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 characteristics of potential categories of chronic disease co-morbid patients' learned helplessness, and to analyze the differential characteristics of different categories of chronic disease co-morbid patients.Methods:Convenience sampling method was used to select patients with chronic disease co-morbidities who attended The NO.1 People's Hospital of Xiangyang, Hubei University of Medicine, from June to December 2023 as survey respondents. General information questionnaire, Learned Helplessness Scale, Health Questionnaire Somatic Symptom Cluster Scale, Kessler Psychological Distress Scale, and Comprehension Social Support Scale were used for the cross-sectional survey. The potential profile of learned helplessness, and the influencing factors of potential categories of learned helplessness was analyzed.Results:A total of 810 patients with chronic co-morbidities were investigated. There were 453 males and 357 females, aged (65.03±10.89) years old. The learned helplessness of these patients was categorized into three different potential categories, which were named as low-level learned helplessness group, medium-level learned helplessness group, high-level learned helplessness, accounting for 17.5% (142/810), 23.5% (190/810), and 59.0% (478/810), respectively. Compared with the low-level learned helplessness group, the probability of belonging to the medium-level learned helplessness group and high-level learned helplessness group was higher for patients with chronic co-morbidities with more severe physical symptoms ( OR=1.456, 1.391, both P<0.01). Compared with the low-level learned helplessness group, the probability of belonging to the medium-level learned helplessness group and high-level learned helplessness group was higher for patients with chronic co-morbidities with more severe the psychological distress ( OR=1.359, 1.917, both P<0.01). Compared with the low-level learned helplessness group, the probability of belonging to the medium-level learned helplessness group and high-level learned helplessness group was higher for patients with chronic co-morbidities with lower levels of social support ( OR=0.928, 0.874, both P<0.01). Compared with the low-level learned helplessness group, patients with a duration of illness >5 years were used as controls, patients with a duration of illness 2-5 years were more likely to belong to the medium-level learned helplessness group and high-level learned helplessness group ( OR=74.586, 62.620, both P<0.01). Compared with the low-level learned helplessness group, patients with neutral personalities were compared, patients with extroverted personalities had a lower probability of belonging to the medium-level learned helplessness group ( OR=0.105, P<0.05), while patients with introverted personalities had a lower probability of belonging to the medium-level learned helplessness group and high-level learned helplessness group ( OR=0.052, 0.046, both P<0.01). Conclusions:Patients with chronic disease co-morbidities have higher levels of learned helplessness during disease treatment and have more distinctive categorical characteristics. Healthcare professionals should adopt targeted nursing interventions according to different categories of chronic disease co-morbid patients to reduce the level of learned helplessness.

Objective:To explore the characteristics of potential categories of chronic disease co-morbid patients' learned helplessness, and to analyze the differential characteristics of different categories of chronic disease co-morbid patients.Methods:Convenience sampling method was used to select patients with chronic disease co-morbidities who attended The NO.1 People's Hospital of Xiangyang, Hubei University of Medicine, from June to December 2023 as survey respondents. General information questionnaire, Learned Helplessness Scale, Health Questionnaire Somatic Symptom Cluster Scale, Kessler Psychological Distress Scale, and Comprehension Social Support Scale were used for the cross-sectional survey. The potential profile of learned helplessness, and the influencing factors of potential categories of learned helplessness was analyzed.Results:A total of 810 patients with chronic co-morbidities were investigated. There were 453 males and 357 females, aged (65.03±10.89) years old. The learned helplessness of these patients was categorized into three different potential categories, which were named as low-level learned helplessness group, medium-level learned helplessness group, high-level learned helplessness, accounting for 17.5% (142/810), 23.5% (190/810), and 59.0% (478/810), respectively. Compared with the low-level learned helplessness group, the probability of belonging to the medium-level learned helplessness group and high-level learned helplessness group was higher for patients with chronic co-morbidities with more severe physical symptoms ( OR=1.456, 1.391, both P<0.01). Compared with the low-level learned helplessness group, the probability of belonging to the medium-level learned helplessness group and high-level learned helplessness group was higher for patients with chronic co-morbidities with more severe the psychological distress ( OR=1.359, 1.917, both P<0.01). Compared with the low-level learned helplessness group, the probability of belonging to the medium-level learned helplessness group and high-level learned helplessness group was higher for patients with chronic co-morbidities with lower levels of social support ( OR=0.928, 0.874, both P<0.01). Compared with the low-level learned helplessness group, patients with a duration of illness >5 years were used as controls, patients with a duration of illness 2-5 years were more likely to belong to the medium-level learned helplessness group and high-level learned helplessness group ( OR=74.586, 62.620, both P<0.01). Compared with the low-level learned helplessness group, patients with neutral personalities were compared, patients with extroverted personalities had a lower probability of belonging to the medium-level learned helplessness group ( OR=0.105, P<0.05), while patients with introverted personalities had a lower probability of belonging to the medium-level learned helplessness group and high-level learned helplessness group ( OR=0.052, 0.046, both P<0.01). Conclusions:Patients with chronic disease co-morbidities have higher levels of learned helplessness during disease treatment and have more distinctive categorical characteristics. Healthcare professionals should adopt targeted nursing interventions according to different categories of chronic disease co-morbid patients to reduce the level of learned helplessness.