Establishment and validation of apnea risk prediction models in preterm infants: a retrospective case control study.

BACKGROUND: Apnea is common in preterm infants and can be accompanied with severe hypoxic damage. Early assessment of apnea risk can impact the prognosis of preterm infants. We constructed a prediction model to assess apnea risk in premature infants for identifying high-risk groups. METHODS: A total of 162 and 324 preterm infants with and without apnea who were admitted to the neonatal intensive care unit of Xiamen University between January 2018 and December 2021 were selected as the case and control groups, respectively. Demographic characteristics, laboratory indicators, complications of the patients, pregnancy-related factors, and perinatal risk factors of the mother were collected retrospectively. The participants were randomly divided into modeling (n = 388) and validation (n = 98) sets in an 8:2 ratio. Least Absolute Shrinkage and Selection Operator (LASSO) and multivariate logistic regression analyses were used to independently filter variables from the modeling set and build a model. A nomogram was used to visualize models. The calibration and clinical utility of the model was evaluated using consistency index, receiver operating characteristic (ROC) curve, calibration curve, and decision curve, and the model was verified using the validation set. RESULTS: Results of LASSO combined with multivariate logistic regression analysis showed that gestational age at birth, birth length, Apgar score, and neonatal respiratory distress syndrome were predictors of apnea development in preterm infants. The model was presented as a nomogram and the Hosmer-Lemeshow goodness of fit test showed a good model fit (χ2=5.192, df=8, P=0.737), with Nagelkerke R2 of 0.410 and C-index of 0.831. The area under the ROC curve and 95% CI were 0.831 (0.787-0.874) and 0.829 (0.722-0.935), respectively. Delong's test comparing the AUC of the two data sets showed no significant difference (P=0.976). The calibration curve showed good agreement between the predicted and actual observations. The decision curve results showed that the threshold probability range of the model was 0.07-1.00, the net benefit was high, and the constructed clinical prediction model had clinical utility. CONCLUSIONS: Our risk prediction model based on gestational age, birth length, Apgar score 10 min post-birth, and neonatal respiratory distress syndrome was validated in many aspects and had good predictive efficacy and clinical utility.

Machine learning-based short-term DFS-associated characteristic factor screening and model construction for patients with gallbladder cancer after radical surgery.

Gallbladder cancer (GBC) is a malignancy with a bleak prognosis, and radical surgery remains the primary treatment option. However, the high postoperative recurrence rate and the lack of individualized risk assessment tools limit the effectiveness of current treatment strategies. This study aims to identify risk factors affecting the short-term disease-free survival (DFS) of GBC patients using machine learning methods and to build a prediction model. A retrospective analysis was conducted on the clinical data from 328 GBC patients treated at the First Affiliated Hospital of Huzhou University from 2008 to 2021. Patients were randomly divided into a training set (n=230) and a validation set (n=98). Clinical data, laboratory indexes, and follow-up data were collected. Univariate Cox regression analysis identified age, tumor T-staging, lymph node metastasis, differentiation degree, and CA199 level as prognostic factors affecting DFS (all P<0.05). A prediction model constructed using the LASSO regression achieved AUCs of 0.827 and 0.801 for predicting 1-year and 3-year DFS, respectively. Notably, the XGBoost regression model showed higher prediction accuracy with AUCs of 0.922 and 0.947, respectively. The Delong test confirmed that the XGBoost model had significantly higher AUC values compared to the LASSO model (all P<0.001). In the validation set, the XGBoost model demonstrated AUCs of 0.764 and 0.761 for predicting 1-year and 3-year DFS, respectively. Overall, the XGBoost regression model demonstrates high accuracy and clinical value in predicting short-term DFS in GBC patients after radical surgery, offering a valuable tool for personalized treatment.

Construction and validation of a risk prediction model for extrauterine growth restriction in preterm infants born at gestational age less than 34 weeks.

Objective: This study aimed to develop and validate a model for predicting extrauterine growth restriction (EUGR) in preterm infants born ≤34 weeks gestation. Methods: Preterm infants from Guangxi Maternal and Child Health Hospital (2019-2021) were randomly divided into training (80%) and testing (20%) sets. Collinear clinical variables were excluded using Pearson correlation coefficients. Predictive factors were identified using Lasso regression. Random forest (RF), support vector machine (SVM), and logistic regression (LR) models were then built and evaluated using the confusion matrix, area under the curve (AUC), and the F1 score. Additionally, calibration curves and decision curve analysis (DCA) were plotted to assess the performance and practical utility of the models. Results: The study included 387 infants, with no significant baseline differences between training (n = 310) and testing (n = 77) sets. LR identified gestational age, birth weight, premature rupture of membranes, patent ductus arteriosus, cholestasis, and neonatal sepsis as key EUGR predictors. The RF model (19 variables) demonstrated an accuracy of greater than 90% during training, and superior AUC (0.62), F1 score (0.80), and accuracy (0.72) in testing compared to other models. Conclusions: Gestational age, birth weight, premature rupture of membranes, patent ductus arteriosus, cholestasis, and neonatal sepsis are significant EUGR predictors in preterm infants ≤34 weeks. The model shows promise for early EUGR prediction in clinical practice, potentially enhancing screening efficiency and accuracy, thus saving medical resources.

Development and external validation of a nomogram for predicting lymph node metastasis in 1-3 cm lung adenocarcinoma.

Aim: This study aimed to investigate the risk factors for lymph node metastasis in 1-3 cm adenocarcinoma and develop a new nomogram to predict the probability of lymph node metastasis.Materials & methods: This study collected clinical data from 1656 patients for risk factor analysis and an additional 500 patients for external validation. The logistic regression analyses were employed for risk factor analysis. The least absolute shrinkage and selection operator regression was used to select variables, and important variables were used to construct the nomogram and an online calculator.Results: The nomogram for predicting lymph node metastasis comprises six variables: tumor size (mediastinal window), consolidation tumor ratio, tumor location, lymphadenopathy, preoperative serum carcinoembryonic antigen level and pathological grade. According to the predicted results, the risk of lymph node metastasis was divided into low-risk group and high-risk group. We confirmed the exceptional clinical efficacy of the model through multiple evaluation methods.Conclusion: The importance of intraoperative frozen section is increasing. We discussed the risk factors for lymph node metastasis and developed a nomogram to predict the probability of lymph node metastasis in 1-3 cm adenocarcinomas, which can guide lymph node resection strategies during surgery.

[Box: see text].

Development and validation of a predictive model for failure of ureteral access sheath placement in patients with ureteral calculi.

OBJECTIVE: The Ureteral Access Sheath (UAS) has notable benefits but may fail to traverse the ureter in some cases. Our objective was to develop and validate a dynamic online nomogram for patients with ureteral stones who experienced UAS placement failure during retrograde intrarenal surgery (RIRS). METHODS: This study is a retrospective cohort analysis using medical records from the Second Hospital of Tianjin Medical University. We reviewed the records of patients with ureteral stones who underwent RIRS in 2022 to identify risk factors associated with UAS placement failure. Lasso combined logistic regression was utilized to identify independent risk factors associated with unsuccessful UAS placement in individuals with ureteral stones. Subsequently, a nomogram model was developed to predict the likelihood of failed UAS placement in this patient cohort. The model's performance was assessed through Receiver Operating Characteristic Curve (ROC) analysis, calibration curve assessment, and Decision Curve Analysis (DCA). RESULTS: Significant independent risk factors for unsuccessful UAS placement in patients with ureteral stones included age (OR = 0.95, P < 0.001), male gender (OR = 2.15, P = 0.017), body mass index (BMI) (OR = 1.12, P < 0.001), history of stone evacuation (OR = 0.35, P = 0.014), and ureteral stone diameter (OR = 0.23, P < 0.001). A nomogram was constructed based on these variables. Model validation demonstrated an area under the ROC curve of 0.789, indicating good discrimination. The calibration curve exhibited strong agreement, and the decision curve analysis revealed a favorable net clinical benefit for the model. CONCLUSIONS: Young age, male sex, high BMI, no history of stone evacuation, and small diameter of ureteral stones were independent risk factors for failure of UAS placement in patients with ureteral stones, and the dynamic nomogram established with these 5 factors was clinically effective in predicting the outcome of UAS placement.

Bioinformatics-Based Identification of Key Prognostic Genes in Neuroblastoma with a Focus on Immune Cell Infiltration and Diagnostic Potential of VGF.

Objective: This study aims to identify differentially expressed genes (DEGs) in neuroblastoma (NB) through comprehensive bioinformatics analysis and machine learning techniques. We seek to elucidate these DEGs' biological functions and associated signaling pathways. Furthermore, our objective extends to predicting upstream microRNAs (miRNAs) and relevant transcription factors of pivotal genes, with the ultimate goal of guiding clinical diagnostics and informing future treatment strategies for Neuroblastoma. Methods: In this study, we sourced datasets GSE49710 and TARGET from the GEO and UCSC-XENA databases, respectively. Differentially expressed genes (DEGs) were identified using the R language "limma" package. Subsequent Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses of these DEGs were conducted using the "clusterProfiler" package. We employed Weighted Gene Co-expression Network Analysis (WGCNA) to isolate the most significant modules associated with death and MYCN amplification, specifically MEpink and MEbrown modules. These modules were then cross-referenced with the DEGs for further GO and KEGG pathway analyses. LASSO regression analysis, facilitated by the "glmnet" package, was utilized to pinpoint three hub genes. We performed differential analysis on these genes and constructed Receiver Operating Characteristic (ROC) curves for disease diagnosis purposes. Immune infiltration analysis was conducted using the "GSVA" package's ssGSEA function. Additionally, single-gene Gene Set Enrichment Analysis (GSEA) on the hub gene was carried out based on Reactome and KEGG databases. Upstream miRNA and transcription factors associated with the hub gene were predicted using RegNetwork, with visual representations created in Cytoscape. Furthermore, to validate the three identified markers in neuroblastoma tissues, quantitative Real-Time Polymerase Chain Reaction (qRT-PCR) analysis was conducted. Results: We identified 483 differentially expressed genes (DEGs) in neuroblastoma. These genes predominantly function in protein translation, membrane composition, and RNA transcription regulation, and are implicated in multiple signaling pathways relevant to neurodegenerative diseases. Utilizing LASSO regression analysis, we pinpointed three hub genes: VGF, DGKD, and C19orf52. The Receiver Operating Characteristic (ROC) curve analysis yielded Area Under Curve (AUC) values of 0.751 and 0.722 for VGF, 0.79 and 0.656 for DGKD, and 0.8 and 0.753 for C19orf52, respectively. Our immune infiltration analysis revealed significant correlations among monocytes, follicular helper T cells, and CD4+ T cells. Notably, in the death group, we observed heightened infiltration levels of activated CD4+ T cells, macrophages, and Th2 cells. C19orf52 exhibited a close association with the infiltration of monocytes, CD4+ T cells, and Th2 cells, with P-values less than 0.05. Furthermore, qRT-PCR analysis corroborated the upregulation of VGF in neuroblastoma tissues, further validating our findings. Conclusion: The hub genes (VGF, DGKD, and C19orf52) of neuroblastoma are screened. VGF, one of the hub genes, may have a high diagnostic value and is involved in the immune cell infiltration in neuroblastoma tissue, which may be used as a biomarker for the diagnosis of neuroblastoma and provides a new direction for clinical prognosis prediction and management improvement.

Risk factors and predictive model for nosocomial infections by extensively drug-resistant Acinetobacter baumannii.

Background: Extensively drug-resistant Acinetobacter baumannii (XDRAB) has become a significant pathogen in hospital environments, particularly in intensive care units (ICUs). XDRAB's resistance to conventional antimicrobial treatments and ability to survive on various surfaces pose a substantial threat to patient health, often resulting in severe infections such as ventilator-associated pneumonia (VAP) and bloodstream infections (BSI). Methods: We retrospectively analyzed clinical data from 559 patients with XDRAB infections admitted to Jinhua Central Hospital between January 2021 and December 2023. Patients were randomly divided into a training set (391 cases) and a testing set (168 cases). Variables were selected using Lasso regression and logistic regression analysis, and a predictive model was constructed and validated internally and externally. Model performance and clinical utility were evaluated using the Hosmer-Lemeshow test, C-index, ROC curve, decision curve analysis (DCA), and clinical impact curve (CIC). Results: Lasso regression analysis was used to screen 35 variables, selecting features through 10-fold cross-validation. We chose lambda.1se=0.03450 (log(lambda.1se)=-3.367), including 10 non-zero coefficient features. These features were then included in a multivariate logistic regression analysis, identifying 8 independent risk factors for XDRAB infection: ICU stay of 1-7 days (OR=3.970, 95%CI=1.586-9.937), ICU stay >7 days (OR=12.316, 95%CI=5.661-26.793), hypoproteinemia (OR=3.249, 95%CI=1.679-6.291), glucocorticoid use (OR=2.371, 95%CI=1.231-4.564), urinary catheterization (OR=2.148, 95%CI=1.120-4.120), mechanical ventilation (OR=2.737, 95%CI=1.367-5.482), diabetes mellitus (OR=2.435, 95%CI=1.050-5.646), carbapenem use (OR=6.649, 95%CI=2.321-19.048), and ß-lactamase inhibitor use (OR=4.146, 95%CI=2.145-8.014). These 8 factors were used to construct a predictive model visualized through a nomogram. The model validation showed a C-index of 0.932 for the training set and 0.929 for the testing set, with a Hosmer-Lemeshow test p-value of 0.47, indicating good calibration. Furthermore, the DCA curve demonstrated good clinical decision-making performance, and the CIC curve confirmed the model's reliable clinical impact. Conclusion: Regression analysis identified ICU stay duration, hypoproteinemia, glucocorticoid use, urinary catheterization, mechanical ventilation, diabetes mellitus, carbapenem use, and ß-lactamase inhibitor use as independent risk factors for XDRAB infection. The corresponding predictive model demonstrated high accuracy and stability.

Integrated machine learning and Mendelian randomization reveal PALMD as a prognostic biomarker for nonspecific orbital inflammation.

BACKGROUND: Nonspecific Orbital Inflammation (NSOI) remains a perplexing enigma among proliferative inflammatory disorders. Its etiology is idiopathic, characterized by distinctive and polymorphous lymphoid infiltration within the orbital region. Preliminary investigations suggest that PALMD localizes within the cytosol, potentially playing a crucial role in cellular processes, including plasma membrane dynamics and myogenic differentiation. The potential of PALMD as a biomarker for NSOI warrants meticulous exploration. METHODS: PALMD was identified through the intersection analysis of common DEGs from datasets GSE58331 and GSE105149 from the GEO database, alongside immune-related gene lists from the ImmPort database, using Lasso regression and SVM-RFE analysis. GSEA and GSVA were conducted with gene sets co-expressed with PALMD. To further investigate the correlation between PALMD and immune-related biological processes, the CIBERSORT algorithm and ESTIMATE method were employed to evaluate immune microenvironment characteristics of each sample. The expression levels of PALMD were subsequently validated using GSE105149. RESULTS: Among the 314 DEGs identified, several showed significant differences. Lasso and SVM-RFE algorithms pinpointed 15 hub genes. Functional analysis of PALMD emphasized its involvement in cell-cell adhesion, leukocyte migration, and leukocyte-mediated immunity. Enrichment analysis revealed that gene sets positively correlated with PALMD were enriched in immune-related pathways. Immune infiltration analysis indicated that resting dendritic cells, resting mast cells, activated NK cells, and plasma cells positively associate with PALMD expression. Conversely, naive B cells, activated dendritic cells, M0 and M1 macrophages, activated mast cells, activated CD4 memory T cells, and naive CD4 T cells showed a negative correlation with PALMD expression. PALMD demonstrated significant diagnostic potential in differentiating NSOI. CONCLUSIONS: This study identifies PALMD as a potential biomarker linked to NSOI, providing insights into its pathogenesis and offering new avenues for tracking disease progression.

A Machine Learning Model for Predicting the Propagation Rate Coefficient in Free-Radical Polymerization.

The propagation rate coefficient (kp) is one of the most crucial kinetic parameters in free-radical polymerization (FRP) as it directly governs the rate of polymerization and the resulting molecular weight distribution. The kp in FRP can typically be obtained through experimental measurements or quantum chemical calculations, both of which can be time consuming and resource intensive. Herein, we developed a machine learning model based solely on the structural features of monomers involved in FRP, utilizing molecular embedding and a Lasso regression algorithm to predict kp more efficiently and accurately. The result shows that the model achieves a mean absolute percentage error (MAPE) of only 5.49% in the predictions for four new monomers, which indicates that the model exhibits strong generalization capabilities and provides reliable and robust predictions. In addition, this model can accurately predict the influence of the ester side chain length of (meth)acrylates on kp, aligning well with established scientific knowledge. This approach offers a straightforward and practical model for other researchers to rapidly obtain accurate kp values by employing monomer structural information. The model is sufficiently general to apply to a wide range of (meth)acrylate and butadiene FRP monomers, thereby supporting kinetic modeling of polymerization reactions.

Discovery of key biomarkers in tourette syndrome by network pharmacology.

Background: Yangxue Xifeng Decoction (YXD) has been utilized in clinical settings for the treatment of Tourette Syndrome (TS). However, the action mechanism of YXD needs further research. Methods: The ingredients and targets of YXD were identified via database searches and then constructed an active ingredient-target network using Cytoscape. Pathway enrichment analysis was performed via Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG). The core genes were determined by LASSO regression and SVM algorithm. Additionally, we analyzed the immune infiltration. The signaling pathways associated with core genes were investigated through KEGG and GO. We predicted the transcription factors using "RcisTarge". Results: 127 active ingredients of YXD and 255 targets were obtained. TNF and the IL-17 signaling pathway were the main pathways. OPRM1 and VIM were screened out as core genes, which were associated with the immune infiltration. The signaling pathways involved in OPRM1 and VIM were enriched. Furthermore, remarkable correlation was found between OPRM1 and VIM levels and other TS-related genes such as MAPT and MAPT. Conclusion: OPRM1 and MAPT, and the signaling pathways are associated with TS. YXD exerts its therapeutic TS through multi-component and multi-targets including immune infiltration.

A two-step framework integrating lasso and Relaxed Lasso for resolving multidimensional collinearity in Chinese baijiu aging research.

The aging process is crucial for Chinese Baijiu production, significantly enhancing the spirit's flavor, aroma and quality. However, aging involves a complex interplay of numerous compounds, and the extensive duration required for aging leads to a scarcity of samples available for scientific research. These limitations pose a challenge in analyzing high-dimensional data with collinearity, complicating the understanding of the intricate chemical processes at play. In this article, a two-step framework was proposed that integrated Relaxed Lasso regression models with Lasso-selected predictors to address this issue. Baijiu samples subjected to various aging conditions were analyzed using direct GC-MS and HS-GC-MS, and the obtained data was processed by this approach. The results demonstrate significantly superior performance compared to other methods, including PLSR and Gradient Boosting. Analyses were also performed on a previously documented dataset, yielding enhanced results and underscoring the method's advantage in processing high dimensional data with multicollinearity. Moreover, this method proved effective in screening of potential indicative compounds, highlighting its utility in Baijiu aging research.

Construction and validation of nomogram to predict surgical site infection after hysterectomy: a retrospective study.

This study aimed to develop a predictive tool for surgical site infections (SSI) following hysterectomy and propose strategies for their prevention and control. We conducted a retrospective analysis at a tertiary maternity and child specialist hospital in Zhejiang Province, focusing on patients who underwent hysterectomy between January 2018 and December 2023 for gynecological malignancies or benign reproductive system diseases resistant to medical treatment. Risk factors associated with surgical site infections (SSI) following hysterectomy were identified using LASSO regression analysis on data from 2018 to 2022 as the training set. Independent risk factors were then used to develop a nomogram. The model was validated using data from 2023 as the validation set. Model performance was assessed using the area under the receiver operating characteristic curve (ROC), while calibration curves were employed to gauge model accuracy. Furthermore, clinical utility was evaluated through clinical decision curve analysis (DCA) and clinical impact curve analysis (CIC), providing insights into the practical application of the nomogram. Multivariate analysis identified six independent risk factors associated with SSI development after hysterectomy: BMI ≥ 24 kg/m2 (OR: 2.58; 95% CI 1.14-6.19; P < 0.05), hypoproteinaemia diagnosis (OR: 4.99; 95% CI 1.95-13.02; P < 0.05), postoperative antibiotic use for ≥ 3 days (OR: 49.53; 95% CI 9.73-91.01; P < 0.05), history of previous abdominal surgery (OR: 7.46; 95% CI 2.93-20.01; P < 0.05), hospital stay ≥ 10 days (OR: 9.67; 95% CI 2.06-76.46; P < 0.05), and malignant pathological type (OR: 4.62; 95% CI 1.78-12.76; P < 0.05). A nomogram model was constructed using these variables. ROC and calibration curves demonstrated good model calibration and discrimination in both training and validation sets. Analysis with DCA and CIC confirmed the clinical utility of the nomogram. Personalized nomogram mapping for SSI after hysterectomy enables early identification of high-risk patients, facilitating timely interventions to reduce SSI incidence post-surgery.

Risk factors and prediction model for osteonecrosis of the femoral head in female systemic lupus erythematosus.

Background: Osteonecrosis of the femoral head (ONFH) is a severe complication of systemic lupus erythematosus (SLE) and occurs more frequently in SLE patients than in other autoimmune diseases, which can influence patients' life quality. The objective of this research was to analyze risk factors for the occurrence of ONFH in female SLE patients, construct and validate a risk nomogram model. Methods: Clinical records of SLE patients who fulfilled the 1997 American College of Rheumatology SLE classification criteria were retrospectively analyzed. The Least absolute shrinkage and selection operator (LASSO) regression and multivariate logistic regression analysis were used to summarize the independent risk factors of ONFH in female SLE patients, which were used to develop a nomogram. The predictive performance of the nomogram was assessed using the receiver characteristic (ROC) curve, calibration curves and decision curve analysis (DCA). Results: 793 female SLE patients were ultimately included in this study, of which 87 patients (10.9%) developed ONFH. Ten independent risk factors including disease duration, respiratory involvement, menstrual abnormalities, Sjögren's syndrome, osteoporosis, anti-RNP, mycophenolate mofetil, cyclophosphamide, biologics, and the largest daily glucocorticoid (GC) were identified to construct the nomogram. The area under the ROC curve of the nomogram model was 0.826 (95% CI: 0.780-0.872) and its calibration for forecasting the occurrence of ONFH was good (χ2 = 5.589, P = 0.693). DCA showed that the use of nomogram prediction model had certain application in clinical practice when the threshold was 0.05 to 0.95. In subgroup analysis, we found that the risk of ONFH was significantly increased in age at SLE onset of ≤ 50 years old, largest daily GC dose of ≥50 mg and the therapy of GC combined with immunosuppressant patients with menstrual abnormalities. Conclusion: Menstrual abnormalities were the first time reported for the risk factors of ONFH in female SLE patients, which remind that clinicians should pay more attention on female SLE patients with menstrual abnormalities and take early interventions to prevent or slow the progression of ONFH. Besides, the nomogram prediction model could provide an insightful and applicable tool for physicians to predict the risk of ONFH.

A nomogram for predicting the risk of temporomandibular disorders in university students.

OBJECTIVES: Temporomandibular disorders (TMDs) have a relatively high prevalence among university students. This study aimed to identify independent risk factors for TMD in university students and develop an effective risk prediction model. METHODS: This study included 1,122 university students from four universities in Changchun City, Jilin Province, as subjects. Predictive factors were screened by using the least absolute shrinkage and selection operator (LASSO) regression and the machine learning Boruta algorithm in the training cohort. A multifactorial logistic regression analysis was used to construct a TMD risk prediction model. Internal validation of the model was conducted via bootstrap resampling, and an external validation cohort comprised 205 university students undergoing oral examinations at the Stomatological Hospital of Jilin University. RESULTS: The prevalence of TMD among university students was 44.30%. Ten predictive factors were included in the model, comprising gender, facial cold stimulation, unilateral chewing, biting hard or resilient foods, clenching teeth, grinding teeth, excessive mouth opening, malocclusion, stress, and anxiety. The model demonstrated good predictive ability with area under the receiver operating characteristic curve (AUC) values of 0.853, 0.838, and 0.821 in the training cohort, internal validation cohort, and external validation cohort, respectively. The calibration curves demonstrated that the predicted results were consistent with the actual results, and the decision curve analysis (DCA) indicated the model's high clinical utility. CONCLUSIONS: An online nomogram of TMD in university students with good predictive performance was constructed, which can effectively predict the risk of TMD in university students. The model provides a useful tool for the early identification and treatment of TMDs in university students, helping clinicians to predict the probability of TMDs in each patient, thus providing more personalized and accurate treatment decisions for patients.

Fracture risk prediction in diabetes patients based on Lasso feature selection and Machine Learning.

Fracture risk among individuals with diabetes poses significant clinical challenges due to the multifaceted relationship between diabetes and bone health. Diabetes not only affects bone density but also alters bone quality and structure, thereby increases the susceptibility to fractures. Given the rising prevalence of diabetes worldwide and its associated complications, accurate prediction of fracture risk in diabetic individuals has emerged as a pressing clinical need. This study aims to investigate the factors influencing fracture risk among diabetic patients. We propose a framework that combines Lasso feature selection with eight classification algorithms. Initially, Lasso regression is employed to select 24 significant features. Subsequently, we utilize grid search and 5-fold cross-validation to train and tune the selected classification algorithms, including KNN, Naive Bayes, Decision Tree, Random Forest, AdaBoost, XGBoost, Multi-layer Perceptron (MLP), and Support Vector Machine (SVM). Among models trained using these important features, Random Forest exhibits the highest performance with a predictive accuracy of 93.87%. Comparative analysis across all features, important features, and remaining features demonstrate the crucial role of features selected by Lasso regression in predicting fracture risk among diabetic patients. Besides, by using a feature importance ranking algorithm, we find several features that hold significant reference values for predicting early bone fracture risk in diabetic individuals.

Diagnostic value of multimodal ultrasound for breast cancer and prediction of sentinel lymph node metastases.

Background: Sentinel lymph node metastasis (SLNM) is a critical factor in the prognosis and treatment planning for breast cancer (BC), as it indicates the potential spread of cancer to other parts of the body. The accurate prediction and diagnosis of SLNM are essential for improving clinical outcomes and guiding treatment decisions. Objective: This study aimed to construct a Lasso regression model by integrating multimodal ultrasound (US) techniques, including US, shear wave elastography (SWE), and contrast-enhanced ultrasound (CEUS), to improve the predictive accuracy of sentinel lymph node metastasis in breast cancer and provide more precise guidance for clinical treatment. Results: A total of 253 eligible samples were screened, of which 148 were group benign and 105 were group malignant. There were statistically significant differences (p < 0.05) between group malignant patients in terms of age, palpable mass, body mass index, distance to nipple, maximum diameter, blood flow, microcalcification, 2D border, 2D morphology, and 2D uniformity and group benign. The Lasso regression model was useful in the diagnosis of benign and malignant nodules with an AUC of 0.966 and in diagnosing SLNM with an AUC of 0.832. Conclusion: In this study, we successfully constructed and validated a Lasso regression model based on the multimodal ultrasound technique for predicting whether SLNM occurs in BCs, showing high diagnostic accuracy.

Machine learning and multiple linear regression models can predict ascorbic acid and polyphenol contents, and antioxidant activity in strawberries.

BACKGROUND: Strawberry is a rich source of antioxidants, including ascorbic acid (ASA) and polyphenols, which have numerous health benefits. Antioxidant content and activity are often determined manually using laboratory equipment, which is destructive and time-consuming. This study constructs a prediction model for antioxidant compounds utilizing machine learning (ML) and multiple linear regression based on environmental, plant growth and agronomic fruit quality-related parameters as well as antioxidant levels. These were studied in three farms at two-week intervals during two years of cultivation. RESULTS: During the ML model screening, artificial neural network (ANN)-boosted models displayed a moderate coefficient of determination (R2) at 0.68-0.78 and relative root mean square error (RRMSE) at 3.8-4.8% in polyphenols and total ASA levels, as well as a high R2 of 0.96 and low RRMSE at <3.0% in antioxidant activity. Additionally, we developed variable selection models regarding the antioxidant activity, and variables two and five (environmental parameters and leaf length, respectively) with high accuracy were selected. The linear regression analysis between the actual and predicted data of antioxidants in the ANN-boosted models revealed high fitness with all parameters in almost all training, validation and test sets. Furthermore, environmental parameters are essential in developing such reliable models. CONCLUSION: We conclude that ANN-boosted, stepwise and double-Lasso regression models can predict antioxidant compounds with enhanced accuracy, and the relevant parameters can be easily acquired on-site without the need for any specific equipment. © 2024 Society of Chemical Industry.

Detection of Alcoholic EEG signal using LASSO regression with metaheuristics algorithms based LSTM and enhanced artificial neural network classification algorithms.

The world has a higher count of death rates as a result of Alcohol consumption. Identification is possible because Alcoholic EEG waves have a certain behavior that is totally different compared to the non-alcoholic individual. The available approaches take longer to provide the feedback because they analyze the data manually. For this reason, in the present paper we propose a novel approach applied to detect alcoholic EEG signals automatically by using deep learning methods. Our strategy has advantages as far as fast detection is concerned; hence people can help immediately when there is a need. The potential for a significant decrease in deaths from alcohol poisoning and improvement to public health is presented by this advancement. In order to create clusters and classify the alcoholic EEG signals, this research uses a cascaded process. To begin with, an initial clustering and feature extraction is done by LASSO regression. After that, a variety of meta-heuristics algorithms like Particle Swarm Optimization (PSO), Binary Coding Harmony Search (BCHS) as well as Binary Dragonfly Algorithm (BDA) are employed for feature minimization. When this method is used, normal and alcoholic EEG signals may be differentiated using non-linear features. PSO, BCHS, and BDA features allow for estimation of statistical parameters through t-test, Friedman statistic test, Mann-Whitney U test, and Z-Score with corresponding p-values for alcoholic EEG signals. Lastly, classification is done by the use of support vector machines (SVM) (including linear, polynomial, and Gaussian kernels), random forests, artificial neural networks (ANN), enhanced artificial neural networks (EANN), and LSTM models. Results showed that LASSO regression with BDA-based EANN proposed classifier have a classification accuracy of 99.59%, indicating that our method is highly accurate at classifying alcoholic EEG signals.

Prognostic nomogram of overall survival for radiation therapy in hepatocellular carcinoma: a population study based on the SEER database and an external cohort.

Purpose: Radiotherapy (RT) plays an important role in the treatment of hepatocellular carcinoma (HCC). To screen patients who benefit most from RT, a nomogram for survival prediction of RT based on a large sample of patients with HCC was created and validated. Methods: A total of 2,252 cases collected from the Surveillance, Epidemiology, and End Results (SEER) database were separated into a training or an internal validation cohort in a 7:3 ratio (n = 1,565:650). An external validation cohort of cases from our institute was obtained (n = 403). LASSO regression and Cox analyses were adopted to develop a nomogram for survival prediction. The decision curve analysis (DCA), calibration curve, and time-dependent receiver operating characteristic curves (TROCs) demonstrated the reliability of the predictive model. Results: For patients with HCC who received RT, the analyses revealed that the independent survival prediction factors were T stage {T2 vs. T1, hazard ratio (HR) =1.452 [95% CI, 1.195-1.765], p < 0.001; T3 vs. T1, HR = 1.469 [95% CI, 1.168-1.846], p < 0.001; T4 vs. T1, HR = 1.291 [95% CI, 0.951-1.754], p = 0.101}, N stage (HR = 1.555 [95% CI, 1.338-1.805], p < 0.001), M stage (HR = 3.007 [95% CI, 2.645-3.418], p < 0.001), max tumor size (>2 and ≤5 vs. ≤2 cm, HR = 1.273 [95% CI, 0.992-1.633], p = 0.057; >5 and ≤10 vs. ≤2 cm, HR = 1.625 [95% CI, 1.246-2.118], p < 0.001; >10 vs. ≤2 cm, HR = 1.784 [95% CI, 1.335-2.385], p < 0.001), major vascular invasion (MVI) (HR = 1.454 [95% CI, 1.028-2.057], p = 0.034), alpha fetoprotein (AFP) (HR = 1.573 [95% CI, 1.315-1.882], p < 0.001), and chemotherapy (HR = 0.511 [95% CI, 0.454-0.576], p < 0.001). A nomogram constructed with these prognostic factors demonstrated outstanding predictive accuracy. The area under the curve (AUC) in the training cohort for predicting overall survival (OS) at 6, 12, 18, and 24 months was 0.824 (95% CI, 0.803-0.846), 0.824 (95% CI, 0.802-0.845), 0.816 (95% CI, 0.792-0.840), and 0.820 (95% CI, 0.794-0.846), respectively. The AUCs were similar in the other two cohorts. The DCA and calibration curve demonstrated the reliability of the predictive model. Conclusion: For patients who have been treated with RT, a nomogram constructed with T stage, N stage, M stage, tumor size, MVI, AFP, and chemotherapy has good survival prediction ability.

Development and validation of a nomogram for predicting advanced liver fibrosis in patients with chronic hepatitis B.

Background: The progression of chronic hepatitis B (CHB) to liver fibrosis and even cirrhosis is often unknown to patients, but noninvasive markers capable of effectively identifying advanced liver fibrosis remains absent. Objective: Based on the results of liver biopsy, we aimed to construct a new nomogram to validate the stage of liver fibrosis in CHB patients by the basic information of CHB patients and routine laboratory tests. Methods: Patients with CHB diagnosed for the first time in the First Affiliated Hospital of Anhui Medical University from 2010 to 2018 were selected, and their basic information, laboratory tests and liver biopsy information were collected. Eventually, 974 patients were enrolled in the study, while all patients were randomized into a training cohort (n = 732) and an internal validation cohort (n = 242) according to a 3:1 ratio. In the training cohort, least absolute shrinkage and selection operator (Lasso) regression were used for predictor variable screening, and binary logistic regression analysis was used to build the diagnostic model, which was ultimately presented as a nomogram. The predictive accuracy of the nomograms was analyzed by running operating characteristic curve (ROC) to calculate area under curve (AUC), and the calibration was evaluated. Decision curve analysis (DCA) was used to determine patient benefit. In addition, we validated the built models with internal as well as external cohort (n = 771), respectively. Results: Ultimately, the training cohort, the internal validation cohort, and the external validation cohort contained sample sizes of 188, 53, and 149, respectively, for advanced liver fibrosis. Gender, albumin (Alb), globulin (Glb), platelets (PLT), alkaline phosphatase (AKP), glutamyl transpeptidase (GGT), and prothrombin time (PT) were screened as independent predictors. Compared with the aminotransferase-to-platelet ratio index (APRI), fibrosis-4 index (FIB-4), and King's score, the model in the training cohort (AUC = 0.834, 95% CI 0.800-0.868, p < 0.05) and internal validation cohort (AUC = 0.804, 95% CI 0.742-0.866, p < 0.05) showed the best discrimination and the best predictive performance. In addition, DCA showed that the clinical benefit of the nomogram was superior to the APRI, FIB-4 and King's scores in all cohorts. Conclusion: This study constructed a validated nomogram model with predictors screened from clinical variables which could be easily used for the diagnosis of advanced liver fibrosis in CHB patients.