ABSTRACT
Objective@#To explore the feasibility of constructing a machine learning classification model for unilateral sudden sensorineural hearing loss (SSHL) patients and normal controls based on diffusion tensor imaging.@*Methods@#Prospective collection of 84 patients with untreated SSHL were recruited from the otolaryngology department of the Union Hospital of Tongji Medical College of Huazhong University of Science and Technology between June 2013 to May 2015 as the SSHL group. Meanwhile, a total of 63 healthy volunteers who were no any ear disease history, and the hearing function were confirmed with pure tone audiometry, were collected as the control group. All subjects underwent a brain DTI scan. The data were divided into the training set and validation set according to the ratio of 7 to 3, that was, the training set contained 58 cases of SSHL patients and 44 control groups, and the validation set included 26 cases of SSHL patients and 19 control groups. A vector which included the DTI parameters such as fractional anisotropy, mean diffusivity, axial diffusivity and radial diffusivity was constructed with the software R. The LASSO regression of machine learning method was used to perform feature dimensionality reduction and construct a classification model. The training set samples were used to map the nomogram based on the multivariate logistic analysis method, the validation set and the AUC were used to evaluate the prediction ability of the nomogram, and the calibration curve was used to evaluate the model.@*Results@#From the 200 feature vectors including the fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), and radial diffusivity (RD) values of each brain region, after each dimension reduction process, a total of six features were retained, which were the MD of left superior corona radiate and right superior fronto-occipital fasciculus, the AD of the body of corpus callosum, and the RD of left inferior cerebellar peduncle, left superior corona radiate and right posterior limb of internal capsule. The six features of patients with unilateral SSHL were higher than the control group, and the difference was statistically significant (P<0.05). Based on this, a two-class model is constructed and a nomogram is drawn. The sensitivity, specificity, accuracy and AUC of the training set were 93.1% (54/58), 72.7% (32/44), 84.3% (86/102) and 0.854, respectively; the sensitivity, specificity, accuracy and AUC of validation set were 80.8% (21/26), 84.2% (16/19), 82.2% (37/45), 0.870, respectively. Nomogram could significantly improve the classification efficiency of the control group and patients, and the model with the LASSO method showed a higher prediction curve than other models.@*Conclusions@#The machine learning classification model based on DTI metrics can effectively distinguish patients with unilateral sudden sensorineural deafness from healthy control people.
ABSTRACT
Objective To compare the differences in radiation doses from CT scanning between children of different age groups and adult patients by using both traditional radiation dose assessment parameters and size-specific dose estimates (SSDE).Methods A total of 406 patients undergoing lung CT examination were studied.They were sampled retrospectively and continuously from the Union Hospital and divided into six groups by age distritution (0-2,3-6,7-10,11-14,15-18,＞18 years old).The CTDIvol and DLP values were randomly sampled using MATLAB platform-based dicom data software.The SSDE and water equivalent diameter were also calculated according to the AAPM 220 Report.The differences in radiation doses from lung CT scaning between children and adult patients were analysed.Results The CTDIvol values for all age groups were significantly lower than the SSDE values.The differences were statistically significant (t =-36.36,-32.83,-30.36,-28.74,-23.89,P＜0.05).The SSDE values were 137％,94％,79％,57％ and 42％ higher than the CTDIvol values,respectively.The CTDIvol values for the adult group were also lower than the SSDE values,and the difference was statistically significant (t=-21.92,P＜0.05),and the SSDE value was about 41％ higher than the CTDIvol value.With the increased age,CTDIvol value,DLP value,Dw value and SSDE value for children of all age groups gradually increased and were significantly smaller than those for the adult group.The difference was statistically significant (F=63.39,203.28,89.27,103.44,P＜0.05).The conversion coefficient f for all age groups decreased significantly with age,which was significantly higher than that for the adult group,and the difference was statistically significant (F =109.83,P ＜ 0.05).Conclusions In lung CT scanning,the CTDIvol value significantly underestimated the radiation doses to children as compared to adults.CTDIvol values are more easily underestimated for younger patients.The SSDE method allows for more accurate reflection of the radiation doses to different patients,taking into account differences in the examined patient size.
ABSTRACT
Objective To explore the feasibility of constructing a machine learning classification model for unilateral sudden sensorineural hearing loss (SSHL) patients and normal controls based on diffusion tensor imaging. Methods Prospective collection of 84 patients with untreated SSHL were recruited from the otolaryngology department of the Union Hospital of Tongji Medical College of Huazhong University of Science and Technology between June 2013 to May 2015 as the SSHL group. Meanwhile, a total of 63 healthy volunteers who were no any ear disease history, and the hearing function were confirmed with pure tone audiometry, were collected as the control group. All subjects underwent a brain DTI scan. The data were divided into the training set and validation set according to the ratio of 7 to 3, that was, the training set contained 58 cases of SSHL patients and 44 control groups, and the validation set included 26 cases of SSHL patients and 19 control groups. A vector which included the DTI parameters such as fractional anisotropy, mean diffusivity, axial diffusivity and radial diffusivity was constructed with the software R. The LASSO regression of machine learning method was used to perform feature dimensionality reduction and construct a classification model. The training set samples were used to map the nomogram based on the multivariate logistic analysis method, the validation set and the AUC were used to evaluate the prediction ability of the nomogram, and the calibration curve was used to evaluate the model. Results From the 200 feature vectors including the fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), and radial diffusivity (RD) values of each brain region, after each dimension reduction process, a total of six features were retained, which were the MD of left superior corona radiate and right superior fronto-occipital fasciculus, the AD of the body of corpus callosum, and the RD of left inferior cerebellar peduncle, left superior corona radiate and right posterior limb of internal capsule. The six features of patients with unilateral SSHL were higher than the control group, and the difference was statistically significant (P<0.05). Based on this, a two-class model is constructed and a nomogram is drawn. The sensitivity, specificity, accuracy and AUC of the training set were 93.1% (54/58), 72.7% (32/44), 84.3% (86/102) and 0.854, respectively; the sensitivity, specificity, accuracy and AUC of validation set were 80.8% (21/26), 84.2% (16/19), 82.2% (37/45), 0.870, respectively. Nomogram could significantly improve the classification efficiency of the control group and patients, and the model with the LASSO method showed a higher prediction curve than other models. Conclusions The machine learning classification model based on DTI metrics can effectively distinguish patients with unilateral sudden sensorineural deafness from healthy control people.
ABSTRACT
Objective To investigate the influence of Zhuanggu granule on the concentration of IL-1β and TN-F-α in knee cavity of patients with knee degenerated osteoarthritis. Methods A total of eighty patients with knee degenerated osteoarthritis were recruited into a Zhuanggu granule group (30 cases), a Sulphuric acid Glucosamine group (15 cases) and a Sodium Hyaluronate group (15 cases) according to Doll grouping method. After all groups were treated for 4 weeks, the changes of concentration of IL-1β and TNF-α was detected before and after the therapy Results After the treatment, the concentration of IL-1β and TNF-α in Zhuangu granule group was significantly lower than the other two groups (Sodium Hyaluronate and sulphuric Glucosamine group). Conclusion Zhuangu Granule could influence the concentration of IL-1β and TNF-α in patients of knee degenerated osteoarthritis.