-censored data, which is robust against unknown censoring mechanisms. Specifically, our two-stage procedure initially selects a set of important features with a dual screening mechanism using nonparametric reproducing-kernel-based ANOVA statistics, followed by identifying a refined set (of features) under directional FDR control through a unified knockoff procedure. The finite sample properties of our method, and its novelty (in light of existing alternatives) are evaluated via simulation studies. Furthermore, we illustrate our methodology via application to a motivating right-censored head and neck (HN) cancer survival data derived from The Cancer Genome Atlas, with further validation on a similar HN cancer data from the Gene Expression Omnibus database. The methodology can be implemented via the R package DSFDRC, available in GitHub.