Warfarin, a classic oral anticoagulant, is characterized by a narrow therapeutic window and considerable interindividual variability in dosing requirements. This makes precise dose adjustment challenging in clinical practice and increases the risk of bleeding or thrombosis. To improve dose prediction, this study developed a streamlined multilayer perceptron (MLP) model using real-world data from the International Warfarin Pharmacogenomics Consortium (IWPC) database. The LASSO-proj algorithm was applied for high-precision feature selection prior to model construction. The resulting model demonstrated strong predictive performance on the test set, achieving a coefficient of determination (R2) of 0.456, a mean absolute error (MAE) of 8.92 mg/week, and 48.522% of its predictions falling within ±20% of the actual stable therapeutic dose. Through SHAP-based interpretation using DeepExplainer, key features influencing warfarin dosing were identified, including the VKORC1 genotype, body weight, age, and ethnicity. The interpretable MLP framework incorporating LASSO-proj not only maintains high predictive accuracy, but also significantly enhances model transparency, providing a valuable tool for guiding warfarin therapy.
ObjectiveTo explore the combined application of neutrophil to lymphocyte ratio (NLR) and systemic immune inflammation index (SII) on the prognosis of hepatitis B-related hepatocellular carcinoma after resection.MethodsRetrospectively collected data of 180 patients with hepatitis B-related hepatocellular carcinoma who were hospitalized in the Department of Infectious Diseases and Hepatobiliary Surgery of the Affiliated Hospital of Southwest Medical University and received surgical treatment from January 2013 to December 2019, including general information, laboratory examination and abdominal CT or MRI results. NLR and SII values were measured at one week before operation, and their critical values of NLR and SII were determined by ROC curve analysis. Univariate and multivariate analysis were performed to determine the risk factors to predict the survival status of patients with hepatitis B-related hepatocellular carcinoma after hepatectomy.ResultsUnivariate analysis showed that AFP, platelets, TNM staging, portal vein tumor thrombus, tumor differentiation, NLR, SII, and NLR+SII combined score were significantly correlated with the prognosis of patients with hepatitis B-related hepatocellular carcinoma (P<0.05). Multivariate analysis showed that PLT [HR=1.791, 95%CI (1.124, 2.854), P=0.014], NLR [HR=4.289, 95%CI (2.571, 7.156), P<0.001], SII [HR=5.317, 95%CI (3.016, 9.374), P<0.001], and NLR+SII combined score [HR=7.901, 95%CI (4.124, 15.138), P<0.001] were independently correlated with the survival of patients with hepatitis B-related hepatocellular carcinoma.ConclusionsThe preoperative NLR+SII combined score can be used to evaluate the postoperative prognosis of patients with hepatitis B-related hepatocellular carcinoma. The higher the score, the lower the postoperative survival rate.
Objective To conduct a systematic review of the construction methods, predictive factors, and model quality of risk prediction models for postoperative chronic pain in knee replacement surgery patients, providing evidence for the development of nursing-sensitive dynamic prediction models. Methods A systematic review of risk prediction models for postoperative chronic pain in knee replacement surgery patients was conducted by searching PubMed, Web of Science, Cochrane Library, CINAHL, SinoMed, CNKI, Wanfang Database, and VIP Database. The search period was from the establishment of the databases to February 28, 2025. Two researchers independently screened the literature, extracted data, and assessed the risk of bias and applicability of the included studies. Results A total of 10 studies involving 10 predictive models were included in this review. Among these, three models underwent internal validation, and one model underwent external validation. Commonly reported predictive factors included postoperative 24-hour Numerical Rating Scale scores, postoperative knee function scores, sleep disorders, preoperative depression, postoperative functional exercises, postoperative complications, preoperative pain, and postoperative C-reactive protein levels. All 10 studies had a high risk of bias and were generally applicable. Conclusions Existing risk prediction models generally rely on static indicators and lack dynamic monitoring of postoperative rehabilitation behaviors and psychosocial factors, with severe deficiencies in model validation. Future research should focus on developing nursing-led multidimensional dynamic models that incorporate functional exercise adherence data collected via wearable devices, standardize external model validation, and enhance clinical translation value.
Objective To explore the correlation between the quantitative and qualitative features of CT images and the invasiveness of pulmonary ground-glass nodules, providing reference value for preoperative planning of patients with ground-glass nodules. MethodsThe patients with ground-glass nodules who underwent surgical treatment and were diagnosed with pulmonary adenocarcinoma from September 2020 to July 2022 at the Third Affiliated Hospital of Kunming Medical University were collected. Based on the pathological diagnosis results, they were divided into two groups: a non-invasive adenocarcinoma group with in situ and minimally invasive adenocarcinoma, and an invasive adenocarcinoma group. Imaging features were collected, and a univariate logistic regression analysis was conducted on the clinical and imaging data of the patients. Variables with statistical difference were selected for multivariate logistic regression analysis to establish a predictive model of invasive adenocarcinoma based on independent risk factors. Finally, the sensitivity and specificity were calculated based on the Youden index. Results A total of 555 patients were collected. The were 310 patients in the non-invasive adenocarcinoma group, including 235 females and 75 males, with a meadian age of 49 (43, 58) years, and 245 patients in the invasive adenocarcinoma group, including 163 females and 82 males, with a meadian age of 53 (46, 61) years. The binary logistic regression analysis showed that the maximum diameter (OR=4.707, 95%CI 2.060 to 10.758), consolidation/tumor ratio (CTR, OR=1.027, 95%CI 1.011 to 1.043), maximum CT value (OR=1.025, 95%CI 1.004 to 1.047), mean CT value (OR=1.035, 95%CI 1.008 to 1.063), spiculation sign (OR=2.055, 95%CI 1.148 to 3.679), and vascular convergence sign (OR=2.508, 95%CI 1.345 to 4.676) were independent risk factors for the occurrence of invasive adenocarcinoma (P<0.05). Based on the independent predictive factors, a predictive model of invasive adenocarcinoma was constructed. The formula for the model prediction was: Logit(P)=–1.293+1.549×maximum diameter of lesion+0.026×CTR+0.025×maximum CT value+0.034×mean CT value+0.72×spiculation sign+0.919×vascular convergence sign. The area under the receiver operating characteristic curve of the model was 0.910 (95%CI 0.885 to 0.934), indicating that the model had good discrimination ability. The calibration curve showed that the predictive model had good calibration, and the decision analysis curve showed that the model had good clinical utility. Conclusion The predictive model combining quantitative and qualitative features of CT has a good predictive ability for the invasiveness of ground-glass nodules. Its predictive performance is higher than any single indicator.
Considering the low accuracy of prediction in the positive samples and poor overall classification effects caused by unbalanced sample data of MicroRNA (miRNA) target, we proposes a support vector machine (SVM)-integration of under-sampling and weight (IUSM) algorithm in this paper, an under-sampling based on the ensemble learning algorithm. The algorithm adopts SVM as learning algorithm and AdaBoost as integration framework, and embeds clustering-based under-sampling into the iterative process, aiming at reducing the degree of unbalanced distribution of positive and negative samples. Meanwhile, in the process of adaptive weight adjustment of the samples, the SVM-IUSM algorithm eliminates the abnormal ones in negative samples with robust sample weights smoothing mechanism so as to avoid over-learning. Finally, the prediction of miRNA target integrated classifier is achieved with the combination of multiple weak classifiers through the voting mechanism. The experiment revealed that the SVM-IUSW, compared with other algorithms on unbalanced dataset collection, could not only improve the accuracy of positive targets and the overall effect of classification, but also enhance the generalization ability of miRNA target classifier.
Acute carbon monoxide poisoning is a common and frequently occurring disease in winter and spring in China, with high disability and mortality. Delayed encephalopathy is a serious sequela after the pseudo-convalescence. Its mechanism is complex, including environmental and genetic factors, hypoxia and energy metabolism disorder, cytotoxicity and oxygen free radical damage, immune disorder and inflammatory activation, neurotransmitter disorder, brain parenchymal changes, vascular and hemorheological abnormalities, calcium overload, and cell apoptosis. At present, methods for predicting delayed encephalopathy in acute carbon monoxide poisoning include detailed inquiry of medical history, laboratory examination of relevant indicators, electrophysiological examination, brain imaging examination, and evaluation scale prediction. This review summarizes the research status of the pathogenesis and early prediction methods of delayed encephalopathy in acute carbon monoxide poisoning, with a view to providing reference for future research directions.
Acute kidney injury (AKI) is a complication with high morbidity and mortality after cardiac surgery. In order to predict the incidence of AKI after cardiac surgery, many risk prediction models have been established worldwide. We made a detailed introduction to the composing features, clinical application and predictive capability of 14 commonly used models. Among the 14 risk prediction models, age, congestive heart failure, hypertension, left ventricular ejection fraction, diabetes, cardiac valve surgery, coronary artery bypass grafting (CABG) combined with cardiac valve surgery, emergency surgery, preoperative creatinine, preoperative estimated glomerular filtration rate (eGFR), preoperative New York Heart Association (NYHA) score>Ⅱ, previous cardiac surgery, cadiopulmonary bypass (CPB) time and low cardiac output syndrome (LCOS) are included in many risks prediction models (>3 times). In comparison to Mehta and SRI models, Cleveland risk prediction model shows the best discrimination for the prediction of renal replacement therapy (RRT)-AKI and AKI in the European. However, in Chinese population, the predictive ability of the above three risk prediction models for RRT-AKI and AKI is poor.
ObjectiveTo explore the clinical value of three early predictive scale of lung injury (ALI) in patients with high risk of acute lung injury (ALI) after lung cancer surgery.MethodsA convenient sampling method was used in this study. A retrospective analysis was performed on patients with lung cancer underwent lung surgery. The patients were divided into an ALI group and a non-ALI group according to ALI diagnostic criteria. Three kinds of lung injury predictive scoring methods were used, including lung injury prediction score (LIPS), surgical lung injury prediction (SLIP) and SLIP-2. The differences in the scores of the two groups were compared. The correlation between the three scoring methods was also analyzed. The diagnostic value was analyzed by drawing receiver operating characteristic (ROC) curves.ResultsA total of 400 patients underwent lung cancer surgery, and 38 patients (9.5%) developed ALI after operation. Among them, 2 cases progressed to acute respiratory distress syndrome and were treated in intensive care unit. There were no deaths. The predictive scores of the patients in the ALI group were higher than those in the non-ALI group, and the difference was statistically significant (all P<0.001). There was a good correlation between the three scoring methods (allP<0.001). The three scoring methods had better diagnostic value for early prediction of high risk ALI patients after lung cancer surgery and their area under ROC curve (AUC) were larger than 0.8. LIPS score performed better than others, with an AUC of 0.833, 95%CI (0.79, 0.87).ConclusionThree predictive scoring methods may be applied to early prediction of high risk ALI patients after lung cancer surgery, in which LIPS performs better than others.
ObjectiveTo systematically review the risk prediction models for readmission within 30 days after discharge in patients with chronic obstructive pulmonary disease (COPD), and provide a reference for clinical selection of risk assessment tools. MethodsDatabases including CNKI, Wanfang Data, VIP, CBM, PubMed, Embase, Web of Science, and Cochrane Library were searched for literature on this topic. The search time was from the inception of the database to April 25, 2023. Literature screening and data extraction were performed by two researchers independently. The risk of bias and applicability of the included literature were evaluated using the risk of bias assessment tool for predictive model studies. ResultsA total of 8 studies were included, including 14 risk prediction models for 30-day readmission of COPD patients after discharge. The total sample size was 125~8 263, the number of outcome events was 24~741, and the area under the receiver operating characteristic curve was 0.58~0.918. The top five most common predictors included in the model were smoking, comorbidities, age, education level, and home oxygen therapy. Although five studies had good applicability, all eight studies had a certain risk of bias. This is mainly due to the small sample size of the model, lack of reporting of blinding, lack of external validation, and inappropriate handling of missing data. ConclusionThe overall prediction performance of the risk prediction model for 30-day readmission of patients with COPD after discharge is good, but the overall research quality is low. In the future, the model should be continuously improved to provide a scientific assessment tool for the early clinical identification of patients with COPD at high risk of readmission within 30 days after discharge.
Objective To investigate the risk factors for Carbapenem-resistant Klebsiella pneumoniae (CRKP) infections, and construct a clinical model for predicting the risk of CRKP infections. Methods A retrospective analysis was performed on Klebsiella pneumoniae infection patients hospitalized in the Third Hospital of Hebei Medical University from May 2020 to May 2021. The patients were divided into a CRKP group (117 cases) and a Carbapenem-sensitive Klebsiella pneumoniae (CSKP) group (191 cases). The predictors were screened by full subset regression using R software (version 4.3.1). The truncation values of continuous data were determined by Youden index. Nomogram and score table model for CRKP infections risk prediction was constructed based on binary logistic regression. The receiver operator characteristic (ROC) curve and area under curve (AUC) were used to evaluate the accuracy of models. Calibration curve and decision curve were used to evaluate the performance of models. Results308 patients with Klebsiella pneumoniae infections were included. A total of 8 predictors were selected by using full subset regression and truncation values were determined according to Youden index: intensive care unit (ICU) stay at time of infection>2 days, male, acute physiology and chronic health evaluation Ⅱ (APACHEⅡ) score>15 points, hospitalization stay at time of infection>10 days, any history of Gram-negative bacteria infection in the last 6 months, heart disease, lung infection, antibiotic exposure history in the last 6 months. The AUC of CRKP prediction risk curve model was 0.811 (95%CI 0.761 - 0.860). When the optimal cut-off value of the constructed CRKP prediction risk rating table was 6 points, the AUC was 0.723 (95%CI 0.672 - 0.774). The Bootstrap method was used for internal repeated sampling for 1000 times for verification. The model calibration curve and Hosmer-Lemeshow test (P=0.618) showed that these models have good calibration degree. The decision curve showed that these models have good clinical effectiveness. Conclusion The prediction model of CRKP infections based on the above 8 risk factors can be used as a risk prediction tool for clinical identification of CRKP infections.