Objective To construct machine learning models to predict the incidence of linezolid-induced thrombocytopenia(LIT).Methods A total of 198 patients treated with linezolid in a hospital between January 2020 and March 2024 were retrospectively included.Firstly,the patients were divided into LIT and non-LIT groups,and the basic characteristics of the two groups were compared.Then,the variables with significant differences between the two groups were selected as potential risk factors to construct models for predicting LIT,including Logistic regression,decision tree and random forest models,and the prediction performance of the models was evaluated and compared.Results There were 52(26.3％)patients developed LIT during the treatment.The univariate analysis showed significant differences in linezolid trough concentration(Cmin),baseline platelet counts and creatinine clearance,the incidence of cerebrovascular disease,acute respiratory distress syndrome,and abdominal infection in patients with and without LIT.Among the three models built based on these variables,the random forest model has the best predictive performance.The results of variable importance analysis based on random forest model showed that Cmin,baseline platelet count and combined with acute respiratory distress syndrome had higher importance scores.Conclusions The random forest model has high accuracy in predicting the occurrence of LIT,and the risk of LIT is higher in patients with higher levels of linezolid exposure and lower baseline platelets.

Immune checkpoint inhibitors are effective tumor treatment agents with survival benefits.However,immune toxicity to various organs has become a new challenge in clinical practice.The cardiac involvement can be presented as heart failure,arrhythmia(atrial fibrillation,atrioventricular block,bundle branch block,ventricular tachycardia,etc.),myocardial-pericarditis,myocardiopathy,and sudden cardiac death,etc.This patient developed abnormally increased myocardial enzymes,impaired cardiac function,and atrioventricular block after 1-month treatment with tislelizumab.Endomyocardial biopsy examination confirmed the diagnosis of immune checkpoint inhibitor-associated myocarditis.Through the diagnosis,treatment,and review of relevant literatures of this case,we wish to improve the understanding of immune checkpoint inhibitor-associated myocarditis,and therefore improve the diagnosis and treatment of immune checkpoint inhibitor-associated myocarditis for clinicians.

Objective To construct machine learning models to predict the incidence of linezolid-induced thrombocytopenia(LIT).Methods A total of 198 patients treated with linezolid in a hospital between January 2020 and March 2024 were retrospectively included.Firstly,the patients were divided into LIT and non-LIT groups,and the basic characteristics of the two groups were compared.Then,the variables with significant differences between the two groups were selected as potential risk factors to construct models for predicting LIT,including Logistic regression,decision tree and random forest models,and the prediction performance of the models was evaluated and compared.Results There were 52(26.3％)patients developed LIT during the treatment.The univariate analysis showed significant differences in linezolid trough concentration(Cmin),baseline platelet counts and creatinine clearance,the incidence of cerebrovascular disease,acute respiratory distress syndrome,and abdominal infection in patients with and without LIT.Among the three models built based on these variables,the random forest model has the best predictive performance.The results of variable importance analysis based on random forest model showed that Cmin,baseline platelet count and combined with acute respiratory distress syndrome had higher importance scores.Conclusions The random forest model has high accuracy in predicting the occurrence of LIT,and the risk of LIT is higher in patients with higher levels of linezolid exposure and lower baseline platelets.

Objectives:To investigate the relationship between locations of ventricular septal perforation and 30-day prognosis in patients with acute myocardial infarction complicated by ventricular septal perforation.Methods:Clinical data of 150 acute myocardial infarction patients with ventricular septal perforation admitted to Fuwai Hospital of Chinese Academy of Medical Sciences and People's Hospital of Xinjiang Uygur Autonomous Region from January 2009 to October 2023 were retrospectively analyzed.Kaplan-Meier method was used to compare the difference in 30-day survival rate among patients with different sites of ventricular septal perforation.The impact of locations of ventricular septal perforation on 30-day prognosis of acute myocardial infarction patients was evaluated by multivariate Cox regression analysis(forward stepwise).Results:In acute myocardial infarction patients,the occurrence of anterior ventricular septal perforation was higher than that of posterior ventricular septal perforation(79.5%vs.20.5%,P<0.001).In the anterior ventricular septal perforation patients,females were more common(50.0%vs.22.6%,P=0.006),the blood glucose level was higher([10.51±5.99]mmol/L vs.[8.02±2.81]mmol/L,P=0.026),the left ventricular end-diastolic diameter was smaller([50.7±6.1]mm vs.[55.1±5.0]mm,P<0.001),the ventricular septal aperture was also smaller([9.8±4.6]mm vs.[12.6±5.4]mm,P=0.004),30-day mortality was higher(55.8%vs.35.5%,P=0.043)compared with posterior ventricular septal perforation patients.Multivariate Cox regression analysis(forward stepwise)showed that no transthoracic surgery or transcatheter closure(HR=26.344,95%CI:8.261-84.009,P<0.001)and anterior ventricular septal perforation(HR=2.432,95%CI:1.281-4.619,P=0.007)were associated with increased risk of 30-day all-cause mortality in patients with acute myocardial infarction complicated by ventricular septal perforation.Conclusions:In patients with acute myocardial infarction complicated by ventricular septal perforation,the incidence of anterior ventricular septal perforation is higher than posterior ventricular septal perforation and the 30-day all-cause mortality of anterior ventricular septal perforation patients is also higher.No transthoracic surgery or transcatheter closure and anterior ventricular septal perforation are the independent influential factors of 30-day all-cause mortality in patients with acute myocardial infarction and ventricular septal perforation.

Objective To analyze the development of nuclear medicine services in Hunan Province and to assess internal radiation doses among the nuclear medicine workers (NMWs) involved in iodine-131 radionuclide therapy. Methods Based on a survey of nuclear medicine institutions in Hunan Province, a total of 61 NMWs from seven hospitals providing iodine-131 therapy for thyroid cancer were selected as the study subjects by convenience sampling method. Thyroidal iodine-131 activity was measured using a portable gamma spectrometer to estimate internal dose and total annual effective dose. Results A total of 47 nuclear medicine institutions were reported in Hunan Province by 2023, most of which were public and tertiary hospitals, accounting for 38. Iodine-131 therapy was performed in 30 institutions, including nine for thyroid cancer. A total of nine participants had detectable thyroidal iodine-131 activity among 61 workers involved in iodine-131 thyroid cancer treatment, with the detection rate of 14.8%. Their internal radiation annual committed effective doses ranged from 0.100 to 1.584 mSv, with a mean of 0.499 mSv and median of 0.426 mSv. Except for one cleaner, the remaining eight physicians and nurses had the total annual effective doses ranging from 0.311 to 3.007 mSv, with a mean of 1.305 mSv, all below the annual dose limit of 20.000 mSv among radiation workers specified in national standard. Conclusion Internal exposure to iodine-131 among the NMWs should not be neglected. Standardized procedures and strengthened internal dose monitoring are recommended.

Diabetic nephropathy(DN)is one of the most common complications of diabetes,and has become the main cause of chronic kidney disease and end-stage renal disease worldwide.At present,the pathogenesis of DN is not completely clear.For a long time,the routine treatment of DN is a combination of life management,hypoglyce-mic,hypotensive with other symptom-based treatment,but its progress cannot be delayed.Therefore,early detec-tion,diagnosis,and treatment of DN are particularly important,but there is currently no single indicator that can be used for early diagnosis of DN.Therefore,the development of simple,sensitive,and efficient biomarkers is be-coming increasingly important.

Objective:The aim of this study was to investigate whether the Model for end-stage liver disease-excluding international normalised ratio ( MELD-XI) score whether it can predict the prognosis of patients on veno-arterial extracorporeal membrane oxygenation support.Methods:This study was a retrospective cohort study, which retrospectively included clinical data data of patients using ECMO from January 2015 to December 2023 in Fuwai Huazhong Cardiovascular Disease Hospital. Inclusion criteria: 1. clinical patients using VA-ECMO, excluding VAV-ECMO and VV-ECMO; 2. available laboratory values of blood creatinine and total bilirubin within the first 24 hours of on-boarding; 3. complete basic information of the patients; and 4. age greater than 18 years. Exclusion criteria: 1. patients whose family members abandoned the treatment due to economic reasons; 2. on-boarding time less than 24 hours; 3. patients with incomplete clinical information or patients who did not have a detailed record of general information on VA-ECMO. Using X-tile software, they were divided into MELD-XI score ≤13.9 and MELD-XI score >13.9 groups, and variables with P < 0.05 were included in the binary logistic regression model after using univariate analysis. Results:: Univariate analysis of 940 patients revealed that the MELD-XI score ≤13.9 group compared with the MELD-XI score >13.9 group had a significant difference in the success of machine withdrawal ( χ2=31.812, P<0.001), death while the machine was in operation ( χ2=52.453, P<0.001), death after machine withdrawal ( χ2=4.210, P=0.040), cerebral thrombotic complications ( χ2=4.319, P=0.038), lower extremity thrombotic complications ( χ2=8.789, P=0.003), and CRRT use ( χ2=15.648, P<0.001), length of boarding (Z=-17.786, P<0.001), length of hospital stay (Z=-17.503, P<0.001), and length of ICU stay ( Z=-18.790, P<0.001) were significantly different. Multifactorial binary logistic regression showed that successful machine withdrawal ( OR=2.078, 95% CI:1.158-3.731, P=0.014), death while the machine was running ( OR=0.271, 95% CI:0.144-0.512, P<0.001), CRRT use ( OR=3.227, 95% CI:1.659-6.474, P=0.001), length of hospital stay ( OR=1.138, 95% CI:1.107-1.171, P<0.001), length of boarding ( OR=1.035, 95% CI:1.027-1.043, P<0.001), ICU stay ( OR=1.365, 95% CI:1.278-1.458, P < 0.001) are independent influencing factor for VA-ECMO support patients. Kaplan-Meier curve analysis showed that both in-hospital mortality ( HR=2.167, 95% CI:1.508-3.114, P<0.001) and withdrawal success ( HR=5.353, 95% CI:4.023-7.121, P<0.001) were significantly lower in the MELD-XI score ≤13.9 group than in the MELD-XI score >13.9 group. Conclusions:The MELD-XI score can predict the prognosis of VA-ECMO-supported patients and help clinician doctors to make complex clinical decisions.

Immune checkpoint inhibitors are effective tumor treatment agents with survival benefits.However,immune toxicity to various organs has become a new challenge in clinical practice.The cardiac involvement can be presented as heart failure,arrhythmia(atrial fibrillation,atrioventricular block,bundle branch block,ventricular tachycardia,etc.),myocardial-pericarditis,myocardiopathy,and sudden cardiac death,etc.This patient developed abnormally increased myocardial enzymes,impaired cardiac function,and atrioventricular block after 1-month treatment with tislelizumab.Endomyocardial biopsy examination confirmed the diagnosis of immune checkpoint inhibitor-associated myocarditis.Through the diagnosis,treatment,and review of relevant literatures of this case,we wish to improve the understanding of immune checkpoint inhibitor-associated myocarditis,and therefore improve the diagnosis and treatment of immune checkpoint inhibitor-associated myocarditis for clinicians.

Objectives:To investigate the relationship between locations of ventricular septal perforation and 30-day prognosis in patients with acute myocardial infarction complicated by ventricular septal perforation.Methods:Clinical data of 150 acute myocardial infarction patients with ventricular septal perforation admitted to Fuwai Hospital of Chinese Academy of Medical Sciences and People's Hospital of Xinjiang Uygur Autonomous Region from January 2009 to October 2023 were retrospectively analyzed.Kaplan-Meier method was used to compare the difference in 30-day survival rate among patients with different sites of ventricular septal perforation.The impact of locations of ventricular septal perforation on 30-day prognosis of acute myocardial infarction patients was evaluated by multivariate Cox regression analysis(forward stepwise).Results:In acute myocardial infarction patients,the occurrence of anterior ventricular septal perforation was higher than that of posterior ventricular septal perforation(79.5%vs.20.5%,P<0.001).In the anterior ventricular septal perforation patients,females were more common(50.0%vs.22.6%,P=0.006),the blood glucose level was higher([10.51±5.99]mmol/L vs.[8.02±2.81]mmol/L,P=0.026),the left ventricular end-diastolic diameter was smaller([50.7±6.1]mm vs.[55.1±5.0]mm,P<0.001),the ventricular septal aperture was also smaller([9.8±4.6]mm vs.[12.6±5.4]mm,P=0.004),30-day mortality was higher(55.8%vs.35.5%,P=0.043)compared with posterior ventricular septal perforation patients.Multivariate Cox regression analysis(forward stepwise)showed that no transthoracic surgery or transcatheter closure(HR=26.344,95%CI:8.261-84.009,P<0.001)and anterior ventricular septal perforation(HR=2.432,95%CI:1.281-4.619,P=0.007)were associated with increased risk of 30-day all-cause mortality in patients with acute myocardial infarction complicated by ventricular septal perforation.Conclusions:In patients with acute myocardial infarction complicated by ventricular septal perforation,the incidence of anterior ventricular septal perforation is higher than posterior ventricular septal perforation and the 30-day all-cause mortality of anterior ventricular septal perforation patients is also higher.No transthoracic surgery or transcatheter closure and anterior ventricular septal perforation are the independent influential factors of 30-day all-cause mortality in patients with acute myocardial infarction and ventricular septal perforation.

Objective To evaluate the relationship between ceftazidime-avibactam(CAZ-AVI)blood concentrations and efficacy in critically ill patients and to investigate the factors influencing blood levels.Methods The CAZ-AVI trough concentrations(Cmin)were detected in 29 patients who received CAZ-AVI treatment for at least 48 hours.The clinical materials of the patients were collected together for retrospective analysis.Results The Cmin of ceftazidime(CAZ)and avibactam(AVI)were(50.95±5.17)and(7.52±0.96)mg·L-1 in the effective group and(31.16±7.03)and(5.37±1.32)mg·L-1 in the ineffective group,respectively.The Cmin of CAZ in the effective group was significantly higher than in the ineffective group(P<0.05),and there was no significant difference in AVI Cmin between the two groups(P>0.05).Spearman's correlation analysis showed that CAZ Cmin was positively correlated with clinical efficacy(P<0.05),and no correlation between AVI Cmin and clinical efficacy(P>0.05).The optimal CAZ Cmin threshold was 24.59 mg·L-1.Multiple linear regression analysis showed that age and creatinine clearance was significantly correlated with the Cmin of CAZ,and creatinine clearance was significantly correlated with AVI Cmin(P<0.05).Conclusions The Cmin of CAZ correlates with efficacy,and it may be more beneficial for clinical treatment to keep the concentration of CAZ-AVI always greater than the minimum inhibitory concentration during the dosing interval.The creatinine clearance should be fully considered when optimizing CAZ-AVI dosage in critically ill patients.