1.Construction and validation of prediction models for delayed encephalopathy after acute carbon monoxide poisoning based on machine learning
Yanwu YU ; Yan ZHANG ; Ding YUAN ; Huihui HAO ; Fang YANG ; Hongyi YAN ; Pin JIANG ; Mengnan GUO ; Zhigao XU ; Changhua SUN ; Gaiqin YAN ; Lu CHE ; Jianjun GUO ; Jihong CHEN ; Yan LI ; Yanxia GAO
Chinese Journal of Emergency Medicine 2025;34(10):1403-1409
Objective:s To investigate the risk factors for delayed encephalopathy after acute carbon monoxide poisoning (DEACMP) in patients with acute carbon monoxide poisoning (ACOP) and to develop predictive models based on machine learning algorithms.Methods:Patients with ACOP hospitalized at the First Affiliated Hospital of Zhengzhou University from August 2019 to October 2024 were included, with the occurrence of DEACMP as the outcome measure. The dataset was randomly divided into training and validation sets at a ratio of 7:3. Lasso regression was used to select features influencing the outcome in training sets. Nine machine learning models—including Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM)—were constructed. Receiver operating characteristic (ROC) curves were plotted and the area under the curve (AUC) calculated for each model. Calibration curves were used to assess accuracy, and decision curve analysis (DCA) was applied to evaluate clinical utility. The SHapley Additive exPlanations (SHAP) method was employed to visualize and interpret the best-performing model.Results:A total of 264 ACOP patients were included, of whom 54 (20.5%) developed DEACMP. Lasso regression identified eight key feature variables. Based on these factors, predictive models were constructed, showing good AUC stability across the nine machine learning models in both training (0.92–0.99) and validation sets (0.85–0.91). The RF model performed best, with an AUC of 0.99 in the training set and 0.90 in the validation set; its calibration curve and DCA curve also demonstrated excellent performance. SHAP analysis of the RF model revealed the importance ranking of factors from highest to lowest as follows: Glasgow Coma Scale (GCS) score, duration of coma, age, history of coronary heart disease, CK-MB level, monocyte count, diastolic blood pressure (DBP), and drinking history.Conclusions:The RF model exhibited the highest predictive performance for DEACMP occurrence in ACOP patients. The influencing factors, ranked in order of importance from highest to lowest, are as follows: GCS score, duration of coma, age, history of coronary heart disease, CK-MB level, monocyte count, DBP, and drinking history.
2.Relationship between serum Sortilin,TMAO and inflammatory factors and abdominal aortic calcification in maintenance hemodialysis patients
Yang WEI ; Gaiqin GAO ; Xiaopeng YAN ; Min YANG
International Journal of Laboratory Medicine 2024;45(23):2856-2861
Objective To investigate the relationship between serum sorting protein(Sortilin),trimethyl-amine oxide(TMAO)and inflammatory factors and abdominal aortic calcification(AAC)in maintenance he-modialysis(MHD)patients.Methods A total of 197 MHD patients(MHD group)admitted to Department of Nephrology in the hospital from January 2021 to May 2023 and 150 physically examined healthy individuals(control group)during the same period were prospectively selected,and the MHD patients were classified into the moderate and severe AAC group(82 patients)and no or mild AAC group(115 patients)according to the AAC score.The serum of serum Sortilin,TMAO and inflammatory factors[interleukin(IL)-1β,IL-6,tumor necrosis factor-α(TNF-α)]were measured using enzyme-linked immunosorbent assay.The correlation be-tween serum Sortilin,TMAO,and inflammatory factors in MHD patients was assessed using Spearman corre-lation analysis,and influencing factors associated with moderate and severe AAC in MHD patients were ex-plored using multivariate Logistic regression analysis.The predictive value of serum Sortilin and TMAO levels for moderate and severe AAC in MHD patients was analyzed using receiver operating characteristic curve.Re-sults The levels of serum Sortilin,TMAO,IL-1β,IL-6 and TNF-α in moderate and severe AAC group were higher than those in no or mild AAC group and control group(all P<0.05).Serum Sortilin and TMAO were positively correlated with IL-1β,IL-6 and TNF-α levels in MHD patients(all P<0.05).Prolonged dialysis age(OR=1.034,95%CI:1.010-1.060),increased levels of IL-6(OR=1.092,95%CI:1.034-1.152),Sortilin(OR=1.076,95%CI:1.043-1.110)and TMAO(OR=1.384,95%CI:1.150-1.664)were independent risk factors for moderate and severe AAC in MHD patients(P<0.05).The area under the curve of serum Sortilin combined with TMAO levels in predicting moderate and severe AAC in MHD patients was 0.885(95%CI:0.831-0.926),which was greater than 0.785(95%CI:0.721-0.841)and 0.797(95%CI:0.734-0.850)predicted by serum Sortilin and TMAO levels alone(P<0.05).Conclusion The levels of se-rum Sortilin and TMAO in MHD patients are increased,and are closely related to the elevation of inflammato-ry factors and AAC.Furthermore,the combination of serum Sortilin and TMAO levels shows certain predic-tive value for moderate and severe AAC in MHD patients.
3.Significance of fecal occult blood test in colorectal cancer screening
Xiaoyue SUN ; Junjie GAO ; Gaiqin GAO ; Pengjin SUN ; Ke YAN ; Baoxia TIE ; Feng GAO
Cancer Research and Clinic 2019;31(6):422-424
Colorectal cancer is one of the most common malignant tumors of the digestive system. The incidence of colorectal cancer in China is increasing year by year. Screening for adenomas, precancerous lesions and early cancers can effectively reduce the incidence and mortality of colorectal cancer. Therefore, colorectal cancer screening is particularly important. At present, the colorectal cancer examination is mainly divided into fecal examination and colon structural examination. The fecal examination includes fecal occult blood test, fecal exfoliated cell test and fecal genetic analysis. The colon structural examination includes barium enema, colonoscopy and computed tomography colonography. Colonoscopy is considered as the gold standard for the diagnosis of colorectal cancer. It has the advantage of high accuracy, and can be used to find precancerous lesions and remove them at the same time. However, the screening should be greatly restricted because of its invasive examination, the need for intestinal preparation, obvious discomfort and the high cost of medical treatment. Comparatively, fecal occult blood test is simple, easy, non-invasive, saving manpower and material resources, and is suitable for large population screening. Some scholars in China have begun to pay attention to colorectal cancer screening, and fecal occult blood test is widely used in these screenings.
4.Effect of pain intervention on limb function exercises in patients with peripheric fractures of knee joint
Ping LIU ; Gaiqin ZHANG ; Zhan WANG ; Yuan LI ; Yinghua DAI ; Yan ZHANG ; Lei ZHANG
Modern Clinical Nursing 2013;(1):46-49
Objective To explore the effect of pain intervention on limb function exercises in patients with peripheric fractures of knee joint.Methods 60 patients with peripheric fractures of knee joint were randomized in equal number into the observation group and control group.Both groups took functional exercises for affected limbs.Besides,the former and latter groups were administered with celecoxib at a dosage of 200mg twice a day from pre-operation to discharge and after operation,respectively.The two groups were compared in terms of pain degree at different time points as well as the functional recovery of affected limbs.Results The observation group was lower in pain scores than the control group at hours 6,8,12,24,36 and 48.The active and passive motions of the affected limbs in the observation group were significantly better than those in the control at days 1,2,3,4 and 5(all P<0.001).Conclusion Pain intervention with celecoxib before operation may help patients to take functional exercises as early as possible,promoting the rehabilitation of functions of affected limbs.

Result Analysis
Print
Save
E-mail