Shah, Jay

Abstract To enhance the prediction of traumatic brain injury (mTBI) outcomes, we propose a deep learning approach that integrates brain computed tomography (CT) scans with corresponding synthetic T1-weighted magnetic resonance imaging (T1-MRI). Our method significantly outperforms the prediction using CT scans alone. TRACK-TBI Pilot dataset, which includes imaging and clinical outcome data from patients with TBI, is studied. The hypothesis is brain CT and T1-MRI complement each other and together will improve TBI prognosis compared to using either CT or T1-MRI alone. Since CT and T1-MRI may not be available for the same individual, we employed a specialized version of a generative adversarial network (GAN), known as fixed-point GAN (FP-GAN). FP-GAN was trained using unpaired CT and T1-MRI scans to generate synthetic T1-MRIs from real CT scans. This process produced pseudo-paired CT-MRI data, which was then used to train a deep learning classifier for outcome prediction. The classifier consists of dual parallel 3D ResNet-18 models, each independently processing T1-MRI and CT scans. We used Glasgow Outcome Scale-Extended (GOSE) scores at 3 months post-TBI as the measure of patient outcomes. To avoid data leakage, the subjects used in FP-GAN and ResNet-18 model have no overlap. We further divided the paired data, allocating 69 samples for 5-fold cross-validation and 17 samples for testing. Prognostic performance was evaluated using the area under the receiver operating characteristic curve (AUC), F1-score (the harmonic mean of precision and recall), sensitivity (true positive rate) and specificity (true negative rate). For binary classification, we defined good recovery as GOSE ≥ 7 (positive) and poor recovery (negative) as 3 ≤ GOSE ≤ 6. Accordingly, our training set consists of 24 subjects with poor recovery and 45 subjects with good recovery, while the testing set includes 5 subjects with poor recovery and 12 subjects with good recovery. A DeLong test on AUC confirms that the improvement from incorporating synthetic T1-MRI (AUC = 0.76 ± 0.10) is statistically significant (P < 0.05) compared to using CT alone (AUC = 0.68 ± 0.13). The significant improvement from using the combination of real CT and synthetic T1-MRI in sensitivity (SEN = 0.95 ± 0.07) and overall performance metrics, such as F1-score (F1 = 0.84 ± 0.03), suggests that the proposed approach provides a robust and effective prognostic approach compared to using CT alone (SEN = 0.83 ± 0.18 and F1 = 0.76 ± 0.07). This pilot research demonstrates the potential of a deep learning-based harmonization model to bridge the gap between CT and T1-MRI in TBI assessment. By integrating synthetic T1-MRI with CT, prediction performance is substantially enhanced.

Background The aim of this study was to examine the potential added value of including neuropsychiatric symptoms (NPS) in machine learning (ML) models, along with demographic features and Alzheimer's disease (AD) biomarkers, to predict decline or non-decline in global and domain-specific cognitive scores among community-dwelling older adults. Objective To evaluate the impact of adding NPS to AD biomarkers on ML model accuracy in predicting cognitive decline among older adults. Methods The study was conducted in the setting of the Mayo Clinic Study of Aging, including participants aged ≥ 50 years with information on demographics (i.e., age, sex, education), NPS (i.e., Neuropsychiatric Inventory Questionnaire; Beck Depression and Anxiety Inventories), at least one AD biomarker (i.e., plasma-, neuroimaging- and/or cerebrospinal fluid [CSF]-derived), and at least 2 repeated neuropsychological assessments. We trained and tested ML models using a stepwise feature addition approach to predict decline versus non-decline in global and domain-specific (i.e., memory, language, visuospatial, and attention/executive function) cognitive scores. Results ML models had better performance when NPS were included along with a) neuroimaging biomarkers for predicting decline in global cognition, as well as language and visuospatial skills; b) plasma-derived biomarkers for predicting decline in visuospatial skills; and c) CSF-derived biomarkers for predicting decline in attention/executive function, language, and memory. Conclusions NPS, added to ML models including demographic and AD biomarker data, improves prediction of downward trajectories in global and domain-specific cognitive scores among community-dwelling older adults, albeit effect sizes are small. These preliminary findings need to be confirmed by future cohort studies.

There is a growing interest in the application of machine learning (ML) in Alzheimer’s disease (AD) research. However, neuropsychiatric symptoms (NPS), frequent in subjects with AD, mild cognitive impairment (MCI), and other related dementias have not been analyzed sufficiently using ML methods. To portray the landscape and potential of ML research in AD and NPS studies, we present a comprehensive literature review of existing ML approaches and commonly studied AD biomarkers. We conducted PubMed searches with keywords related to NPS, AD biomarkers, machine learning, and cognition. We included a total of 38 articles in this review after excluding some irrelevant studies from the search results and including 6 articles based on a snowball search from the bibliography of the relevant studies. We found a limited number of studies focused on NPS with or without AD biomarkers. In contrast, multiple statistical machine learning and deep learning methods have been used to build predictive diagnostic models using commonly known AD biomarkers. These mainly included multiple imaging biomarkers, cognitive scores, and various omics biomarkers. Deep learning approaches that combine these biomarkers or multi-modality datasets typically outperform single-modality datasets. We conclude ML may be leveraged to untangle the complex relationships of NPS and AD biomarkers with cognition. This may potentially help to predict the progression of MCI or dementia and develop more targeted early intervention approaches based on NPS.