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.

The intervention and prevention of perioperative hypothermia is not only reflected in the technical level, but also reveals the important role of humanistic care in the whole intervention work. If perioperative patients have hypothermia, it is likely to cause a series of complications such as postoperative shivering, which seriously threatens the life safety of patients. Prevention and intervention was based on a comprehensive understanding of the causes and hazards of hypothermia, especially the impact on the lives of the elderly. Effective supervision was implemented in the whole process of operation, such as dynamic monitoring of vital signs including body temperature, followed by room temperature regulation, body temperature protection and preoperative and postoperative psychological nursing. At this time, the sense of responsibility, good humanistic care of medical staff are of positive significance to effectively prevent and reduce the probability of perioperative hypothermia and accelerate the postoperative rehabilitation of patients.

ObjectiveTo determine the therapeutic effect of Gegentang granules on a disease-syndrome mouse model combining human coronavirus 229E （hCoV-229E） pneumonia with Hanshi Yidu Xifei syndrome in vivo. MethodMice were randomly divided into normal group， infection group， cold-dampness group， model group， chloroquine phosphate group （0.18 g·kg^-1）， interferon-α2b （IFN-α2b） group （1.83×10⁶ U·kg^-1）， Gegentang granules high-dose and low-dose groups （6.6， 3.3 g·kg^-1） with 10 mice in each group. Cold-dampness environment and hCoV-229E infection were used for modeling， and the general status and lung index of mice in each group were observed. The viral load in lung tissue was detected by real-time fluorescent quantitative polymerase chain reaction （Real-time PCR）， the pathological changes in lung tissue were evaluated by hematoxylin-eosin （HE） staining， the levels of serum gastrointestinal hormones and inflammatory factors in lung tissue were detected by enzyme-linked immunosorbent assay （ELISA）， and the percentage of peripheral blood lymphocytes was detected by flow cytometry. ResultComparing with model group， Gegentang granules could significantly alleviate the physical signs of Hanshi Yidu Xifei syndrome， including listlessness， weakness of limbs， sticky stool， etc. Comparing with model group， Gegentang granules high-dose group significantly reduced lung index， histopathological score of interstitial lung and bronchus， and the level of serum motilin （P<0.05， P<0.01）， two doses of Gegentang granules could significantly increase the level of serum gastrin （P<0.05， P<0.01）， the percentage of CD4⁺， CD8⁺ T lymphocytes in peripheral blood （P<0.05， P<0.01）， and the level of tumor necrosis factor-α （TNF-α） in lung tissue was significantly decreased （P<0.01）， and the level of interleukin-6 （IL-6） showed decreasing tendency. ConclusionGegentang granules has therapeutic effect on model mice. It can improve the appearance and behavior characterization， regulate the level of gastrointestinal hormones， decrease lung index and histopathological score， and possibly play an immunomodulatory role by inhibiting the expression of inflammatory cytokines in lung tissue and restoring the percentage of peripheral blood lymphocytes.

The intervention and prevention of perioperative hypothermia is not only reflected in the technical level, but also reveals the important role of humanistic care in the whole intervention work. If perioperative patients have hypothermia, it is likely to cause a series of complications such as postoperative shivering, which seriously threatens the life safety of patients. Prevention and intervention was based on a comprehensive understanding of the causes and hazards of hypothermia, especially the impact on the lives of the elderly. Effective supervision was implemented in the whole process of operation, such as dynamic monitoring of vital signs including body temperature, followed by room temperature regulation, body temperature protection and preoperative and postoperative psychological nursing. At this time, the sense of responsibility, good humanistic care of medical staff are of positive significance to effectively prevent and reduce the probability of perioperative hypothermia and accelerate the postoperative rehabilitation of patients.