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 explore the feasibility of differential diagnosis of Gleason score (GS)(3+4)and (4+3)in prostate cancer (PCa) based on texture parameters of T2 WI and ADC maps.Methods A total of 77 patients with GS 7 points in PCa confirmed by pathology were enrolled in this retrospective study,including 45 GS(3+4)cases and 32 GS(4+3)cases.ROI was manually drew on the largest section of tumor on the axial T2 WI and ADC maps,and five texture parameters were extracted,namely,angular second moment (ASM),contrast, correlation,inverse difference moment and entropy,and the texture parameters between groups were analyzed statistically,then ROC curve was used to evaluate the diagnostic efficiency of texture parameters with statistical differences.Results There was no significant difference in age and prostate specific antigen (PSA)between GS (3 + 4)and GS (4 + 3)groups (P＞0.05).There were significant differences in ASM and entropy between T2 WI and ADC (P＜0.05),but there was no statistical difference in contrast,correlation and inverse difference moment (P＞0.05).Except for the AUC of T2 WIASM,there were statistical differences among T2 WIentropy ,ADCASM and ADCentropy.The AUC of ADCASM and ADCentropy were larger than that of T2 WIASM and T2 WIentropy.The AUC of ADCentropy had the largest AUC (0.732),the cut off value was 5.71 ,with the sensitivity was 97.6% and specificity was 5 9.5%.Conclusion MRI texture analysis can be used to differentiate GS (3 + 4)from GS (4 + 3)in PCa,and the ADCentropy have the best diagnostic efficacy.

Objective To explore the effects of behavioral activation (BA) intervention on patients with chronic obstructive pulmonary disease (COPD) complicated with anxiety and depression. Methods Totally 70 patients with COPD complicated with anxiety and depression who were hospitalized in a ClassⅢ Grade A hospital from August 2018 to April 2019 were selected using convenient sampling and divided into experimental (n=35) and control (n=35) groups according to the time of admission. Patients in the control group received conventional hospital care and psychological guidance in the Department of Respiratory Medicine, while patients in the experimental group received BA intervention on this basis. Anxiety, depression and fatigue scores were compared between the two groups. Results A total of 33 patients in control group and 32 patient in experimental group completed the study. After BA intervention, the anxiety and depression scores of the experimental group were lower than those of the control group, and there were statistically significant differences between the two groups (P＜0.05). The total score of multi-dimensional fatigue scale of COPD patients in the experimental group was lower than that of the control group, the difference was statistically (P＜ 0.05), and there was no statistically significant difference in the score of mental fatigue between the two groups (P＞0.05). Conclusions BA intervention can ameliorate the anxiety and depression in patients and reduce their sense of fatigue, thus improving their quality of life.

Objective To investigate the application value of two kinds of endometrial preparation in patients with thin endometrium of frozen thawed embryo transfer cycle.Methods A retrospective analysis of the clinical data of 82 cycle of 76 patients was carried out.According to the difference of the endometrial preparation,the two groups were divided into two groups.One group was progynova group (42 cycles),and the other group was femonston group (40 cycles).Baseline information,endometrial status and pregnancy outcome were compared between the two groups.Results There was no significant difference in baseline data (age,years of infertility,body mass index,basal hormone level) between the two groups.There was no significant difference in endometrial thickness[progynova group (5.52 ± 0.74) mm,femonston group (5.33 ± 0.66) mm,t =1.290,P =0.203],endometrial volume (progynova grouP ＜ 2mL and ≥ 2mL 38 patients and 4 patients,that of femonston group 36 cases and 4 cases,x2 =0.005,P =0.942),endometrial type (progynova group A,B,C type 35 cases,7 cases,0 case,those of emonston group 34 cases,6 cases,0 case,x2 =0.043,P =0.836) and blood flow (progynova group Ⅰ + Ⅱ and Ⅲ 34 cases and 8 cases,those of femonston group 35 cases and 5 cases,x2 =0.658,.P =0.417) between the two groups before treatment.After administration,endometrial thickness [progynova group (6.90 ± 0.62) mm,femonston group (7.60 ± 0.63) mm,t =5.04,P =0.000],neointimal growth [progynova group (1.67 ± 0.48) mm,femonston group (3.20 ± 0.61) mm,t =12.74,P =0.000],ratio of endometrial volume more than or equal to 2 mL [progynova group 52.38 ％ (22/42),femonston group 80.00％ (32/40),x2 =6.95,P =0.008],and ratio of endometrial blood flow type Ⅲ [progynova group 38.10％ (16/42),femonston group 70.00％ (28/40),x2 =8.387,P =0.004] of femonston group were higher than those of progynova group.The dosage[progynova group (112.43 ± 16.39)mg,femonston group (78.85 ± 10.17)mg,t =11.08,P =0.000] was lower than that of progynova group,and the difference was statistically significant.There was no significant difference in the two groups in endometrial type (progynova group A,B,C 30 cases,12 cases and 0 case,those of femonston group 28,12 and 0,x2 =0.020,P =0.887) after the treatment.There was no significant difference in the number of transplanted embryos (progynova group 1.78 ± 0.47,femonston group 1.77 ± 0.42,t =0.108,P =0.914),high quality embryo rate [progynova group 74.67 ％ (56/75),femonston group 73.24 ％ (52/71),x2 =0.039,P =0.844],implantation rate [progynova group 14.67 ％ (11/75),femonston group 16.90％ (12/71),x2 =0.137,P =0.711],biochemical pregnancy rate[progynova group 38.10％ (16/42),femonston group 40.00％ (16/40),x2 =0.031,P =0.860] and clinical pregnancy rate [progynova group 28.57 ％ (12/42),femonston group 32.50％ (13/40),x2 =0.149,P =0.699] between the two groups.Conclusion Femonston with less dosage,better improvement of the endometrial thickness,endometrial volume,endometrial blood flow of patients with thin endometrium of patients can obtain similar pregnancy outcomes compared with progynova.

OBJECTIVEIn China, the coverage rate of work injury insurance was 23.2%in 2011, which was far lower than expected. The factors affecting the insurance's enrollment has very little known. This paper aims to study the existing coverage of work injury insurance scheme and its influencing factors.

METHODSThe data were collected from 2 836 workers who came from 9 industries in three cities of Zhejiang province using face-to-face questionnaire interview.

RESULTSOf these 2836 workers, the work injury insurance coverage was 50.1%, and 29.6% were not sure if they were covered or not. The results showed that the awareness of occupational disease and industrial injury insurance was helpful in increasing the coverage rate. Besides, the logistic regression analysis showed that in certain circumstances working population shared higher coverage of work injury insurance. For examples, male workers with local household registration and longer working years; people who had been informed about occupational risk factors, and thus gained more training on the issue; people who had exposed to occupational hazards or involved in administrative duties; and people who had already insured by a medical insurance scheme. In the contrary, the heavier family burden with longer working hours per week they needed, the lower possibility they joined the insurance scheme.

CONCLUSIONSThe coverage of work injury insurance is higher than native average level but much lower than the average international level. The awareness of occupational disease and injury insurance was closely associated with the coverage of work injury insurance. Therefore, it is imperative to popularize the knowledge on OHS for migrant workers, as well as to reinforce the supervision and management of the issue would have been an effective way to elevate the coverage rate of work injury insurance.

China ; Cities ; Health Services Needs and Demand ; Humans ; Insurance Coverage ; statistics & numerical data ; Male ; Occupational Diseases ; Surveys and Questionnaires ; Transients and Migrants

OBJECTIVETo investigate workers' willingness to participate and wiliness to pay for a hypothetical industrial injury insurance scheme, to analyze the influential factors, and to provide information for policy making of the government.

METHODSMultistage cluster sampling was used to select subjects: In the first stage, 9 small, medium, orlarge enterprises were selected fromthree cities (counties) in Zhejiang province, China, according to the level of economic development, transportation convenience, and cooperation of government agencies; in the second stage, several workshops were randomly selected from each of the 9 enterprises. Face-to-face interviews among all workers in the workshops were conducted by trained interviewers using a pre-designed questionnaire.

RESULTSIt was found that 73.87% (2095) of all workers were willing to participate in the hypothetical work injury insurance scheme and to pay 2.21% of monthly wage (51.77 yuan) on average, and more than half of the workers were willing to pay less than 1%of monthly wage (35 yuan). Of the 741 workers who were not willing to participate, 327 thought that the premium should be borne by the state or enterprises, instead of individuals, and others were not willing to participate because of low income, unstable job, or poor understanding of the hypothetical industrial injury insurance scheme. Logistic regression analysis showed that workers with higher education levels, longer length of services, longer weekly working time, or more knowledge of occupational diseases showed higher willingness to participate in the scheme; workers who were exposed to physical hazards, had health records, or had participated in the existing medical insurance or industrial injury insurance were more willing to participate. Multiple linear regression analysis showed that with increasing average monthly wage, weekly working time, and self?health evaluation, the proportion of workers with willingness to pay increased; however, with increasing work intensity and awareness of occupational disease, the proportion of workers with willingness to pay decreased. The workers who were not covered by the industrial injury insurance paid more than those covered by the industrial injury insurance.

CONCLUSIONThe hypothetical industrial injury insurance scheme increased the applicability and advantage of independent third-party running and lifetime insurance, which significantly increased the workers' willingness to participate in or to pay for the insurance scheme. Therefore, the industrial injury insurance can be improved in these aspects to promote workers' willingness to participate in and to pay for the insurance scheme. This conclusion provided a reference for the solution of delayed or shirking corporate responsibility for paying the premium.

Accidents, Occupational ; economics ; Attitude to Health ; China ; Cluster Analysis ; Financing, Personal ; Health Policy ; Humans ; Insurance ; Insurance, Health ; economics ; utilization ; Models, Theoretical ; Occupational Diseases ; economics ; Surveys and Questionnaires