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 enhance the understanding of the diagnosis and individualized treatment of myelodysplastic syndrome/myeloproliferative neoplasms with ring sideroblasts and thrombocytosis (MDS/MPN-RS-T).Methods:A retrospective case series study was conducted. The clinical data, diagnosis and treatment process and prognosis of 4 patients with MDS/MPN-RS-T admitted to Affiliated Hospital of Hebei University from September 2015 to May 2021 were retrospectively analyzed, and the related literature was reviewed.Results:All the 4 patients were male, aged 63 to 75 years. Patients 1 and 2 were classified as revised international prognostic scoring system (IPSS-R) high-risk group, combined with ASXL1 mutation and high risk cytogenetic abnormality. The therapeutic effect of various treatment regimens was poor, and they were converted to acute myeloid leukemia (AML) and then died due to disease progression. Patient 3 was classified as IPSS-R medium-risk group. His main manifestation was myelodysplastic syndrome (MDS) combined with ring sideroblasts in the early stage and was transformed into MDS/MPN-RS-T during the treatment, and JAK2 mutation occurred in the subsequent treatment. After lenalidomide treatment, the patient was removed from blood transfusion and the condition was stable at present. Patient 4 was classified as IPSS-R medium-risk group, and lenalidomide showed significant therapeutic effects and he was in stable condition.Conclusions:Lenalidomide can significantly improve transfusion dependence in patients with MDS/MPN-RS-T, and ASXL1 mutation and high-risk cytogenetic abnormality may be associated with AML transformation.

Objective:To investigate the therapeutic efficacy and prognosis of multiple myeloma (MM) patients with early relapse and the influencing factors of early relapse.Methods:The clinical data of 164 patients with newly diagnosed MM admitted to Affiliated Hospital of Hebei University from January 2018 to January 2021 were retrospectively analyzed, and 53 cases (32.3%) relapsed at the end of the follow-up. According to the recurrence within 12 months or not, the patients were divided into early relapse group and advanced relapse group; the clinical characteristics, overall response rate (ORR) and overall survival (OS) of both groups were compared. Logistic regression was used to analyze if the following indexes including age, gender, albumin, lactate dehydrogenase (LDH), β 2-microglobulin (β 2-MG), hemoglobin, creatinine, serum calcium, bone marrow plasma cell ratio, extramedullary disease, high-risk fluorescent in situ hybridization (FISH) were the influencing factors of the early relapse. Based on 7 published clinical trials, simplified early relapse MM (S-ERMM) scoring system was constructed to subgroup all relapsed patients. The difference in risk stratification between early relapsed patients and advanced relapsed patients was compared. Results:The median follow-up time of 164 newly diagnosed MM patients was 26 months (12-48 months). Among 53 relapsed MM patients, 24 cases had early relapse and 29 cases had advanced relapse. The ORR of patients with early relapse was decreased compared with that of those with advanced relapse [70.8% (17/24) vs. 89.7% (26/29), χ2 = 3.04, P = 0.001]. The median OS of the early relapse group was shorter than that of the advanced relapse group (24 months vs. not reached, P < 0.001). The OS of patient in the early relapse group with the best response ≥ complete remission (CR), ≥ very good partial remission (VGPR) and ≥ partial remission (PR) during initial induction therapy was worse than that of those in the advanced relapse group, and the differences were statistically significant ( P values were 0.008, 0.011, 0.012, respectively). Multivariate Logistic regression analysis showed low albumin (<35 g/L vs. ≥35 g/L: OR = 1.644, 95% CI 1.076-2.511, P = 0.022) and high LDH (< the upper limit of normal value vs. ≥ the upper limit of normal value: OR = 0.998, 95% CI 0.985-1.011, P = 0.030) were independent influencing factors of early relapse. Among 24 early relapse patients, there were 5 cases (20.8%), 13 cases (54.2%), 6 cases (25.0%), respectively in the S-ERMM scoring system low-risk, middle-risk, high-risk groups; among 29 advanced relapse patients, there were 18 cases (62.1%),9 cases (31.0%), 2 cases (6.9%), respectively in the S-ERMM scoring system low-risk, middle-risk, high-risk groups; the difference in risk stratification of the S-ERMM scoring system between the early relapse group and the advanced relapse group was statistically significant ( χ2 = 9.09, P = 0.003). Conclusions:MM patients with early relapse have poor therapeutic efficacy and prognosis. The prognosis is not affected by the depth of remission to first-line therapy. Low albumin and high LDH may be independent risk factors of MM patients with early relapse.

NKX6-2 encodes a transcription factor involving the genesis and development of oligodendrocytes.Mutations in the NKX6-2 gene are related to a severe variant of hypomyelinating leukodystrophy, namely the NKX6-2-related spastic ataxia type 8 (SPAX8). As of March 24, 2020, there are 36 cases of SPAX8 involving 11 mutations of the NKX6-2 gene, which has not been reported in Chinese population.This article for the first time reported a 31-month-old Chinese boy diagnosed as SPAX8 caused by a novel mutation of the NKX6-2 gene at c. 234dup(p.Leu79Alafs*? ) admitted to the Department of Rehabilitation, Guangdong Women and Children Hospital in October 2019 retrospectively.He presented severe global psychomotor delay, spasticity, nystagmus, hearing impairment and trichiasis, ametropia of both eyes, and retinal degeneration of the right eye, which have not been reported in previous cases.His elder sister presented relevant manifestations, but did not perform the genetic testing.Through this case report and literature review, the genotype and phenotype of SPAX8 were expanded.

MicroRNA,a type of small non-coding RNA specialized in regulation of gene expression,extensively participates in biological cell development,differentiation apoptosis and other cellular processes.Studies have shown that microRNA plays vital regulatory roles in epilepsy.Its mechanisms include regulation of inflammatory responses,proliferation of glial cells,the reconstruction of the synaptic contact and pro-apoptotic gene expression.This article reviews the molecular mechanisms of microRNA in regulation of epilepsy and the possible regulatory roles of microRNA in other nervous diseases.