Prognostication of chronic disorders of consciousness using resting state fMRI and clinical characteristics
Severe brain injury can lead to disorders of consciousness (DOC). Prognostication is a fundamental concern for DOC patients, as medical treatment and rehabilitation therapy depends on this information. However, despite many efforts, the prediction of outcome for a chronic DOC patient is still challenging and requires more researches. Here, for research purpose only, we present a package "pDOC" to predict more than one year outcome in chronic DOC patients (>1months from time of initial injury). The package "pDOC" includes two prognostic models based on clinical characteristics only and the combination of clinical characteristics and resting state fMRI. The two models can calculate and output a probability of consciousness recovery for individual patient. These models were developed and validated in 112 chronic DOC patients from two medical centers in China. The combination model discriminated between patients who would later recover consciousness and those who would not with an accuracy of around 88% in our datasets. Nonetheless, the models are in the phase of research, and it needs more validation. Here, we provide these prognostic models for informational purposes only. For more information about the development, please see our paper in eLife (https://elifesciences.org/articles/36173).
We disclaim any warranty concerning its accuracy, timeliness, and completeness, and any other warranty, express or implied, including warranties of merchantability or fitness for a particular purpose. For medical treatment or answers to personal questions, we strongly encourage you to consult with a qualified health care provider.
(1) Matlab 2010 or later
(2) SPM8 or later
How to use:
Please refer to the enclosed "How_to_use.docx".