The freezing of gait (FoG) is a common type of motor dysfunction in advanced Parkinson’s disease (PD) associated with falls. Over the last decade, a significant amount of studies has been focused on detecting FoG episodes in clinical and home environments. Yet, there remains a paucity of techniques regarding real-time prediction of FoG before its occurrence. In this paper, a new algorithm was employed to define the best combination of sensor position, axis, sampling window length, and features to predict FoG. We hypothesized that gait deterioration before FoG onsets can be discriminated from normal gait using statistical analysis of features from successive windows of data collected from lower-limb accelerometers. We defined a new performance measure, “predictivity”, to compare the number of correctly predicted FoG events among different combinations. We characterized the system performance using data from 10 PD patients, who experienced FoG while performing several walking tasks in a lab environment. The analysis of 120 different combinations revealed that prediction of FoG can be realized by using an individual shank sensor and sample entropy calculated from the horizontal forward axis with window length of 2 s (88.8%, 92.5%, and 89.0% for average predictivity, sensitivity, and specificity, respectively).

Freezing of gait (FoG) is a common motor symptom in patients with Parkinson’s disease (PD). FoG impairs gait initiation and walking and increases fall risk. Intelligent external cueing systems implementing FoG detection algorithms have been developed to help patients recover gait after freezing. However, predicting FoG before its occurrence enables preemptive cueing and may prevent FoG. Such prediction remains challenging given the relative infrequency of freezing compared to non-freezing events. In this study, we investigated the ability of individual and ensemble classifiers to predict FoG. We also studied the effect of the ADAptive SYNthetic (ADASYN) sampling algorithm and classification cost on classifier performance. Eighteen PD patients performed a series of daily walking tasks wearing accelerometers on their ankles, with nine experiencing FoG. The ensemble classifier formed by Support Vector Machines, K-Nearest Neighbors, and Multi-Layer Perceptron using bagging techniques demonstrated highest performance (F1 = 90.7) when synthetic FoG samples were added to the training set and class cost was set as twice that of normal gait. The model identified 97.4% of the events, with 66.7% being predicted. This study demonstrates our algorithm’s potential for accurate prediction of gait events and the provision of preventive cueing in spite of limited event frequency.

Freezing of gait (FoG) is a common motor dysfunction in individuals with Parkinson’s disease. FoG impairs walking and is associated with increased fall risk. On-demand external cueing systems can detect FoG and provide stimuli to help individuals overcome freezing. Predicting FoG before onset enables preemptive cueing and may prevent FoG. However, detection and prediction remain challenging. If FoG data are not available for an individual, patient-independent models have been used to detect FoG, which have shown great sensitivity and poor specificity, or vice versa. In this study, we introduce a Deep Gait Anomaly Detector (DGAD) using a transfer learning-based approach to improve FoG detection accuracy. We also evaluate the effect of data augmentation and additional pre-FoG segments on prediction rate. Seven individuals with PD performed a series of daily walking tasks wearing inertial measurement units on their ankles. The DGAD algorithm demonstrated average sensitivity and specificity of 63.0% and 98.6% (3.2% improvement compared with the highest specificity in the literature). The target models identified 87.4% of FoG onsets, with 21.9% predicted. This study demonstrates our algorithm’s potential for accurate identification of FoG and delivery of cues for patients for whom no FoG data is available for model training.

Background: This single-arm prospective study evaluated the feasibility of a novel wrist-worn thermal device that applies cooling to the inside of the wrist for management of bothersome hot flashes in prostate cancer survivors. Methods: 57 individuals were enrolled and instructed to use the thermal device as needed for management of hot flashes for 4 weeks. The primary outcome was thermal device usage (hours and sessions per day). Additional outcomes included the change in Hot Flash Related Daily Interference Scale (HFRDIS, range 0–10) and Patient Reported Outcomes Measurement Information System Sleep Disturbance 4a (PROMIS SD T-score, range 0–100) and Sleep-Related Impairment 8a (PROMIS SRI T-score, range 0–100). Study procedures were conducted remotely from May to Dec 2021 in the US. Results: 44 participants completed the study and 39 had retrievable usage data. The mean ± SD age was 67 ± 6 years and 5 ± 5 years since cancer diagnosis. The baseline mean ± SD HFRDIS score of 4.3 ± 2.0 indicated moderate hot flash interference in this population. During the study, participants used the thermal device (mean ± SD) 3.2 ± 2.5 hours/day and 7.6 ± 3.6 sessions/day. Most (67%) participants reported using the device 7 days and 7 nights each week. Statistically significant improvements from baseline at Week 4 were observed for HFRDIS (mean ± SE change: −1.1 ± 0.3), PROMIS SD (−6.0 ± 1.0), and PROMIS SRI (−5.5 ± 1.2) scores (all p < 0.001). The majority (69%) of participants reported that the thermal device was effective at helping them manage hot flashes. No adverse events were reported. Conclusions: Results support the feasibility of using the thermal device for management of bothersome hot flashes in prostate cancer survivors. Future randomized controlled studies are warranted to evaluate the impact of the thermal device on frequency and severity of hot flashes, sleep quality, fatigue, and overall quality of life.

This review examined literature that has examined mobility in pulmonary arterial hypertension (PAH) using digital technology. Specifically, the review focussed on: (a) digital mobility measurement in PAH; (b) commonly reported mobility outcomes in PAH; (c) PAH specific impact on mobility outcomes; and (d) recommendations concerning protocols for mobility measurement in PAH. PubMed, Scopus, and Medline databases were searched. Two independent reviewers screened articles that described objective measurement of mobility in PAH using digital technology. Twenty-one articles were screened, and 16 articles met the inclusion/exclusion criteria and were reviewed. Current methodologies for mobility measurement in PAH with digital technologies are discussed. In brief, the reviewed evidence demonstrated that there is a lack of standardisation across studies for instrumentation, outcomes, and interpretation in PAH. The validity and reliability of digital approaches were insufficiently reported in all studies. Future research is required to standardise digital mobility measurement and characterise mobility impairments in PAH across clinical and real-world settings. The reviewed evidence suggests that digital mobility outcomes may be useful clinical measures and may be impaired in PAH, but further research is required to accurately and robustly establish findings. Recommendations are provided for future studies that encompass comprehensive reporting, validation, and measurement.

During menopause, the majority of women experience hot flashes (HF) that have a significant negative impact on sleep and quality of life. Current HF therapies are either ineffective or associated with unacceptable side effects. Digital health technologies offer a novel opportunity to fill this treatment gap with just‐in‐time thermal interventions through wearable devices. Thermal interventions have shown promise in reducing the negative impact of HFs. We hypothesized that HF event onsets can be accurately and reliably predicted from physiological signals prior to a person's perception of the events. This study investigated the feasibility of using skin conductance (SC) to predict the onset of HF events before they are subjectively perceived. 62 women who were experiencing HFs and self‐reported being in peri‐ or postmenopause were recruited. Data collection consisted of three remotely conducted 48‐h sessions. During each session, SC from the lateral torso was measured continuously and participants logged the precise timing of each perceived HF event onset. We developed new features to identify characteristics of SC signals before HFs were perceived. The best performing model trained with these features identified 82% of HF events on average 17 s before the onset with less than 2% false‐positive rate. Among the identified events, the model predicted 69% of HF events before onset. This study demonstrates the feasibility of predicting HF event onsets before subjective perception. Future studies should investigate both multimodal prediction as well as user acceptance and effectiveness of just‐in‐time thermal interventions.