Retrospective Study on the Influencing Factors and Prediction of Hospitalization Expenses for Chronic Renal Failure in China Based on Random Forest and LASSO Regression

Exposure to polycyclic aromatic hydrocarbons and risk of abnormal liver function: The mediating role of C-reactive protein

Polycyclic aromatic hydrocarbons (PAHs) exposure has been suggested to be linked to abnormal liver function (ALF). However, the conclusions are inconsistent, and the underlying mechanism is still unclear. In this study, a cross-sectional design including 4935 adults from the National Health and Nutrition Examination Survey (NHANES) between 2003 and 2010 was conducted to quantify the PAHs-ALF associations, and to investigate the possible mediation role of systemic inflammation. Capillary gas chromatography coupled with tandem mass spectrometry (GC-MS/MS) was utilized to detect nine urinary levels of PAH metabolites (OH-PAHs). Plasma levels of systemic inflammation biomarker, C-reactive protein (CRP), were measured by enhanced turbidimetry. ALF was diagnosed on the basis of any abnormities in albumin (ALB), aspartate aminotransferase (AST), γ-glutamyl transpeptidase (GGT), and alanine aminotransferase (ALT). Logistic regression model and the least absolute shrinkage and selection operator (LASSO) regression models indicated positive associations between urinary 1-hydroxypyrene (1-OH-PYR), 2-hydroxyphenanthrene (2-OH-PHE), and ALF risk. Significant synergistic effect of 1-OH-PYR and 2-OH-PHE on ALF was observed via additive interaction analysis. The weighted quantile sum (WQS) analysis and the quantile-based g computation (qgcomp) were employed to investigate the mixed effect of PAHs but no significant results were found. However, these two analyses consistently showed that 2-OH-PHE and 1-OH-PYR had top dominant weights in the positive association with ALF. Furthermore, mediation analysis indicated that plasma CRP mediated 13.4 % of the association between 1-OH-PYR and ALF risk. These results enhanced our comprehension of the health effects of PAHs exposure on liver function as well as the underlying mechanism.

Identifying GAP43, NMU, and TEX29 as Potential Prognostic Biomarkers for COPD Combined With Lung Cancer Patients Using Machine Learning

Chronic obstructive pulmonary disease (COPD) and lung cancer, frequently comorbid conditions intricately linked through smoking, represent significant global health challenges. COPD is a common comorbidity in nonsmall cell lung cancer (NSCLC) patients and has been shown to negatively impact prognosis. However, the molecular mechanisms underlying the interplay between COPD and lung cancer remain unclear. This study aims to identify differentially expressed genes (DEGs) associated with COPD-related lung cancer and, using various machine learning (ML) algorithms, uncover potential biomarkers for prognosis. We analyzed RNA sequencing data from 41 lung cancer patients (with and without COPD) and identified 61 DEGs, all of which were upregulated in solitary lung cancer compared to COPD-associated cases. Functional enrichment analysis revealed that these genes are involved in biological processes such as granulocyte chemotaxis and smooth muscle contraction and molecular functions including neuropeptide receptor binding. Three ML methods-support vector machine recursive feature elimination (SVM-RFE), least absolute shrinkage and selection operator (LASSO), and random forest-were applied to prioritize key biomarkers. Three genes, GAP43, NMU, and TEX29, were consistently selected across all methods. Further analysis demonstrated significant correlations between these genes and immune cell infiltration, with notable differences in immune cell composition observed in COPD-associated lung cancer. High expression levels of GAP43, NMU, and TEX29 were associated with poor survival outcomes in lung cancer patients, as validated through survival analysis of TCGA database data. Our findings suggest that these genes may serve as diagnostic and prognostic biomarkers for COPD-related lung cancer, thereby providing insights into potential therapeutic targets. Further studies with larger cohorts are required to validate these results and elucidate the underlying molecular mechanisms.

Diabetic Retinopathy (DR) nomogram construction based on optical coherence tomography angiography parameters: a preliminary exploration of DR prediction

AIMS

To construct a diabetic retinopathy (DR) prediction nomogram based on optical coherence tomography angiography (OCTA) parameters. Ophthalmologists can then use this nomogram to assess the risk of early-stage DR.

METHODS

In this retrospective study, patients with type 2 diabetes mellitus who completed DR screening were enrolled and divided into training and validation sets. Fifteen parameters, including OCTA parameters, axial length (AL), age, and sex, were selected via least absolute shrinkage and selection operator (LASSO) in the training set. The chosen parameters were used to construct the model. Model performance was evaluated for both the training and validation sets via receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). A corresponding nomogram was created.

RESULTS

A total of 464 eyes from 464 patients were divided into a training set (324, 69.83%) and a validation set (140, 30.17%). The superficial parafoveal capillary density (CD), deep parafoveal CD, foveal CD in the 300 µm-wide area surrounding the foveal avascular zone (FD- 300 area), AL, and patient ages were included in the final model. The area under curve of the model was 0.825 in the training set and 0.831 in the validation set. The calibration curves showed good alignment between the actual and predicted outcomes in both datasets. DCA demonstrated that the nomogram was clinically useful.

CONCLUSIONS

A model with good performance for predicting DR via OCTA parameters was developed. The superficial parafoveal CD, deep parafoveal CD, and FD- 300 area were important predictive parameters in this model. The corresponding nomogram may serve as a convenient tool for early DR risk prediction and lay the foundation for developing OCTA-based automated diagnostic software for early DR detection.

Identification of thyroid cancer biomarkers using WGCNA and machine learning

OBJECTIVE

The incidence of thyroid cancer (TC) is increasing in China, largely due to overdiagnosis from widespread screening and improved ultrasound technology. Identifying precise TC biomarkers is crucial for accurate diagnosis and effective treatment.

METHODS

TC patient data were obtained from TCGA. DEGs were analyzed using DESeq2, and WGCNA identified gene modules associated with TC. Machine learning algorithms (XGBoost, LASSO, RF) identified key biomarkers, with ROC and AUC > 0.95 indicating strong diagnostic performance. Immune cell infiltration and biomarker correlation were analyzed using CIBERSORT.

RESULTS

Four key genes (P4HA2, TFF3, RPS6KA5, EYA1) were found as potential biomarkers. High P4HA2 expression was associated with suppressed anti-tumor immune responses and promoted disease progression. In vitro studies showed that P4HA2 upregulation increased TC cell growth and migration, while its suppression reduced these activities.

CONCLUSION

Through bioinformatics and experimental validation, we identified P4HA2 as a key potential thyroid cancer biomarker. This finding provides new molecular targets for diagnosis and treatment. P4HA2 has the potential to be a diagnostic or therapeutic target, which could have significant implications for improving clinical outcomes in thyroid cancer patients.

Using machine learning methods to investigate the impact of age on the causes of death in patients with early intrahepatic cholangiocarcinoma who underwent surgery

BACKGROUND

The impact of age on the causes of death (CODs) in patients with early-stage intrahepatic cholangiocarcinoma (ICC) who had undergone surgery was analyzed in this study.

METHODS

A total of 1555 patients (885 in the older group and 670 in the younger group) were included in this study. Before and after applying inverse probability of treatment weighting (IPTW), the different CODs in the 2 groups were further investigated. Additionally, 7 different machine learning models were used as predictive tools to identify key variables, aiming to evaluate the therapeutic outcome in early ICC patients undergoing surgery.

RESULTS

Before (5.92 vs. 4.08 years, P < 0.001) and after (6.00 vs. 4.08 years, P < 0.001) IPTW, the younger group consistently showed longer overall survival (OS) compared with the older group. Before IPTW, there were no significant differences in cholangiocarcinoma-related deaths (CRDs, P = 0.7) and secondary malignant neoplasms (SMNs, P = 0.78) between the 2 groups. However, the younger group had a lower cumulative incidence of cardiovascular disease (CVD, P = 0.006) and other causes (P < 0.001) compared with the older group. After IPTW, there were no differences between the 2 groups in CRDs (P = 0.2), SMNs (P = 0.7), and CVD (P = 0.1). However, the younger group had a lower cumulative incidence of other CODs compared with the older group (P < 0.001). The random forest (RF) model showed the highest C-index of 0.703. Time-dependent variable importance bar plots showed that age was the most important factor affecting the 2-, 4-, and 6-year survival, followed by stage and size.

CONCLUSIONS

Our study confirmed that younger patients have longer OS compared with older patients. Further analysis of the CODs indicated that older patients are more likely to die from CVDs. The RF model demonstrated the best predictive performance and identified age as the most important factor affecting OS in early ICC patients undergoing surgery.

Comprehensive integration of diagnostic biomarker analysis and immune cell infiltration features in sepsis via machine learning and bioinformatics techniques

Introduction

Sepsis, a critical medical condition resulting from an irregular immune response to infection, leads to life-threatening organ dysfunction. Despite medical advancements, the critical need for research into dependable diagnostic markers and precise therapeutic targets.

Methods

We screened out five gene expression datasets (GSE69063, GSE236713, GSE28750, GSE65682 and GSE137340) from the Gene Expression Omnibus. First, we merged the first two datasets. We then identified differentially expressed genes (DEGs), which were subjected to KEGG and GO enrichment analyses. Following this, we integrated the DEGs with the genes from key modules as determined by Weighted Gene Co-expression Network Analysis (WGCNA), identifying 262 overlapping genes. 12 core genes were subsequently selected using three machine-learning algorithms: random forest (RF), Least Absolute Shrinkage and Selection Operator (LASSO), and Support Vector Machine-Recursive Feature Elimination (SVW-RFE). The utilization of the receiver operating characteristic curve in conjunction with the nomogram model served to authenticate the discriminatory strength and efficacy of the key genes. CIBERSORT was utilized to evaluate the inflammatory and immunological condition of sepsis. Astragalus, Salvia, and Safflower are the primary elements of Xuebijing, commonly used in the clinical treatment of sepsis. Using the Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform (TCMSP), we identified the chemical constituents of these three herbs and their target genes.

Results

We found that CD40LG is not only one of the 12 core genes we identified, but also a common target of the active components quercetin, luteolin, and apigenin in these herbs. We extracted the common chemical structure of these active ingredients -flavonoids. Through docking analysis, we further validated the interaction between flavonoids and CD40LG. Lastly, blood samples were collected from healthy individuals and sepsis patients, with and without the administration of Xuebijing, for the extraction of peripheral blood mononuclear cells (PBMCs). By qPCR and WB analysis. We observed significant differences in the expression of CD40LG across the three groups. In this study, we pinpointed candidate hub genes for sepsis and constructed a nomogram for its diagnosis.

Discussion

This research not only provides potential diagnostic evidence for peripheral blood diagnosis of sepsis but also offers insights into the pathogenesis and disease progression of sepsis.

Antiviral therapy can effectively suppress irAEs in HBV positive hepatocellular carcinoma treated with ICIs: validation based on multi machine learning

Background

Immune checkpoint inhibitors have proven efficacy against hepatitis B-virus positive hepatocellular. However, Immunotherapy-related adverse reactions are still a major challenge faced by tumor immunotherapy, so it is urgent to establish new methods to effectively predict immunotherapy-related adverse reactions.

Objective

Multi-machine learning model were constructed to screen the risk factors for irAEs in ICIs for the treatment of HBV-related hepatocellular and build a prediction model for the occurrence of clinical IRAEs.

Methods

Data from 274 hepatitis B virus positive tumor patients who received PD-1 or/and CTLA4 inhibitor treatment and had immune cell detection results were collected from Henan Cancer Hospital for retrospective analysis. Models were established using Lasso, RSF (RandomForest), and xgBoost, with ten-fold cross-validation and resampling methods used to ensure model reliability. The impact of influencing factors on irAEs (immune-related adverse events) was validated using Decision Curve Analysis (DCA). Both uni/multivariable analysis were accomplished by Chi-square/Fisher's exact tests. The accuracy of the model is verified in the DCA curve.

Results

A total of 274 HBV-related liver cancer patients were enrolled in the study. Predictive models were constructed using three machine learning algorithms to analyze and statistically evaluate clinical characteristics, including immune cell data. The accuracy of the Lasso regression model was 0.864, XGBoost achieved 0.903, and RandomForest reached 0.961. Resampling internal validation revealed that RandomForest had the highest recall rate (AUC = 0.892). Based on machine learning-selected indicators, antiviral therapy and The HBV DNA copy number showed a significant correlation with both the occurrence and severity of irAEs. Antiviral therapy notably reduced the incidence of IRAEs and may modulate these events through regulation of B cells. The DCA model also demonstrated strong predictive performance. Effective control of viral load through antiviral therapy significantly mitigates the occurrence of irAEs.

Conclusion

ICIs show therapeutic potential in the treatment of HBV-HCC. Following antiviral therapy, the incidence of severe irAEs decreases. Even in cases where viral load control is incomplete, continuous antiviral treatment can still mitigate the occurrence of irAEs.

Cardiac computer tomography-derived radiomics in assessing myocardial characteristics at the connection between the left atrial appendage and the left atrium in atrial fibrillation patients

Objectives

To evaluate the feasibility of utilizing cardiac computer tomography (CT) images for extracting the radiomic features of the myocardium at the junction between the left atrial appendage (LAA) and the left atrium (LA) in patients with atrial fibrillation (AF) and to evaluate its asscociation with the risk of AF.

Methods

A retrospective analysis was conducted on 82 cases of AF and 56 cases in the control group who underwent cardiac CT at our hospital from May 2022 to May 2023, with recorded clinical information. The morphological parameters of the LAA were measured. A radiomics model, a clincal feature model and a model combining radiomics and clinical features were constructed. The radiomics model was built by extracting radiomic features of the myocardial tissue using Pyradiomics, and employing Least absolute shrinkage and selection operator (LASSO) method for feature selection, combining random forest with support vector machine (SVM) classifier.

Results

There were 82 cases in the AF group [44 males, 65.00 (59, 70)], and 56 cases in the control group (21 males, 61.09 ± 7.18). Age, BMI, hypertension, CHA2DS-VASC score, neutrophil to lymphocyte ratio (NLR), LAA volume, LA volume, the myocardial thickness at the junction of LAA and LA, the area, circumference, short diameter, and long diameter of the LAA opening, were significantly different between the AF group and the control group (P < 0.05). After conducting multivariate logistic regression analysis, it was found that BMI, the myocardial thickness at the junction of the LAA and the LA, LA volume, NLR and CHA2DS-VASC score were related to AF. 12 radiomics features of the myocardium at the junction of the LAA and the LA were extracted and identified. ROC curve analysis confirmed that the nomogram based on radiomics scores and clinical factors can effectively predict AF (AUC 0.869).

Conclusion

Radiomics enables the extraction of the myocardial characteristics at the junction of the LAA and the LA, which are related with AF, facilitating the assessment of its relationship with the risk of AF. The combination of radiomics with clinical characteristics enhances the evaluation capabilities significantly.

Effects of Internet Plus-Based Continuous Nursing on Hemodialysis Adherence in Patients with Chronic Renal Failure: A Retrospective Study

Aims/Background Chronic renal failure (CRF) is the eventual outcome shared by various progressive renal diseases, posing a serious threat to the physical health of patients. CRF patients are required to undergo hemodialysis (HD), which imposes heavy psychological and mental burdens for most individuals. This study explores the effects of Internet Plus-based continuous nursing on the compliance of CRF patients with HD. Methods This study retrospectively analyzed the clinical data of 160 CRF patients undergoing HD in the Yantai Yuhuangding Hospital from March 2021 to April 2023, after excluding eight cases from an originally selected cohort of 168 cases. These patients were divided into two groups: 79 cases who received the routine nursing from March 2021 to March 2022 were categorized as the routine group, whereas 81 cases who were given Internet Plus-based continuous nursing from April 2022 to April 2023 were assigned into the observation group. The treatment adherence, self-management behaviors, quality of life and incidence of HD complications were compared in both groups. Results Both groups demonstrated no significant difference in the baseline information (p > 0.05). The scores of adherence in terms of HD attendance, medications, fluid restrictions and diet recommendations in the observation group were significantly higher than those in the routine group (p < 0.001). No significant difference in the Hemodialysis Self-Management Instrument (HDSMI) scores on the day of discharge between the two groups was found (p > 0.05). After 6 months of follow-up, the observation group showed significantly higher scores of partnership, problem solving, self-management execution and emotional processing than the routine group (p < 0.001). Both groups had no significant difference in the scores of Kidney Disease-Targeted Areas (KDTA) and 36-Item Short Form (SF-36) on the day of discharge (p > 0.05). After 6 months of follow-up, the scores of KDTA and SF-36 in the observation group were significantly higher than those in the routine group (p < 0.001). The incidence of HD complications in the observation group (7.41%) was significantly lower than that in the routine group (21.52%) (p < 0.05). Conclusion Internet Plus-based continuous nursing can effectively improve treatment adherence, self-management behaviors as well as quality of life in patients, and reduce the incidence of HD complications.

Identification and experimental verification of senescence-related gene signatures and molecular subtypes in idiopathic pulmonary arterial hypertension

Evidences illustrate that cell senescence contributes to the development of pulmonary arterial hypertension. However, the molecular mechanisms remain unclear. Since there may be different senescence subtypes between PAH patients, consistent senescence-related genes (SRGs) were utilized for consistent clustering by unsupervised clustering methods. Senescence is inextricably linked to the immune system, and the immune cells in each cluster were estimated by ssGSEA. To further screen out more important SRGs, machine learning algorithms were used for identification and their diagnostic value was assessed by ROC curves. The expression of hub genes were verified in vivo and in vitro. Transcriptome analysis was used to assess the effects of silence of hub gene on different pathways. Three senescence molecular subtypes were identified by consensus clustering. Compared with cluster A and B, most immune cells and checkpoint genes were higher in cluster C. Thus, we identified senescence cluster C as the immune subtype. The ROC curves of IGF1, HOXB7, and YWHAZ were remarkable in both datasets. The expression of these genes was increased in vitro. Western blot and immunohistochemical analyses revealed that YWHAZ expression was also increased. Our transcriptome analysis showed autophagy-related genes were significantly elevated after silence of YWHAZ. Our research provided several prospective SRGs and molecular subtypes. Silence of YWHAZ may contribute to the clearance of senescent endothelial cells by activating autophagy.

Identification of Potential Key Genes for the Comorbidity of Myasthenia Gravis With Thymoma by Integrated Bioinformatics Analysis and Machine Learning

Background

Thymoma is a key risk factor for myasthenia gravis (MG). The purpose of our study was to investigate the potential key genes responsible for MG patients with thymoma.

Methods

We obtained MG and thymoma dataset from GEO database. Differentially expressed genes (DEGs) were determined and functional enrichment analyses were conducted by R packages. Weighted gene co-expression network analysis (WGCNA) was used to screen out the crucial module genes related to thymoma. Candidate genes were obtained by integrating DEGs of MG and module genes. Subsequently, we identified several candidate key genes by machine learning for diagnosing MG patients with thymoma. The nomogram and receiver operating characteristics (ROC) curves were applied to assess the diagnostic value of candidate key genes. Finally, we investigated the infiltration of immunocytes and analyzed the relationship among key genes and immune cells.

Results

We obtained 337 DEGs in MG dataset and 2150 DEGs in thymoma dataset. Biological function analyses indicated that DEGs of MG and thymoma were enriched in many common pathways. Black module (containing 207 genes) analyzed by WGCNA was considered as the most correlated with thymoma. Then, 12 candidate genes were identified by intersecting with MG DEGs and thymoma module genes as potential causes of thymoma-associated MG pathogenesis. Furthermore, five candidate key genes (JAM3, MS4A4A, MS4A6A, EGR1, and FOS) were screened out through integrating least absolute shrinkage and selection operator (LASSO) regression and Random forest (RF). The nomogram and ROC curves (area under the curve from 0.833 to 0.929) suggested all five candidate key genes had high diagnostic values. Finally, we found that five key genes and immune cell infiltrations presented varying degrees of correlation.

Conclusions

Our study identified five key potential pathogenic genes that predisposed thymoma to the development of MG, which provided potential diagnostic biomarkers and promising therapeutic targets for MG patients with thymoma.

Simple and accurate genomic classification model for distinguishing between human and pig Staphylococcus aureus

Staphylococcus aureus (S. aureus) can cause various infections in humans and animals, contributing to high morbidity and mortality. To prevent and control cross-species transmission of S. aureus, it is necessary to understand the host-associated genetic variants. We performed a two-stage genome-wide association study (GWAS) including initial screening and further validation to compare genomic differences between human and pig S. aureus, aiming to identify host-associated determinants. Our multiple GWAS analyses found six consensus significant k-mers associated with host species, providing novel genetic evidence for distinguishing human from pig S. aureus. The best k-mer predictor achieved a high classification accuracy of 98.12% on its own and had extremely high resolution similar to the SNPs-based phylogeny, offering a very simple target for predicting the cross-species transmission risk of S. aureus. The final k-mer model revealed that 90% of S. aureus isolates from farm workers were predicted as livestock origin, suggesting a high risk of cross-species transmission. Bayesian inference revealed different cross-species transmission directions, with the human-to-pig transmission for ST5 and the pig-to-human transmission for ST398. Our findings provide a simple and accurate k-mer model for identifying and predicting the cross-species transmission risk of S. aureus.

Comparison of Machine Learning Algorithms and Nomogram Construction for Diabetic Retinopathy Prediction in Type 2 Diabetes Mellitus Patients

INTRODUCTION

The aim of this study was to compare various machine learning algorithms for constructing a diabetic retinopathy (DR) prediction model among type 2 diabetes mellitus (DM) patients and to develop a nomogram based on the best model.

METHODS

This cross-sectional study included DM patients receiving routine DR screening. Patients were randomly divided into training (244) and validation (105) sets. Least absolute shrinkage and selection operator regression was used for the selection of clinical characteristics. Six machine learning algorithms were compared: decision tree (DT), k-nearest neighbours (KNN), logistic regression model (LM), random forest (RF), support vector machine (SVM), and XGBoost (XGB). Model performance was assessed via receiver-operating characteristic (ROC), calibration, and decision curve analyses (DCAs). A nomogram was then developed on the basis of the best model.

RESULTS

Compared with the five other machine learning algorithms (DT, KNN, RF, SVM, and XGB), the LM demonstrated the highest area under the ROC curve (AUC, 0.894) and recall (0.92) in the validation set. Additionally, the calibration curves and DCA results were relatively favourable. Disease duration, DPN, insulin dosage, urinary protein, and ALB were included in the LM. The nomogram exhibited robust discrimination (AUC: 0.856 in the training set and 0.868 in the validation set), calibration, and clinical applicability across the two datasets after 1,000 bootstraps.

CONCLUSION

Among the six different machine learning algorithms, the LM algorithm demonstrated the best performance. A logistic regression-based nomogram for predicting DR in type 2 DM patients was established. This nomogram may serve as a valuable tool for DR detection, facilitating timely treatment.

Changes in patterns of multimorbidity and associated with medical costs among Chinese middle-aged and older adults from 2013 to 2023: an analysis of repeated cross-sectional surveys in Xiangyang, China

Background

Multimorbidity has become a major public health problem among Chinese middle-aged and older adults, and the most costly to the health care system. However, most previous population-based studies of multimorbidity have focused on a limited number of chronic diseases, and diagnosis was based on participants' self-report, which may oversimplify the problem. At the same time, there were few reports on the relationship between multimorbidity patterns and health care costs. This study analyzed the multimorbidity patterns and changes among middle-aged and older people in China over the past decade, and their association with medical costs, based on representative hospital electronic medical record data.

Methods

Two cross-sectional surveys based on representative hospital data were used to obtain adults aged 45 years and older in Xiangyang in 2013 (n = 20,218) and 2023 (n = 63,517). Latent Class Analysis was used to analyze changes in the patterns of multimorbidity, gray correlation analysis and ordered logistics model were used to assess the association of multimorbidity patterns with medical expenses. The diagnosis and classification of chronic diseases were based on the International Classification of Diseases, Tenth Revision codes (ICD-10).

Results

The detection rate of chronic disease multimorbidity has increased (70.74 vs. 76.63%, p < 0.001), and multimorbidity patterns have increased from 6 to 9 (2013: Malignant tumors pattern, non-specific multimorbidity pattern, ischemic heart disease + hypertension pattern, cerebral infarction + hypertension pattern, kidney disease + hypertension pattern, lens disease + hypertension pattern; new in 2023: Nutritional metabolism disorders + hypertension pattern, chronic lower respiratory diseases + malignant tumors pattern, and gastrointestinal diseases pattern) in China. The medical cost of all multimorbidity patients have been reduced between 2013 and 2023 (RMB: 8216.74 vs. 7247.96, IQR: 5802.28-15,737 vs. 5014.63-15434.06). The top three specific multimorbidity patterns in both surveys were malignancy tumor pattern, ischemic heart disease + hypertension pattern, and cerebral infarction + hypertension pattern. Hypertension and type 2 diabetes are important components of multimorbidity patterns. Compared with patients with a single disease, only lens disorders + hypertension pattern were at risk of higher medical costs in 2013 (aOR:1.23, 95% CI: 1.03, 1.47), whereas all multimorbidity patterns were significantly associated with increased medical costs in 2023, except for lens disorders + hypertension (aOR:0.35, 95% CI: 0.32, 0.39). Moreover, the odds of higher medical costs were not consistent across multimorbidity patterns. Among them, ischemic heart disease + hypertension pattern [adjusted odds ratio (aOR):4.66, 95%CI: 4.31, 5.05] and cerebral infarction + hypertension pattern (aOR: 3.63, 95% CI: 3.35, 3.92) were the two patterns with the highest risk. Meanwhile, men (aOR:1.12, 95CI:1.09, 1.16), no spouse (aOR:1.09, 95CI: 1.03, 1.16) had a positive effect on medical costs, while patients with total self-pay (aOR: 0.45, 95CI: 0.29, 0.70), no surgery (aOR: 0.05, 95CI: 0.05, 0.05), rural residence (aOR: 0.92, 95CI: 0.89, 0.95), hospitalization days 1-5 (aOR: 0.04, 95CI: 0.04, 0.04), and hospitalization days 6-9 (aOR: 0.15, 95CI: 0.15, 0.16) had a negative impact on medical costs.

Conclusion

Multimorbidity patterns among middle-aged and older adults in China have diversified over the past decade and are associated with rising health care costs in China. Smart, decisive and comprehensive policy and care interventions are needed to effectively manage NCDS and their risk factors and to reduce the economic burden of multimorbidity on patients and the country.

Unveiling the role of AGT in lipid metabolism and regulated cell death in colon cancer

BACKGROUND

Lipid metabolism and regulated cell death (RCD) play a role in the remodeling of tumor immune microenvironment and regulation of cancer progression. Since the underlying immune mechanisms of colon cancer remain elusive, this study aims to identify potential therapeutic target genes.

METHODS

Differential genes related to lipid metabolism and RCD in COAD patients were identified using R language and online tools. Based on the expression of genes, two groups were classified using consensus clustering. CIBERSORT and ssGSEA were used to detect immune infiltration in both groups. Prognostic signature genes for colon cancer were screened using machine learning algorithms. KEGG, GO and GSEA for gene pathway enrichment. In addition, interacting genes in the immune module were obtained using a weighted gene co-expression network (WGCNA). Finally, expression and mutation of key in colon cancer genes were detected using TIMER, HPR, cBioPortal website and qPCR.

RESULTS

The consensus clustering analysis revealed that 231 relevant differential genes were highly associated with immune infiltration. A series of machine learning and website analyses identified AGT as a hub gene linked to lipid metabolism and regulated cell death, which is overexpressed in colon cancer.

CONCLUSION

AGT, as a signature gene of lipid metabolism and regulated cell death, plays a critical role in the development of COAD and is associated with tumor immune infiltration.

Predictive nomogram for 28-day mortality risk in mitral valve disorder patients in the intensive care unit: A comprehensive assessment from the MIMIC-III database

BACKGROUND

Mitral valve disorder (MVD) stands as the most prevalent valvular heart disease. Presently, a comprehensive clinical index to predict mortality in MVD remains elusive. The aim of our study is to construct and assess a nomogram for predicting the 28-day mortality risk of MVD patients.

METHODS

Patients diagnosed with MVD were identified via ICD-9 code from the MIMIC-III database. Independent risk factors were identified utilizing the LASSO method and multivariate logistic regression to construct a nomogram model aimed at predicting the 28-day mortality risk. The nomogram's performance was assessed through various metrics including the area under the curve (AUC), calibration curves, Hosmer-Lemeshow test, integrated discriminant improvement (IDI), net reclassification improvement (NRI), and decision curve analysis (DCA).

RESULTS

The study encompassed a total of 2771 patients diagnosed with MVD. Logistic regression analysis identified several independent risk factors: age, anion gap, creatinine, glucose, blood urea nitrogen level (BUN), urine output, systolic blood pressure (SBP), respiratory rate, saturation of peripheral oxygen (SpO2), Glasgow Coma Scale score (GCS), and metastatic cancer. These factors were found to independently influence the 28-day mortality risk among patients with MVD. The calibration curve demonstrated adequate calibration of the nomogram. Furthermore, the nomogram exhibited favorable discrimination in both the training and validation cohorts. The calculations of IDI, NRI, and DCA analyses demonstrate that the nomogram model provides a greater net benefit compared to the Simplified Acute Physiology Score II (SAPSII), Acute Physiology Score III (APSIII), and Sequential Organ Failure Assessment (SOFA) scoring systems.

CONCLUSION

This study successfully identified independent risk factors for 28-day mortality in patients with MVD. Additionally, a nomogram model was developed to predict mortality, offering potential assistance in enhancing the prognosis for MVD patients. It's helpful in persuading patients to receive early interventional catheterization treatment, for example, transcatheter mitral valve replacement (TMVR), transcatheter mitral valve implantation (TMVI).

Nomogram built based on machine learning to predict recurrence in early-stage hepatocellular carcinoma patients treated with ablation

Introduction

To analyze the risk factors affecting recurrence in early-stage hepatocellular carcinoma (HCC) patients treated with ablation and then establish a nomogram to provide a clear and accessible representation of the patients' recurrence risk.

Methods

Collect demographic and clinical data of 898 early-stage HCC patients who underwent ablation treatment at Beijing You'an Hospital, affiliated with Capital Medical University from January 2014 to December 2022. Patients admitted from 2014 to 2018 were included in the training cohort, while 2019 to 2022 were in the validation cohort. Lasso and Cox regression was used to screen independent risk factors for HCC patients recurrence, and a nomogram was then constructed based on the screened factors.

Results

Age, gender, Barcelona Clinic Liver Cancer (BCLC) stage, tumor size, globulin (Glob) and γ-glutamyl transpeptidase (γ-GT) were finally incorporated in the nomogram for predicting the recurrence-free survival (RFS) of patients. We further confirmed that the nomogram has optimal discrimination, consistency and clinical utility by the C-index, Receiver Operating Characteristic Curve (ROC), calibration curve and Decision Curve Analysis (DCA). Moreover, we divided the patients into different risk groups and found that the nomogram can effectively identify the high recurrence risk patients by the Kaplan-Meier curves.

Conclusion

This study developed a nomogram using Lasso-Cox regression to predict RFS in early-stage HCC patients following ablation, aiding clinicians in identifying high-risk groups for personalized follow-up treatments.

Nomogram for predicting post-therapy recurrence in BCLC A/B hepatocellular carcinoma with Child-Pugh B cirrhosis

Introduction

This study conducts a retrospective analysis on patients with BCLC stage A/B hepatocellular carcinoma (HCC) accompanied by Child-Pugh B cirrhosis, who underwent transarterial chemoembolization (TACE) in combination with local ablation therapy. Our goal was to uncover risk factors contributing to post-treatment recurrence and to develop and validate an innovative 1-, 3-, and 5-year recurrence free survival (RFS) nomogram.

Methods

Data from 255 BCLC A/B HCC patients with Child-Pugh B cirrhosis treated at Beijing You'an Hospital (January 2014 - January 2020) were analyzed using random survival forest (RSF), LASSO regression, and multivariate Cox regression to identify independent risk factors for RFS. The prognostic nomogram was then constructed and validated, categorizing patients into low, intermediate, and high-risk groups, with RFS assessed using Kaplan-Meier curves.

Results

The nomogram, integrating the albumin/globulin ratio, gender, tumor number, and size, showcased robust predictive performance. Harrell's concordance index (C-index) values for the training and validation cohorts were 0.744 (95% CI: 0.703-0.785) and 0.724 (95% CI: 0.644-0.804), respectively. The area under the curve (AUC) values for 1-, 3-, and 5-year RFS in the two cohorts were also promising. Calibration curves highlighted the nomogram's reliability and decision curve analysis (DCA) confirmed its practical clinical benefits. Through meticulous patient stratification, we also revealed the nomogram's efficacy in distinguishing varying recurrence risks.

Conclusion

This study advances recurrence prediction in BCLC A/B HCC patients with Child-Pugh B cirrhosis following TACE combined with ablation. The established nomogram accurately predicts 1-, 3-, and 5-year RFS, facilitating timely identification of high-risk populations.

Using a k-means clustering to identify novel phenotypes of acute ischemic stroke and development of its Clinlabomics models

Objective

Acute ischemic stroke (AIS) is a heterogeneous condition. To stratify the heterogeneity, identify novel phenotypes, and develop Clinlabomics models of phenotypes that can conduct more personalized treatments for AIS.

Methods

In a retrospective analysis, consecutive AIS and non-AIS inpatients were enrolled. An unsupervised k-means clustering algorithm was used to classify AIS patients into distinct novel phenotypes. Besides, the intergroup comparisons across the phenotypes were performed in clinical and laboratory data. Next, the least absolute shrinkage and selection operator (LASSO) algorithm was used to select essential variables. In addition, Clinlabomics predictive models of phenotypes were established by a support vector machines (SVM) classifier. We used the area under curve (AUC), accuracy, sensitivity, and specificity to evaluate the performance of the models.

Results

Of the three derived phenotypes in 909 AIS patients [median age 64 (IQR: 17) years, 69% male], in phenotype 1 (N = 401), patients were relatively young and obese and had significantly elevated levels of lipids. Phenotype 2 (N = 463) was associated with abnormal ion levels. Phenotype 3 (N = 45) was characterized by the highest level of inflammation, accompanied by mild multiple-organ dysfunction. The external validation cohort prospectively collected 507 AIS patients [median age 60 (IQR: 18) years, 70% male]. Phenotype characteristics were similar in the validation cohort. After LASSO analysis, Clinlabomics models of phenotype 1 and 2 were constructed by the SVM algorithm, yielding high AUC (0.977, 95% CI: 0.961-0.993 and 0.984, 95% CI: 0.971-0.997), accuracy (0.936, 95% CI: 0.922-0.956 and 0.952, 95% CI: 0.938-0.972), sensitivity (0.984, 95% CI: 0.968-0.998 and 0.958, 95% CI: 0.939-0.984), and specificity (0.892, 95% CI: 0.874-0.926 and 0.945, 95% CI: 0.923-0.969).

Conclusion

In this study, three novel phenotypes that reflected the abnormal variables of AIS patients were identified, and the Clinlabomics models of phenotypes were established, which are conducive to individualized treatments.

Development and validation of a machine learning model to predict time to renal replacement therapy in patients with chronic kidney disease

BACKGROUND

Predicting time to renal replacement therapy (RRT) is important in patients at high risk for end-stage kidney disease. We developed and validated machine learning models for predicting the time to RRT and compared its accuracy with conventional prediction methods that uses the rate of estimated glomerular filtration rate (eGFR) decline.

METHODS

Data of adult chronic kidney disease (CKD) patients who underwent hemodialysis at Oita University Hospital from April 2016 to March 2021 were extracted from electronic medical records (N = 135). A new machine learning predictor was compared with the established prediction method that uses the eGFR decline rate and the accuracy of the prediction models was determined using the coefficient of determination (R2). The data were preprocessed and split into training and validation datasets. We created multiple machine learning models using the training data and evaluated their accuracy using validation data. Furthermore, we predicted the time to RRT using a conventional prediction method that uses the eGFR decline rate for patients who had measured eGFR three or more times in two years and evaluated its accuracy.

RESULTS

The least absolute shrinkage and selection operator regression model exhibited moderate accuracy with an R2 of 0.60. By contrast, the conventional prediction method was found to be extremely low with an R2 of -17.1.

CONCLUSIONS

The significance of this study is that it shows that machine learning can predict time to RRT moderately well with continuous values from data at a single time point. This approach outperforms the conventional prediction method that uses eGFR time series data and presents new avenues for CKD treatment.

Changes in serum inflammatory factors after hip arthroplasty and analysis of risk factors for prosthesis loosening

OBJECTIVE

To explore the relationship of serum levels of IL-1β, IL-6, and TNF-α with prosthesis loosening after hip arthroplasty, and to establish a predictive model for prosthesis loosening.

METHODS

We retrospectively analyzed the data of 501 patients who underwent hip arthroplasty in Xi'an International Medical Center Hospital from January 2020 to August 2022. Based on radiological diagnosis, the patients were divided into a prosthesis loosening group and a non-loosening group. Clinical data including postoperative serum levels of inflammatory cytokines were collected. Univariant analysis, Lasso regression, decision tree, and random forest models were used to screen feature variables. Based on the screening results, a nomogram model for predicting the risk of prosthesis loosening was established and then validated using ROC curve, and calibration curve, and other methods.

RESULTS

There were 50 cases in the loosening group and 451 cases in the non-loosening group. Postoperative levels of IL-1β, IL-6, and TNF-α were found to be significantly higher in the loosening group (P<0.0001). Univariant analysis showed that osteoporosis and postoperative infection were risk factors for prosthesis loosening (P<0.001). The machine learning algorithm identified osteoporosis, postoperative infection, IL-1β, IL-6, and TNF-α as 5 relevant variables. The predictive model based on these 5 variables exhibited an area under the ROC curve of 0.763. The calibration curve and DCA curve verified the accuracy and practicality of the model.

CONCLUSION

Serum levels of IL-1β, IL-6, and TNF-α were significantly elevated in patients with postoperative prosthesis loosening. Osteoporosis, postoperative infection, and inflammatory cytokines are independent risk factors for prosthesis loosening. The predictive model we established through machine learning can effectively determine the risk of prosthesis loosening. Monitoring inflammatory cytokines and postoperative infections, combined with prevention of osteoporosis, can help reduce the risk of prosthesis loosening.

Prediction and the influencing factor study of colorectal cancer hospitalization costs in China based on machine learning-random forest and support vector regression: a retrospective study

Aims

As people's standard of living improves, the incidence of colorectal cancer is increasing, and colorectal cancer hospitalization costs are relatively high. Therefore, predicting the cost of hospitalization for colorectal cancer patients can provide guidance for controlling healthcare costs and for the development of related policies.

Methods

This study used the first page of medical record data on colorectal cancer inpatient cases of a tertiary first-class hospital in Shenzhen from 2018 to 2022. The impacting factors of hospitalization costs for colorectal cancer were analyzed. Random forest and support vector regression models were used to establish predictive models of the cost of hospitalization for colorectal cancer patients and to compare and evaluate.

Results

In colorectal cancer inpatients, major procedures, length of stay, level of procedure, Charlson comorbidity index, age, and medical payment method were the important influencing factors. In terms of the test set, the R2 of the Random forest model was 0.833, the R2 of the Support vector regression model was 0.824; the root mean square error (RMSE) of the Random forest model was 0.029, and the RMSE of the Support vector regression model was 0.032. In the Random Forest model, the weight of the major procedure was the highest (0.286).

Conclusion

Major procedures and length of stay have the greatest impacts on hospital costs for colorectal cancer patients. The random forest model is a better method to predict the hospitalization costs for colorectal cancer patients than the support vector regression.

The effect and mechanism of Fushen Granule on gut microbiome in the prevention and treatment of chronic renal failure

Background

Fushen Granule is an improved granule based on the classic formula Fushen Formula, which is used for the treatment of peritoneal dialysis-related intestinal dysfunction in patients with end-stage renal disease. However, the effect and mechanism of this granule on the prevention and treatment of chronic renal failure have not been fully elucidated.

Methods

A 5/6 nephrectomy model of CRF was induced and Fushen Granule was administered at low and high doses to observe its effects on renal function, D-lactate, serum endotoxin, and intestinal-derived metabolic toxins. The 16SrRNA sequencing method was used to analyze the abundance and structure of the intestinal flora of CRF rats. A FMT assay was also used to evaluate the effects of transplantation of Fushen Granule fecal bacteria on renal-related functional parameters and metabolic toxins in CRF rats.

Results

Gavage administration of Fushen Granule at low and high doses down-regulated creatinine, urea nitrogen, 24-h urine microalbumin, D-lactate, endotoxin, and the intestinal-derived toxins indophenol sulphateand p-cresol sulphate in CRF rats. Compared with the sham-operated group in the same period, CRF rats had a decreased abundance of the firmicutes phylum and an increased abundance of the bacteroidetes phylum at the phylum level, and a decreasing trend of the lactobacillus genus at the genus level. Fushen Granule intervention increased the abundance of the firmicutes phylum, decreased the abundance of the bacteroidetes phylum, and increased the abundance of the lactobacillus genus. The transplantation of Fushen Granule fecal bacteria significantly reduced creatinine(Cr), blood urea nitrogen(Bun), uric acid(UA), 24-h urinary microalbumin, D-lactate, serum endotoxin, and enterogenic metabolic toxins in CRF rats. Compared with the sham-operated group, the transplantation of Fushen Granule fecal bacteria modulated the Firmicutes and Bacteroidetes phyla and the Lactobacillus genus.

Conclusion

Fushen Granule improved renal function and intestinal barrier function by regulating intestinal flora, inhibiting renal fibrosis, and delaying the progression of chronic renal failure.

A machine learning model to predict the risk of depression in US adults with obstructive sleep apnea hypopnea syndrome: a cross-sectional study

Objective

Depression is very common and harmful in patients with obstructive sleep apnea hypopnea syndrome (OSAHS). It is necessary to screen OSAHS patients for depression early. However, there are no validated tools to assess the likelihood of depression in patients with OSAHS. This study used data from the National Health and Nutrition Examination Survey (NHANES) database and machine learning (ML) methods to construct a risk prediction model for depression, aiming to predict the probability of depression in the OSAHS population. Relevant features were analyzed and a nomogram was drawn to visually predict and easily estimate the risk of depression according to the best performing model.

Study design

This is a cross-sectional study.

Methods

Data from three cycles (2005-2006, 2007-2008, and 2015-2016) were selected from the NHANES database, and 16 influencing factors were screened and included. Three prediction models were established by the logistic regression algorithm, least absolute shrinkage and selection operator (LASSO) algorithm, and random forest algorithm, respectively. The receiver operating characteristic (ROC) area under the curve (AUC), specificity, sensitivity, and decision curve analysis (DCA) were used to assess evaluate and compare the different ML models.

Results

The logistic regression model had lower sensitivity than the lasso model, while the specificity and AUC area were higher than the random forest and lasso models. Moreover, when the threshold probability range was 0.19-0.25 and 0.45-0.82, the net benefit of the logistic regression model was the largest. The logistic regression model clarified the factors contributing to depression, including gender, general health condition, body mass index (BMI), smoking, OSAHS severity, age, education level, ratio of family income to poverty (PIR), and asthma.

Conclusion

This study developed three machine learning (ML) models (logistic regression model, lasso model, and random forest model) using the NHANES database to predict depression and identify influencing factors among OSAHS patients. Among them, the logistic regression model was superior to the lasso and random forest models in overall prediction performance. By drawing the nomogram and applying it to the sleep testing center or sleep clinic, sleep technicians and medical staff can quickly and easily identify whether OSAHS patients have depression to carry out the necessary referral and psychological treatment.

Personalized Music Therapy for Elderly Patients with Chronic Renal Failure to Improve their Quality of Life and Mental Health: A Retrospective Study

BACKGROUND

Chronic renal failure (CRF) poses significant clinical risks. Therefore, attention should be paid to the daily nursing of such patients, and better clinical nursing programs should be provided.

METHODS

The data of 120 patients with CRF at Yantai Yuhuangding Hospital from March 2020 to March 2022 were retrospectively analyzed. After 8 patients were excluded, 112 patients were finally included in this study. The included patients were divided into group A (58 patients receiving clinical routine nursing) and group B (54 patients receiving clinical routine nursing and personalized music) according to different nursing schemes. The anxiety level, depression level, quality of life (QOL), and clinical satisfaction of the patients in both groups were compared before and after nursing.

RESULTS

Before the implementation of nursing, no significant difference existed in the levels of anxiety, depression, and QOL between the two groups (P > 0.05). After nursing, group B had significantly lower levels of anxiety and depression and significantly higher QOL than group A (P < 0.001). No significant difference in clinical nursing satisfaction was found between the two groups (P > 0.05).

CONCLUSION

The implementation of personalized music can improve the QOL and psychological states of patients, with clinical application value.

Development of a novel machine learning model based on laboratory and imaging indices to predict acute cardiac injury in cancer patients with COVID-19 infection: a retrospective observational study

PURPOSE

Due to the increased risk of acute cardiac injury (ACI) and poor prognosis in cancer patients with COVID-19 infection, our aim was to develop a novel and interpretable model for predicting ACI occurrence in cancer patients with COVID-19 infection.

METHODS

This retrospective observational study screened 740 cancer patients with COVID-19 infection from December 2022 to April 2023. The least absolute shrinkage and selection operator (LASSO) regression was used for the preliminary screening of the indices. To enhance the model accuracy, we introduced an alpha index to further screen and rank the indices based on their significance. Random forest (RF) was used to construct the prediction model. The Shapley Additive Explanation (SHAP) and Local Interpretable Model-Agnostic Explanation (LIME) methods were utilized to explain the model.

RESULTS

According to the inclusion criteria, 201 cancer patients with COVID-19, including 36 variables indices, were included in the analysis. The top eight indices (albumin, lactate dehydrogenase, cystatin C, neutrophil count, creatine kinase isoenzyme, red blood cell distribution width, D-dimer and chest computed tomography) for predicting the occurrence of ACI in cancer patients with COVID-19 infection were included in the RF model. The model achieved an area under curve (AUC) of 0.940, an accuracy of 0.866, a sensitivity of 0.750 and a specificity of 0.900. The calibration curve and decision curve analysis showed good calibration and clinical practicability. SHAP results demonstrated that albumin was the most important index for predicting the occurrence of ACI. LIME results showed that the model could predict the probability of ACI in each cancer patient infected with COVID-19 individually.

CONCLUSION

We developed a novel machine-learning model that demonstrates high explainability and accuracy in predicting the occurrence of ACI in cancer patients with COVID-19 infection, using laboratory and imaging indices.

Efficacy of Jinshuibao as an adjuvant treatment for chronic renal failure in China: A meta-analysis

BACKGROUND

Research on Jinshuibao (JSB) for chronic renal failure (CRF) is limited, its clinical efficacy on CRF has not been evaluated. Our aim is to systematically evaluate the efficacy of JSB for the treatment of CRF in Chinese patients, and to provide evidence-based medical advice for clinical practice.

METHODS

Randomized controlled trials (RCTs) which compared JSB combined with conventional treatment (CT) with CT alone in CRF were searched in 8 databases including PubMed, EMBASE, Cochrane Library, Web of science, China Biology Medicine disc, Wanfang, Chinese Scientific Journal Database (VIP) and China National Knowledge Infrastructure form inception to March 31, 2023. RevMan5.4 statistical software was used for meta-analysis.

RESULTS

17 trials involving 1431 cases were identified for meta-analysis. The results showed that total effective rate (relative risk [RR] = 1.25, 95% confidence internal [CI]: 1.17-1.34, P < .00001), creatinine clearance rate (Ccr) (MD = -8.63, 95% CI: -12.42 to -4.84, P < .00001), albumin (Alb) (MD = -2.88, 95% CI: -4.85 to -0.92, P = .004) and hemoglobin (Hb) (MD = -5.88, 95% CI: -7.42 to -4.34, P < .00001) in JSB plus CT were significantly higher than those in CT; while blood urea nitrogen (BUN) (MD = 2.03, 95% CI: 1.27-2.80, P < .00001), serum creatinine (Scr) (MD = 48.23, 95% CI: 31.96-64.49, P < .00001), 24-hour urine protein (24hpro) (MD = 0.19, 95% CI: 0.06-0.31, P = .003), uric acid (UA) (MD = 76.36, 95% CI: 12.40-140.31, P = .02), tumor necrosis factor-α (TNF-α) (MD = 10.74, 95% CI: 5.04-16.45, P = .0002), interleukin-6 (IL-6) (MD = 5.07,95% CI: 1.21-8.92, P = .01), high-sensitivity C-reactive protein (hs-CRP) (MD = 3.74, 95% CI: 0.96-6.52, P = .008) in JSB plus CT were significantly lower than those in CT.

CONCLUSION

Combining JSB with CT has a good effect on the treatment of CRF in Chinese people. High-quality RCTs are needed to further confirm the results.

Constructing a prognostic risk model for Alzheimer's disease based on ferroptosis

Introduction

The aim of this study is to establish a prognostic risk model based on ferroptosis to prognosticate the severity of Alzheimer's disease (AD) through gene expression changes.

Methods

The GSE138260 dataset was initially downloaded from the Gene expression Omnibus database. The ssGSEA algorithm was used to evaluate the immune infiltration of 28 kinds of immune cells in 36 samples. The up-regulated immune cells were divided into Cluster 1 group and Cluster 2 group, and the differences were analyzed. The LASSO regression analysis was used to establish the optimal scoring model. Cell Counting Kit-8 and Real Time Quantitative PCR were used to verify the effect of different concentrations of Aβ_1-42 on the expression profile of representative genes in vitro.

Results

Based on the differential expression analysis, there were 14 up-regulated genes and 18 down-regulated genes between the control group and Cluster 1 group. Cluster 1 and Cluster 2 groups were differentially analyzed, and 50 up-regulated genes and 101 down-regulated genes were obtained. Finally, nine common differential genes were selected to establish the optimal scoring model. In vitro, CCK-8 experiments showed that the survival rate of cells decreased significantly with the increase of Aβ_1-42 concentration compared with the control group. Moreover, RT-qPCR showed that with the increase of Aβ_1-42 concentration, the expression of POR decreased first and then increased; RUFY3 was firstly increased and then decreased.

Discussion

The establishment of this research model can help clinicians make decisions on the severity of AD, thus providing better guidance for the clinical treatment of Alzheimer's disease.

Application of machine learning in predicting aggressive behaviors from hospitalized patients with schizophrenia

Objective

To establish a predictive model of aggressive behaviors from hospitalized patients with schizophrenia through applying multiple machine learning algorithms, to provide a reference for accurately predicting and preventing of the occurrence of aggressive behaviors.

Methods

The cluster sampling method was used to select patients with schizophrenia who were hospitalized in our hospital from July 2019 to August 2021 as the survey objects, and they were divided into an aggressive behavior group (611 cases) and a non-aggressive behavior group (1,426 cases) according to whether they experienced obvious aggressive behaviors during hospitalization. Self-administered General Condition Questionnaire, Insight and Treatment Attitude Questionnaire (ITAQ), Family APGAR (Adaptation, Partnership, Growth, Affection, Resolve) Questionnaire (APGAR), Social Support Rating Scale Questionnaire (SSRS) and Family Burden Scale of Disease Questionnaire (FBS) were used for the survey. The Multi-layer Perceptron, Lasso, Support Vector Machine and Random Forest algorithms were used to build a predictive model for the occurrence of aggressive behaviors from hospitalized patients with schizophrenia and to evaluate its predictive effect. Nomogram was used to build a clinical application tool.

Results

The area under the receiver operating characteristic curve (AUC) values of the Multi-Layer Perceptron, Lasso, Support Vector Machine, and Random Forest were 0.904 (95% CI: 0.877-0.926), 0.901 (95% CI: 0.874-0.923), 0.902 (95% CI: 0.876-0.924), and 0.955 (95% CI: 0.935-0.970), where the AUCs of the Random Forest and the remaining three models were statistically different (p < 0.0001), and the remaining three models were not statistically different in pair comparisons (p > 0.5).

Conclusion

Machine learning models can fairly predict aggressive behaviors in hospitalized patients with schizophrenia, among which Random Forest has the best predictive effect and has some value in clinical application.

A multi-granularity convolutional neural network model with temporal information and attention mechanism for efficient diabetes medical cost prediction

As the cost of diabetes treatment continues to grow, it is critical to accurately predict the medical costs of diabetes. Most medical cost studies based on convolutional neural networks (CNNs) ignore the importance of multi-granularity information of medical concepts and time interval characteristics of patients' multiple visit sequences, which reflect the frequency of patient visits and the severity of the disease. Therefore, this paper proposes a new end-to-end deep neural network structure, MST-CNN, for medical cost prediction. The MST-CNN model improves the representation quality of medical concepts by constructing a multi-granularity embedding model of medical concepts and incorporates a time interval vector to accurately measure the frequency of patient visits and form an accurate representation of medical events. Moreover, the MST-CNN model integrates a channel attention mechanism to adaptively adjust the channel weights to focus on significant medical features. The MST-CNN model systematically addresses the problem of deep learning models for temporal data representation. A case study and three comparative experiments are conducted using data collected from Pingjiang County. Through experiments, the methods used in the proposed model are analyzed, and the super contribution of the model performance is demonstrated.

Machine learning links different gene patterns of viral infection to immunosuppression and immune-related biomarkers in severe burns

Introduction

Viral infection, typically disregarded, has a significant role in burns. However, there is still a lack of biomarkers and immunotherapy targets related to viral infections in burns.

Methods

Virus-related genes (VRGs) that were extracted from Gene Oncology (GO) database were included as hallmarks. Through unsupervised consensus clustering, we divided patients into two VRGs molecular patterns (VRGMPs). Weighted gene co-expression network analysis (WGCNA) was performed to study the relationship between burns and VRGs. Random forest (RF), least absolute shrinkage and selection operator (LASSO) regression, and logistic regression were used to select key genes, which were utilized to construct prognostic signatures by multivariate logistic regression. The risk score of the nomogram defined high- and low-risk groups. We compared immune cells, immune checkpoint-related genes, and prognosis between the two groups. Finally, we used network analysis and molecular docking to predict drugs targeting CD69 and SATB1. Expression of CD69 and SATB1 was validated by qPCR and microarray with the blood sample from the burn patient.

Results

We established two VRGMPs, which differed in monocytes, neutrophils, dendritic cells, and T cells. In WGCNA, genes were divided into 14 modules, and the black module was correlated with VRGMPs. A total of 65 genes were selected by WGCNA, STRING, and differential expression analysis. The results of GO enrichment analysis were enriched in Th1 and Th2 cell differentiation, B cell receptor signaling pathway, alpha-beta T cell activation, and alpha-beta T cell differentiation. Then the 2-gene signature was constructed by RF, LASSO, and LOGISTIC regression. The signature was an independent prognostic factor and performed well in ROC, calibration, and decision curves. Further, the expression of immune cells and checkpoint genes differed between high- and low-risk groups. CD69 and SATB1 were differentially expressed in burns.

Discussion

This is the first VRG-based signature (including 2 key genes validated by qPCR) for predicting survival, and it could provide vital guidance to achieve optimized immunotherapy for immunosuppression in burns.

Short-form development of the specific module of the QLICD-CRF(V2.0) for assessing the quality of life of patients with chronic renal failure

Background

A short instrument would enhance the viability of a study. Therefore, we aimed to shorten the specific module (SPD-10) of the Quality of Life Instrument for Chronic Diseases - Chronic Renal Failure (QLICD-CRF) for assessing the quality of life of patients with chronic renal failure.

Methods

The 10-item SPD-10 was self-administered to 164 patients with chronic renal failure. A shortened form was first obtained by a tandem use of the classical test theory (CTT), the generalizability theory (GT), and the item response theory (IRT). In addition, we also shortened the SPD-10 by the Optimal Test Assembly (OTA).

Results

Both the tandem use of GT, CTT and IRT, and the OTA derived the same 7-item shortened version (SPD-7). It included items CRF1, CRF2, CRF3, CRF4, CRF6, CRF8, and CRF9 of the SPD-10. The SPD-7 had a Cronbach alpha of 0.78. The correlation coefficients of its total and factor scores with those of the SPD-10 were 0.96 and 0.98, respectively. Confirmatory factor analysis confirmed the unidimensional structure of the SPD-7, with the comparative fit index=0.96, the Tucker-Lewis index=0.94, and the root mean square error of approximation=0.09.

Conclusion

The short-form SPD-7 is reliable and valid for assessing the impact of clinical symptoms and side effects on the quality of life of patients with chronic renal failure. It is an efficient option without compromising the measurement performance of the SPD-10.

Development and validation of the prediction models for preeclampsia: a retrospective, single-center, case-control study

Background

Preeclampsia (PE) is a major cause of adverse maternal and infant outcomes. Accurate screening of PE is currently the focus of clinical attention. This study aimed to develop a model for predicting PE.

Methods

A retrospective case-control study was conducted with 916 pregnant women who received care at the Second Hospital of Tianjin Medical University (October 2018 to July 2020). Women were randomly divided into the training (n=680) and testing (n=236) sets based on a ratio of 3:1. Demographic and clinical data of women were collected. In training set, logistic regression (LR), classification tree (CT) model, and random forest (RF) algorithm were used to develop prediction models for PE. Using the testing set was to validate these prediction models. The predictive performance of three models were assessed by the area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

Results

Of the total 916 women, 237 had PE. The family history of hypertension, pre-pregnancy body mass index (pBMI), blood pressure (BP) ≥130/80 mmHg in early pregnancy, age, chronic hypertension, and duration of hypertension were the predictors of PE. The AUCs for the LR, CT, and RF models were 0.778, 0.850, and 0.871, respectively (all P<0.05 for all pair-wise comparisons). The RF had the best predictive efficiency with sensitivity, specificity, PPV, and NPV of 79.6%, 94.7%, 79.6%, and 94.7%, respectively.

Conclusions

The RF model could be a practical screening approach for predicting PE, which is helpful for clinicians to identify high-risk individuals and prevent the occurrence of adverse pregnancy outcomes.

Predicting the behavioral intentions of hospice and palliative care providers from real-world data using supervised learning: A cross-sectional survey study

Background

Hospice and palliative care (HPC) aims to improve end-of-life quality and has received much more attention through the lens of an aging population in the midst of the coronavirus disease pandemic. However, several barriers remain in China due to a lack of professional HPC providers with positive behavioral intentions. Therefore, we conducted an original study introducing machine learning to explore individual behavioral intentions and detect factors of enablers of, and barriers to, excavating potential human resources and improving HPC accessibility.

Methods

A cross-sectional study was designed to investigate healthcare providers' behavioral intentions, knowledge, attitudes, and practices in hospice care (KAPHC) with an indigenized KAPHC scale. Binary Logistic Regression and Random Forest Classifier (RFC) were performed to model impacting and predict individual behavioral intentions.

Results

The RFC showed high sensitivity (accuracy = 0.75; F1 score = 0.84; recall = 0.94). Attitude could directly or indirectly improve work enthusiasm and is the most efficient approach to reveal behavioral intentions. Continuous practice could also improve individual confidence and willingness to provide HPC. In addition, scientific knowledge and related skills were the foundation of implementing HPC.

Conclusion

Individual behavioral intention is crucial for improving HPC accessibility, particularly at the initial stage. A well-trained RFC can help estimate individual behavioral intentions to organize a productive team and promote additional policies.

Assessment of influencing factors of hospitalization expenses for Crohn's disease patients: Based on LASSO and linear mixed model

Aims

Crohn's disease (CD) is a global disease that is dramatically increasing. This study aimed to identify the primary drivers of hospitalization expenses for CD patients to provide guidance on the allocation and control of health care costs.

Methods

This study retrospectively collected the homepage data of the electronic medical records of CD patients in two tertiary hospitals in Zhejiang Province, China, from January 2016 to December 2021. The influencing factors of hospitalization expenses for CD were analyzed. A linear mixed model with least absolute shrinkage (LASSO-LMM) was used to develop a predictive model for hospitalization expenses for CD patients.

Results

A total of 4,437 CD patients were analyzed in this study. CD patients' age, length of hospital stay, admission route, comorbidities, and main treatment were found to be statistically significant variables for CD patients' hospitalization expenses. The AIC and BIC of LASSO-LMM model were 319.033 and 306.241, respectively. Patients who were older, had a longer hospital stay, and had comorbidities had higher hospitalization expenses. The hospitalization expenses of outpatients were lower than those of emergency patients. The weight of surgical treatment was the highest among three treatments (0.602).

Conclusions

Identifying and examining factors that influence hospitalization expenses for CD patients can help to control healthcare expenditures. Treatment mode was the most important impact on CD hospitalization expenses. Medical security departments can consider implement personalized and precise hospitalization expense compensation scheme base on LASSO-LMM prediction model in the future.

Nomogram-based prediction of clinically significant macular edema in diabetes mellitus patients

AIMS

The aim of the study was to construct and validate a risk nomogram for clinically significant macular edema (CSME) prediction in diabetes mellitus (DM) patients using systemic variables.

METHODS

In this retrospective study, DM inpatients who underwent routine diabetic retinopathy screening were recruited and divided into training and validation sets according to their admission date. Ninety-three demographic and systemic variables were collected. The least absolute shrinkage and selection operator was used to select the predictive variables from the training set. The selected variables were used to construct the CSME prediction nomogram. Internal and external validations were performed. The C-index, calibration curve and decision curve analysis (DCA) were reported.

RESULTS

A total of 349 patients were divided into the training set (240, 68.77%) and the validation set (109, 31.23%). The presence of diabetic peripheral neuropathy (DPN) symptoms, uric acid, use of insulin only or not for treatment, insulin dosage, urinary protein grade and disease duration were chosen for the nomogram. The C-index of the prediction nomogram was 0.896, 0.878 and 0.837 in the training set, internal validation and external validation, respectively. The calibration curves of the nomogram showed good agreement between the predicted and actual outcomes. DCA demonstrated that the nomogram was clinically useful.

CONCLUSIONS

A nomogram with good performance for predicting CSME using systemic variables was developed. It suggested that DPN symptoms and renal function may be crucial risk factors for CSME. Moreover, this nomogram may be a convenient tool for non-ophthalmic specialists to rapidly recognize CSME in patients and to transfer them to ophthalmologists for early diagnosis and treatment.

A Novel Prognostic Model for Identifying the Risk of Hepatocellular Carcinoma Based on Angiogenesis Factors

Hepatocellular carcinoma (HCC) is the most common primary liver cancer with poor prognosis. An optimized stratification of HCC patients to discriminate clinical benefit regarding different degrees of malignancy is urgently needed because of no effective and reliable prognostic biomarkers currently. HCC is typically characterized by rich vascular. The dysregulated vascular endothelial growth factor was proved a pivotal regulator of the development of HCC. Therefore, we investigated the capability of angiogenic factors (AFs) in stratifying patients and constructed a prognostic risk model. A total of 6 prognostic correlated AFs (GRM8, SPC25, FSD1L, SLC386A, FAM72A and SLC39A10) were screened via LASSO Cox regression, which provided the basis for developing a novel prognostic risk model. Based on the risk model, HCC patients were subdivided into high-risk and low-risk groups. Kaplan-Meier curve indicated that patients in the high-risk group have a lower survival rate compared with those in the low-risk group. The prognostic model showed good predictive efficacy, with AUCs reaching 0.802 at 1 year, 0.694 at 2 years, and 0.672 at 3 years. Univariate and multivariate cox regression analysis demonstrated that the risk score had significant prognostic value and was an independent prognostic factor for HCC. Moreover, this model also showed a good diagnostic positive rate in the ICGC-LIRI-JP and GSE144269. Finally, we demonstrated the efficacy of the AF-risk model in HCC patients following sorafenib adjuvant chemotherapy. And revealed the underlying molecular features involving tumor stemness, immune regulation, and genomic alterations associated with the risk score. Based on a large population, we established a novel prognostic model based on 6 AFs to help identify HCC patients with a greater risk of death. The model may provide a reference for better clinical management of HCC patients in the era of cancer precision medicine.