More Like this

1. Deep neural networks for wearable sensor-based activity recognition in Parkinson’s disease: investigating generalizability and model complexity

   https://doi.org/10.1186/s12938-024-01214-2  

   Davidashvilly, Shelly; Cardei, Maria; Hssayeni, Murtadha; Chi, Christopher; Ghoraani, Behnaz (February 2024, BioMedical Engineering OnLine)

   Abstract BackgroundThe research gap addressed in this study is the applicability of deep neural network (NN) models on wearable sensor data to recognize different activities performed by patients with Parkinson’s Disease (PwPD) and the generalizability of these models to PwPD using labeled healthy data. MethodsThe experiments were carried out utilizing three datasets containing wearable motion sensor readings on common activities of daily living. The collected readings were from two accelerometer sensors. PAMAP2 and MHEALTH are publicly available datasets collected from 10 and 9 healthy, young subjects, respectively. A private dataset of a similar nature collected from 14 PwPD patients was utilized as well. Deep NN models were implemented with varying levels of complexity to investigate the impact of data augmentation, manual axis reorientation, model complexity, and domain adaptation on activity recognition performance. ResultsA moderately complex model trained on the augmented PAMAP2 dataset and adapted to the Parkinson domain using domain adaptation achieved the best activity recognition performance with an accuracy of 73.02%, which was significantly higher than the accuracy of 63% reported in previous studies. The model’s F1 score of 49.79% significantly improved compared to the best cross-testing of 33.66% F1 score with only data augmentation and 2.88% F1 score without data augmentation or domain adaptation. ConclusionThese findings suggest that deep NN models originating on healthy data have the potential to recognize activities performed by PwPD accurately and that data augmentation and domain adaptation can improve the generalizability of models in the healthy-to-PwPD transfer scenario. The simple/moderately complex architectures tested in this study could generalize better to the PwPD domain when trained on a healthy dataset compared to the most complex architectures used. The findings of this study could contribute to the development of accurate wearable-based activity monitoring solutions for PwPD, improving clinical decision-making and patient outcomes based on patient activity levels. 

   more » « less
2. The Relationship between Intracranial Pressure and Visual Field Zones in Normal-Tension Glaucoma Patients

   https://doi.org/10.3390/diagnostics13020174  

   Stoskuviene, Akvile; Siaudvytyte, Lina; Januleviciene, Ingrida; Vaitkus, Antanas; Simiene, Evelina; Bakstyte, Viktorija; Ragauskas, Arminas; Antman, Gal; Siesky, Brent; Harris, Alon (January 2023, Diagnostics)

   Growing evidence suggests that intracranial pressure (ICP) plays an important role in the pathophysiology of glaucoma, especially in normal-tension glaucoma (NTG) patients. Controversial results exist about ICP’s relationship to visual field (VF) changes. With the aim to assess the relationship between ICP and VF zones in NTG patients, 80 NTG patients (age 59.5 (11.6) years) with early-stage glaucoma were included in this prospective study. Intraocular pressure (IOP) (Goldmann), visual perimetry (Humphrey) and non-invasive ICP (via a two-depth Transcranial Doppler, Vittamed UAB, Lithuania) were evaluated. Translaminar pressure difference (TPD) was calculated according to the formula TPD = IOP − ICP. The VFs of each patient were divided into five zones: nasal, temporal, peripheral, central, and paracentral. The average pattern deviation (PD) scores were calculated in each zone. The level of significance p < 0.05 was considered significant. NTG patients had a mean ICP of 8.5 (2.4) mmHg. Higher TPD was related with lower mean deviation (MD) (p = 0.01) and higher pattern standard deviation (PSD) (p = 0.01). ICP was significantly associated with the lowest averaged PD scores in the nasal VF zone (p < 0.001). There were no significant correlations between ICP and other VF zones with the most negative mean PD value. (p > 0.05). Further studies are needed to analyze the involvement of ICP in NTG management. 

   more » « less
3. Neural network-based measure of consonant lenition in Parkinson's Disease

   https://doi.org/10.1121/2.0001913  

   Wayland, Ratree; Tang, Kevin; Wang, Fenqi; Vellozzi, Sophia; Meyer, Rachel; Sengupta, Rahul (January 2023, Acoustical Society of America)

   This study investigated the effects of Parkinson’s disease (PD) and various linguistic factors on the degree of lenition in Spanish stops. Lenition was estimated from posterior probabilities calculated by recurrent neural networks trained to recognize sonorant and continuant phonological features. Firstly, individuals with PD exhibited a higher degree of lenition in their voiceless stops compared to healthy controls, suggesting that PD significantly impacts the articulatory control of stops, resulting in more pronounced lenition. Secondly, lenition was significantly more advanced for dental stops than bilabial stops, further suggesting that the muscles controlling tongue tip movement are more affected than those involved in lip movement among PD patients. These findings are consistent with previous literature. Importantly, the results highlight the sensitivity of Phonet in quantifying lenition in this group of PD patients. 

   more » « less
4. COMPARISONS OF ENERGY EXPENDITURES AMONG CHILDREN DIAGNOSED WITH IDIOPATHIC TOE WALKING AND TYPICAL CHILDREN USING INERTIAL SENSORS

   Woo, John; Shiraishi, Michael; Soangra, Rahul; GrantBeuttler, Marybeth (April 2023, Biomedical sciences instrumentation)

   Children diagnosed with Idiopathic Toe Walking (ITW) walk on their toes and are liable for leg pain and fall injuries. It is crucial to understand how toe walking affects energy expenditure in these children compared to typical children of the same age. In this study, we utilized an inertial measurement unit (IMU) attached to the low back to evaluate the number of steps and energy expenditure in the child’s natural setting for three days. Twenty participants were instructed to wear a sensor on their low back for three days, and their activities of daily living (ADL) were objectively quantified during weekdays and weekends in their natural settings. We found total energy expenditure was significantly higher among children diagnosed with ITW compared to typical controls (p<0.05). We also found the children diagnosed with ITW took shorter and significantly more steps than age-matched controls (p<0.05). A future investigation into biomechanics and new gait interventions is needed to improve gait efficiency and energy expenditure among children diagnosed with ITW. 

   more » « less
5. Predictive Models of Mortality for Hospitalized Patients With COVID-19: Retrospective Cohort Study

   https://doi.org/10.2196/21788  

   Wang, Taiyao; Paschalidis, Aris; Liu, Quanying; Liu, Yingxia; Yuan, Ye; Paschalidis, Ioannis Ch (January 2020, JMIR Medical Informatics)

   null (Ed.)

   Background The novel coronavirus SARS-CoV-2 and its associated disease, COVID-19, have caused worldwide disruption, leading countries to take drastic measures to address the progression of the disease. As SARS-CoV-2 continues to spread, hospitals are struggling to allocate resources to patients who are most at risk. In this context, it has become important to develop models that can accurately predict the severity of infection of hospitalized patients to help guide triage, planning, and resource allocation. Objective The aim of this study was to develop accurate models to predict the mortality of hospitalized patients with COVID-19 using basic demographics and easily obtainable laboratory data. Methods We performed a retrospective study of 375 hospitalized patients with COVID-19 in Wuhan, China. The patients were randomly split into derivation and validation cohorts. Regularized logistic regression and support vector machine classifiers were trained on the derivation cohort, and accuracy metrics (F1 scores) were computed on the validation cohort. Two types of models were developed: the first type used laboratory findings from the entire length of the patient’s hospital stay, and the second type used laboratory findings that were obtained no later than 12 hours after admission. The models were further validated on a multicenter external cohort of 542 patients. Results Of the 375 patients with COVID-19, 174 (46.4%) died of the infection. The study cohort was composed of 224/375 men (59.7%) and 151/375 women (40.3%), with a mean age of 58.83 years (SD 16.46). The models developed using data from throughout the patients’ length of stay demonstrated accuracies as high as 97%, whereas the models with admission laboratory variables possessed accuracies of up to 93%. The latter models predicted patient outcomes an average of 11.5 days in advance. Key variables such as lactate dehydrogenase, high-sensitivity C-reactive protein, and percentage of lymphocytes in the blood were indicated by the models. In line with previous studies, age was also found to be an important variable in predicting mortality. In particular, the mean age of patients who survived COVID-19 infection (50.23 years, SD 15.02) was significantly lower than the mean age of patients who died of the infection (68.75 years, SD 11.83; P<.001). Conclusions Machine learning models can be successfully employed to accurately predict outcomes of patients with COVID-19. Our models achieved high accuracies and could predict outcomes more than one week in advance; this promising result suggests that these models can be highly useful for resource allocation in hospitals. 

   more » « less