RESUMO
Objective:To construct an automatic recognition system for PD patients with freezing of gait (FOG) based on mobile phone videos by recording the gait videos of PD patients with FOG.Methods:Forty-nine PD patients with FOG, admitted to our hospital from December 2020 to May 2021, were chosen in our study. Their clinical data were collected. The processes of these patients accepted "3-meter-round trip" and "3-meter-round trip through narrow (0.6 m)" were recorded and 87 valid gait videos were extracted. Position signals of key points in the video were extracted, and featured data were extracted after signal preprocessing. From the featured data, action recognition model, straight FOG recognition model and turn FOG recognition model were established respectively, and finally end-to-end FOG recognition model was formed. Leave-one-subject-out (LOSO) method was used to evaluate the performance of the above models.Results:A total of 22 066 non-FOG window samples and 3815 FOG window samples were obtained from 87 valid videos, which constituted the training sample pool of this study. LOSO method showed that the motion recognition model enjoyed 83.27% sensitivity, 91.38% specificity, and 89.28% accuracy; the straight FOG recognition model enjoyed 57.69% sensitivity and 88.12% specificity; the turn FOG recognition model enjoyed 61.54% sensitivity and specificity 98.72%; and the end-to-end FOG recognition model enjoyed 85.71% sensitivity and 75.73% specificity.Conclusion:The automatic recognition system for PD patients with FOG based on mobile phone videos has relatively high sensitivity and specificity, which can realize remote assessment and is convenient for screening and follow-up of PD patients with FOG.
RESUMO
Objective To investigate the incidence and the related factors of the depression in Parkinson's disease. Methods 52 cases with idiopathic Parkinson's disease were included in this study. Such scales as Hamilton depression scale-24 item (HAMD-24), Non Motor Symptoms Scale for Parkinson's disease (NMSS), 39-item Parkinson's Disease Questionnaire (PDQ-39), unified Parkinson's disease rating scale (UPDRS), revised Hoehn-Yahr rating scale (H-Y), revised Schwab and English daily life event scale (S-E), Minimum Mental State Examination (MMSE), etc. were applied and underwent Spearman correlation analysis. Results Thirty-six patients with Parkinson's disease (69.23%) met the criteria for depression. The spearman rank correlation analysis showed that MMSE (r=-0.294, P=0.036) and S-E (r=-0.506, P<0.001) had negative correlation with depression in Parkinson's disease, and the course of the disease (r=0.274, P=0.049), UPDRS (r=0.485, P<0.001), H-Y (r = 0.459, P = 0.001), NMSE (r = 0.729, P < 0.001) and PDQ-39 (r = 0.619, P < 0.001) had positive correlation with depression in Parkinson's disease. Conclusions The patients with Parkinson's disease had high incidence of depression. The depression in Parkinson's disease is associated with many factors and affected the quality of life of the patients.
RESUMO
Objective To evaluate the treatment outcome and prognostic factors in patients with grade Ⅲ/Ⅳ glioma following postoperative chemoradiotherapy.Methods A retrospective analysis was performed on the medical records of 119 patients with grade Ⅲ/Ⅳ glioma who received treatment in our hospital from January 2007 to April 2012.Of the 119 patients,49 received radiotherapy alone,21 received radiotherapy combined with nitrosoureas,and 49 received radiotherapy combined with temozolomide.The Kaplan-Meier method was used to calculate overall survival (OS) rates and recurrence rates.The Cox regression model was used for multivariate prognostic analysis.Results The follow-up rate was 94.1％.Fifty-three patients were followed up for at least 1 year,and 10 for at least 2 years.The overall recurrence rate was 69.7％.The 1-and 2-year OS rates were 44.5％ and 8.4％,respectively.The multivariate analysis showed that age,presence or absence of seizures before surgery,extent of tumor resection,and radiotherapy plus concurrent and adjuvant temozolomide were the main prognostic factors for tumor recurrence (P =0.002,0.005,0.000,and 0.000).The above factors and the pathological grade of tumor were the independent prognostic factors for patients' survival (P =0.006,0.010,0.000,0.000,and 0.001).Conclusions Postoperative radiotherapy plus concurrent and adjuvant temozolomide produce a good clinical effect in patients with grade Ⅲ/Ⅳ glioma.Age of ＜ 60 years,no seizures before surgery,total tumor resection,and pathological grade Ⅲ of tumor are the favorable prognostic factors for the long-term survival in patients with malignant glioma.
