Predicting osteoporotic fractures post-vertebroplasty: a machine learning approach with a web-based calculator.

PURPOSE: The aim of this study was to develop and validate a machine learning (ML) model for predicting the risk of new osteoporotic vertebral compression fracture (OVCF) in patients who underwent percutaneous vertebroplasty (PVP) and to create a user-friendly web-based calculator for clinical use. METHODS: A retrospective analysis of patients undergoing percutaneous vertebroplasty: A retrospective analysis of patients treated with PVP between June 2016 and June 2018 at Liuzhou People's Hospital was performed. The independent variables of the model were screened using Boruta and modelled using 9 algorithms. Model performance was assessed using the area under the receiver operating characteristic curve (ROC_AUC), and clinical utility was assessed by clinical decision curve analysis (DCA). The best models were analysed for interpretability using SHapley Additive exPlanations (SHAP) and the models were deployed visually using a web calculator. RESULTS: Training and test groups were split using time. The SVM model performed best in both the training group tenfold cross-validation (CV) and validation group AUC, with an AUC of 0.77. DCA showed that the model was beneficial to patients in both the training and test sets. A network calculator developed based on the SHAP-based SVM model can be used for clinical risk assessment ( https://nicolazhang.shinyapps.io/refracture_shap/ ). CONCLUSIONS: The SVM-based ML model was effective in predicting the risk of new-onset OVCF after PVP, and the network calculator provides a practical tool for clinical decision-making. This study contributes to personalised care in spinal surgery.

Interpretable machine learning-based clinical prediction model for predicting lymph node metastasis in patients with intrahepatic cholangiocarcinoma.

OBJECTIVE: Prediction of lymph node metastasis (LNM) for intrahepatic cholangiocarcinoma (ICC) is critical for the treatment regimen and prognosis. We aim to develop and validate machine learning (ML)-based predictive models for LNM in patients with ICC. METHODS: A total of 345 patients with clinicopathological characteristics confirmed ICC from Jan 2007 to Jan 2019 were enrolled. The predictors of LNM were identified by the least absolute shrinkage and selection operator (LASSO) and logistic analysis. The selected variables were used for developing prediction models for LNM by six ML algorithms, including Logistic regression (LR), Gradient boosting machine (GBM), Extreme gradient boosting (XGB), Random Forest (RF), Decision tree (DT), Multilayer perceptron (MLP). We applied 10-fold cross validation as internal validation and calculated the average of the areas under the receiver operating characteristic (ROC) curve to measure the performance of all models. A feature selection approach was applied to identify importance of predictors in each model. The heat map was used to investigate the correlation of features. Finally, we established a web calculator using the best-performing model. RESULTS: In multivariate logistic regression analysis, factors including alcoholic liver disease (ALD), smoking, boundary, diameter, and white blood cell (WBC) were identified as independent predictors for LNM in patients with ICC. In internal validation, the average values of AUC of six models ranged from 0.820 to 0.908. The XGB model was identified as the best model, the average AUC was 0.908. Finally, we established a web calculator by XGB model, which was useful for clinicians to calculate the likelihood of LNM. CONCLUSION: The proposed ML-based predicted models had a good performance to predict LNM of patients with ICC. XGB performed best. A web calculator based on the ML algorithm showed promise in assisting clinicians to predict LNM and developed individualized medical plans.

Photo-modulated activation of organic bases enabling microencapsulation and on-demand reactivity.

A method is developed for facile encapsulation of reactive organic bases with potential application for autonomous damage detection and self-healing polymers. Highly reactive chemicals such as bases and acids are challenging to encapsulate by traditional oil-water emulsion techniques due to unfavorable physical and chemical interactions. In this work, reactivity of the bases is temporarily masked with photo-removable protecting groups, and the resulting inactive payloads are encapsulated via an in situ emulsion-templated interfacial polymerization method. The encapsulated payloads are then activated to restore the organic bases via photo irradiation, either before or after being released from the core-shell carriers. The efficacy of the photo-activated capsules is demonstrated by a damage-triggered, pH-induced color change in polymeric coatings and by recovery of adhesive strength of a damaged interface. Given the wide range of potential photo-deprotection chemistries, this encapsulation scheme provides a simple but powerful method for storage and targeted delivery of a broad variety of reactive chemicals, promoting design of diverse autonomous functionalities in polymeric materials.

Nanoparticle-Empowered Core-Shell Microcapsules: From Architecture Design to Fabrication and Functions.

Compartmentalization is a powerful concept to integrate multiscale components with diverse functionalities into miniature architectures. Inspired by evolution-optimized cell compartments, synthetic core-shell capsules enable storage of actives and on-demand delivery of programmed functions, driving scientific progress across various fields including adaptive materials, sustainable electronics, soft robotics, and precision medicine. To simultaneously maximize structural stability and environmental sensitivity, which are the two most critical characteristics dictating performance, diverse nanoparticles are incorporated into microcapsules with a dense shell and a liquid core. Recent studies have revealed that these nano-additives not only enhance the intrinsic properties of capsules including mechanical robustness, optical behaviors, and thermal conductivity, but also empower dynamic features such as triggered release, deformable structures, and fueled mobility. In this review, the physicochemical principles that govern nanoparticle assembly during microencapsulation are examined in detail and the architecture-controlled functionalities are outlined. Through the analysis of how each primary method implants nanoparticles into microcapsules, their distinct spatial organizations within the core-shell structures are highlighted. Following a detailed discussion of the specialized functions enabled by specific nanoparticles, the vision of the required fundamental insights and experimental studies for this class of microcarriers to fulfill its potential are sketched.

DNA methylome analysis reveals novel insights into active hypomethylated regulatory mechanisms of temperature-dependent flower opening in Osmanthus fragrans.

Short-term ambient low temperature (ALT) stimulation is necessary for Osmanthus fragrans to facilitate continued flower opening after floral bud development reaches maturity. DNA methylation, a vital epigenetic modification, regulates various biological processes in response to temperature fluctuations. However, its role in temperature-driven flower opening remains elusive. In this study, we identified the pivotal timeframe during which O. fragrans promptly detected temperature cues. Using whole-genome bisulfite sequencing, we explored global DNA hypomethylation during this phase, with the most significant changes occurring in CHH sequence contexts. Auxin transport inhibitor (TIBA) application revealed that ALT-induced endogenous auxin accumulation promoted peduncle elongation. In our mRNA-seq analysis, we discovered that the differentially expressed genes (DEGs) with hypo-differentially methylated regions (hypo-DMRs) were mainly enriched in auxin and temperature response, RNA processing, and carbohydrate and lipid metabolism. Transcripts of three DNA demethylase genes (OfROS1a, OfDML3, OfDME) showed upregulation. Furthermore, all DNA methylase genes, except OfCMT2b, also displayed increased expression, specifically with two of them, OfCMT3a and OfCMT1, being associated with hypo-DMRs. Promoter assays showed that OfROS1a, with promoters containing low-temperature- and auxin-responsive elements, were activated by ALT and exogenous IAA at low concentrations but inhibited at high concentrations. Overexpression of OfROS1 reduced endogenous auxin levels but enhanced the expression of genes related to auxin response and spliceosome in petunia. Furthermore, OfROS1 promoted sucrose synthesis in petunia corollas. Our data characterized the rapid response of active DNA hypomethylation to ALT and suggested a possible epiregulation of temperature-dependent flower opening in O. fragrans. This study revealed the pivotal role of DNA hypomethylation in O. fragrans during the ALT-responsive phase before flower opening, involving dynamic DNA demethylation, auxin signaling modulation, and a potential feedback loop between hypomethylation and methylation.

Unveiling research trends in the prognosis of osteosarcoma: A bibliometric analysis from 2000 to 2022.

Background: Osteosarcoma (OSA) is the most prevalent form of malignant bone tumor in children and adolescents, producing osteoid and immature bone. Numerous high quality studies have been published in the OSA field, however, no bibliometric study related to this area has been reported thus far. Therefore, the present study retrieved the published data from 2000 to 2022 to reveal the dynamics, development trends, hotspots and future directions of the OSA. Methods: Publications regard to osteogenic sarcoma and prognosis were searched in the core collection on Web of Science database. The retrieved publications were analyzed by publication years, journals, categories, countries, citations, institutions, authors, keywords and clusters using the two widely available bibliometric visualization tools, VOS viewer (Version 1.6.16), Citespace (Version 6.2. R1). Results: A total of 6260 publications related to the current topic were retrieved and analyzed, revealing exponential increase in the number of publications with an improvement in the citations on the OSA over time, in which China and the USA are the most productive nations. Shanghai Jiao Tong University, University of Texas System and Harvard University are prolific institutions, having highest collaboration network. Oncology Letters and Journal of Clinical Oncology are the most productive and the most cited journals respectively. The Wang Y is a prominent author and articles published by Bacci G had the highest number of citations indicating their significant impact in the field. According to keywords analysis, osteosarcoma, expression and metastasis were the most apparent keywords whereas the current research hotspots are biomarker, tumor microenvironment, immunotherapy and DNA methylation. Conclusion: Our findings offer valuable information for researchers to understand the current research status and the necessity of future research to mitigate the mortality of the OS patients.

Ensemble learning-assisted prediction of prolonged hospital length of stay after spine correction surgery: a multi-center cohort study.

PURPOSE: This research aimed to develop a machine learning model to predict the potential risk of prolonged length of stay in hospital before operation, which can be used to strengthen patient management. METHODS: Patients who underwent posterior spinal deformity surgery (PSDS) from eleven medical institutions in China between 2015 and 2022 were included. Detailed preoperative patient data, including demographics, medical history, comorbidities, preoperative laboratory results, and surgery details, were collected from their electronic medical records. The cohort was randomly divided into a training dataset and a validation dataset with a ratio of 70:30. Based on Boruta algorithm, nine different machine learning algorithms and a stack ensemble model were trained after hyperparameters tuning visualization and evaluated on the area under the receiver operating characteristic curve (AUROC), precision-recall curve, calibration, and decision curve analysis. Visualization of Shapley Additive exPlanations method finally contributed to explaining model prediction. RESULTS: Of the 162 included patients, the K Nearest Neighbors algorithm performed the best in the validation group compared with other machine learning models (yielding an AUROC of 0.8191 and PRAUC of 0.6175). The top five contributing variables were the preoperative hemoglobin, height, body mass index, age, and preoperative white blood cells. A web-based calculator was further developed to improve the predictive model's clinical operability. CONCLUSIONS: Our study established and validated a clinical predictive model for prolonged postoperative hospitalization duration in patients who underwent PSDS, which offered valuable prognostic information for preoperative planning and postoperative care for clinicians. Trial registration ClinicalTrials.gov identifier NCT05867732, retrospectively registered May 22, 2023, https://classic. CLINICALTRIALS: gov/ct2/show/NCT05867732 .

Machine learning predictors of risk of death within 7 days in patients with non-traumatic subarachnoid hemorrhage in the intensive care unit: A multicenter retrospective study.

Non-traumatic subarachnoid hemorrhage (SAH) is a critical neurosurgical emergency with a high mortality rate, imposing a significant burden on both society and families. Accurate prediction of the risk of death within 7 days in SAH patients can provide valuable information for clinicians, enabling them to make better-informed medical decisions. In this study, we developed six machine learning models using the MIMIC III database and data collected at our institution. These models include Logistic Regression (LR), AdaBoosting (AB), Multilayer Perceptron (MLP), Bagging (BAG), Gradient Boosting Machines (GBM), and Extreme Gradient Boosting (XGB). The primary objective was to identify predictors of death within 7 days in SAH patients admitted to intensive care units. We employed univariate and multivariate logistic regression as well as Pearson correlation analysis to screen the clinical variables of the patients. The initially screened variables were then incorporated into the machine learning models, and the performance of these models was evaluated. Furthermore, we compared the performance differences among the six models and found that the MLP model exhibited the highest performance with an AUC of 0.913. In this study, we conducted risk factor analysis using Shapley values to identify the factors associated with death within 7 days in patients with SAH. The risk factors we identified include Gcsmotor, bicarbonate, wbc, spo2, heartrate, age, nely, glucose, aniongap, GCS, rbc, sysbp, sodium, and gcseys. To provide clinicians with a useful tool for assessing the risk of death within 7 days in SAH patients, we developed a web calculator based on the MLP machine learning model.

Development and validation of a clinical prediction model for the risk of distal metastasis in intrahepatic cholangiocarcinoma: a real-world study.

BACKGROUND: Cholangiocarcinoma (CCA) is a highly malignant and easily metastatic bile duct tumor with poor prognosis. We aimed at studying the associated risk factors affecting distal metastasis of CCA and using nomogram to guide clinicians in predicting distal metastasis of CCA. METHODS: Based on inclusion and exclusion criteria, 345 patients with CCA were selected from the Fifth Medical Center of Chinese PLA General Hospital and were divided into distal metastases (N = 21) and non-distal metastases (N = 324). LASSO regression models were used to screen for relevant parameters and to compare basic clinical information between the two groups of patients. Risk factors for distal metastasis were identified based on the results of univariate and multivariate logistic regression analyses. The nomogram was established based on the results of multivariate logistic regression, and we drawn the corresponding correlation heat map. The predictive accuracy of the nomogram was evaluated by receiver operating characteristic (ROC) curves and calibration plots. The utility of the model in clinical applications was illustrated by applying decision curve analysis (DCA), and overall survival(OS) analysis was performed using the method of Kaplan-meier. RESULTS: This study identified 4 independent risk factors for distal metastasis of CCA, including CA199, cholesterol, hypertension and margin invasion, and developed the nomogram based on this. The result of validation showed that the model had significant accuracy for diagnosis with the area under ROC (AUC) of 0.882 (95% CI: 0.843-0.914). Calibration plots and DCA showed that the model had high clinical utility. CONCLUSIONS: This study established and validated a model of nomogram for predicting distal metastasis in patients with CCA. Based on this, it could guide clinicians to make better decisions and provide more accurate prognosis and treatment for patients with CCA.

Pneumonia detection based on RSNA dataset and anchor-free deep learning detector.

Pneumonia is a highly lethal disease, and research on its treatment and early screening tools has received extensive attention from researchers. Due to the maturity and cost reduction of chest X-ray technology, and with the development of artificial intelligence technology, pneumonia identification based on deep learning and chest X-ray has attracted attention from all over the world. Although the feature extraction capability of deep learning is strong, existing deep learning object detection frameworks are based on pre-defined anchors, which require a lot of tuning and experience to guarantee their excellent results in the face of new applications or data. To avoid the influence of anchor settings in pneumonia detection, this paper proposes an anchor-free object detection framework and RSNA dataset based on pneumonia detection. First, a data enhancement scheme is used to preprocess the chest X-ray images; second, an anchor-free object detection framework is used for pneumonia detection, which contains a feature pyramid, two-branch detection head, and focal loss. The average precision of 51.5 obtained by Intersection over Union (IoU) calculation shows that the pneumonia detection results obtained in this paper can surpass the existing classical object detection framework, providing an idea for future research and exploration.

Early-life antibiotic exposure promotes house dust mite-induced allergic airway inflammation by impacting gut microbiota and lung lipid metabolism.

Asthma is a chronic inflammatory respiratory disease. Early-life antibiotic exposure is a unique risk factor for the incidence and severity of asthma later in life. Perturbations in microbial-metabolite-immune interaction caused by antibiotics are closely associated with the pathogenesis of allergy and asthma. We investigated the effect of early intervention with common oral antibiotics on later asthma exacerbations and found that different antibiotic exposures can amplify different types of immune responses induced by HDM. Cefixime (CFX) promoted a biased type 2 inflammation, azithromycin (AZM) enhanced Th17 immune response, and cefuroxime axetil (CFA) induced eosinophils recruitment. Moreover, early-life antibiotic exposure can have short- and long-term effects on the abundance, composition, and diversity of the gut microbiota. In the model of CFX-promoted type 2 airway inflammation, fecal metabolomics indicated abnormal lipid metabolism and T cell response. Lipidomic also suggested allergic airway inflammation amplified by CFX is closely associated with abnormal lipid metabolism in lung tissues. Moreover, abnormalities in lipid metabolism-related genes (LMRGs) were found to have cellular heterogeneity be associated with asthma severity by bioinformatics analysis.

Co-doped RuO2 nanoparticles with enhanced catalytic activity and stability for the oxygen evolution reaction.

Efficient and durable electrocatalysts for the oxygen evolution reaction (OER) play an important role in the use of hydrogen energy. Rutile RuO2, despite being considered as an advanced electrocatalyst for the OER, performs poorly in stability due to its easy oxidative dissolution at very positive (oxidizing) potentials. Herein, we report a type of Co-doped RuO2 nanoparticle for boosting OER catalytic activity and stability in alkaline solutions. The replacement of Ru by Co atoms with a lower ionic valence and smaller electronegativity can promote the generation of O vacancies and increase the electron density around Ru, thus enhancing the adsorption of oxygen species and inhibiting the peroxidative dissolution of RuO2 during the OER process. It was found that Ru0.95Co0.05Oy exhibited excellent OER performance with overpotentials as low as 217 mV at 10 mA cm-2 and 290 mV at 100 mA cm-2 in 1 M KOH, as well as outstanding stability in continuous testing for 50 h at a current density of 100 mA cm-2, and nearly no significant degradation after the accelerated durability test of 2000 cycles.

Facile synthesis of Ag lattice doped mesoporous In2O3 nanocubes for high performance ethanol sensing.

Ag lattice doped In2O3 with a mesoporous structure was synthesized through a combination of hydrothermal and calcination methods. The structural and morphological characteristics were assessed using XRD, SEM, TEM, TGA, BET, and XPS analyses. Gas sensing measurements revealed that the 7.0 mol% Ag-doped In2O3 sensor displayed a response of 420 towards 100 ppm ethanol at 140 °C, which was 19 times higher than that of the pure In2O3 gas sensor. Density functional theory calculations indicated that Ag-doped In2O3 exhibited enhanced adsorption performance, higher adsorption energy, and electron transfer, resulting in higher sensitivity to ethanol. These findings were also supported by the electronic band structure, work function, and DOS analyses. These results indicated that the Ag doped mesoporous In2O3 has high potential for the preparation of high-performance ethanol sensors in practical applications.

MOF-derived S-doped NiCo2O4 hollow cubic nanocage for highly efficient electrocatalytic oxygen evolution.

Inducing the surface reconstruction of spinels is critical for improving the electrocatalytic oxygen evolution reaction (OER) activity. Herein, S-doped NiCo2O4 hollow cubic nanocage was synthesized by anion etching Metal-Organic Frameworks (MOFs) template and air annealing strategies. The hollow structure possesses a large specific surface area and pore size, facilitating active site exposure and mass transport. S2- doping regulates the electronic structure, reducing the oxidation potential of Ni sites during the OER process, thus promoting the surface reconstruction into γ-NiOOH active species. Meanwhile, S2- doping enhances conductivity, accelerating interfacial charge transfer. As a result, S-NiCo2O4-6 exhibits superior OER activity (262 mV overpotential @ 10 mA cm-2) and stability in 1.0 M KOH solution. Furthermore, 20 % Pt/C‖S-NiCo2O4-6 only needs 1.832 V to achieve 50 mA (the electrochemical active area is 4 cm2) in a homemade anion exchange membrane (AEM) electrolyzer. This work proposes a novel approach for preparing efficient anion-doped spinel-based OER electrocatalysts.

A clinical prediction model based on interpretable machine learning algorithms for prolonged hospital stay in acute ischemic stroke patients: a real-world study.

Objective: Acute ischemic stroke (AIS) brings an increasingly heavier economic burden nowadays. Prolonged length of stay (LOS) is a vital factor in healthcare expenditures. The aim of this study was to predict prolonged LOS in AIS patients based on an interpretable machine learning algorithm. Methods: We enrolled AIS patients in our hospital from August 2017 to July 2019, and divided them into the "prolonged LOS" group and the "no prolonged LOS" group. Prolonged LOS was defined as hospitalization for more than 7 days. The least absolute shrinkage and selection operator (LASSO) regression was applied to reduce the dimensionality of the data. We compared the predictive capacity of extended LOS in eight different machine learning algorithms. SHapley Additive exPlanations (SHAP) values were used to interpret the outcome, and the most optimal model was assessed by discrimination, calibration, and clinical utility. Results: Prolonged LOS developed in 149 (22.0%) of the 677 eligible patients. In eight machine learning algorithms, prolonged LOS was best predicted by the Gaussian naive Bayes (GNB) model, which had a striking area under the curve (AUC) of 0.878 ± 0.007 in the training set and 0.857 ± 0.039 in the validation set. The variables sorted by the gap values showed that the strongest predictors were pneumonia, dysphagia, thrombectomy, and stroke severity. High net benefits were observed at 0%-76% threshold probabilities, while good agreement was found between the observed and predicted probabilities. Conclusions: The model using the GNB algorithm proved excellent for predicting prolonged LOS in AIS patients. This simple model of prolonged hospitalization could help adjust policies and better utilize resources.

A machine learning-based model for clinical prediction of distal metastasis in chondrosarcoma: a multicenter, retrospective study.

Background: The occurrence of distant metastases (DM) limits the overall survival (OS) of patients with chondrosarcoma (CS). Early diagnosis and treatment of CS remains a great challenge in clinical practice. The aim of this study was to investigate metastatic factors and develop a risk stratification model for clinicians' decision-making. Methods: Six machine learning (ML) algorithms, including logistic regression (LR), plain Bayesian classifier (NBC), decision tree (DT), random forest (RF), gradient boosting machine (GBM) and extreme gradient boosting (XGBoost). A 10-fold cross-validation was performed for each model separately, multicenter data was used as external validation, and the best (highest AUC) model was selected to build the network calculator. Results: A total of 1,385 patients met the inclusion criteria, including 82 (5.9%) patients with metastatic CS. Multivariate logistic regression analysis showed that the risk of DM was significantly higher in patients with higher pathologic grades, T-stage, N-stage, and non-left primary lesions, as well as those who did not receive surgery and chemotherapy. The AUC of the six ML algorithms for predicting DM ranged from 0.911-0.985, with the extreme gradient enhancement algorithm (XGBoost) having the highest AUC. Therefore, we used the XGB model and uploaded the results to an online risk calculator for estimating DM risk. Conclusions: In this study, combined with adequate SEER case database and external validation with data from multicenter institutions in different geographic regions, we confirmed that CS, T, N, laterality, and grading of surgery and chemotherapy were independent risk factors for DM. Based on the easily available clinical risk factors, machine learning algorithms built the XGB model that predicts the best outcome for DM. An online risk calculator helps simplify the patient assessment process and provides decision guidance for precision medicine and long-term cancer surveillance, which contributes to the interpretability of the model.

Elucidation of the anti-colon cancer mechanism of Phellinus baumii polyphenol by an integrative approach of network pharmacology and experimental verification.

Colon cancer, a prevalent malignant tumor affecting the digestive system, presents a substantial risk to human health due to its high occurrence and mortality rates. Phellinus baumii polyphenol (PBP), a natural product derived from traditional Chinese medicine, has gained widespread popularity due to its low toxicity and minimal side effects, compared to radiation and chemotherapy. This study used an integrated approach of network pharmacology and experimental verification to elucidate the anti-colon cancer effects of PBP and its potential mechanisms. In network pharmacology, the identification of relevant targets involved a comprehensive search across multiple databases using keywords such as "active components of PBP" and "colon cancer". Venn diagram analysis was subsequently performed to ascertain the shared targets. To identify the key active components and core targets, we constructed a network of "Disease-Drug-Pathways-Targets" and a protein-protein interaction (PPI) network among the targets using Cytoscape 3.9.1. Furthermore, molecular docking was carried out to predict the binding affinity and conformation between the main active compounds (davallialactone and citrinin) of PBP and the core targets (TP53, STAT3, CASP3, CTNNB1, PARP1, MYC). To validate our findings, in vitro experiments were conducted. We verified that PBP exerted an anti-colon cancer effect on human colon cancer HCT116 cells by significantly inhibiting cell proliferation, promoting apoptosis and arresting the cell cycle in S phase by using Cell Counting Kit-8 (CCK-8) and flow cytometry. Finally, we determined the key regulatory proteins related to apoptosis and the cell cycle by western blot analysis, and proposed the potential mechanism by which PBP exerts an anti-colon cancer effect by inducing the caspase-dependent mitochondrial-mediated intrinsic apoptotic pathway and arresting the cell cycle in S phase in HCT116 cells. These results suggest that PBP possesses substantial potential for the treatment of colon cancer and may serve as a viable alternative therapeutic strategy in colon cancer treatment.

Development and evaluation of short-form version of the Constitution in Chinese Medicine Questionnaire: study a new and best brief instrument of Chinese medicine for health management.

BACKGROUND: More efficient instruments for body constitution identification are needed for clinical practice. We aimed to develop the short-form version of the Constitution in Chinese Medicine Questionnaire (CCMQ) and evaluate for health management. METHODS: First, the short forms were developed through expert survey, classical test theory (CTT), and modern item response (IRT) based on the CCMQ. A combination of e-mail and manual methods was used in expert survey. Then, five indexes of CTT including criteria value-critical ratio, correlation coefficient, discrete tendency, internal consistency, and factor loading were used. And, IRT method was used through analyzing the discrimination and difficulty parameters of items. Second, the three top-ranked items of each constitution scale were selected for the simplified CCMQ, based on the three combined methods of different conditions and weights. Third, The psychometric properties such as completion time, validity (Construct, criterion, and divergent validity), and reliability (test-retest and internal consistency reliability) were evaluated. Finally, the diagnostic validity of the best short-form used receiver operating characteristic (ROC) curve. RESULTS: Three short-form editions were developed, and retained items 27, 23 and 27, which are named as WangQi nine body constitution questionnaire of Traditional Chinese Medicine (short-form) (SF-WQ9CCMQ)- A, B, and C, respectively. SF-WQ9CCMQ- A is showed the best psychometric property on Construct validity, Criterion validity, test-retest reliability and internal consistency reliability. The diagnostic validity indicated that the area under the ROC curve was 0.928 (95%CI: 0.924-0.932) for the Gentleness constitution scale, and were 0.895-0.969 and 0.911-0.981 for unbalance constitution scales using the cut-off value of the original CCMQ as 40 ("yes" standard) and 30 ("tendency" standard), respectively. CONCLUSIONS: Our study successfully developed a well short-form which has good psychometric property, and excellent diagnostic validity consistent with the original. New and simplified instrument and opportunity are provided for body constitution identification, health management and primary care implementation.

Application and interpretation of machine learning models in predicting the risk of severe obstructive sleep apnea in adults.

BACKGROUND: Obstructive sleep apnea (OSA) is a globally prevalent disease with a complex diagnostic method. Severe OSA is associated with multi-system dysfunction. We aimed to develop an interpretable machine learning (ML) model for predicting the risk of severe OSA and analyzing the risk factors based on clinical characteristics and questionnaires. METHODS: This was a retrospective study comprising 1656 subjects who presented and underwent polysomnography (PSG) between 2018 and 2021. A total of 23 variables were included, and after univariate analysis, 15 variables were selected for further preprocessing. Six types of classification models were used to evaluate the ability to predict severe OSA, namely logistic regression (LR), gradient boosting machine (GBM), extreme gradient boosting (XGBoost), adaptive boosting (AdaBoost), bootstrapped aggregating (Bagging), and multilayer perceptron (MLP). All models used the area under the receiver operating characteristic curve (AUC) was calculated as the performance metric. We also drew SHapley Additive exPlanations (SHAP) plots to interpret predictive results and to analyze the relative importance of risk factors. An online calculator was developed to estimate the risk of severe OSA in individuals. RESULTS: Among the enrolled subjects, 61.47% (1018/1656) were diagnosed with severe OSA. Multivariate LR analysis showed that 10 of 23 variables were independent risk factors for severe OSA. The GBM model showed the best performance (AUC = 0.857, accuracy = 0.766, sensitivity = 0.798, specificity = 0.734). An online calculator was developed to estimate the risk of severe OSA based on the GBM model. Finally, waist circumference, neck circumference, the Epworth Sleepiness Scale, age, and the Berlin questionnaire were revealed by the SHAP plot as the top five critical variables contributing to the diagnosis of severe OSA. Additionally, two typical cases were analyzed to interpret the contribution of each variable to the outcome prediction in a single patient. CONCLUSIONS: We established six risk prediction models for severe OSA using ML algorithms. Among them, the GBM model performed best. The model facilitates individualized assessment and further clinical strategies for patients with suspected severe OSA. This will help to identify patients with severe OSA as early as possible and ensure their timely treatment. TRIAL REGISTRATION: Retrospectively registered.

A pan-cancer analysis reveals the diagnostic and prognostic role of CDCA2 in low-grade glioma.

BACKGROUND: Cell division cycle associated 2 (CDCA2), a member of the cell division cycle associated proteins (CDCA) family, is crucial in the regulation of cell mitosis and DNA repair. CDCA2 was extensively examined in our work to determine its role in a wide range of cancers. METHODS: CDCA2 differential expression was studied in pan-cancer and in diverse molecular and immunological subgroups in this research. Additionally, the diagnostic and prognostic significance of CDCA2 in pan-cancer was also evaluated using receiver operating characteristic (ROC) and Kaplan-Meier (KM) curves. Prognostic value of CDCA2 in distinct clinical subgroups of lower grade glioma (LGG) was also investigated and a nomogram was constructed. Lastly, potential mechanisms of action of CDCA2 were interrogated including biological functions, ceRNA networks, m6A modification and immune infiltration. RESULTS: CDCA2 is shown to be differentially expressed in a wide variety of cancers. Tumors are diagnosed and forecasted with a high degree of accuracy by CDCA2, and the quantity of expression CDCA2 is linked to the prognosis of many cancers. Additionally, the expression level of CDCA2 in various subgroups of LGG is also closely related to prognosis. The results of enrichment analyses reveal that CDCA2 is predominantly enriched in the cell cycle, mitosis, and DNA replication. Subsequently, hsa-miR-105-5p is predicted to target CDCA2. In addition, 4 lncRNAs were identified that may inhibit the hsa-miR-105-5p/CDCA2 axis in LGG. Meanwhile, CDCA2 expression is shown to be associated to m6A-related genes and levels of immune cell infiltration in LGG. CONCLUSION: CDCA2 can serve as a novel biomarker for the diagnosis and prognosis in pan-cancer, especially in LGG. For the development of novel targeted therapies in LGG, it may be a potential molecular target. However, to be sure, we'll need to do additional biological experiments to back up our results from bioinformatic predictions.