Convolutional neural networks can detect orthostatic hypotension in Parkinson's disease using resting-state functional near-infrared spectroscopy data.

Neurological disorders such as Parkinson's disease (PD) often adversely affect the vascular system, leading to alterations in blood flow patterns. Functional near-infrared spectroscopy (fNIRS) is used to monitor hemodynamic changes via signal measurement. This study investigated the potential of using resting-state fNIRS data through a convolutional neural network (CNN) to evaluate PD with orthostatic hypotension. The CNN demonstrated significant efficacy in analyzing fNIRS data, and it outperformed the other machine learning methods. The results indicate that judicious input data selection can enhance accuracy by over 85%, while including the correlation matrix as an input further improves the accuracy to more than 90%. This study underscores the promising role of CNN-based fNIRS data analysis in the diagnosis and management of the PD. This approach enhances diagnostic accuracy, particularly in resting-state conditions, and can reduce the discomfort and risks associated with current diagnostic methods, such as the head-up tilt test.

Regional analysis of cerebral hemodynamic changes during the head-up tilt test in Parkinson's disease patients with orthostatic intolerance.

Significance: Cerebral oxygenation changes in the superior, middle, and medial gyri were used to elucidate spatial impairments of autonomic hemodynamic recovery during the head-up tilt table test (HUTT) in Parkinson's disease (PD) patients with orthostatic intolerance (OI) symptoms. Aim: To analyze dynamic oxygenation changes during the HUTT and classify PD patients with OI symptoms using clinical and oxygenation features. Approach: Thirty-nine PD patients with OI symptoms [10: orthostatic hypotension (PD-OH); 29: normal HUTT results (PD-NOR)] and seven healthy controls (HCs) were recruited. Prefrontal oxyhemoglobin (HbO) changes during the HUTT were reconstructed with diffuse optical tomography and segmented using the automated anatomical labeling system. Decision trees were used for classification. Results: HCs and PD-NOR patients with positive rates of HbO change (PD-POS) showed the greatest HbO recovery in the superior frontal gyrus (SFG) during tilt. PD-OH and PD-NOR patients with negative rates of HbO change (PD-NEG) showed asymmetric reoxygenation. The classification accuracy was 89.4% for PD-POS versus PD-NEG, 71% for PD-NOR versus PD-OH, and 55.8% for PD-POS versus PD-NEG versus PD-OH. The oxygenation features were more discriminative than the clinical features. Conclusions: PD-OH showed decreased right SFG function, which may be associated with impaired compensatory autonomic responses to orthostatic stress.

Cerebral hemodynamic monitoring of Parkinson's disease patients with orthostatic intolerance during head-up tilt test.

Significance: Monitoring of cerebral perfusion rather than blood pressure changes during a head-up tilt test (HUTT) is proposed to understand the pathophysiological effect of orthostatic intolerance (OI), including orthostatic hypotension (OH), in Parkinson's disease (PD) patients. Aim: We aim to characterize and distinguish the cerebral perfusion response to a HUTT for healthy controls (HCs) and PD patients with OI symptoms. Approach: Thirty-nine PD patients with OI symptoms [10 PD patients with OH (PD-OH) and 29 PD patients with normal HUTT results (PD-NOR)], along with seven HCs participated. A 108-channel diffuse optical tomography (DOT) system was used to reconstruct prefrontal oxyhemoglobin (HbO), deoxyhemoglobin (Hb), and total hemoglobin (HbT) changes during dynamic tilt (from supine to 70-deg tilt) and static tilt (remained tilted at 70 deg). Results: HCs showed rapid recovery of cerebral perfusion in the early stages of static tilt. PD-OH patients showed decreasing HbO and HbT during dynamic tilt, continuing into the static tilt period. The rate of HbO change from dynamic tilt to static tilt is the distinguishing feature between HCs and PD-OH patients. Accordingly, PD-NOR patients were subgrouped based on positive-rate and negative-rate of HbO change. PD patients with a negative rate of HbO change were more likely to report severe OI symptoms in the COMPASS questionnaire. Conclusions: Our findings showcase the usability of DOT for sensitive detection and quantification of autonomic dysfunction in PD patients with OI symptoms, even those with normal HUTT results.

Simultaneous blood flow and blood oxygenation measurements using a combination of diffuse speckle contrast analysis and near-infrared spectroscopy.

A combined diffuse speckle contrast analysis (DSCA)-near-infrared spectroscopy (NIRS) system is proposed to simultaneously measure qualitative blood flow and blood oxygenation changes in human tissue. The system employs an optical switch to alternate two laser sources at two different wavelengths and a CCD camera to capture the speckle image. Therefore, an optical density can be measured from two wavelengths for NIRS measurements and a speckle contrast can be calculated for DSCA measurements. In order to validate the system, a flow phantom test and an arm occlusion protocol for arterial and venous occlusion were performed. Shorter exposure times (<1 ms ) show a higher drop (between 50% and 66%) and recovery of 1/K²S values after occlusion (approximately 150%), but longer exposure time (3 ms) shows more consistent hemodynamic changes. For four subjects, the 1/K²S values dropped to an average of 82.1±4.0% during the occlusion period and the average recovery of 1/K²S values after occlusion was 109.1±0.8% . There was also an approximately equivalent amplitude change in oxyhemoglobin (OHb) and deoxyhemoglobin (RHb) during arterial occlusion (max RHb=0.0085±0.0024 mM/DPF, min OHb=-0.0057±0.0044 mM/DPF). The sensitivity of the system makes it a suitable modality to observe qualitative hemodynamic trends during induced physiological changes.

A discrepancy of penile hemodynamics during visual sexual stimulation observed by near-infrared spectroscopy.

BACKGROUND: In this paper, we observed a discrepancy of penile hemodynamics dependent on location by using near infrared spectroscopy (NIRS) sensor, and showcase NIRS as a potentially suitable sensor in supplementing the diagnosis and treatment of erectile dysfunction. METHODS: To observe the effect that location has on penile hemodynamics, the NIRS sensor was placed on the top and the side of genital organ, and oxy- (HbO), deoxy-(RHb), and total (HbT) hemoglobin concentration changes were acquired. Our results from 6 healthy subjects show that hemodynamic changes vary depending on where the probe was placed. To observe a statistical difference between the signals, a Wilcoxon signed-rank test was performed. RESULTS: The result shows a significant difference (p < 0.05) between concentration changes of RHb and HbT depending on the probes' location. Moreover, the sensor placed on the top of the organ shows a rise of HbO and HbT concentration while RHb concentration decreased. However, hemodynamics from the side of the organ showed that RHb concentration increased along with HbO. CONCLUSIONS: The outcomes demonstrates an ability of NIRS to be sensitive enough to detect the different hemodynamic changes in various locations of a healthy male genital organ during visual sexual stimulation. The results also show the importance of sensor location on the genital organ for the resulting hemodynamic changes. We can foresee our results as a way for clinicians to obtain more accurate hemodynamic measurements from the penis, and also show the likelihood for NIRS enhanced diagnosis tool of male erectile dysfunction over the current standards.