A nomogram and heat map based on LASSO-Cox regression for predicting the risk of early-stage severe fever with thrombocytopenia syndrome patients developing into critical illness at 7-day and 14-day.

Severe fever with thrombocytopenia syndrome (SFTS) represents an emerging infectious disease characterized by a substantial mortality risk. Early identification of patients is crucial for effective risk assessment and timely interventions. In the present study, least absolute shrinkage and selection operator (LASSO)-Cox regression analysis was conducted to identify key risk factors associated with progression to critical illness at 7-day and 14-day. A nomogram was constructed and subsequently assessed for its predictive accuracy through evaluation and validation processes. The risk stratification of patients was performed using X-tile software. The performance of this risk stratification system was assessed using the Kaplan-Meier method. Additionally, a heat map was generated to visualize the results of these analyses. A total of 262 SFTS patients were included in this study, and four predictive factors were included in the nomogram, namely viral copies, aspartate aminotransferase (AST) level, C-reactive protein (CRP), and neurological symptoms. The AUCs for 7-day and 14-day were 0.802 [95% confidence interval (CI): 0.707-0.897] and 0.859 (95% CI: 0.794-0.925), respectively. The nomogram demonstrated good discrimination among low, moderate, and high-risk groups. The heat map effectively illustrated the relationships between risk groups and predictive factors, providing valuable insights with high predictive and practical significance.

Construction and validation of a nomogram prediction model for the catheter-related thrombosis risk of central venous access devices in patients with cancer: a prospective machine learning study.

Central venous access devices (CVADs) are integral to cancer treatment. However, catheter-related thrombosis (CRT) poses a considerable risk to patient safety. It interrupts treatment; delays therapy; prolongs hospitalisation; and increases the physical, psychological and financial burden of patients. Our study aims to construct and validate a predictive model for CRT risk in patients with cancer. It offers the possibility to identify independent risk factors for CRT and prevent CRT in patients with cancer. We prospectively followed patients with cancer and CVAD at Xiangya Hospital of Central South University from January 2021 to December 2022 until catheter removal. Patients with CRT who met the criteria were taken as the case group. Two patients with cancer but without CRT diagnosed in the same month that a patient with cancer and CRT was diagnosed were selected by using a random number table to form a control group. Data from patients with CVAD placement in Qinghai University Affiliated Hospital and Hainan Provincial People's Hospital (January 2023 to June 2023) were used for the external validation of the optimal model. The incidence rate of CRT in patients with cancer was 5.02% (539/10 736). Amongst different malignant tumour types, head and neck (9.66%), haematological (6.97%) and respiratory (6.58%) tumours had the highest risks. Amongst catheter types, haemodialysis (13.91%), central venous (8.39%) and peripherally inserted central (4.68%) catheters were associated with the highest risks. A total of 500 patients with CRT and 1000 without CRT participated in model construction and were randomly assigned to the training (n = 1050) or testing (n = 450) groups. We identified 11 independent risk factors, including age, catheterisation method, catheter valve, catheter material, infection, insertion history, D-dimer concentration, operation history, anaemia, diabetes and targeted drugs. The logistic regression model had the best discriminative ability amongst the three models. It had an area under the curve (AUC) of 0.868 (0.846-0.890) for the training group. The external validation AUC was 0.708 (0.618-0.797). The calibration curve of the nomogram model was consistent with the ideal curve. Moreover, the Hosmer-Lemeshow test showed a good fit (P > 0.05) and high net benefit value for the clinical decision curve. The nomogram model constructed in this study can predict the risk of CRT in patients with cancer. It can help in the early identification and screening of patients at high risk of cancer CRT.

Predictability comparison of sizing parameters for postoperative vault after implantable Collamer lens implantation.

PURPOSE: This study aims to assess the accuracy of three parameters (white-to-white distance [WTW], angle-to-angle [ATA], and sulcus-to-sulcus [STS]) in predicting postoperative vault and to formulate an optimized predictive model. METHODS: In this retrospective study, a cohort of 465 patients (comprising 769 eyes) who underwent the implantation of the V4c implantable Collamer lens with a central port (ICL) for myopia correction was examined. Least absolute shrinkage and selection operator (LASSO) regression and classification models were used to predict postoperative vault. The influences of WTW, ATA, and STS on predicting the postoperative vault and ICL size were analyzed and compared. RESULTS: The dataset was randomly divided into training (80%) and test (20%) sets, with no significant differences observed between them. The screened variables included only seven variables which conferred the largest signal in the model, namely, lens thickness (LT, estimated coefficients for logistic least absolute shrinkage of -0.20), STS (-0.04), size (0.08), flat K (-0.006), anterior chamber depth (0.15), spherical error (-0.006), and cylindrical error (-0.0008). The optimal prediction model depended on STS (R2=0.419, RMSE=0.139), whereas the least effective prediction model relied on WTW (R2=0.395, RMSE=0.142). In the classified prediction models of the vault, classification prediction of the vault based on STS exhibited superior accuracy compared to ATA or WTW. CONCLUSIONS: This study compared the capabilities of WTW, ATA, and STS in predicting postoperative vault, demonstrating that STS exhibits a stronger correlation than the other two parameters.

Chest CT radiomics is feasible in evaluating bone changes in chronic kidney diseases.

BACKGROUND: Non-invasive imaging methods are still lacking for evaluating bone changes in chronic kidney diseases (CKD). PURPOSE: To investigate the feasibility of chest CT radiomics in evaluating bone changes caused by CKD. MATERIAL AND METHODS: In total, 75 patients with stage 1 CKD (CKD1) and 75 with stage 5 CKD (CKD5) were assessed using the chest CT radiomics method. Radiomics features of bone were obtained using 3D Slicer software and were then compared between CKD1 and CKD5 cases. The methods of maximum correlation minimum redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) were used to establish a prediction model to determine CKD. The receiver operating characteristic (ROC) curve was used to determine the performance of the model. RESULTS: Cases of CKD1 and CKD5 differed in 40 radiomics features (P <0.05). Using the mRMR and LASSO methods, five features were finally selected to establish a predication model. The area under the receiver operating characteristic curve of the model in the determination of CKD1 and CKD5 was 0.903 and 0.854, respectively, for the training and validation cohorts. CONCLUSION: Chest CT radiomics is feasible in evaluating bone changes caused by CKD.

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.

A novel nomogram for predicting overall survival in patients with tongue squamous cell carcinoma using clinical features and MRI radiomics data: a pilot study.

OBJECTIVE: Tongue squamous cell carcinoma (TSCC) accounts for 43.4% of oral cancers in China and has a poor prognosis. This study aimed to explore whether radiomics features extracted from preoperative magnetic resonance imaging (MRI) could predict overall survival (OS) in patients with TSCC. METHODS: The clinical imaging data of 232 patients with pathologically confirmed TSCC at Xiangyang No. 1 People's Hospital were retrospectively analyzed from February 2010 to October 2022. Based on 2-10 years of follow-up, patients were categorized into two groups: control (healthy survival, n = 148) and research (adverse events: recurrence or metastasis-related death, n = 84). A training and a test set were established using a 7:3 ratio and a time node. Radiomics features were extracted from axial T2-weighted imaging, contrast-enhanced T1-weighted imaging, and diffusion-weighted imaging (DWI) sequences. The corresponding radiomics scores were generated using the least absolute shrinkage and selection operator algorithm. Kaplan-Meier and multivariate Cox regression analyses were used to screen for independent factors affecting adverse events in patients with TSCC using clinical and pathological results. A novel nomogram was established to predict the probability of adverse events and OS in patients with TSCC. RESULTS: The incidence of adverse events within 2-10 years after surgery was 36.21%. Kaplan-Meier analysis revealed that hot pot consumption, betel nut chewing, platelet-lymphocyte ratio, drug use, neutrophil-lymphocyte ratio, Radscore, and other factors impacted TSCC survival. Multivariate Cox regression analysis revealed that the clinical stage (P < 0.001), hot pot consumption (P < 0.001), Radscore 1 (P = 0.01), and Radscore 2 (P < 0.001) were independent factors affecting TSCC-OS. The same result was validated by the XGBoost algorithm. The nomogram based on the aforementioned factors exhibited good discrimination (C-index 0.86/0.81) and calibration (P > 0.05) in the training and test sets, accurately predicting the risk of adverse events and survival. CONCLUSION: The nomogram constructed using clinical data and MRI radiomics parameters may accurately predict TSCC-OS noninvasively, thereby assisting clinicians in promptly modifying treatment strategies to improve patient prognosis.

Predicting Acupuncture Efficacy in Chronic Prostatitis/Chronic Pelvic Pain Syndrome: A Study on Model Development and Result Visualization.

INTRODUCTION: Acupuncture is one of primary treatment options for chronic prostatitis/chronic pelvic pain syndrome (CP/CPPS), but its efficacy varies among patients. This study aimed to develop and validate a nomogram for predicting the efficacy of acupuncture in CP/CPPS. METHODS: This study enrolled 220 patients with CP/CPPS who received acupuncture. Patients were divided into a responder group and nonresponder group based on the reduction in the National Institutes of Health Chronic Prostatitis Symptom Index (NIH-CPSI). Potential variables were selected using the least absolute shrinkage and selection operator regression, and a nomogram was established using the multivariable logistic regression model. The performance of the nomogram was assessed by the receiver operating characteristic curves and calibration curves. RESULTS: Two Hundred Twenty men were randomly assigned to the training cohort (n = 154) and the internal test cohort (n = 66). The developed nomogram included age, current drinking status, sedentary lifestyle, habit of staying up late, expectations for acupuncture, comorbidities, NIH-CPSI pain subscale and total scores. The area under the curve of the prediction model was 0.777 (95% CI: 0.702-0.851) in the training cohort, 0.752 (95% CI: 0.616-0.888) in the internal test cohort, demonstrating satisfactory discriminative ability as indicated by the calibration curve. CONCLUSIONS: The nomogram accurately identified CP/CPPS patients who would benefit from acupuncture. Factors such as youth, abstention from alcohol, avoiding sedentary habits and staying up late, having high expectations for acupuncture, being free from comorbidities, and baseline high scores on both the NIH-CPSI pain subscale and total scores may positively affect the efficacy of acupuncture. Further validation of our findings requires multicenter and large-sample prospective studies.

A prognostic four-gene signature and a therapeutic strategy for hepatocellular carcinoma: Construction and analysis of a circRNA-mediated competing endogenous RNA network.

BACKGROUND: Hepatocellular carcinoma (HCC) has a poor long-term prognosis. The competition of circular RNAs (circRNAs) with endogenous RNA is a novel tool for predicting HCC prognosis. Based on the alterations of circRNA regulatory networks, the analysis of gene modules related to HCC is feasible. METHODS: Multiple expression datasets and RNA element targeting prediction tools were used to construct a circRNA-microRNA-mRNA network in HCC. Gene function, pathway, and protein interaction analyses were performed for the differentially expressed genes (DEGs) in this regulatory network. In the protein-protein interaction network, hub genes were identified and subjected to regression analysis, producing an optimized four-gene signature for prognostic risk stratification in HCC patients. Anti-HCC drugs were excavated by assessing the DEGs between the low- and high-risk groups. A circRNA-microRNA-hub gene subnetwork was constructed, in which three hallmark genes, KIF4A, CCNA2, and PBK, were subjected to functional enrichment analysis. RESULTS: A four-gene signature (KIF4A, CCNA2, PBK, and ZWINT) that effectively estimated the overall survival and aided in prognostic risk assessment in the The Cancer Genome Atlas (TCGA) cohort and International Cancer Genome Consortium (ICGC) cohort was developed. CDK inhibitors, PI3K inhibitors, HDAC inhibitors, and EGFR inhibitors were predicted as four potential mechanisms of drug action (MOA) in high-risk HCC patients. Subsequent analysis has revealed that PBK, CCNA2, and KIF4A play a crucial role in regulating the tumor microenvironment by promoting immune cell invasion, regulating microsatellite instability (MSI), and exerting an impact on HCC progression. CONCLUSIONS: The present study highlights the role of the circRNA-related regulatory network, identifies a four-gene prognostic signature and biomarkers, and further identifies novel therapy for HCC.

Using LASSO Regression to Estimate the Population-Level Impact of Pneumococcal Conjugate Vaccines.

Pneumococcal conjugate vaccines (PCVs) protect against diseases caused by Streptococcus pneumoniae, such as meningitis, bacteremia, and pneumonia. It is challenging to estimate their population-level impact due to the lack of a perfect control population and the subtleness of signals when the endpoint-such as all-cause pneumonia-is nonspecific. Here we present a new approach for estimating the impact of PCVs: using least absolute shrinkage and selection operator (LASSO) regression to select variables in a synthetic control model to predict the counterfactual outcome for vaccine impact inference. We first used a simulation study based on hospitalization data from Mexico (2000-2013) to test the performance of LASSO and established methods, including the synthetic control model with Bayesian variable selection (SC). We found that LASSO achieved accurate and precise estimation, even in complex simulation scenarios where the association between the outcome and all control variables was noncausal. We then applied LASSO to real-world hospitalization data from Chile (2001-2012), Ecuador (2001-2012), Mexico (2000-2013), and the United States (1996-2005), and found that it yielded estimates of vaccine impact similar to SC. The LASSO method is accurate and easily implementable and can be applied to study the impact of PCVs and other vaccines.

Motor progression marker for newly diagnosed drug-naïve patients with Parkinson's disease: A resting-state functional MRI study.

The effective early prediction of clinical outcomes of Parkinson's disease (PD) is of great significance in the implementation of appropriate interventions. We aimed to propose a method based on the use of baseline resting-state functional characteristics (i.e., fractional amplitude of low-frequency fluctuations, fALFF) to predict motor progression in PD patients. Resting-state functional magnetic resonance imaging was performed on 48 newly-diagnosed drug-naïve PD patients and 27 age- and sex- matched healthy controls (HCs). Two PD subgroups were defined with different annual increase of Unified PD Rating Scale Part III motor scores. Least absolute shrinkage and selection operator regression analysis was performed to explore the baseline region-functional indicators for PD discrimination as well as the predictors for future motor deficits. Two significant models composed of baseline fALFF values from cerebral subregions were proposed. The classification model that distinguished PD patients from HCs (area under the curve [AUC] = 0.897) showed the most significant imaging characteristics in the putamen and precentral gyrus. The other prediction model that evaluated the degree of future deterioration of motor symptoms in PD patients (AUC = 0.916) showed the most significant imaging characteristics in the superior occipital gyrus and caudate nucleus. Furthermore, the increased regional function in bilateral caudate nuclei was correlated with the lower annual increase in motor deficits in all PD patients. The caudate nucleus might be the core region responsible for future motor deficits in newly-diagnosed PD patients, which may aid the development of disease progression preventive strategies in clinical practice.

Analysis of metabolomics and transcriptomics data in head and neck squamous cell carcinoma.

OBJECTIVE: Studies have shown that cancer progression of head and neck squamous cell carcinoma (HNSCC) is related with metabolic alterations. The aim of this study is to identify the clinical roles of metabolic alterations in HNSCC. MATERIALS AND METHODS: Metabolism-related genes associated with HNSCC were searched in public databases. A predictive and efficacious LASSO model was fabricated to optimize the diagnosis that was based on these genes. Meantime, ultra-performance liquid chromatography-quadrupole/orbitrap high resolution mass spectrometry (UHPLC-Q-Orbitrap HRMS) was used to compare patients with HNSCC (n = 73) with healthy controls (n = 51) for serum metabolites. Potential biomarkers and alterations in serum metabolites were analysed and evaluated using t test analysis, principal component analysis and orthogonal partial least square-discrimination analysis. RESULTS: Overall, 21 differential metabolites were probed in serum, of which eight metabolites had potential for clinical uses. Transcriptome analysis showed that four genes in the constructed LASSO model were found to be associated with seven differential metabolites. Metabolic pathway analysis by MetaboAnalyst showed that the biomarkers that were related with HNSCC were closely related to four metabolism pathways (p < 0.05). CONCLUSION: To conclude, future research on HNSCC should be directed towards multi-omics to provide treatment, intervention or diagnosis of the disease.

Risk factors for hyponatremia in acute exacerbation chronic obstructive pulmonary disease (AECOPD): a multicenter cross-sectional study.

BACKGROUND: Hyponatremia is an independent predictor of poor prognosis, including increased mortality and readmission, in COPD patients. Identifying modifiable etiologies of hyponatremia may help reduce adverse events in patients with AECOPD. Therefore, the aim of this study was to explore the risk factors and underlying etiologies of hyponatremia in AECOPD patients. METHODS: A total of 586 AECOPD patients were enrolled in this multicenter cross-sectional study. Finally, 323 had normonatremia, and 90 had hyponatremia. Demographics, underlying diseases, comorbidities, symptoms, and laboratory data were collected. The least absolute shrinkage and selection operator (LASSO) regression was used to select potential risk factors, which were substituted into binary logistic regression to identify independent risk factors. Nomogram was built to visualize and validate binary logistics regression model. RESULTS: Nine potential hyponatremia-associated variables were selected by LASSO regression. Subsequently, a binary logistic regression model identified that smoking status, rate of community-acquired pneumonia (CAP), anion gap (AG), erythrocyte sedimentation rate (ESR), and serum magnesium (Mg2+) were independent variables of hyponatremia in AECOPD patients. The AUC of ROC curve of nomogram was 0.756. The DCA curve revealed that the nomogram could yielded more clinical benefits if the threshold was between 10% and 52%. CONCLUSIONS: Collectively, our results showed that smoking status, CAP, AG, ESR, and serum Mg2+ were independently associated with hyponatremia in AECOPD patients. Then, these findings indicate that pneumonia, metabolic acidosis, and hypomagnesemia were the underlying etiologies of hyponatremia in AECOPD patients. However, their internal connections need further exploration.

Identification of key biomarkers of the glomerulus in focal segmental glomerulosclerosis and their relationship with immune cell infiltration based on WGCNA and the LASSO algorithm.

OBJECTIVE: The aim of our study was to identify key biomarkers of glomeruli in focal glomerulosclerosis (FSGS) and analyze their relationship with the infiltration of immune cells. METHODS: The expression profiles (GSE108109 and GSE200828) were obtained from the GEO database. The differentially expressed genes (DEGs) were filtered and analyzed by gene set enrichment analysis (GSEA). MCODE module was constructed. Weighted gene coexpression network analysis (WGCNA) was performed to obtain the core gene modules. Least absolute shrinkage and selection operator (LASSO) regression was applied to identify key genes. ROC curves were employed to explore their diagnostic accuracy. Transcription factor prediction of the key biomarkers was performed using the Cytoscape plugin IRegulon. The analysis of the infiltration of 28 immune cells and their correlation with the key biomarkers were performed. RESULTS: A total of 1474 DEGs were identified. Their functions were mostly related to immune-related diseases and signaling pathways. MCODE identified five modules. The turquoise module of WGCNA had significant relevance to the glomerulus in FSGS. TGFB1 and NOTCH1 were identified as potential key glomerular biomarkers in FSGS. Eighteen transcription factors were obtained from the two hub genes. Immune infiltration showed significant correlations with T cells. The results of immune cell infiltration and their relationship with key biomarkers implied that NOTCH1 and TGFB1 were enhanced in immune-related pathways. CONCLUSION: TGFB1 and NOTCH1 may be strongly correlated with the pathogenesis of the glomerulus in FSGS and are new candidate key biomarkers. T-cell infiltration plays an essential role in the FSGS lesion process.

An integrated bioinformatics approach to identify key biomarkers in the tubulointerstitium of patients with focal segmental glomerulosclerosis and construction of mRNA-miRNA-lncRNA/circRNA networks.

OBJECTIVE: The purpose of this study was to identify potential biomarkers in the tubulointerstitium of focal segmental glomerulosclerosis (FSGS) and comprehensively analyze its mRNA-miRNA-lncRNA/circRNA network. METHODS: The expression data (GSE108112 and GSE200818) were downloaded from the Gene Expression Omnibus database (https://www.ncbi.nlm.nih.gov/geo/). Identification and enrichment analysis of differentially expressed genes (DEGs) were performed. the PPI networks of the DEGs were constructed and classified using the Cytoscape molecular complex detection (MCODE) plugin. Weighted gene coexpression network analysis (WGCNA) was used to identify critical gene modules. Least absolute shrinkage and selection operator regression analysis were used to screen for key biomarkers of the tubulointerstitium in FSGS, and the receiver operating characteristic curve was used to determine their diagnostic accuracy. The screening results were verified by quantitative real-time-PCR (qRT-PCR) and Western blot. The transcription factors (TFs) affecting the hub genes were identified by Cytoscape iRegulon. The mRNA-miRNA-lncRNA/circRNA network for identifying potential biomarkers was based on the starBase database. RESULTS: A total of 535 DEGs were identified. MCODE obtained eight modules. The green module of WGCNA had the greatest association with the tubulointerstitium in FSGS. PPARG coactivator 1 alpha (PPARGC1A) was screened as a potential tubulointerstitial biomarker for FSGS and verified by qRT-PCR and Western blot. The TFs FOXO4 and FOXO1 had a regulatory effect on PPARGC1A. The ceRNA network yielded 17 miRNAs, 32 lncRNAs, and 50 circRNAs. CONCLUSIONS: PPARGC1A may be a potential biomarker in the tubulointerstitium of FSGS. The ceRNA network contributes to the comprehensive elucidation of the mechanisms of tubulointerstitial lesions in FSGS.

Suitability Analysis of Machine Learning Algorithms for Crack Growth Prediction Based on Dynamic Response Data.

Machine learning has the potential to enhance damage detection and prediction in materials science. Machine learning also has the ability to produce highly reliable and accurate representations, which can improve the detection and prediction of damage compared to the traditional knowledge-based approaches. These approaches can be used for a wide range of applications, including material design; predicting material properties; identifying hidden relationships; and classifying microstructures, defects, and damage. However, researchers must carefully consider the appropriateness of various machine learning algorithms, based on the available data, material being studied, and desired knowledge outcomes. In addition, the interpretability of certain machine learning models can be a limitation in materials science, as it may be difficult to understand the reasoning behind predictions. This paper aims to make novel contributions to the field of material engineering by analyzing the compatibility of dynamic response data from various material structures with prominent machine learning approaches. The purpose of this is to help researchers choose models that are both effective and understandable, while also enhancing their understanding of the model's predictions. To achieve this, this paper analyzed the requirements and characteristics of commonly used machine learning algorithms for crack propagation in materials. This analysis assisted the authors in selecting machine learning algorithms (K nearest neighbor, Ridge, and Lasso regression) to evaluate the dynamic response of aluminum and ABS materials, using experimental data from previous studies to train the models. The results showed that natural frequency was the most significant predictor for ABS material, while temperature, natural frequency, and amplitude were the most important predictors for aluminum. Crack location along samples had no significant impact on either material. Future work could involve applying the discussed techniques to a wider range of materials under dynamic loading conditions.

Predicting suicide attempts among people with diabetes using a large multicenter electronic health records dataset.

OBJECTIVE: People with diabetes have a higher risk of suicidal behaviors than the general population. However, few studies have focused on understanding this relationship. We investigated risk factors and predicted suicide attempts in people with diabetes using Least Absolute Shrinkage and Selection Operator (LASSO) regression. METHOD: Data was retrieved from Cerner Real-World Data and included over 3 million diabetes patients in the study. LASSO regression was applied to identify associated factors. Gender, diabetes-type, and depression-specific LASSO regression models were analyzed. RESULTS: There were 7764 subjects diagnosed with suicide attempts with an average age of 45. Risk factors for suicide attempts in diabetes patients were American Indian or Alaska Native race (ß = 0.637), receiving atypical antipsychotic agents (ß = 0.704), benzodiazepines (ß = 0.784), or antihistamines (ß = 0.528). Amyotrophy was negatively associated with suicide attempts in males (ß = 2.025); in contrast, amyotrophy significantly increased the risk in females (ß = 3.339). Using a MAOI was negatively related to suicide attempts in T1DM patients (ß = 7.304). Age less than 20 was positively associated with suicide attempts in depressed (ß = 2.093) and non-depressed patients (ß = 1.497). The LASSO model achieved a 94.4% AUC and 87.4% F1 score. CONCLUSIONS: To our knowledge, this is the first study to use LASSO regression to identify risk factors for suicide attempts in patients with diabetes. The shrinkage technique successfully reduced the number of variables in the model to improve the fit. Further research is needed to determine cause-and-effect relationships. The results may help providers to identify high-risk groups for suicide attempt among diabetic patients.

Lasso algorithm and support vector machine strategy to screen pulmonary arterial hypertension gene diagnostic markers.

BACKGROUND: This study employs machine learning strategy algorithms to screen the optimal gene signature of pulmonary arterial hypertension (PAH) under big data in the medical field. METHODS: The public database Gene Expression Omnibus (GEO) was used to analyze datasets of 32 normal controls and 37 PAH disease samples. The enrichment analysis was performed after selecting the differentially expressed genes. Two machine learning methods, the least absolute shrinkage and selection operator (LASSO) and support vector machine (SVM), were used to identify the candidate genes. The external validation data set further tests the expression level and diagnostic value of candidate diagnostic genes. The diagnostic effectiveness was evaluated by obtaining the receiver operating characteristic curve (ROC). The convolution tool CIBERSORT was used to estimate the composition pattern of the immune cell subtypes and to perform correlation analysis based on the combined training dataset. RESULTS: A total of 564 differentially expressed genes (DEGs) were screened in normal control and pulmonary hypertension samples. The enrichment analysis results were found to be closely related to cardiovascular diseases, inflammatory diseases, and immune-related pathways. The LASSO and SVM algorithms in machine learning used 5 × cross-validation to identify 9 and 7 characteristic genes. The two machine learning algorithms shared Caldesmon 1 (CALD1) and Solute Carrier Family 7 Member 11 (SLC7A11) as genetic signals highly correlated with PAH. The results showed that the area under ROC (AUC) of the specific characteristic diagnostic genes were CALD1 (AUC = 0.924) and SLC7A11 (AUC = 0.962), indicating that the two diagnostic genes have high diagnostic value. CONCLUSION: CALD1 and SLC7A11 can be used as diagnostic markers of PAH to obtain new insights for the further study of the immune mechanism involved in PAH.

[Keloid nomogram prediction model based on weighted gene co-expression network analysis and machine learning].

Keloids are benign skin tumors resulting from the excessive proliferation of connective tissue in wound skin. Precise prediction of keloid risk in trauma patients and timely early diagnosis are of paramount importance for in-depth keloid management and control of its progression. This study analyzed four keloid datasets in the high-throughput gene expression omnibus (GEO) database, identified diagnostic markers for keloids, and established a nomogram prediction model. Initially, 37 core protein-encoding genes were selected through weighted gene co-expression network analysis (WGCNA), differential expression analysis, and the centrality algorithm of the protein-protein interaction network. Subsequently, two machine learning algorithms including the least absolute shrinkage and selection operator (LASSO) and the support vector machine-recursive feature elimination (SVM-RFE) were used to further screen out four diagnostic markers with the highest predictive power for keloids, which included hepatocyte growth factor (HGF), syndecan-4 (SDC4), ectonucleotide pyrophosphatase/phosphodiesterase 2 (ENPP2), and Rho family guanosine triphophatase 3 (RND3). Potential biological pathways involved were explored through gene set enrichment analysis (GSEA) of single-gene. Finally, univariate and multivariate logistic regression analyses of diagnostic markers were performed, and a nomogram prediction model was constructed. Internal and external validations revealed that the calibration curve of this model closely approximates the ideal curve, the decision curve is superior to other strategies, and the area under the receiver operating characteristic curve is higher than the control model (with optimal cutoff value of 0.588). This indicates that the model possesses high calibration, clinical benefit rate, and predictive power, and is promising to provide effective early means for clinical diagnosis.

Perfluoroalkyl substances (PFASs) as risk factors for breast cancer: a case-control study in Chinese population.

BACKGROUND: Perfluoroalkyl substances (PFASs) are a large family of synthetic chemicals, some of which are mammary toxicants and endocrine disruptors. Recent studies have implicated exposure to PFASs as a risk factor for breast cancer in Europe and America. Little is known about the role of PFASs with respect to breast cancer in the Chinese population. METHODS: Participants who were initially diagnosed with breast cancer at Tianjin Medical University Cancer Institute and Hospital between 2012 and 2016 were recruited as cases. The controls were randomly selected from the participants with available blood samples in the Chinese National Breast Cancer Screening Program (CNBCSP) cohort. Ultimately, we enrolled 373 breast cancer patients and 657 controls. Plasma PFASs were measured by an ultra-performance liquid chromatography (UPLC) system coupled to a 5500 Q-Trap triple quadrupole mass spectrometer. A logistic regression model with least absolute shrinkage and selection operator (LASSO) regularization was used to calculate odds ratios (ORs) and 95% confidence intervals (CIs) to assess the relationships between PFASs and breast cancer. The three most predictive variables in the LASSO model were selected from 17 PFASs, which was based on the optimal penalty coefficient (λ = 0.0218) identified with the minimum criterion. Additionally, Bayesian kernel machine regression (BKMR) and quantile g-computation models were applied to evaluate the associations between separate and mixed exposure to PFASs and breast cancer. RESULTS: Perfluorooctanesulfonic acid (PFOS) exhibited the highest concentration in both the cases and controls. Perfluorooctanoic acid (PFOA) and perfluoro-n-decanoic acid (PFDA) were positively associated with breast cancer, and perfluoro-n-tridecanoic acid (PFTrDA) was negatively associated with breast cancer according to both the continuous-PFASs and the quartile-PFASs logistic regression models. Of note, PFOA was associated with the occurrence of estrogen receptor (ER)-, progesterone receptor (PR)-, and human epidermal growth factor receptor 2 (HER2)-positive breast cancer (ORER+ = 1.47, 95% CI: 1.19, 1.80; ORPR+ = 1.36, 95% CI: 1.09, 1.69; ORHER2 = 1.62, 95% CI: 1.19, 2.21). CONCLUSIONS: Overall, we observed that PFASs were associated with breast cancer in Chinese women. Prospective cohort studies and mechanistic experiments are warranted to elucidate whether these associations are causal.

Development and application of a novel model to predict the risk of non-alcoholic fatty liver disease among lean pre-diabetics with normal blood lipid levels.

BACKGROUND: Non-alcoholic fatty liver disease (NAFLD) has been associated with type 2 diabetes, but its relationship with pre-diabetes is still unknown. This study aims to determine whether pre-diabetes is associated with NAFLD, followed by establishing a NAFLD predictive nomogram for lean Chinese pre-diabetics with normal blood lipids. METHODS: Datasets from 3 previous studies, 1 (2774 pre-diabetics with normal blood lipids for training, 925 for validation), 2 (546 for longitudinal internal validation, post-5-year follow-up), and 3 (501 from another institution for external validation), were used. Kaplan-Meier determined cumulative NAFLD hazard, and least absolute shrinkage and selection operator regression analysis uncovered its risk factors. Multivariate logistic regression analysis constructed the nomogram, followed by validation with receiver operating characteristic curve, calibration plot, and decision curve analyses. RESULTS: NAFLD incidence increased with diabetes progression, and pre-diabetics had higher cumulative risk versus non-diabetics, even for lean individuals with normal blood lipids. Six risk factors were identified: body mass index, total cholesterol, alanine aminotransferase:aspartate aminotransferase, triglyceride:high density lipoprotein cholesterol, fasting blood glucose and γ-glutamyl-transferase. The nomogram yielded areas under the curve of 0.808, 0.785, 0.796 and 0.832, for respectively, training, validation, longitudinal internal validation, and external validation, which, along with calibration curve values of p = 0.794, 0.875, 0.854 and 0.810 for those 4 datasets and decision curve analyses, validated its clinical utility. CONCLUSIONS: Lean pre-diabetic Chinese with normal blood lipids have higher NAFLD risk versus non-diabetics. The nomogram is able to predict NAFLD among such individuals, with high discrimination, enabling its use for early detection and intervention.