RESUMEN

Approaching patients with paraproteinemic neuropathies can be challenging for the practicing neurologist, and a well-defined strategy considering specific etiologies is necessary to arrive at the correct diagnosis. In this case, a 49-year-old man presented with a 2-year history of progressive upper then lower extremity numbness, weakness, gait instability, and tremors. His examination was marked by proximal and distal symmetric upper and lower extremity weakness, large more than small-fiber sensory loss, prominent sensory ataxia, action and postural tremors, and globally absent deep tendon reflexes. His workup was notable for a chronic demyelinating sensorimotor polyradiculoneuropathy and a monoclonal immunoglobulin (Ig) M kappa gammopathy. This case highlights the approach to a patient with a rare subtype of IgM paraproteinemic neuropathy with a review of the differential diagnoses, red flag features of co-occurring hematologic disorders, and guided workup. We further discuss typical features of this rare diagnosis and therapeutic options.

Asunto(s)

RESUMEN

Background: Measurement of freezing of gait (FOG) relies on the sensitivity and reliability of tasks to provoke FOG. It is currently unclear which tasks provide the best outcomes and how medication state plays into this. Objective: To establish the sensitivity and test-retest reliability of various FOG-provoking tasks for presence and severity of FOG, with (ON) and without (OFF) dopaminergic medication. Methods: FOG-presence and percentage time frozen (% TF) were derived from video annotations of a home-based FOG-provoking protocol performed in OFF and ON. This included: the four meter walk (4MW), Timed Up and Go (TUG) single (ST) and dual task (DT), 360° turns in ST and DT, a doorway condition, and a personalized condition. Sensitivity was tested at baseline in 63 definite freezers. Test-retest reliability was evaluated over 5 weeks in 26 freezers. Results: Sensitivity and test-retest reliability were highest for 360° turns and higher in OFF than ON. Test-retest intra-class correlation coefficients of % TF varied between 0.63-0.90 in OFF and 0.18-0.87 in ON, and minimal detectable changes (MDCs) were high. The optimal protocol included TUG ST, 360° turns ST, 360° turns DT and a doorway condition, provoking FOG in all freezers in OFF and 91.9% in ON and this could be done reliably in 95.8% (OFF) and 84.0% (ON) of the sample. Combining OFF and ON further improved outcomes. Conclusions: The highest sensitivity and reliability was achieved with a multi-trigger protocol performed in OFF + ON. However, the high MDCs for % TF underscore the need for further optimization of FOG measurement.

Freezing of gait is a very burdensome and episodic symptom in Parkinson's disease that is difficult to measure. Measurement of freezing is needed to determine whether someone has freezing and how severe this is, and relies on observation during a freezing-triggering protocol. However, it is unclear what protocol is sufficiently sensitive to trigger freezing in many freezers, and whether freezing can be triggered reliably at different timepoints. Here, we investigated 1) which tasks can trigger freezing-presence and freezing-severity sensitively and reliably, 2) how medication state influences this, and 3) what task combination was most reliable. Sixty-three patients with daily freezing performed several freezing-triggering tasks in their homes, both with (ON) and without (OFF) anti-Parkinsonian medication. In twenty-six patients, the measurement was repeated 5 weeks later to determine test-retest reliability. First, we found that performing 360° turns in place with a cognitive dual task was the most sensitive and reliable task to trigger FOG. Second, sensitivity and reliability were better in OFF than in ON. Third, the most reliable protocol included: the Timed-Up and Go, 360° turns in place with and without the dual task, and a doorway condition. This protocol triggered freezing in all patients in OFF and 91.9% in ON and did so reliably in 95.8% (OFF) and 84.0% (ON) of the sample. We recommend to measure freezing with this protocol in OFF + ON, which further improved reliability. However, the measurement error for freezing-severity was high, even for this optimal protocol, underscoring the need for further optimization of freezing measurement.

Asunto(s)

RESUMEN

BACKGROUND: Neurodegenerative diseases (NDDs) pose significant challenges due to their debilitating nature and limited therapeutic options. Accurate and timely diagnosis is crucial for optimizing patient care and treatment strategies. Gait analysis, utilizing wearable sensors, has shown promise in assessing motor abnormalities associated with NDDs. RESEARCH QUESTION: Research Question 1 To what extent can analyzing the interaction of both limbs in the time-frequency domain serve as a suitable methodology for accurately classifying NDDs? Research Question 2 How effective is the utilization of color-coded images, in conjunction with deep transfer learning models, for the classification of NDDs? METHODS: GaitNDD database was used, comprising recordings from patients with Huntington's disease, amyotrophic lateral sclerosis, Parkinson's disease, and healthy controls. The gait signals underwent signal preparation, wavelet coherence analysis, and principal component analysis for feature enhancement. Deep transfer learning models (AlexNet, GoogLeNet, SqueezeNet) were employed for classification. Performance metrics, including accuracy, sensitivity, specificity, precision, and F1 score, were evaluated using 5-fold cross-validation. RESULTS: The classification performance of the models varied depending on the time window used. For 5-second gait signal segments, AlexNet achieved an accuracy of 95.91 %, while GoogLeNet and SqueezeNet achieved accuracies of 96.49 % and 92.73 %, respectively. For 10-second segments, AlexNet outperformed other models with an accuracy of 99.20 %, while GoogLeNet and SqueezeNet achieved accuracies of 96.75 % and 95.00 %, respectively. Statistical tests confirmed the significance of the extracted features, indicating their discriminative power for classification. SIGNIFICANCE: The proposed method demonstrated superior performance compared to previous studies, offering a non-invasive and cost-effective approach for the automated diagnosis of NDDs. By analyzing the interaction between both legs during walking using wavelet coherence, and utilizing deep transfer learning models, accurate classification of NDDs was achieved.

Asunto(s)

RESUMEN

BACKGROUND: Although pose estimation algorithms have been used to analyze videos of patients with Parkinson's disease (PD) to assess symptoms, their feasibility for differentiating PD from other neurological disorders that cause gait disturbances has not been evaluated yet. We aimed to determine whether it was possible to differentiate between PD and spinocerebellar degeneration (SCD) by analyzing video recordings of patient gait using a pose estimation algorithm. METHODS: We videotaped 82 patients with PD and 61 patients with SCD performing the timed up-and-go test. A pose estimation algorithm was used to extract the coordinates of 25 key points of the participants from these videos. A transformer-based deep neural network (DNN) model was trained to predict PD or SCD using the extracted coordinate data. We employed a leave-one-participant-out cross-validation method to evaluate the predictive performance of the trained model using accuracy, sensitivity, and specificity. As there were significant differences in age, weight, and body mass index between the PD and SCD groups, propensity score matching was used to perform the same experiment in a population that did not differ in these clinical characteristics. RESULTS: The accuracy, sensitivity, and specificity of the trained model were 0.86, 0.94, and 0.75 for all participants and 0.83, 0.88, and 0.78 for the participants extracted by propensity score matching. CONCLUSION: The differentiation of PD and SCD using key point coordinates extracted from gait videos and the DNN model was feasible and could be used as a collaborative tool in clinical practice and telemedicine.

Asunto(s)

RESUMEN

BACKGROUND: Homolateral Imitative Synkinesis (HIS) is a rare form of associative movement between the ipsilateral upper and lower limbs. The incidence of HIS or its correlation with various movements remains uninvestigated. This study expounds on the characteristics of HIS, the frequency at which it occurs, and its relationship with movement, particularly walking. METHODS: This study included 1328 patients with acute stroke admitted to our healthcare facility between October 2019 and February 2022. We evaluated the severity of motor paralysis and sensory impairment in instances where HIS manifested, and assessed the relationship between HIS, basic activities, and gait. RESULTS: HIS was observed in 13/1328 patients. Motor paralysis was mild in all the cases. Each patient displayed a degree of sensory impairment, albeit of varying severity. HIS did not manifest during basic activities but was evident during walking movements in five instances. These patients displayed involuntary repetitive lifting of their upper limbs during the swing phase of their gait. Some individuals expressed discontent with involuntary upper-limb movements, citing them as contributors to a suboptimal gait. CONCLUSIONS: This study identified HIS as a rare syndrome, manifesting at a rate of 0.9%. Focus was more common in patients with damage to the thalamus and parietal lobe. No manifestations of the HIS occurred during basic activities, suggesting a weak correlation between the HIS and such activities. Certain patients exhibit HIS during gait, report suboptimal gait, and have an increased risk of falls, potentially influencing their gait proficiency.

Asunto(s)

RESUMEN

A woman in her 70s presented with approximately 2 years of sudden-onset gait and cognitive problems. She had been diagnosed with normal pressure hydrocephalus (NPH) and underwent ventriculoperitoneal shunt (VPS) placement 1 year prior. Before VPS placement, brain imaging showed ventriculomegaly and chronic infarction of the right putamen and claustrum. A lumbar drain trial resulted in modest improvement of gait dysfunction. She underwent VPS placement for suspected NPH, but her symptoms remained unchanged. Examination revealed mild cognitive impairment, left-sided and lower body predominant parkinsonism, as well as disproportionately prominent postural instability. Gait analysis showed increased gait variability, reduced velocity and shortened step length bilaterally. Motor and gait abnormalities did not change after administration of levodopa. Her symptoms have remained stable for up to 52 months since symptom onset. We postulate that the infarction affecting the right putamen and claustrum could have led to a higher-level gait disorder mimicking NPH.

Asunto(s)

RESUMEN

BACKGROUND: Progressive supranuclear palsy (PSP) is characterized by early onset postural instability and frequent falls. Circular walking necessitates dynamic postural control, which is impaired in patients with PSP. We aimed to explore gait parameters associated with the risk of falls in patients with PSP, focusing on circular walking. METHODS: Sixteen drug-naïve patients with PSP, 22 drug-naïve patients with Parkinson's disease (PD), and 23 healthy controls were enrolled. Stride lengths/velocities and their coefficients of variation (CV) during straight and circular walking (walking around a circle of 1-m diameter) were measured under single-task and cognitive dual-task conditions. Correlation analysis was performed between gait parameters and postural instability and gait difficulty (PIGD) motor subscores, representing the risk of falls. RESULTS: Patients with PSP had significantly higher CVs of stride lengths/velocities during circular walking than those during straight walking, and the extent of exacerbation of CVs in patients with PSP was larger than that in patients with PD under single-task conditions. Stride lengths/velocities and their CVs were significantly correlated with PIGD motor subscores in patients with PSP only during single-task circular walking. In addition, patients with PSP showed progressive decrements of stride lengths/velocities over steps only during single-task circular walking. CONCLUSIONS: Worse gait parameters during circular walking are associated with an increased risk of falls in patients with PSP. Circular walking is a challenging task to demand the compromised motor functions of patients with PSP, unmasking impaired postural control and manifesting sequence effect. Assessing circular walking is useful for evaluating the risk of falls in patients with early PSP.

Asunto(s)

RESUMEN

BACKGROUND: Multiple sclerosis can cause locomotor and cognitive impairments even at lower levels of disability, which can impact daily life. The cognitive-motor dual task is commonly used to assess everyday locomotion. Thus, this study aimed to examine the effect of cognitive-motor dual tasks on gait parameters among patients with multiple sclerosis in the early disease stages and to determine whether dual tasks could be used as a clinical test to detect locomotion impairments. METHODS: A systematic search of five databases was conducted in May 2024. The population of interest was patients with multiple sclerosis with an Expanded Disability Status Scale score of 4 or less. The following outcome measures were examined: spatiotemporal and kinematic parameters. The Newcastle-Ottawa Scale was used to assess the quality of the studies. FINDINGS: Eleven studies including 270 patients with multiple sclerosis and 221 healthy controls. Three spatiotemporal parameters were modified both in patients with multiple sclerosis and healthy controls during dual-task performance: gait speed, stride length and the double support phase. No spatiotemporal parameter was affected during dual-task performance in patients with multiple sclerosis alone. INTERPRETATION: Dual-task performance could be useful for assessing gait impairments in patients with multiple sclerosis provided that assessments and protocols are standardized. Nevertheless, the spatiotemporal parameters did not allow discrimination between patients with multiple sclerosis at an early stage and healthy controls. Three-dimensional gait analysis during dual-task performance could be a useful approach for detecting early gait impairments in patients with multiple sclerosis, assessing their progression and adjusting rehabilitation programs.

Asunto(s)

RESUMEN

BACKGROUND: Walking impairment is a common disability post acquired brain injury (ABI), with visually evident arm movement abnormality identified as negatively impacting a multitude of psychological factors. The International Classification of Functioning, Disability and Health (ICF) qualifiers scale has been used to subjectively assess arm movement abnormality, showing strong intra-rater and test-retest reliability, however, only moderate inter-rater reliability. This impacts clinical utility, limiting its use as a measurement tool. To both automate the analysis and overcome these errors, the primary aim of this study was to evaluate the ability of a novel two-level machine learning model to assess arm movement abnormality during walking in people with ABI. METHODS: Frontal plane gait videos were used to train four networks with 50%, 75%, 90%, and 100% of participants (ABI: n = 42, healthy controls: n = 34) to automatically identify anatomical landmarks using DeepLabCut™ and calculate two-dimensional kinematic joint angles. Assessment scores from three experienced neurorehabilitation clinicians were used with these joint angles to train random forest networks with nested cross-validation to predict assessor scores for all videos. Agreement between unseen participant (i.e. test group participants that were not used to train the model) predictions and each individual assessor's scores were compared using quadratic weighted kappa. One sample t-tests (to determine over/underprediction against clinician ratings) and one-way ANOVA (to determine differences between networks) were applied to the four networks. RESULTS: The machine learning predictions have similar agreement to experienced human assessors, with no statistically significant (p < 0.05) difference for any match contingency. There was no statistically significant difference between the predictions from the four networks (F = 0.119; p = 0.949). The four networks did however under-predict scores with small effect sizes (p range = 0.007 to 0.040; Cohen's d range = 0.156 to 0.217). CONCLUSIONS: This study demonstrated that machine learning can perform similarly to experienced clinicians when subjectively assessing arm movement abnormality in people with ABI. The relatively small sample size may have resulted in under-prediction of some scores, albeit with small effect sizes. Studies with larger sample sizes that objectively and automatically assess dynamic movement in both local and telerehabilitation assessments, for example using smartphones and edge-based machine learning, to reduce measurement error and healthcare access inequality are needed.

Asunto(s)

RESUMEN

Freezing of gait (FOG) is an episodic and highly disabling symptom of Parkinson's disease (PD). Although described as a single phenomenon, FOG is heterogeneous and can express as different manifestations, such as trembling in place or complete akinesia. We aimed to analyze the efficacy of deep learning (DL) trained on inertial measurement unit data to classify FOG into both manifestations. We adapted and compared four state-of-the-art FOG detection algorithms for this task and investigated the advantages of incorporating a refinement model to address oversegmentation errors. We evaluated the model's performance in distinguishing between trembling and akinesia, as well as other forms of movement cessation (e.g., stopping and sitting), against gold-standard video annotations. Experiments were conducted on a dataset of eighteen PD patients completing a FOG-provoking protocol in a gait laboratory. Results showed our model achieved an F1 score of 0.78 and segment F1@50 of 0.75 in detecting FOG manifestations. Assessment of FOG severity was strong for trembling (ICC=0.86, [0.66,0.95]) and moderately strong for akinesia (ICC=0.78, [0.51,0.91]). Importantly, our model successfully differentiated FOG from other forms of movement cessation during 360-degree turning-in-place tasks. In conclusion, our study demonstrates that DL can accurately assess different types of FOG manifestations, warranting further investigation in larger and more diverse verification cohorts.

Asunto(s)

RESUMEN

Freezing of Gait (FOG) is a noticeable symptom of Parkinson's disease, like being stuck in place and increasing the risk of falls. The wearable multi-channel sensor system is an efficient method to predict and monitor the FOG, thus warning the wearer to avoid falls and improving the quality of life. However, the existing approaches for the prediction of FOG mainly focus on a single sensor system and cannot handle the interference between multi-channel wearable sensors. Hence, we propose a novel multi-channel time-series neural network (MCT-Net) approach to merge multi-channel gait features into a comprehensive prediction framework, alerting patients to FOG symptoms in advance. Owing to the causal distributed convolution, MCT-Net is a real-time method available to give optimal prediction earlier and implemented in remote devices. Moreover, intra-channel and inter-channel transformers of MCT-Net extract and integrate different sensor position features into a unified deep learning model. Compared with four other state-of-the-art FOG prediction baselines, the proposed MCT-Net obtains 96.21% in accuracy and 80.46% in F1-score on average 2 s before FOG occurrence, demonstrating the superiority of MCT-Net.

Asunto(s)

RESUMEN

Background: Gait disturbance is a vital characteristic of motor manifestation in α- synucleinopathies, especially Parkinson's disease. Subtle gait alterations are present in isolated rapid eye movement sleep behavior disorder (iRBD) patients before phenoconversion; it is yet unclear, if gait analysis may predict phenoconversion. Objective: To investigate subtle gait alterations and explore whether gait analysis using wearable sensors is associated with phenoconversion of iRBD to α-synucleinopathies. Methods: Thirty-one polysomnography-confirmed iRBD patients and 33 healthy controls (HCs) were enrolled at baseline. All participants walked for a minute while wearing 6 inertial sensors on bilateral wrists, ankles, and the trunk (sternal and lumbar region). Three conditions were tested: (i) normal walking, (ii) fast walking, and (iii) dual-task walking. Results: Decreased arm range of motion and increased gait variation (stride length, stride time and stride velocity) discriminate converters from HCs at baseline. After an average of 5.40 years of follow-up, 10 patients converted to neurodegenerative diseases (converters). Cox regression analysis showed higher value of stride length asymmetry under normal walking condition to be associated with an early conversion of iRBD to α- synucleinopathies (adjusted HR 4.468, 95% CI 1.088- 18.349, p = 0.038). Conclusions: Stride length asymmetry is associated with progression to α- synucleinopathies in patients with iRBD. Gait analysis with wearable sensors may be useful for screening, monitoring, and risk stratification for disease-modifying therapy trials in patients with iRBD.

Asunto(s)

RESUMEN

BACKGROUND: Gait impairment is an early marker of Parkinson's disease (PD) and is frequently monitored to evaluate disease progression. Wearable sensors are increasingly being used to quantify gait in the real-world setting among people with PD (pwPD). Particularly, embedding wearables on devices or clothing that are worn daily may represent a useful strategy to improve compliance and regular monitoring of gait. RESEARCH QUESTION: The current investigation examined the validity of innovative smart glasses to measure gait among pwPD. METHODS: Participants wore the smart glasses and 6 APDM gait sensors simultaneously, while performing two walking tasks: the 3-meters Timed Up and Go test (TUG) and the 7-meters Stand and Walk (SAW) test. The following spatiotemporal gait parameters were calculated from the data collected using the two different devices: step time, step length, swing percentage, TUG duration, turn duration, and turn velocity. RESULTS: A total of 31 pwPD (mean age=68.6±8.5 years; 35.48 % female(N=11), mean Unified Parkinson's Disease Rating Scale (UPDRS) total score=32.1±14.7) participated in the study. Smart glasses achieved high validity in measuring step time (ICC=0.92, p=0.01) and TUG duration (ICC=0.96, p=0.03) compared to APDM sensors. On the other hand, the smart glasses did not achieve adequate validity when measuring step length, swing percentage, turn duration or turn velocity. SIGNIFICANCE: The current study suggests that smart glasses has the potential to measure TUG and step time in individuals living with PD. However, further research is needed to improve algorithms for sensors worn on the head.

Asunto(s)

RESUMEN

Parkinson's Disease (PD), a neurodegenerative disorder, significantly impacts the quality of life for millions of people worldwide. PD primarily impacts dopaminergic neurons in the brain's substantia nigra, resulting in dopamine deficiency and gait impairments such as bradykinesia and rigidity. Currently, several well-established tools, such as the Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) and Hoehn and Yahr (H&Y) Scale, are used for evaluating gait dysfunction in PD. While insightful, these methods are subjective, time-consuming, and often ineffective in early-stage diagnosis. Other methods using specialized sensors and equipment to measure movement disorders are cumbersome and expensive, limiting their accessibility. This study introduces a hierarchical approach to evaluating gait dysfunction in PD through videos. The novel 2-Stream Spatial-Temporal Neural Network (2S-STNN) leverages the spatial-temporal features from the skeleton and silhouette streams for PD classification. This approach achieves an accuracy rate of 89% and outperforms other state-of-the-art models. The study also employs saliency values to highlight critical body regions that significantly influence model decisions and are severely affected by the disease. For a more detailed analysis, the study investigates 21 specific gait attributes for a nuanced quantification of gait disorders. Parameters such as walking pace, step length, and neck forward angle are found to be strongly correlated with PD gait severity categories. This approach offers a comprehensive and convenient solution for PD management in clinical settings, enabling patients to receive a more precise evaluation and monitoring of their gait impairments.

Asunto(s)

RESUMEN

BACKGROUND: Recently, the use of inertial measurement units (IMUs) in quantitative gait analysis has been widely developed in clinical practice. Numerous methods have been developed for the automatic detection of gait events (GEs). While many of them have achieved high levels of efficiency in healthy subjects, detecting GEs in highly degraded gait from moderate to severely impaired patients remains a challenge. In this paper, we aim to present a method for improving GE detection from IMU recordings in such cases. METHODS: We recorded 10-meter gait IMU signals from 13 healthy subjects, 29 patients with multiple sclerosis, and 21 patients with post-stroke equino varus foot. An instrumented mat was used as the gold standard. Our method detects GEs from filtered acceleration free from gravity and gyration signals. Firstly, we use autocorrelation and pattern detection techniques to identify a reference stride pattern. Next, we apply multiparametric Dynamic Time Warping to annotate this pattern from a model stride, in order to detect all GEs in the signal. RESULTS: We analyzed 16,819 GEs recorded from healthy subjects and achieved an F1-score of 100%, with a median absolute error of 8 ms (IQR [3-13] ms). In multiple sclerosis and equino varus foot cohorts, we analyzed 6067 and 8951 GEs, respectively, with F1-scores of 99.4% and 96.3%, and median absolute errors of 18 ms (IQR [8-39] ms) and 26 ms (IQR [12-50] ms). CONCLUSIONS: Our results are consistent with the state of the art for healthy subjects and demonstrate a good accuracy in GEs detection for pathological patients. Therefore, our proposed method provides an efficient way to detect GEs from IMU signals, even in degraded gaits. However, it should be evaluated in each cohort before being used to ensure its reliability.

Asunto(s)

RESUMEN

Assessing the motor impairments of individuals with neurological disorders holds significant importance in clinical practice. Currently, these clinical assessments are time-intensive and depend on qualitative scales administered by trained healthcare professionals at the clinic. These evaluations provide only coarse snapshots of a person's abilities, failing to track quantitatively the detail and minutiae of recovery over time. To overcome these limitations, we introduce a novel machine learning approach that can be administered anywhere including home. It leverages a spatial-temporal graph convolutional network (STGCN) to extract motion characteristics from pose data obtained from monocular video captured by portable devices like smartphones and tablets. We propose an end-to-end model, achieving an accuracy rate of approximately 76.6% in assessing children with Cerebral Palsy (CP) using the Gross Motor Function Classification System (GMFCS). This represents a 5% improvement in accuracy compared to the current state-of-the-art techniques and demonstrates strong agreement with professional assessments, as indicated by the weighted Cohen's Kappa ( κlw = 0.733 ). In addition, we introduce the use of metric learning through triplet loss and self-supervised training to better handle situations with a limited number of training samples and enable confidence estimation. Setting a confidence threshold at 0.95 , we attain an impressive estimation accuracy of 88% . Notably, our method can be efficiently implemented on a wide range of mobile devices, providing real-time or near real-time results.

Asunto(s)

RESUMEN

Parkinson's Disease (PD) is a complex neurodegenerative disorder characterized by a spectrum of motor and non-motor symptoms, prominently featuring the freezing of gait (FOG), which significantly impairs patients' quality of life. Despite extensive research, the precise mechanisms underlying FOG remain elusive, posing challenges for effective management and treatment. This paper presents a comprehensive meta-analysis of FOG prediction and detection methodologies, with a focus on the integration of wearable sensor technology and machine learning (ML) approaches. Through an exhaustive review of the literature, this study identifies key trends, datasets, preprocessing techniques, feature extraction methods, evaluation metrics, and comparative analyses between ML and non-ML approaches. The analysis also explores the utilization of cueing devices. The limited adoption of explainable AI (XAI) approaches in FOG prediction research represents a significant gap. Improving user acceptance and comprehension requires an understanding of the logic underlying algorithm predictions. Current FOG detection and prediction research has a number of limitations, which are identified in the discussion. These include issues with cueing devices, dataset constraints, ethical and privacy concerns, financial and accessibility restrictions, and the requirement for multidisciplinary collaboration. Future research avenues center on refining explainability, expanding and diversifying datasets, adhering to user requirements, and increasing detection and prediction accuracy. The findings contribute to advancing the understanding of FOG and offer valuable guidance for the development of more effective detection and prediction methodologies, ultimately benefiting individuals affected by PD.

Asunto(s)

RESUMEN

Freezing of gait (FoG) is a prevalent symptom among individuals with Parkinson's disease and related disorders. FoG detection from videos has been developed recently; however, the process requires using videos filmed within a controlled environment. We attempted to establish an automatic FoG detection method from videos taken in uncontrolled environments such as in daily clinical practices. Motion features of 16 patients were extracted from timed-up-and-go test in 109 video data points, through object tracking and three-dimension pose estimation. These motion features were utilized to form the FoG detection model, which combined rule-based and machine learning-based models. The rule-based model distinguished the frames in which the patient was walking from those when the patient has stopped, using the pelvic position coordinates; the machine learning-based model distinguished between FoG and stop using a combined one-dimensional convolutional neural network and long short-term memory (1dCNN-LSTM). The model achieved a high intraclass correlation coefficient of 0.75-0.94 with a manually-annotated duration of FoG and %FoG. This method is novel as it combines object tracking, 3D pose estimation, and expert-guided feature selection in the preprocessing and modeling phases, enabling FoG detection even from videos captured in uncontrolled environments.

Asunto(s)

RESUMEN

Freezing of gait (FOG) is a debilitating problem that markedly impairs the mobility and independence of 38-65% of people with Parkinson's disease. During a FOG episode, patients report that their feet are suddenly and inexplicably "glued" to the floor. The lack of a widely applicable, objective FOG detection method obstructs research and treatment. To address this problem, we organized a 3-month machine-learning contest, inviting experts from around the world to develop wearable sensor-based FOG detection algorithms. 1,379 teams from 83 countries submitted 24,862 solutions. The winning solutions demonstrated high accuracy, high specificity, and good precision in FOG detection, with strong correlations to gold-standard references. When applied to continuous 24/7 data, the solutions revealed previously unobserved patterns in daily living FOG occurrences. This successful endeavor underscores the potential of machine learning contests to rapidly engage AI experts in addressing critical medical challenges and provides a promising means for objective FOG quantification.

Asunto(s)

RESUMEN

INTRODUCTION: Cognitive decline frequently occurs in individuals with Parkinson's disease (PD), but the clinical methods to predict the onset of cognitive changes are limited. Given preliminary evidence of the link between gait and cognition, the purpose of this study was to determine if dual task (DT) gait was related to declines in cognition over two years in PD. METHODS: A retrospective two-year longitudinal study of 48 individuals with PD using data from the Parkinson's Progression Markers Initiative of the Michael J. Fox Foundation. The following data were extracted at baseline: spatiotemporal gait (during single and DT), demographics (age, sex), PD disease duration (time since diagnosis), motor function (Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS)), and cognition (Montreal Cognitive Assessment (MoCA)), with MoCA scores also extracted after two years. RESULTS: A binomial logistic regression was conducted, with all covariates (above) in block 1 and DT effect (DTE) of gait characteristics in block 2 entered in a stepwise fashion. The final model was statistically significant (χ2(6) = 23.20, p < 0.001) and correctly classified 78.7 % of participants by cognitive status after two years. Only DTE of arm swing asymmetry (ASA) (p = 0.030) was included in block 2 such that a 1 % decline in DTE resulted in 1.6 % increased odds of cognitive decline. CONCLUSIONS: Individuals with greater change in arm swing asymmetry from single to DT gait may be more likely to experience a decline in cognition within two years. These results suggested that reduced automaticity or poor utilization of attentional resources may be indicative of subtle changes in cognition and indicate that DT paradigms may hold promise as a marker of future cognitive decline.

Asunto(s)