Objective To investigate the influencing factors related to the severity of tinnitus with normal hearing and to provide a clinical basis for the treatment of such patients.Methods From November 2019 to May 2020,150 normal hearing patients with tinnitus as their first chief complain in the outpatient clinic of our center were selected.The severity of tinnitus was assessed by the tinnitus handicap inventory(THI),and the quality of sleep and psychological condition were assessed by the Pittsburgh sleep quality index inventory(PSQI)and the anxie-ty and depression scale(HADS).The relationship between tinnitus severity and patients'gender,age,duration of illness,tinnitus side,tinnitus dominant sound frequency,tinnitus dominant sound loudness,sleep quality,anxiety and depression were analyzed using Pearson's method and Logistic multi-factor regression.Results The Pearson correlation analysis suggested that sleep quality(r=0.667,P＜0.001),anxiety status(r=0.603,P＜0.001)and depression status(r=0.593,P＜0.001)were correlated with the THI classification,and patients with poorer sleep quality and higher anxiety and depression scores had more severe tinnitus.Logistic multi-factor regression analysis showed that only sleep quality had a significant effect on THI classification(P＜0.001).Conclusion Sleep quality may be related to the severity of tinnitus patients with normal hearing,and it is important to focus on their sleep sta-tus in the clinical management of such patients.

Objective To explore causal relationship between 25-hydroxyvitamin D[25(OH)D]and ankylosing spondylitis(AS).Methods Genetic data of 25(OH)D and AS were extracted from the genome-wide association study.The causal effect of 25(OH)D on AS was estimated by MR-Egger regression method,weighted median,inverse variance weighted(IVW),simple mode and weighted mode,and sensitivity analysis was conducted for verification.Results The IVW results indicated that there was a causal relationship between 25(OH)D concentration and AS(OR=0.805,95％CI:0.686-0.944,P=0.008),and the maximum likelihood ratio(OR=0.799,95％CI:0.678-0.940,P=0.007)showed consistent results.The IVW results of the reverse Mendelian randomization study showed that there was no causal relationship between the two(OR=1.019,95％CI:0.995-1.043,P=0.110).In addition,MR-Egger intercept,Cochran Q test,"leave-one-out"and MR-PRESSO analysis showed no horizontal pleipotency or heterogeneity.Conclusion There may be a genetic causal relationship between the concentration of 25(OH)D and the onset of AS.AS cannot cause changes in the concentration of 25(OH)D in the body.

Objective:To develop an artificial intelligence (AI)-based platelet review strategy to identify abnormal platelet histograms with no significant difference between initial impedance platelet count (PLT-I) and PLT-F results.Methods:This study included 5 119 routine blood analysis in Nanfang Hospital of Southern Medical University and its Ganzhou branch from July 2023 and March 2024. Specimens exhibiting abnormal platelet histograms and an initial platelet count >40×10?/L underwent review using the fluorescent platelet count (PLT-F) channel. Consistency of the results was defined as a difference between impedance platelet count (PLT-I) and PLT-F less than ±20% of the PLT-F results. A deep learning model was developed using platelet and red blood cell histogram data from a training set of 3 807 specimens. The model′s diagnostic performance was evaluated on an independent external validation set ( n=805) using receiver operating characteristic (ROC) curve analysis. Changes in the number of reviewed samples and sample turnaround time were analyzed to assess its clinical utility. Results:The deep learning model based on platelet and red blood cell histograms achieved an area under the ROC curve (AUC) of 0.854 in the training set. At a cutoff value of 0.1, the sensitivity was 0.954 and specificity was 0.358. The model could reduce review by 16.80% (190/1 131). In the validation set, the AUC was 0.805, with a sensitivity of 0.955 and specificity of 0.307, corresponding to a reduction of 17.41% (47/270) in reviewed specimens.Conclusion:The platelet review prediction model developed based on deep learning technology can efficiently identify samples with consistent results before and after review, reducing unnecessary reviews and shortening specimen testing time, thereby improving the efficiency of platelet test.

Objective To investigate the influencing factors related to the severity of tinnitus with normal hearing and to provide a clinical basis for the treatment of such patients.Methods From November 2019 to May 2020,150 normal hearing patients with tinnitus as their first chief complain in the outpatient clinic of our center were selected.The severity of tinnitus was assessed by the tinnitus handicap inventory(THI),and the quality of sleep and psychological condition were assessed by the Pittsburgh sleep quality index inventory(PSQI)and the anxie-ty and depression scale(HADS).The relationship between tinnitus severity and patients'gender,age,duration of illness,tinnitus side,tinnitus dominant sound frequency,tinnitus dominant sound loudness,sleep quality,anxiety and depression were analyzed using Pearson's method and Logistic multi-factor regression.Results The Pearson correlation analysis suggested that sleep quality(r=0.667,P＜0.001),anxiety status(r=0.603,P＜0.001)and depression status(r=0.593,P＜0.001)were correlated with the THI classification,and patients with poorer sleep quality and higher anxiety and depression scores had more severe tinnitus.Logistic multi-factor regression analysis showed that only sleep quality had a significant effect on THI classification(P＜0.001).Conclusion Sleep quality may be related to the severity of tinnitus patients with normal hearing,and it is important to focus on their sleep sta-tus in the clinical management of such patients.

Objective To explore causal relationship between 25-hydroxyvitamin D[25(OH)D]and ankylosing spondylitis(AS).Methods Genetic data of 25(OH)D and AS were extracted from the genome-wide association study.The causal effect of 25(OH)D on AS was estimated by MR-Egger regression method,weighted median,inverse variance weighted(IVW),simple mode and weighted mode,and sensitivity analysis was conducted for verification.Results The IVW results indicated that there was a causal relationship between 25(OH)D concentration and AS(OR=0.805,95％CI:0.686-0.944,P=0.008),and the maximum likelihood ratio(OR=0.799,95％CI:0.678-0.940,P=0.007)showed consistent results.The IVW results of the reverse Mendelian randomization study showed that there was no causal relationship between the two(OR=1.019,95％CI:0.995-1.043,P=0.110).In addition,MR-Egger intercept,Cochran Q test,"leave-one-out"and MR-PRESSO analysis showed no horizontal pleipotency or heterogeneity.Conclusion There may be a genetic causal relationship between the concentration of 25(OH)D and the onset of AS.AS cannot cause changes in the concentration of 25(OH)D in the body.

Objective:To develop an artificial intelligence (AI)-based platelet review strategy to identify abnormal platelet histograms with no significant difference between initial impedance platelet count (PLT-I) and PLT-F results.Methods:This study included 5 119 routine blood analysis in Nanfang Hospital of Southern Medical University and its Ganzhou branch from July 2023 and March 2024. Specimens exhibiting abnormal platelet histograms and an initial platelet count >40×10?/L underwent review using the fluorescent platelet count (PLT-F) channel. Consistency of the results was defined as a difference between impedance platelet count (PLT-I) and PLT-F less than ±20% of the PLT-F results. A deep learning model was developed using platelet and red blood cell histogram data from a training set of 3 807 specimens. The model′s diagnostic performance was evaluated on an independent external validation set ( n=805) using receiver operating characteristic (ROC) curve analysis. Changes in the number of reviewed samples and sample turnaround time were analyzed to assess its clinical utility. Results:The deep learning model based on platelet and red blood cell histograms achieved an area under the ROC curve (AUC) of 0.854 in the training set. At a cutoff value of 0.1, the sensitivity was 0.954 and specificity was 0.358. The model could reduce review by 16.80% (190/1 131). In the validation set, the AUC was 0.805, with a sensitivity of 0.955 and specificity of 0.307, corresponding to a reduction of 17.41% (47/270) in reviewed specimens.Conclusion:The platelet review prediction model developed based on deep learning technology can efficiently identify samples with consistent results before and after review, reducing unnecessary reviews and shortening specimen testing time, thereby improving the efficiency of platelet test.

Objective:To investigate the clinical features, diagnostic methods and treatments of left ventricular apical fibroma.Methods:The clinical manifestations, ECG, imaging features and treatment plans of 2 patients with giant fibroma of left ventricular apex diagnosed in September 2020 and May 2022 were analyzed retrospectively, and the related literature was reviewed.Results:Both patients had slight chest distress and discomfort after activities. The ECG showed T-wave inversion of different degrees, which were misdiagnosed as “myocarditis” and “coronary heart disease” respectively. The cardiac magnetic resonance imaging and echocardiography showed left ventricular apical mass. Coronary artery stenosis was not found in coronary angiography. One patient required conservative treatment, and there was no significant change in clinical symptoms and tumor size in the follow-up for half a year; Another patient underwent cardiac mass removal, and the pathological examination after operation confirmed that it was cardiac fibroma, and there was no recurrence in the follow-up 2 years.Conclusion:Fibroma of left ventricular apex is a rare cardiac tumor, which is easy to be missed and misdiagnosed, and is one of the rare causes of T-wave inversion. Cardiac magnetic resonance imaging, CT and echocardiography are commonly used imaging methods to diagnose cardiac fibroma, and surgical resection is an effective treatment.

Objective:To explore the influence factors of neurodevelopmental disorders in children with SCN8A-related early-onset epilepsy through analyzing their clinical characteristics and following up their neurodeve-lopmental status. Methods:A retrospective analysis was carried out on 21 children (13 males and 8 females, the age ranged from 4 months to 8 years, average 31.6 months)with SCN8A-related early-onset epilepsy treated in Guangzhou Women and Children′s Medical Center and Kunming Children′s Hospital between January 2017 and February 2021.All patients underwent whole-exome sequencing and Sanger sequencing.The pathogenicity was estimated according to the American College of Medical Genetics and Genomics guidelines.The clinical data of all patients were also collected, including the age of onset of the disease, forms of seizures, seizure frequency, neurological development at onset, electroencephalogram (EEG) and brain magnetic resonance imaging (MRI). Besides, the patients were followed up to acquire the effect of sodium channel blockers after the onset of seizures, the process or improvement of neurodeve-lopment, EEG evaluation and neurodevelopmental outcomes.Patients were grouped based on data analysis results.The Fisher′s exact test was conducted to measure the effect of various factors on the neurodevelopmental process and outcome, and corresponding coe-fficients were calculated. Results:The average onset age of 21 patients was 0-9 months.The follow-up duration was 4 months-8 years.Three cases died.Sixteen cases (76.2%) had early infantile epileptic encephalopathy (EIEE), 5 cases (23.8%) had epilepsy without encephalopathy, and 1 case had benign infantile epilepsy.Fourteen cases (66.7%) belonged to drug resistant epilepsy.Only one child showed normal neurodevelopment.Eleven children showed delayed neurodevelopment, but improvement was observed.Nine children were retrogressed and stagnated in terms of neurodevelopment.Small age at onset ( Fisher=9.517, P=0.020, r=0.571), high seizure frequency ( Fisher=10.512, P=0.003, r=0.572), EEG background ( Fisher=10.512, P=0.003, r=0.572), epileptic discharges ( Fisher=8.288, P=0.008, r=0.542), and EEG changes before and after treatment ( Fisher=10.437, P=0.009, r=0.586) were important factors affecting the neurodevelopmental process.Neurodevelopmental outcome was normal in only 1 case, 1 child belonged to mild mental retardation (MR), 7 children belonged to moderate MR, 3 children belonged to severe MR, and 9 children belonged to profound MR.Statistical analysis indicated that the clinical phenotype ( Fisher=10.059, P=0.004, r=0.739) and drug resistance ( Fisher=13.706, P=0.001, r=0.640) were significantly correlated with neurodevelopmental outcomes.However, the forms of seizures, EEG findings at onset and mutation sites were not related to neurodevelopmental disorders. Conclusions:Most children with SCN8A-related early-onset epilepsy are accompanied with neurodevelopmental retardation of varying degrees.Epileptic encephalopathy and poor response to drug treatment will lead to severe neurodevelopmental disorders.

Objective:To explore the effect of well-being therapy on fatigue and self-management efficacy of leukemia patients undergoing chemotherapy.Methods:From January 2018 to December 2019, totally 76 leukemia patients who undergoing chemotherapy were divided into experimental group and control group according to the enrolled time, with 38 cases in each group. Patients in the control group recieved routine nursing, the experimental group carried out well-being therapy. Before and after intervention, the effects were assessed by Cancer fatigue scale-Chinses version (CFS-C) and Strategies used by people to promote health-Chinses version (SUPPH-C), respectively.Results:After intervention, the physical fatigue, affective fatigue, cognitive fatigue, and total fatigue scores in CFS-C were 7.64±3.63, 7.28±1.60, 5.19±1.24 and 20.11±3.96 in the experimental group, significantly lower than those in the control group (9.57±3.52, 8.76±2.60, 6.08±1.62 and 24.41±3.86); the positive coping, stress reduction, making decisions, and total scores in SUPPH-C were 57.56±9.72, 40.11±5.99, 12.17±1.95 and 109.83±11.69 in the experimental group, significantly higher than in the control group (50.54±10.80, 36.70±7.62, 10.86±2.10 and 98.11±14.13), the difference was statistically significant ( t value was 2.119-3.856, P<0.05). Conclusion:Well-being therapy can effectively allivate cancer fatigue and promote self-management efficacy of leukemia patients undergoing chemotherapy.

Objective:To explore the accuracy and clinical application value of a Multi-Agent Reinforcement Learning framework (MARL framework) in three-dimensional ultrasound to automatically locate the coronal plane of the uterus.Methods:A total of 144 female patients who underwent routine gynecological examinations in Luohu People′s Hospital during May 2020 were selected as the experimental subjects. The three-dimensional volume data of the uterus of all the experimental subjects were collected by using the Resona-8 high-end color Doppler ultrasound system. A sonographer with more than 5 years of clinical experience manually locate the coronal plane of the uterus in all collected data, and at the same time automatically locate the coronal plane of the uterus MARL framework. The coronal plane images of the uterus obtained by the two methods were saved, and the operation time of the two methods was recorded. The coronal plane uterine images obtained by the two methods were mixed together, and the images were scored 0-1 by two senior ultrasound experts in a double-blind manner. The average score greater than or equal to 0.6 points was considered qualified.Results:①In 144 volunteers, among the coronal planes of the uterus located by the two methods, 131 were qualified by the manual method, and 137 were qualified by the automatic method.There was no statistical difference between the manual and automatic coronal plane images of the uterus (χ 2=1.934, P=0.164) by the chi-square test. ②Using interquartile range analysis, the median and interquartile range of the image score of the automatic group was 0.80(0.75, 0.90), while the median and interquartile range of the image score of the manual group was 0.80(0.75, 0.90). The Wilcoxon signed rank test was used to analyze the quality of the coronal plane images obtained by manual and automatic methods, and the difference was not statistically significant ( Z=1.241, P=0.215). ③The paired t test was used to compare the time required to locate the coronal surface of the uterus, by manual method (63.65±10.182)s, by automatic method (3.25±0.294)s, the difference between the two methods was statistically significant ( t=19.52, P<0.001). Conclusions:The method based on MARL framework has a high correlation with the manual locating of the coronal plane of uterus in three-dimensional ultrasound, and greatly reduces the operation time. It can be effectively applied in clinical practice and lays a foundation for the automatic diagnosis of uterine related diseases.