Clinical Utility of Plantar Pressure Measurements as Screening in Patients With Parkinson Disease With and Without Freezing of Gait History.

OBJECTIVE: To test the feasibility of objective assessments using the TekScan MatScan pressure mat plantar pressure measurement as a time-effective screening service for Parkinson disease (PD) with and without freezing of gait (FOG) history. DESIGN: Prospective cross-sectional study. SETTING: Largest medical center in southern Taiwan. INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURES: Plantar pressure measurements including average peak pressure (PP), contact area (CA), and pressure-time integral (PTI) in static and dynamic conditions as well as clinical scores during off-medication states. PARTICIPANTS: A total of 103 patients with PD and 22 age- and sex-matched volunteers without PD (N=125). RESULTS: Plantar pressure assessment including PP, CA, and PTI on the total foot areas between participants with PD and controls without PD in the static conditions are similar. Patients with PD presented higher PTI on total foot areas as well as hallux, midfoot area, and medial and lateral heels during dynamic conditions than controls without PD. The PP, CA, and PTI during the static condition and CA during the dynamic condition on the hallux showed statistical significance between PD with and without FOG history. Stepwise logistic regression after controlling with age and body mass index showed only PTI on hallux (static conditions) was significantly associated with the presence of FOG. The receiver operating characteristic curve analysis in diagnostic accuracy for FOG in PTI was statistically significant (P=.002; area under the curve, 0.71). CONCLUSIONS: FOG screening using the TekScan MatScan pressure mat plantar pressure measurement could serve as a time-effective screening service at the outpatient clinic. Based on our study, PTI may be valuable in auxiliary diagnosis.

Evaluation of the effect of different sitting assistive devices in reclining wheelchair on interface pressure.

BACKGROUND: Reclining wheelchair users often add one or more sitting assistive devices to their wheelchairs, but the effect of these additional sitting assistive devices on the risk of pressure ulcers has rarely been investigated. This study examined the four modes of reclining wheelchair without and with different sitting assistive devices, namely the back reclined mode, the lumbar support with back reclined mode, the femur upward with back reclined mode, and the lumbar support with femur upward with back reclined mode, in terms of their effects on human-wheelchair interface pressure. METHODS: This study recruited 16 healthy participants to undergo the aforementioned four modes in random order and have their human-wheelchair interface pressure measured. The initial setting of experimental reclining wheelchair backrest was pushed backward to reach a 150° recline. The data on interface pressure were collected for 5 s while the participant maintained a stable sitting position. The contact area, average pressure, and peak pressure on the back area, ischial area, and femur area were recorded and calculated. RESULTS: Among all tested modes, the lumbar support with femur upward with back reclined mode provided the most significant reduction in stress load on the ischial area (P ≤ 0.010) and shifted part of the load to the femur area (P ≤ 0.009). CONCLUSIONS: This study quantified the effects of and differences between various reclining wheelchair-sitting assistive device combination modes. These findings are useful for the decision-making processes of rehabilitation physicians, wheelchair users, and manufacturers.

Longitudinal artificial intelligence-based deep learning models for diagnosis and prediction of the future occurrence of polyneuropathy in diabetes and prediabetes.

OBJECTIVE: The objective of this study was to develop artificial intelligence-based deep learning models and assess their potential utility and accuracy in diagnosing and predicting the future occurrence of diabetic distal sensorimotor polyneuropathy (DSPN) among individuals with type 2 diabetes mellitus (T2DM) and prediabetes. METHODS: In 394 patients (T2DM=300, Prediabetes=94), we developed a DSPN diagnostic and predictive model using Random Forest (RF)-based variable selection techniques, specifically incorporating the combined capabilities of the Clinical Toronto Neuropathy Score (TCNS) and nerve conduction study (NCS) to identify relevant variables. These important variables were then integrated into a deep learning framework comprising Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. To evaluate temporal predictive efficacy, patients were assessed at enrollment and one-year follow-up. RESULTS: RF-based variable selection identified key factors for diagnosing DSPN. Numbness scores, sensory test results (vibration), reflexes (knee, ankle), sural nerve attributes (sensory nerve action potential [SNAP] amplitude, nerve conduction velocity [NCV], latency), and peroneal/tibial motor NCV were candidate variables at baseline and over one year. Tibial compound motor action potential amplitudes were used for initial diagnosis, and ulnar SNAP amplitude for subsequent diagnoses. CNNs and LSTMs achieved impressive AUC values of 0.98 for DSPN diagnosis prediction, and 0.93 and 0.89 respectively for predicting the future occurrence of DSPN. RF techniques combined with two deep learning algorithms exhibited outstanding performance in diagnosing and predicting the future occurrence of DSPN. These algorithms have the potential to serve as surrogate measures, aiding clinicians in accurate diagnosis and future prediction of DSPN.

Effectiveness of Center of Pressure Trajectory as Anticipatory Postural Adjustment Measurement in Parkinson's Disease With Freezing of Gait History.

BACKGROUND: Evidence showed that patients with Parkinson's disease (PD) who have a history of freezing of gait (FOG) have hypometric anticipatory postural adjustment (APA) during gait initiation (GI) compared to PD without FOG. OBJECTIVES: This study aimed to test the feasibility of center of pressure (COP) displacement during GI as the measure of APA in PD with and without a history of FOG. METHODS: Patients with PD underwent COP trajectory measurements, including duration, length, velocity, and acceleration in different phases of APA (APA1, APA2a, APA2, and LOC), as well as evaluation of New Freezing of Gait Questionnaire (NFOG-Q), Tinetti balance and gait score, and Postural Instability and Gait Difficulty (PIGD) score in the on and off medication states. RESULTS: The duration (seconds) of APA2a, APA2b, and LOC were highest while velocity in mediolateral direction (X) (m/s), including APA1, APA2a, APA2b, and LOC showed lowest in PD with FOG. Velocity in the mediolateral direction in different phases of APA increased in patients with FOG after dopaminergic therapy. APA2a (seconds) and APA2b (X) (m/s) were significantly associated with NFOG-Q part II, APA2b (X) (m/s) was significantly associated with NFOG-Q part III, and APA2a (seconds) was significantly associated with Tinetti balance and gait and PIGD score. CONCLUSIONS: PD with FOG history showed a favorable response of APAs to dopaminergic replacement. The APA parameters by COP trajectory, especially lateral COP shift toward the stance foot (APA2b (X) (m/s) and APA2a (seconds)) are surrogate markers to assess PD with FOG history.

Machine learning models for predicting in-hospital mortality in patient with sepsis: Analysis of vital sign dynamics.

Purpose: To build machine learning models for predicting the risk of in-hospital death in patients with sepsis within 48 h, using only dynamic changes in the patient's vital signs. Methods: This retrospective observational cohort study enrolled septic patients from five emergency departments (ED) in Taiwan. We adopted seven variables, i.e., age, sex, systolic blood pressure, diastolic blood pressure, heart rate, respiratory rate, and body temperature. Results: Among all 353,253 visits, after excluding 159,607 visits (45%), the study group consisted of 193,646 ED visits. With a leading time of 6 h, the convolutional neural networks (CNNs), long short-term memory (LSTM), and random forest (RF) had accuracy rates of 0.905, 0.817, and 0.835, respectively, and the area under the receiver operating characteristic curve (AUC) was 0.840, 0.761, and 0.770, respectively. With a leading time of 48 h, the CNN, LSTM, and RF achieved accuracy rates of 0.828, 0759, and 0.805, respectively, and an AUC of 0.811, 0.734, and 0.776, respectively. Conclusion: By analyzing dynamic vital sign data, machine learning models can predict mortality in septic patients within 6 to 48 h of admission. The performance of the testing models is more accurate if the lead time is closer to the event.

Clinical Disease Severity Mediates the Relationship between Stride Length and Speed and the Risk of Falling in Parkinson's Disease.

The shuffling gait with slowed speed and reduced stride length has been considered classic clinical features in idiopathic Parkinson's disease (PD), and the risk of falling increases as the disease progresses. This raises the possibility that clinical disease severity might mediate the relationship between stride length and speed and the risk of falling in patients with PD. Sixty-one patients with PD patients underwent the clinical scores as well as quantitative biomechanical measures during walking cycles before and after dopamine replacement therapy. Mediation analysis tests whether the direct effect of an independent variable (stride length and speed) on a dependent variable (three-step fall prediction model score) can be explained by the indirect influence of the mediating variable (Unified Parkinson's Disease Rating Scale (UPDRS) total scores). The results demonstrate that decreased stride length, straight walking speed, and turning speed is associated with increased three-step fall prediction model score (r = -0.583, p < 0.0001, r = -0.519, p < 0.0001, and r = -0.462, p < 0.0001, respectively). We further discovered that UPDRS total scores value is negatively correlated with stride length, straight walking, and turning speed (r = -0.651, p < 0.0001, r = -0.555, p < 0.0001, and r = -0.372, p = 0.005, respectively) but positively correlated with the fall prediction model score value (r = 0.527, p < 0.0001). Further mediation analysis shows that the UPDRS total score values serve as mediators between lower stride length, straight walking, and turning speed and higher fall prediction model score values. Our results highlighted the relationship among stride length and speed, clinical disease severity, and risk of falling. As decreased stride length and speed are hallmarks of falls, monitoring the changes of quantitative biomechanical measures along with the use of wearable technology in a longitudinal study can provide a scientific basis for pharmacology, rehabilitation programs, and selecting high-risk candidates for surgical treatment to reduce future fall risk.