Diagnostic Accuracy of Parkinson Disease by Support Vector Machine (SVM) Analysis of I-123-FP-CIT Brain SPECT Data

作者：Palumbo Barbara^*; Fravolini Mario Luca; Buresta Tommaso; Pompili Filippo; Forini Nevio; Nigro Pasquale; Calabresi Paolo; Tambasco Nicola

来源：Medicine, 2014, 93(27): e228.

DOI：10.1097/MD.0000000000000228

Brain single-photon-emission-computerized tomography (SPECT) with I-123-ioflupane (I-123-FP-CIT) is useful to diagnose Parkinson disease (PD). To investigate the diagnostic performance of I-123-FP-CIT brain SPECT with semiquantitative analysis by Basal Ganglia V2 software (BasGan), we evaluated semiquantitative data of patients with suspect of PD by a support vector machine classifier (SVM), a powerful supervised classification algorithm. %26lt;br%26gt;I-123-FP-CIT SPECT with BasGan analysis was performed in 90 patients with suspect of PD showing mild symptoms (bradykinesia-rigidity and mild tremor). PD was confirmed in 56 patients, 34 resulted non-PD (essential tremor and drug-induced Parkinsonism). A clinical follow-up of at least 6 months confirmed diagnosis. To investigate BasGan diagnostic performance we trained SVM classification models featuring different descriptors using both a %26quot;leave-one-out%26apos;%26apos; and a %26quot;five-fold%26apos;%26apos; method. In the first study we used as class descriptors the semiquantitative radiopharmaceutical uptake values in the left (L) and right (R) putamen (P) and in the L and R caudate nucleus (C) for a total of 4 descriptors (CL, CR, PL, PR). In the second study each patient was described only by CL and CR, while in the third by PL and PR descriptors. Age was added as a further descriptor to evaluate its influence in the classification performance. %26lt;br%26gt;I-123-FP-CIT SPECT with BasGan analysis reached a classification performance higher than 73.9% in all the models. Considering the %26quot;Leave-one-out%26apos;%26apos; method, PL and PR were better predictors (accuracy of 91% for all patients) than CL and CR descriptors; using PL, PR, CL, and CR diagnostic accuracy was similar to that of PL and PR descriptors in the different groups. Adding age as a further descriptor accuracy improved in all the models. The best results were obtained by using all the 5 descriptors both in PD and non-PD subjects (CR and CL+PR and PL+age = 96.4% and 94.1%, respectively). Similar results were observed for the %26quot;five-fold%26apos;%26apos; method. %26lt;br%26gt;I-123-FP-CIT SPECT with BasGan analysis using SVM classifier was able to diagnose PD. Putamen was the most discriminative descriptor for PD and the patient age influenced the classification accuracy.

• 出版日期2014-12
• 单位Perugia