RESUMO
Background and Motivation: Parkinson's disease (PD) is one of the most serious, non-curable, and expensive to treat. Recently, machine learning (ML) has shown to be able to predict cardiovascular/stroke risk in PD patients. The presence of COVID-19 causes the ML systems to become severely non-linear and poses challenges in cardiovascular/stroke risk stratification. Further, due to comorbidity, sample size constraints, and poor scientific and clinical validation techniques, there have been no well-explained ML paradigms. Deep neural networks are powerful learning machines that generalize non-linear conditions. This study presents a novel investigation of deep learning (DL) solutions for CVD/stroke risk prediction in PD patients affected by the COVID-19 framework. Method: The PRISMA search strategy was used for the selection of 292 studies closely associated with the effect of PD on CVD risk in the COVID-19 framework. We study the hypothesis that PD in the presence of COVID-19 can cause more harm to the heart and brain than in non-COVID-19 conditions. COVID-19 lung damage severity can be used as a covariate during DL training model designs. We, therefore, propose a DL model for the estimation of, (i) COVID-19 lesions in computed tomography (CT) scans and (ii) combining the covariates of PD, COVID-19 lesions, office and laboratory arterial atherosclerotic image-based biomarkers, and medicine usage for the PD patients for the design of DL point-based models for CVD/stroke risk stratification. Results: We validated the feasibility of CVD/stroke risk stratification in PD patients in the presence of a COVID-19 environment and this was also verified. DL architectures like long short-term memory (LSTM), and recurrent neural network (RNN) were studied for CVD/stroke risk stratification showing powerful designs. Lastly, we examined the artificial intelligence bias and provided recommendations for early detection of CVD/stroke in PD patients in the presence of COVID-19. Conclusion: The DL is a very powerful tool for predicting CVD/stroke risk in PD patients affected by COVID-19.
RESUMO
A non-invasive method for measurement of the bladder wall nonlinear elastic behavior is presented. The method is based on acoustoelasticity modeling of the elasticity changes in bladder tissue modulus at different volumetric strain levels. At each volume, tissue strain is obtained from the real-time ultrasound images. Using acoustic radiation force, a transient Lamb wave is excited on the bladder wall and instantaneous modulus of shear elasticity is obtained from the 2-D Fourier analysis of the spatial-temporal dispersion maps. Measured elasticity and strain data are then used in an acoustoelasticity formulation to obtain the third order elastic coefficient, referred to as nonlinearity parameter A, and initial resting elasticity µ0. The method was tested in ex vivo porcine bladder samples (N = 9) before and after treatment with formalin. The estimated nonlinearity parameter, A, was significantly higher in the treated samples compared to intact (p < 0.00062). The proposed method was also applied on 16 patients with neurogenic bladders (10 compliant and 6 non-compliant subjects). The estimated nonlinearity parameter A was significantly higher in the non-compliant cases compared to the compliant (p < 0.0293). These preliminary results promise a new method for non-invasive evaluation of the bladder tissue nonlinearity which may serve as a new diagnostic and prognostic biomarker for management of the patients with neurogenic bladders.
Assuntos
Técnicas de Imagem por Elasticidade/métodos , Bexiga Urinaria Neurogênica/diagnóstico , Bexiga Urinaria Neurogênica/patologia , Bexiga Urinária/diagnóstico por imagem , Bexiga Urinária/patologia , Estimulação Acústica/métodos , Estimulação Acústica/veterinária , Animais , Estudos de Casos e Controles , Módulo de Elasticidade , Elasticidade , Técnicas de Imagem por Elasticidade/veterinária , Humanos , Fenômenos Mecânicos , Tamanho do Órgão , Prognóstico , Resistência ao Cisalhamento/fisiologia , Som , Suínos , Ultrassonografia , Bexiga Urinária/fisiologia , Bexiga Urinaria Neurogênica/fisiopatologiaRESUMO
Medical ultrasound scanners use high-energy pulses to probe the human body. The radiation force resulting from the impact of such pulses on an object can vibrate the object, producing a localized high-intensity sound in the audible range. Here, a theoretical model for the audio sound generated by ultrasound scanners is presented. This model describes the temporal and spectral characteristics of the sound. It has been shown that the sound has rich frequency components at the pulse repetition frequency and its harmonics. Experiments have been conducted in a water tank to measure the sound generated by a clinical ultrasound scanner in various operational modes. Results are in general agreement with the theory. It is shown that a typical ultrasound scanner with a typical spatial-peak pulse-average intensity value at 2 MHz may generate a localized sound-pressure level close to 100 dB relative to 20 microPa in the audible (< 20 kHz) range under laboratory conditions. These findings suggest that fetuses may become exposed to a high-intensity audio sound during maternal ultrasound examinations. Therefore, contrary to common beliefs, ultrasound may not be considered a passive tool in fetal imaging.