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 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 understand the disinfectant-resistant genes in the gram-negative bacteria isolated from the dirt retention on air recure filters of air conditioners and observe the drug resistance.METHODS The dirt re-tention samples were collected from the air return filters of air conditioners of some wards in 3 hospitals of Wuhan(Tongji Hospital of Tongji Medical College of Huazhong University of Science and Technology,Wuhan Central Hospital,and Hubei Provincial Maternal and Child Health Hospital)from 2018 to 2024.The gram-negative bac-teria were screened out,the disinfectant-resistant genes in the strains were detected by polymerase chain reaction(PCR),and the results of drug susceptibility test were analyzed.RESULTS Of 354 dirt retention samples that were collected from the air return filers of air conditioners,77 were detected with 138 strains of gram-negative bacteria,87 of which were Acinetobacter baumannii,50 were Enterobacteriaceae,and 1 was Pseudomonas aerug-inosa.The detection rates of qacEΔ1,qacEΔ1-sul1,aceI and qacA/B were 73.19％,82.61％,69.57％and 2.90％,respectively.None of the strains were detected with qacC,qacH or qacJ.The result of drug susceptibility test showed that 76.81％of the gram-negative bacteria were resistant to at least 1 type of antibiotic;93 strains of multidrug-resistant gram-negative bacteria were isolated,most of which were isolated from intensive care unit(ICU).The detection rates of qacEΔ1 and qacEΔ1-sul1 were higher in the drug-resistant strains than those in the non-drug-resistant strains;there were significant differences in the drug resistance rates to carbapenems,quin-olones and β-lactams between the qacEΔ1-sul 1-positive strains and the qacEΔ1-sul1-negative strains(P＜0.05).CONCLUSIONS There are drug-resistant gram-negative bacteria contaminations in some wards of the 3 hospitals in Wuhan.The carrying rates of disinfectant-resistant genes of the strains are high,and the strains show varying degree of resistance to the commonly used antibiotics;the strains carrying the qacEΔ1-sul1 have certain statistical association with the drug resistance.It is suggested that the hospital should take targeted disinfec-tion measures for the environment and reasonably use antibiotics.

OBJECTIVE To understand the disinfectant-resistant genes in the gram-negative bacteria isolated from the dirt retention on air recure filters of air conditioners and observe the drug resistance.METHODS The dirt re-tention samples were collected from the air return filters of air conditioners of some wards in 3 hospitals of Wuhan(Tongji Hospital of Tongji Medical College of Huazhong University of Science and Technology,Wuhan Central Hospital,and Hubei Provincial Maternal and Child Health Hospital)from 2018 to 2024.The gram-negative bac-teria were screened out,the disinfectant-resistant genes in the strains were detected by polymerase chain reaction(PCR),and the results of drug susceptibility test were analyzed.RESULTS Of 354 dirt retention samples that were collected from the air return filers of air conditioners,77 were detected with 138 strains of gram-negative bacteria,87 of which were Acinetobacter baumannii,50 were Enterobacteriaceae,and 1 was Pseudomonas aerug-inosa.The detection rates of qacEΔ1,qacEΔ1-sul1,aceI and qacA/B were 73.19％,82.61％,69.57％and 2.90％,respectively.None of the strains were detected with qacC,qacH or qacJ.The result of drug susceptibility test showed that 76.81％of the gram-negative bacteria were resistant to at least 1 type of antibiotic;93 strains of multidrug-resistant gram-negative bacteria were isolated,most of which were isolated from intensive care unit(ICU).The detection rates of qacEΔ1 and qacEΔ1-sul1 were higher in the drug-resistant strains than those in the non-drug-resistant strains;there were significant differences in the drug resistance rates to carbapenems,quin-olones and β-lactams between the qacEΔ1-sul 1-positive strains and the qacEΔ1-sul1-negative strains(P＜0.05).CONCLUSIONS There are drug-resistant gram-negative bacteria contaminations in some wards of the 3 hospitals in Wuhan.The carrying rates of disinfectant-resistant genes of the strains are high,and the strains show varying degree of resistance to the commonly used antibiotics;the strains carrying the qacEΔ1-sul1 have certain statistical association with the drug resistance.It is suggested that the hospital should take targeted disinfec-tion measures for the environment and reasonably use antibiotics.

Children with cerebral palsy (CP) frequently experience secondary musculoskeletal issues, with a high incidence of fractures and severe symptoms. These factors cannot be overlooked in the rehabilitation process for children with CP. This article examines the causes of fractures in children with CP, including low bone mineral density, abnormal training, premature delivery, and falls. Furthermore, it outlines intervention measures to improve bone mineral density and exercise training, in order to assist in the prevention and treatment of fractures in children with CP.

Medicine, Chinese Traditional ; Drugs, Chinese Herbal ; China