Objective:To evaluate the value of ultrasound radiomics combined with machine learning for early diagnosis of seronegative Hashimoto’s thyroiditis (SN-HT) .Methods:This retrospective study included 164 patients from Liaoning Provincial People’s Hospital , Lixin County People’s Hospital, Linghai Dalinghe Hospital, Fengcheng Phoenix Hospital, who underwent thyroidectomy for solitary nodules with normal thyroid function between Nov. 2016 and Jan. 2024. Postoperative pathology confirmed Hashimoto’s thyroiditis (HT) in some cases, who were further categorized into antibody-positive and antibody-negative groups based on serum antibody status. Patients without Hashimoto’s thyroiditis served as the control group. A total of 298 ultrasound images were analyzed. Radiomics features were extracted from hypoechoic non-nodular areas within 0.5 cm surrounding the tumor. Two senior pathologists and two senior ultrasound physicians independently assessed lymphocytic infiltration, eosinophilic changes of follicular epithelium, and the proportion of hypoechoic areas in pathology and ultrasound images, respectively. A machine learning model, CCH-NET, was developed using linear regression and t-distributed stochastic neighbor embedding (t-SNE) techniques. The dataset was divided into a training set (80%) and a validation set (20%) to compare the diagnostic accuracy of CCH-NET with that of senior ultrasound physicians. Results:In internal validation, CCH-NET achieved a diagnostic accuracy of 88.89% for both antibody-positive and antibody-negative groups, significantly higher than the 66.67% accuracy of senior ultrasound physicians ( P<0.01). In external validation, CCH-NET achieved 75.00% and 66.67% accuracy for the two groups, compared to 50.00% by senior ultrasound physicians. For the control group, both methods achieved 93.33% accuracy. The AUC of CCH-NET was 0.848, outperforming senior ultrasound physicians (0.681) ,demonstrating superior diagnostic performance. Conclusion:The radiomics-based CCH-NET model, using non-nodular hypoechoic areas as a specific indicator, can accurately identify early SN-HT in euthyroid patients. It significantly outperforms senior ultrasound physicians, improving diagnostic accuracy and reducing missed diagnoses.

Objective To investigate the risk factors and countermeasures of linezolid-induced thrombocytopenia.Methods Clinical pharmacists participated in the pharmacy practice of linezolid-induced thrombocytopenia in a patient with liver cirrhosis.They analyzed the risk factors,took timely countermeasures,and conducted pharmaceutical care.Results The liver cirrhosis,low creatinine clearance and basic platelet values were closely related to linezolid-related thrombocytopenia,platelet recovered after discontinuation.Linezolid(0.3 g,Ⅳ,q12h)was used again under serum drug concentration monitoring,and the infection was effectively controlled,no thrombocytopenia occurred.Conclusions Clinical pharmacists should conduct pharmaceutical care for patients,pay close attention to adverse reactions,and timely adjust the treatment plan to better ensure the effectiveness and safety of treatment.

Objective To investigate the risk factors and countermeasures of linezolid-induced thrombocytopenia.Methods Clinical pharmacists participated in the pharmacy practice of linezolid-induced thrombocytopenia in a patient with liver cirrhosis.They analyzed the risk factors,took timely countermeasures,and conducted pharmaceutical care.Results The liver cirrhosis,low creatinine clearance and basic platelet values were closely related to linezolid-related thrombocytopenia,platelet recovered after discontinuation.Linezolid(0.3 g,Ⅳ,q12h)was used again under serum drug concentration monitoring,and the infection was effectively controlled,no thrombocytopenia occurred.Conclusions Clinical pharmacists should conduct pharmaceutical care for patients,pay close attention to adverse reactions,and timely adjust the treatment plan to better ensure the effectiveness and safety of treatment.

Objective This study aimed to investigate the antimicrobial resistance profiles of bacterial strains isolated from pediatric intensive care units(PICU)in China for better antimicrobial therapy.Methods Clinical isolates were collected from 17 institutions,including tertiary care children's hospitals and pediatric department of tertiary general hospitals in China from January 1,2020 to December 31,2022.Antimicrobial susceptibility testing was carried out according to a unified protocol using Kirby-Bauer method or automated systems.Results were interpreted according to the breakpoints released by the Clinical and Laboratory Standards Institute(CLSI)in 2020.Results A total of 10 688 isolates were collected,including gram-positive organisms(39.2％)and gram-negative organisms(60.8％).The top three organisms were S.aureus(13.6％,1 453/10 688),A.baumannii(10.0％,1 067/10 688),and coagulase-negative Staphylococcus(9.9％,1 058/10 688).Multi-drug resistant organisms(MDROs)were very common in children.The prevalence of methicillin-resistant Staphylococcus aureus(MRSA),carbapenem-resistant Enterobacterales(CRE),carbapenem-resistant E.coli,carbapenem-resistant K.pneumoniae(CRKP),carbapenem-resistant A.baumannii(CRAB),and carbapenem-resistant P.aeruginosa(CRPA)was 41.1％,19.4％,8.8％,30.9％,67.4％,and 28.8％,respectively.Overall,more than 50％of Enterobacteriales isolates were resistant to cephalosporins,while nearly 25％of Enterobacteriales isolates were resistant to carbapenems.MDROs were highly resistant to commonly used antibiotics.More than 80％of CRE and CRAB strains were resistant to all beta-lactam antibiotics.CRE and CRAB showed low resistance rates to tigecycline and polymyxin.CRPA showed lower resistance rates to piperacillin,beta-lactamase inhibitor combinations than the resistance rates to third and fourth generation cephalosporins.All of the Staphylococcus and Enterococcus isolates were susceptible to vancomycin and tigecycline.None of PRSP strains isolated from meningitis and nonmeningitis samples were resistant to rifampicin,vancomycin,or linezolid.The prevalence of β-lactamase-negative ampicillin-resistant(BLNAR)strains was 43.3％in Haemophilus influenzae.Conclusions MDROs were prevalent in PICU.It is necessary to establish an effective multidisciplinary team(MDT)to control the antimicrobial resistance.

Objective This study aims to provide theoretical support for the formulation of thyroid nodule prevention and treatment strategies in Northwest China and to investigate the characteristics of thyroid nodules and their association with metabolic indicators in this population.Methods A cross-sectional survey was conducted by retrospectively enrolling healthy individuals who underwent routine health examinations at our hospital between January 1 and December 31,2023.A total of 38 919 participants were included.The detection rate of thyroid nodules was stratified by age and sex.Univariate and multivariate binary logistic regression analyses were performed to identify risk factors for thyroid nodules.Results Among the 38 919 participants,20 395 were men(52.4%)and 18 524 were women(47.6%).The overall detection rate of thyroid nodules was 47.1%(18 317/38 919),including 40.1%(8 187/20 395)in men and 54.7%(10 130/18 524)in women.Across all age groups,women had a significantly higher detection rate than men(P<0.001).The detection rate increased with age in both sexes(χ2trend=1392.867,P<0.001 in men;χ2trend=1521.215,P<0.001 in women).Significant differences were observed between participants with and without thyroid nodules in age,body mass index(BMI),fasting blood glucose(FBG),glycated hemoglobin(HbA1c),total cholesterol(TC),low-density lipoprotein cholesterol(LDL-C),triiodothyronine(T3),thyroid-stimulating hormone(TSH),and anti-thyroglobulin antibodies(TGAB),anti-thyroid microsomal antibodies,the proportion of hypertension and central obesity(all P<0.05).Multivariate binary logistic regression analysis identified female sex(OR=2.158),older age(OR=1.040),central obesity(OR=1.144),elevated FBG(OR=1.039),hypertension(OR=1.095),elevated TGAB(OR=1.008),and elevated T3(OR=1.154)as independent risk factors for thyroid nodules(all P<0.05).Conclusion Women in Northwest China are at higher risk of developing thyroid nodules.Screening and health management should be prioritized for older individuals,those with central obesity,elevated FBG,hypertension,elevated TGAB,and elevated T3 levels.

BACKGROUND:Cervical instability is a common orthopedic disease in young and middle-aged people,and is the early manifestation of cervical spondylosis,which has a great impact on the quality of life of patients.Therefore,early diagnosis of cervical instability to implement early intervention has positive clinical and social significance.OBJECTIVE:The clinical prediction model of cervical instability in young and middle-aged people was constructed based on machine learning to realize early screening of cervical instability in young and middle-aged people before X-ray examination.METHODS:From September 2022 to October 2023,155 young and middle-aged adults with cervical instability and 88 with non-cervical instability recruited through recruitment advertisements and spinal department outpatient of Wangjing Hospital,China Academy of Chinese Medical Sciences were selected as research subjects.The research subjects'general information,living and working habits,discomfort symptoms,visual analog scale score,Neck Disability Index,and 36-ltem Short Form Health Survey were collected on site based on questionnaires.The above information was used as predictive factors.After screening,six machine learning algorithms of Support Vector Machine,LightGBM,RandomForest,Logistic,AdaBoost,and XGBClassifier were used to train the model by ten-fold cross-validation method,and the clinical prediction model of cervical instability was constructed.Area under the curve was used as the main evaluation index.Univariate analysis was performed on the predictors,and SHAP method was used to rank the importance of the predictors.Correlation heat maps were used to show the degree of linear correlation between the predictors and the cervical instability.RESULTS AND CONCLUSION:(1)Among the six machine learning models,RandomForest model was chosen as the final prediction model,including nine predictors,such as age,body mass index,neck circumference/neck length,visual analog scale score,Neck Disability Index,bodily pain,general health,vitality,and mental health,area under the curve=0.725 4,and the calibration degree was good.It could be used as a reference tool for early screening of cervical instability in young and middle-aged people.(2)There were significant differences in age,visual analog scale score,Neck Disability Index,bodily pain,general health,and vitality between the two groups(P＜0.05).(3)The order of importance of predictors was age,Neck Disability Index,visual analog scale score,general health,body mass index,vitality,bodily pain,neck circumference/neck length,mental health,among which age,visual analog scale score,Neck Disability Index were positively correlated with cervical instability,while general health,body mass index,vitality,bodily pain,neck circumference/neck length,and mental health were negatively correlated with cervical instability.

Objective:To evaluate the value of ultrasound radiomics combined with machine learning for early diagnosis of seronegative Hashimoto’s thyroiditis (SN-HT) .Methods:This retrospective study included 164 patients from Liaoning Provincial People’s Hospital , Lixin County People’s Hospital, Linghai Dalinghe Hospital, Fengcheng Phoenix Hospital, who underwent thyroidectomy for solitary nodules with normal thyroid function between Nov. 2016 and Jan. 2024. Postoperative pathology confirmed Hashimoto’s thyroiditis (HT) in some cases, who were further categorized into antibody-positive and antibody-negative groups based on serum antibody status. Patients without Hashimoto’s thyroiditis served as the control group. A total of 298 ultrasound images were analyzed. Radiomics features were extracted from hypoechoic non-nodular areas within 0.5 cm surrounding the tumor. Two senior pathologists and two senior ultrasound physicians independently assessed lymphocytic infiltration, eosinophilic changes of follicular epithelium, and the proportion of hypoechoic areas in pathology and ultrasound images, respectively. A machine learning model, CCH-NET, was developed using linear regression and t-distributed stochastic neighbor embedding (t-SNE) techniques. The dataset was divided into a training set (80%) and a validation set (20%) to compare the diagnostic accuracy of CCH-NET with that of senior ultrasound physicians. Results:In internal validation, CCH-NET achieved a diagnostic accuracy of 88.89% for both antibody-positive and antibody-negative groups, significantly higher than the 66.67% accuracy of senior ultrasound physicians ( P<0.01). In external validation, CCH-NET achieved 75.00% and 66.67% accuracy for the two groups, compared to 50.00% by senior ultrasound physicians. For the control group, both methods achieved 93.33% accuracy. The AUC of CCH-NET was 0.848, outperforming senior ultrasound physicians (0.681) ,demonstrating superior diagnostic performance. Conclusion:The radiomics-based CCH-NET model, using non-nodular hypoechoic areas as a specific indicator, can accurately identify early SN-HT in euthyroid patients. It significantly outperforms senior ultrasound physicians, improving diagnostic accuracy and reducing missed diagnoses.

BACKGROUND:Cervical instability is a common orthopedic disease in young and middle-aged people,and is the early manifestation of cervical spondylosis,which has a great impact on the quality of life of patients.Therefore,early diagnosis of cervical instability to implement early intervention has positive clinical and social significance.OBJECTIVE:The clinical prediction model of cervical instability in young and middle-aged people was constructed based on machine learning to realize early screening of cervical instability in young and middle-aged people before X-ray examination.METHODS:From September 2022 to October 2023,155 young and middle-aged adults with cervical instability and 88 with non-cervical instability recruited through recruitment advertisements and spinal department outpatient of Wangjing Hospital,China Academy of Chinese Medical Sciences were selected as research subjects.The research subjects'general information,living and working habits,discomfort symptoms,visual analog scale score,Neck Disability Index,and 36-ltem Short Form Health Survey were collected on site based on questionnaires.The above information was used as predictive factors.After screening,six machine learning algorithms of Support Vector Machine,LightGBM,RandomForest,Logistic,AdaBoost,and XGBClassifier were used to train the model by ten-fold cross-validation method,and the clinical prediction model of cervical instability was constructed.Area under the curve was used as the main evaluation index.Univariate analysis was performed on the predictors,and SHAP method was used to rank the importance of the predictors.Correlation heat maps were used to show the degree of linear correlation between the predictors and the cervical instability.RESULTS AND CONCLUSION:(1)Among the six machine learning models,RandomForest model was chosen as the final prediction model,including nine predictors,such as age,body mass index,neck circumference/neck length,visual analog scale score,Neck Disability Index,bodily pain,general health,vitality,and mental health,area under the curve=0.725 4,and the calibration degree was good.It could be used as a reference tool for early screening of cervical instability in young and middle-aged people.(2)There were significant differences in age,visual analog scale score,Neck Disability Index,bodily pain,general health,and vitality between the two groups(P＜0.05).(3)The order of importance of predictors was age,Neck Disability Index,visual analog scale score,general health,body mass index,vitality,bodily pain,neck circumference/neck length,mental health,among which age,visual analog scale score,Neck Disability Index were positively correlated with cervical instability,while general health,body mass index,vitality,bodily pain,neck circumference/neck length,and mental health were negatively correlated with cervical instability.

Objective This study aims to provide theoretical support for the formulation of thyroid nodule prevention and treatment strategies in Northwest China and to investigate the characteristics of thyroid nodules and their association with metabolic indicators in this population.Methods A cross-sectional survey was conducted by retrospectively enrolling healthy individuals who underwent routine health examinations at our hospital between January 1 and December 31,2023.A total of 38 919 participants were included.The detection rate of thyroid nodules was stratified by age and sex.Univariate and multivariate binary logistic regression analyses were performed to identify risk factors for thyroid nodules.Results Among the 38 919 participants,20 395 were men(52.4%)and 18 524 were women(47.6%).The overall detection rate of thyroid nodules was 47.1%(18 317/38 919),including 40.1%(8 187/20 395)in men and 54.7%(10 130/18 524)in women.Across all age groups,women had a significantly higher detection rate than men(P<0.001).The detection rate increased with age in both sexes(χ2trend=1392.867,P<0.001 in men;χ2trend=1521.215,P<0.001 in women).Significant differences were observed between participants with and without thyroid nodules in age,body mass index(BMI),fasting blood glucose(FBG),glycated hemoglobin(HbA1c),total cholesterol(TC),low-density lipoprotein cholesterol(LDL-C),triiodothyronine(T3),thyroid-stimulating hormone(TSH),and anti-thyroglobulin antibodies(TGAB),anti-thyroid microsomal antibodies,the proportion of hypertension and central obesity(all P<0.05).Multivariate binary logistic regression analysis identified female sex(OR=2.158),older age(OR=1.040),central obesity(OR=1.144),elevated FBG(OR=1.039),hypertension(OR=1.095),elevated TGAB(OR=1.008),and elevated T3(OR=1.154)as independent risk factors for thyroid nodules(all P<0.05).Conclusion Women in Northwest China are at higher risk of developing thyroid nodules.Screening and health management should be prioritized for older individuals,those with central obesity,elevated FBG,hypertension,elevated TGAB,and elevated T3 levels.

Objective:To explore the trajectory of changes in electronic health literacy in young and middle-aged patients with coronary heart disease (CHD) combined with diabetes mellitus (DM) after percutaneous coronary intervention (PCI), and to analyze its relationship with unplanned readmission within 30 days.Methods:A convenience sample of 210 young and middle-aged CHD patients with DM who underwent PCI in the Department of Cardiology, Xinxiang Central Hospital, from February 2023 to June 2024 was selected. The e-Health Literacy Scale (eHEALS) was used to assess electronic health literacy at the 3rd day (T 1), 15th day (T 2), and 30th day (T 3) after PCI. Unplanned readmission within 30 days after discharge was recorded. Latent class growth model (LCGM) was used to identify categories and characteristics of electronic health literacy trajectories. Kaplan-Meier method was applied to plot the cumulative incidence of 30-day unplanned readmission, and the Log-Rank test was used to compare differences among different trajectory types. Results:A total of 207 patients completed the entire survey and follow-up, with a valid response rate of 98.57% (207/210). eHEALS scores gradually increased after PCI, with scores of (6.75±1.31), (11.55±3.31), and (15.56±5.75) at T 1, T 2, and T 3, respectively. Two potential categories were identified: persistent low-level type (85 cases, 41.06%) and gradually improving type (122 cases, 58.94%). Twenty-six patients experienced unplanned readmission within 30 days, with an incidence of 12.56%. The proportions of unplanned readmission within 30 days were 20.00% (17/85) in the persistent low-level group and 7.38% (9/122) in the gradually improving group, with a statistically significant difference (χ 2=7.268, P=0.007). Kaplan-Meier cumulative risk function analysis showed that the cumulative incidence of 30-day unplanned readmission in the gradually improving group was lower than that in the persistent low-level group, with a statistically significant difference (Log-Rank=7.683, P=0.006) . Conclusions:Young and middle-aged CHD patients with DM after PCI show trajectory characteristics in electronic health literacy. Although the electronic health literacy of some patients gradually improved after PCI, persistent low-level literacy was still common, and patients in the persistent low-level group had a higher risk of 30-day unplanned readmission, which deserves clinical attention.