The full neural circuits of conscious perception remain unknown. Using a visual perception task, we directly recorded a subcortical thalamic awareness potential (TAP). We also developed a unique paradigm to classify perceived versus not perceived stimuli using eye measurements to remove confounding signals related to reporting on conscious experiences. Using fMRI, we discovered three major brain networks driving conscious visual perception independent of report: first, increases in signal detection regions in visual, fusiform cortex, and frontal eye fields; and in arousal/salience networks involving midbrain, thalamus, nucleus accumbens, anterior cingulate, and anterior insula; second, increases in frontoparietal attention and executive control networks and in the cerebellum; finally, decreases in the default mode network. These results were largely maintained after excluding eye movement-based fMRI changes. Our findings provide evidence that the neurophysiology of consciousness is complex even without overt report, involving multiple cortical and subcortical networks overlapping in space and time.

Consciousness is not explained by a single mechanism, rather it involves multiple specialized neural systems overlapping in space and time. We hypothesize that synergistic, large-scale subcortical and cortical attention and signal processing networks encode conscious experiences. To identify brain activity in conscious perception without overt report, we classified visual stimuli as perceived or not using eye measurements. Report-independent event-related potentials and functional magnetic resonance imaging (fMRI) signals both occurred at early times after stimuli. Direct recordings revealed a novel thalamic awareness potential linked to conscious visual perception based on report. fMRI showed thalamic and cortical detection, arousal, attentional salience, task-positive, and default mode networks were involved independent of overt report. These findings identify a specific sequence of neural mechanisms in human conscious visual perception.

Cardiovascular Disease (CVD) remains the leading cause of death, worldwide and in the United States. Approximately 30% of global deaths can be attributed to one form of CVD, including conditions such as heart disease, stroke, heart attack, and arrhythmia. In diagnosing CVD, electrocardiograms (ECG) are commonly used to measure and record the electrical activity of the heart. Their non-invasive, informative, and relatively simple nature allows for rapid deployment. However, because analysis of ECGs depends solely on a physician, ECG analysis becomes subjective, adding a potential layer of error to patient healthcare. Studies indicate that physicians often misread ECGs and disagree with each other's interpretations. In order to develop an accurate and objective method for ECG analysis, this study evaluates various ensemble algorithms to design and create a supervised classification model. Several ensemble models were evaluated to derive one which correctly classifies CVD with sufficiently high accuracy. A boosted decision tree ensemble created to evaluate cardiac condition performs best, with an overall accuracy of 84.6% and an AUC of 0.828.

Parkinson's Disease (PD) is one of the most common neurological disorders, affecting more than ten million people globally. The hallmark symptoms of PD are tremors, limb rigidity, and imbalance. PD shares many of these symptoms with other disorders, making it difficult to diagnose. Furthermore, due to the lack of definitive laboratory tests, PD is poorly diagnosed with subjective examinations such as family history evaluations, resulting in high misdiagnosis rates. Recent research shows that an additional symptom, dysphonia, is uniquely present in over 80% of PD patients. Dysphonia is a speaking disorder caused by involuntary muscle movement and other neurological factors in PD. In this project, that unique symptom. A cross-validated neural network was programmed to deliver rapid and accurate diagnoses using biomedical voice data from 195 patients of varying statuses. This automated, machine-learning based PD diagnostic tool was successfully created and functions with over 95% accuracy. This rate includes nearly zero false negatives and few false positives, showing significant improvement over previous attempts which had misdiagnosis rates of nearly 20%. A low probability of false negatives is favorable. The neural network was designed such that overfitting is avoided, and more features/data would further improve the algorithm's accuracy. An early and accurate diagnosis is critical for treating PD patients, and this project proposes a way to achieve that.

INTRODUCTION: Continuous cardiotocography (CTG) is widely used to monitor fetal heart rate and uterine contractions as a means of detecting intrapartum fetal distress. CTG use is associated with reductions in neonatal seizures and with increases in rates of cesarean sections (C-sections) and instrumental vaginal births. Given that unnecessary C-sections are associated with higher rates of morbidity and mortality, correct identification of C-section candidates is critical. However, agreement in CTG interpretation remains elusive, with high inter-and intra-observer variability in interpretation of tracings, which may lead to inappropriate interventions. Further, machine learning (ML) advances in other vital monitoring analytics have not been matched in CTG analysis. The objective of this study was to develop a cardiotocographic ML algorithm, a random forest (RF) model, which accurately predicts neonatal pathologic disposition to inform obstetric intervention. METHODS: We trained RF models to classify neonatal condition as healthy or pathologic on 13 summary statistics (features) from 1,831 continuous CTGs from the University of Porto SisPorto dataset. All measures of performance were calculated as out-of-bag (OOB), a statistical proxy for cross-validation, over 128 weak learner models. RESULTS: Our model identified healthy CTGs as not requiring obstetric intervention with an OOB sensitivity of 82.4%, a specificity of 99.4%, an accuracy of 97.9%, and a C-statistic of 0.908. CONCLUSION: Our model's OOB performance exceeds that of current methods and could dramatically reduce the rate of cesarean sections if widely implemented. The model is accurate, rapid, readily deployable, and extensible. Further research should test our algorithm on a larger population and in real-time.