Contributions
Abstract: P487
Type: Poster
Abstract Category: Pathology and pathogenesis of MS - Imaging
Objective: The goal of this study was to develop a model that integrates imaging and clinical information observed at lesion incidence for predicting the recovery of white matter lesions in multiple sclerosis (MS) patients.
Methods: Demographic, clinical, and magnetic resonance imaging (MRI) data were obtained from 32 subjects with MS participating in research studies at the National Institutes of Health. A total of 401 lesions met the inclusion criteria and were used in the study. Imaging features were extracted from intensity-normalized T1-weighted (T1w) and T2-weighted as well as magnetization transfer ratio (MTR) sequences acquired at lesion incidence. T1w and MTR signatures were also extracted from images acquired 1-year post-incidence. Imaging features were integrated with clinical and demographic data observed at lesion incidence to create statistical prediction models for long-term damage in each lesion.
Validation: The performance of the T1w and MTR predictions was assessed in two ways: first, the predictive accuracy was measured quantitatively using leave-one-lesion-out cross-validated (CV) mean-squared predictive error. Then, to assess the prediction performance from the perspective of a clinical expert, three board-certified MS clinicians were asked to individually score how similar the CV model-predicted 1-year appearance was to the true 1-year appearance for a random sample of 100 lesions.
Results: The cross-validated root-mean-square predictive error was 0.95 standard-deviation units for normalized T1w and 0.064 for MTR, compared to the estimated measurement errors of 0.48 and 0.078 respectively. The three expert raters agreed that T1w and MTR predictions closely resembled the true 1-year follow-up appearance of the lesions in both degree and pattern of recovery within lesions.
Conclusion: This study demonstrates that using only information from a single visit at incidence, an accurate prediction of how a new lesion will recover can be obtained using relatively simple statistical techniques. The potential to visualize the likely course of recovery has implications for clinical decision-making, as well as trial enrichment.
Disclosure:
Jordan D. Dworkin: nothing to disclose
Elizabeth M. Sweeney: nothing to disclose
Matthew K. Schindler: nothing to disclose
Salim Chahin: nothing to disclose
Daniel S. Reich: nothing to disclose
Russell T. Shinohara: nothing to disclose
Abstract: P487
Type: Poster
Abstract Category: Pathology and pathogenesis of MS - Imaging
Objective: The goal of this study was to develop a model that integrates imaging and clinical information observed at lesion incidence for predicting the recovery of white matter lesions in multiple sclerosis (MS) patients.
Methods: Demographic, clinical, and magnetic resonance imaging (MRI) data were obtained from 32 subjects with MS participating in research studies at the National Institutes of Health. A total of 401 lesions met the inclusion criteria and were used in the study. Imaging features were extracted from intensity-normalized T1-weighted (T1w) and T2-weighted as well as magnetization transfer ratio (MTR) sequences acquired at lesion incidence. T1w and MTR signatures were also extracted from images acquired 1-year post-incidence. Imaging features were integrated with clinical and demographic data observed at lesion incidence to create statistical prediction models for long-term damage in each lesion.
Validation: The performance of the T1w and MTR predictions was assessed in two ways: first, the predictive accuracy was measured quantitatively using leave-one-lesion-out cross-validated (CV) mean-squared predictive error. Then, to assess the prediction performance from the perspective of a clinical expert, three board-certified MS clinicians were asked to individually score how similar the CV model-predicted 1-year appearance was to the true 1-year appearance for a random sample of 100 lesions.
Results: The cross-validated root-mean-square predictive error was 0.95 standard-deviation units for normalized T1w and 0.064 for MTR, compared to the estimated measurement errors of 0.48 and 0.078 respectively. The three expert raters agreed that T1w and MTR predictions closely resembled the true 1-year follow-up appearance of the lesions in both degree and pattern of recovery within lesions.
Conclusion: This study demonstrates that using only information from a single visit at incidence, an accurate prediction of how a new lesion will recover can be obtained using relatively simple statistical techniques. The potential to visualize the likely course of recovery has implications for clinical decision-making, as well as trial enrichment.
Disclosure:
Jordan D. Dworkin: nothing to disclose
Elizabeth M. Sweeney: nothing to disclose
Matthew K. Schindler: nothing to disclose
Salim Chahin: nothing to disclose
Daniel S. Reich: nothing to disclose
Russell T. Shinohara: nothing to disclose