[Objective]To construct a prediction model for brucellosis by using a deep neural network algorithm to improve the early detection.[Methods]We collected the clinical data of 202 brucellosis patients and 319 non-brucellosis patients admitted to Hohhot Occupational Disease Prevention and Treatment Hospital in 2023,and analyzed data such as gender,age,blood routine indices and clinical diagnosis.A prediction model for brucellosis was constructed by using a deep neural network algorithm and optimized through 10-fold cross-validation.Performance metrics included sensitivity,false negative rate,specificity,false positive rate,accuracy,positive predictive value,negative predictive value,F1 score,and area under the receiver operating characteristic curve(AUC).The optimal model was interpreted by using SHapley Additive exPlanations(SHAP)to clarify decision-making logic and feature influencing mechanisms.[Results]Data visualization analysis revealed no significant difference between brucellosis and non-brucellosis groups.The optimal model demonstrated good performance:sensitivity(85.3%),specificity(92.1%),accuracy(89.5%),AUC(96.6%),95%CI(0.937,0.977).SHAP analysis identified age,platelet count,mean platelet volume,basophil ratio,red blood cell distribution width,and absolute basophil count as significant predictors of brucellosis.[Conclusions]The deep neural network prediction model constructed in this study has good performance and can provide reliable support for the early diagnosis,prevention and control of brucellosis.Identification of key brucellosis-related influencing features will help further understand the pathogenesis of the disease,and this model holds promise for broad clinical application in the future.

[Objective]To construct a prediction model for brucellosis by using a deep neural network algorithm to improve the early detection.[Methods]We collected the clinical data of 202 brucellosis patients and 319 non-brucellosis patients admitted to Hohhot Occupational Disease Prevention and Treatment Hospital in 2023,and analyzed data such as gender,age,blood routine indices and clinical diagnosis.A prediction model for brucellosis was constructed by using a deep neural network algorithm and optimized through 10-fold cross-validation.Performance metrics included sensitivity,false negative rate,specificity,false positive rate,accuracy,positive predictive value,negative predictive value,F1 score,and area under the receiver operating characteristic curve(AUC).The optimal model was interpreted by using SHapley Additive exPlanations(SHAP)to clarify decision-making logic and feature influencing mechanisms.[Results]Data visualization analysis revealed no significant difference between brucellosis and non-brucellosis groups.The optimal model demonstrated good performance:sensitivity(85.3%),specificity(92.1%),accuracy(89.5%),AUC(96.6%),95%CI(0.937,0.977).SHAP analysis identified age,platelet count,mean platelet volume,basophil ratio,red blood cell distribution width,and absolute basophil count as significant predictors of brucellosis.[Conclusions]The deep neural network prediction model constructed in this study has good performance and can provide reliable support for the early diagnosis,prevention and control of brucellosis.Identification of key brucellosis-related influencing features will help further understand the pathogenesis of the disease,and this model holds promise for broad clinical application in the future.

OBJECTIVE: To explore the genetic basis for a child with multiple malformations. METHODS: A child who had presented at Shanxi Provincial Children's Hospital in February 2021 was selected as the study subject. Clinical data of the patient was collected, and whole exome sequencing (WES) was carried out to screen pathogenic variants associated with the phenotype. Candidate variant was validated by Sanger sequencing of her family members. RESULTS: The child had normal skin, but right ear defect, hemivertebral deformity, ventricular septal defect, arterial duct and patent foramen ovale, and separation of collecting system of the left kidney. Cranial MRI showed irregular enlargement of bilateral ventricles and widening of the distance between the cerebral cortex and temporal meninges. Genetic testing revealed that she has harbored a heterozygous variant of NM_178014.4: c.217A>G (p.Met73Val) in the TUBB gene, which was unreported previously and predicted to be likely pathogenic based on the guidelines from the American College of Medical Genetics and Genomics (ACMG). The child was diagnosed with Complex cortical dysplasia with other brain malformations 6 (CDCBM6). CONCLUSION CDCBM is a rare and serious disease with great genetic heterogeneity, and CDCBM6 caused by mutations of the TUBB gene is even rarer. Above finding has enriched the variant and phenotypic spectrum of the TUBB gene, and provided important reference for summarizing the genotype-phenotype correlation of the CDCBM6.
Humans ; Child ; Female ; Abnormalities, Multiple ; Blood Group Antigens ; Family ; Malformations of Cortical Development/genetics* ; Brain ; Mutation

Objective Midkine ( MK ) and nuclear factor-kappa B ( NF-kB ) play pivotal roles in tumorigenesis, which are considered as promising cancer biomarkers. The efficacy of MK and NF-kB as markers for diagnosis and prediction of synchronous metastasis in papillary thyroid cancer ( PTC ) was the aim of present investigation. Methods Seventy six cases of PTC and seventy cases of multi-nodular goiter ( MNG ) were retrieved. The PTC group was further divided into subgroup 1 (16 cases with synchronous metastasis) and subgroup 2 (60 cases without metastases). A retrospective review of clinical information, radiological examinations,131 I treatments and post-131 I-therapy scans were done. Immunohistochemistry of MK, NF-kB p65, and Ki-67 was performed on paraffin-embedded specimens and results were quantified. Diagnostic values of the parameters were conducted by receiver operating characteristic (ROC) curves. Diagnostic sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were determined. Protein levels of MK and NF-kB p65 were then confirmed by Western blot. Results Immunoreactivities of MK and NF-kB p65, and positive percentage of Ki-67 were significantly higher in PTC group than in MNG group (all P<0. 01). ROC showed good differential diagnostic capabilities of all three parameters with diagnostic accuracies of 82. 192% , 80. 137% , and 84. 091%respectively. Moreover, all three parameters were significantly higher in subgroup 1 than those in subgroup 2 (all P<0. 01). ROC showed good predicting efficacies in synchronous metastasis of all three parameters with diagnostic accuracies of 82. 895% , 80. 263% , and 76. 316% respectively. By one-way analysis of variance, Western blot showed that MK and NF-kB p65 protein levels in lesions from subgroup 1 were significantly higher than those from subgroup 2, both were significantly higher than those in MNG lesions ( P<0. 01). Conclusion MK and NF-kB immunohistochemistry can potentially be used for differential diagnosis between PTC and MNG, and for prediction of synchronous metastases.

Objective To evaluate the curative effects of esophageal voice training on life quality of laryngectomees .Methods Between June 2011 and June 2013 , 46 patients in clinical department who underwent total laryngectomies were trained by esophageal voice rehabilitation successfully .The questionnaires of performance status scale for head and neck cancer patients ( PPS-HN ) and quality of life instruments for cancer patients-head and neck cancer ( PLICP-HN) were answered by them before esophageal voice training and 3 months after successful vocal rehabilitation .Results Total laryngectomy deteriorated the performance status and life quality in laryngectomees , the mean score of PPS-HN scale was (160.76 ±78.05) evidently lower than the standard score of 300,and the difference was statistically significant (t=12.10,P<0.05).After successful esophageal speech training , the mean scores of the laryngectomees were significantly improved both in PPS-HN (217.28 ±57.66) and PLICO-HN(143.09 ±22.16) than before , and the differences were statistically significant(t=6.64,7.62,respectively;P<0.05).Conclusions The performance status and life quality of laryngectomees decline obviously , which can be improved by esophageal voice training .

OBJECTIVETo identify the small supernumerary marker chromosomes (sSMC) and guide the genetic counseling and medical treatment in two patients with Turner syndrome.

METHODSHigh resolution GTG and C banding, SRY amplification by PCR and fluorescence in situ hybridization (FISH) on metaphase chromosomes were performed to the two patients.

RESULTSThe karyotypes of the two patients were 45, X [29]/46,X, +mar[31] and 45,X[71]/46,X, +mar[29] respectively. SRY test indicated SRY-positive for patient 1, whose sSMC was originated from chromosome Y. The karyotype was confirmed as 45,X[29]/46,X,idic(Y)(q10)[31]. ish idic(Y)(q10)(RP11-115H13x2) (SRY+) by FISH. While in patient 2, the sSMC was originated from chromosome X, whose karyotype was determined as 45, X[71]/46,X, r(X)(p11.23q21)[29]. ish r(X) (p11.23q21)(AL591394.11xAC092268.3).

CONCLUSIONUsing cytogenetic and molecular cytogenetic analyses, we have identified the sSMCs in two patients with Turner syndrome, which was helpful to the clinical diagnosis and treatment.

Adolescent ; Child ; Chromosomes, Human, X ; genetics ; Chromosomes, Human, Y ; genetics ; Female ; Genetic Markers ; Humans ; In Situ Hybridization, Fluorescence ; Karyotyping ; Turner Syndrome ; genetics