Highly comparative time series analysis of oxygen saturation and heart rate to predict respiratory outcomes in extremely preterm infants.

Objective: Highly comparative time series analysis (HCTSA) is a novel approach involving massive feature extraction using publicly available code from many disciplines. The Prematurity-Related Ventilatory Control (Pre-Vent) observational multicenter prospective study collected bedside monitor data from > 700 extremely preterm infants to identify physiologic features that predict respiratory outcomes. We calculated a subset of 33 HCTSA features on > 7M 10-minute windows of oxygen saturation (SPO2) and heart rate (HR) from the Pre-Vent cohort to quantify predictive performance. This subset included representatives previously identified using unsupervised clustering on > 3500 HCTSA algorithms. Performance of each feature was measured by individual area under the receiver operating curve (AUC) at various days of life and binary respiratory outcomes. These were compared to optimal PreVent physiologic predictor IH90 DPE, the duration per event of intermittent hypoxemia events with threshold of 90%. Main Results: The top HCTSA features were from a cluster of algorithms associated with the autocorrelation of SPO2 time series and identified low frequency patterns of desaturation as high risk. These features had comparable performance to and were highly correlated with IH90_DPE but perhaps measure the physiologic status of an infant in a more robust way that warrants further investigation. The top HR HCTSA features were symbolic transformation measures that had previously been identified as strong predictors of neonatal mortality. HR metrics were only important predictors at early days of life which was likely due to the larger proportion of infants whose outcome was death by any cause. A simple HCTSA model using 3 top features outperformed IH90_DPE at day of life 7 (.778 versus .729) but was essentially equivalent at day of life 28 (.849 versus .850). These results validated the utility of a representative HCTSA approach but also provides additional evidence supporting IH90_DPE as an optimal predictor of respiratory outcomes.

Maturation of cardioventilatory physiological trajectories in extremely preterm infants.

BACKGROUND: In extremely preterm infants, persistence of cardioventilatory events is associated with long-term morbidity. Therefore, the objective was to characterize physiologic growth curves of apnea, periodic breathing, intermittent hypoxemia, and bradycardia in extremely preterm infants during the first few months of life. METHODS: The Prematurity-Related Ventilatory Control study included 717 preterm infants <29 weeks gestation. Waveforms were downloaded from bedside monitors with a novel sharing analytics strategy utilized to run software locally, with summary data sent to the Data Coordinating Center for compilation. RESULTS: Apnea, periodic breathing, and intermittent hypoxemia events rose from day 3 of life then fell to near-resolution by 8-12 weeks of age. Apnea/intermittent hypoxemia were inversely correlated with gestational age, peaking at 3-4 weeks of age. Periodic breathing was positively correlated with gestational age peaking at 31-33 weeks postmenstrual age. Females had more periodic breathing but less intermittent hypoxemia/bradycardia. White infants had more apnea/periodic breathing/intermittent hypoxemia. Infants never receiving mechanical ventilation followed similar postnatal trajectories but with less apnea and intermittent hypoxemia, and more periodic breathing. CONCLUSIONS: Cardioventilatory events peak during the first month of life but the actual postnatal trajectory is dependent on the type of event, race, sex and use of mechanical ventilation. IMPACT: Physiologic curves of cardiorespiratory events in extremely preterm-born infants offer (1) objective measures to assess individual patient courses and (2) guides for research into control of ventilation, biomarkers and outcomes. Presented are updated maturational trajectories of apnea, periodic breathing, intermittent hypoxemia, and bradycardia in 717 infants born <29 weeks gestation from the multi-site NHLBI-funded Pre-Vent study. Cardioventilatory events peak during the first month of life but the actual postnatal trajectory is dependent on the type of event, race, sex and use of mechanical ventilation. Different time courses for apnea and periodic breathing suggest different maturational mechanisms.

A Wearable Sensor System to Measure Step-Based Gait Parameters for Parkinson's Disease Rehabilitation.

Spatiotemporal parameters of gait serve as an important biomarker to monitor gait impairments as well as to develop rehabilitation systems. In this work, we developed a computationally-efficient algorithm (SDI-Step) that uses segmented double integration to calculate step length and step time from wearable inertial measurement units (IMUs) and assessed its ability to reliably and accurately measure spatiotemporal gait parameters. Two data sets that included simultaneous measurements from wearable sensors and from a laboratory-based system were used in the assessment. The first data set utilized IMU sensors and a GAITRite mat in our laboratory to monitor gait in fifteen participants: 9 young adults (YA1) (5 females, 4 males, age 23.6 ± 1 years), and 6 people with Parkinson's disease (PD) (3 females, 3 males, age 72.3 ± 6.6 years). The second data set, which was accessed from a publicly-available repository, utilized IMU sensors and an optoelectronic system to monitor gait in five young adults (YA2) (2 females, 3 males, age 30.5 ± 3.5 years). In order to provide a complete representation of validity, we used multiple statistical analyses with overlapping metrics. Gait parameters such as step time and step length were calculated and the agreement between the two measurement systems for each gait parameter was assessed using Passing-Bablok (PB) regression analysis and calculation of the Intra-class Correlation Coefficient (ICC (2,1)) with 95% confidence intervals for a single measure, absolute-agreement, 2-way mixed-effects model. In addition, Bland-Altman (BA) plots were used to visually inspect the measurement agreement. The values of the PB regression slope were close to 1 and intercept close to 0 for both step time and step length measures. The results obtained using ICC (2,1) for step length showed a moderate to excellent agreement for YA (between 0.81 and 0.95) and excellent agreement for PD (between 0.93 and 0.98), while both YA and PD had an excellent agreement in step time ICCs (>0.9). Finally, examining the BA plots showed that the measurement difference was within the limits of agreement (LoA) with a 95% probability. Results from this preliminary study indicate that using the SDI-Step algorithm to process signals from wearable IMUs provides measurements that are in close agreement with widely-used laboratory-based systems and can be considered as a valid tool for measuring spatiotemporal gait parameters.

Unsupervised Pre-trained Models from Healthy ADLs Improve Parkinson's Disease Classification of Gait Patterns.

Application and use of deep learning algorithms for different healthcare applications is gaining interest at a steady pace. However, use of such algorithms can prove to be challenging as they require large amounts of training data that capture different possible variations. This makes it difficult to use them in a clinical setting since in most health applications researchers often have to work with limited data. Less data can cause the deep learning model to over-fit. In this paper, we ask how can we use data from a different environment, different use-case, with widely differing data distributions. We exemplify this use case by using single-sensor accelerometer data from healthy subjects performing activities of daily living - ADLs (source dataset), to extract features relevant to multi-sensor accelerometer gait data (target dataset) for Parkinson's disease classification. We train the pre-trained model using the source dataset and use it as a feature extractor. We show that the features extracted for the target dataset can be used to train an effective classification model. Our pretrained source model consists of a convolutional autoencoder, and the target classification model is a simple multi-layer perceptron model. We explore two different pre-trained source models, trained using different activity groups, and analyze the influence the choice of pre-trained model has over the task of Parkinson's disease classification.

Topological Descriptors for Parkinson's Disease Classification and Regression Analysis.

At present, the vast majority of human subjects with neurological disease are still diagnosed through in-person assessments and qualitative analysis of patient data. In this paper, we propose to use Topological Data Analysis (TDA) together with machine learning tools to automate the process of Parkinson's disease classification and severity assessment. An automated, stable, and accurate method to evaluate Parkinson's would be significant in streamlining diagnoses of patients and providing families more time for corrective measures. We propose a methodology which incorporates TDA into analyzing Parkinson's disease postural shifts data through the representation of persistence images. Studying the topology of a system has proven to be invariant to small changes in data and has been shown to perform well in discrimination tasks. The contributions of the paper are twofold. We propose a method to 1) classify healthy patients from those afflicted by disease and 2) diagnose the severity of disease. We explore the use of the proposed method in an application involving a Parkinson's disease dataset comprised of healthy-elderly, healthy-young and Parkinson's disease patients. Our code is available at https://github.com/itsmeafra/Sublevel-Set-TDA.

Mind-Body and Psychosocial Interventions May Similarly Affect Heart Rate Variability Patterns in Cancer Recovery: Implications for a Mechanism of Symptom Improvement.

BACKGROUND: Advancements in early detection and treatment of cancer have led to increased survival rates and greater need to identify effective supportive care options for resolving symptoms of survivorship. Many non-pharmacological approaches to symptom management during and after cancer treatment involve emotional self-regulation as a central strategy for improving well-being. Identifying commonalities among these strategies' mechanisms of action may facilitate understanding of what might be useful for optimizing intervention effects. Heart rate variability (HRV) parameters are indicative of improved autonomic nervous system (ANS) balance and resiliency and reduced emotional distress and are thus identified as a mechanism to discuss as a marker of potential for intervention efficacy and a target for optimization. METHODS: HRV data from 2 studies, 1 examining a mind-body intervention and 1 examining a psychosocial intervention, are presented as a point of discussion about preliminary associations between the interventions, change in HRV, and emotional distress reduction. RESULTS: HRV significantly decreased in sympathetic activity in response to a mind-body intervention (Qigong/Tai Chi), and increased vagal tone in response to a psychosocial (storytelling) intervention. In both, these changes in HRV parameters were associated with improved emotional states. CONCLUSION: Our preliminary data suggest that HRV may serve as an important marker of underlying changes that mediate emotional regulation; this observation deserves further investigation. If identified as a worthy target, focusing on interventions that improve HRV within the context of interventions for cancer patients may be important to key outcomes and clinical practice.

ReadySteady intervention to promote physical activity in older adults with Parkinson's disease: Study design and methods.

The main motor impairments of gait and balance experienced by people with Parkinson's disease (PD) contribute to a sedentary lifestyle, resulting in poor physical conditioning, loss of functional independence, and reduced quality of life. Despite the known benefits of physical activity in PD, the majority of older adults with PD are insufficiently active. Few studies incorporate behavioral change approaches to promoting physical activity in PD. The main goal of this research is to foster community mobility in older adults with PD by promoting physical activity and improving gait patterns using a theory-based behavioral change intervention. The ReadySteady intervention combines wellness motivation theory with polestriding physical activity, which has been shown to be beneficial for people with PD. The intervention will be tested using a randomized controlled design, including inactive older adults diagnosed with PD. Participants will be randomly assigned the 12-week ReadySteady intervention, 12-week polestriding, and education intervention, or 12-week education intervention. Thirty-six older adults with PD will participate in each of the interventions. Level of physical activity, clinical scores, quantitative measures of gait and balance control, and motivational variables for each intervention will be measured at three time points: pre-intervention, post-intervention (12 weeks), and follow-up (24 weeks). If the intervention is beneficial, it may serve as a sustainable addition to current practice in health promotion efforts serving the PD population.

A comprehensive Movement and Motion training program improves mobility in Parkinson's disease.

BACKGROUND: Mobility in Parkinson's disease (PD) is restricted due to impairments in gait and postural control. Although typical dance-based movement programs are beneficial in PD, many did not improve gait which may be due to the nature of the training, limited data, or both. Moreover, the investigation of the effects of a dance program specifically designed for people with PD is scarce. AIMS: To examine the effects of our newly developed, PD-specific, dance-based training program Movement and Motion (M&M), on mobility in people with PD. METHODS: Nineteen participants with mild-to-moderate PD (Hoehn and Yahr score 1-2) participated in a 10-week M&M training program (two 1-h sessions per week). Several quantitative and objective indices of stride-to-stride gait, posture, and range of motion and clinical scores were obtained pre- and post-M&M training. The significance of the changes in these measures after the training was tested using paired t test or Wilcoxon signed-rank test and changes were considered significant at p < 0.05. RESULTS: Gait velocity, stride length, double support and stance durations, the degree of arm swing, and turning significantly improved after the training. Moreover, the time taken to initiate movement shifts and target reach significantly decreased after the training. In addition, the range of motion at many major joints significantly increased. DISCUSSION: The improvements in the gait, posture, and range of motion measures indicate greater gait stability, posture control, and flexibility, respectively, after M&M training. CONCLUSIONS: The movements involved in M&M training address specific impairments in PD, such as decreased amplitude and speed of movements, increased stiffness, and altered posture control during leaning and reaching. Results indicate that regular practice of PD-specific M&M training can alleviate the targeted impairments and, thus, may lead to improved mobility and quality of life for people with PD.

Cueing Paradigms to Improve Gait and Posture in Parkinson's Disease: A Narrative Review.

Progressive gait dysfunction is one of the primary motor symptoms in people with Parkinson's disease (PD). It is generally expressed as reduced step length and gait speed and as increased variability in step time and step length. People with PD also exhibit stooped posture which disrupts gait and impedes social interaction. The gait and posture impairments are usually resistant to the pharmacological treatment, worsen as the disease progresses, increase the likelihood of falls, and result in higher rates of hospitalization and mortality. These impairments may be caused by perceptual deficiencies (poor spatial awareness and loss of temporal rhythmicity) due to the disruptions in processing intrinsic information related to movement initiation and execution which can result in misperceptions of the actual effort required to perform a desired movement and maintain a stable posture. Consequently, people with PD often depend on external cues during execution of motor tasks. Numerous studies involving open-loop cues have shown improvements in gait and freezing of gait (FoG) in people with PD. However, the benefits of cueing may be limited, since cues are provided in a consistent/rhythmic manner irrespective of how well a person follows them. This limitation can be addressed by providing feedback in real-time to the user about performance (closed-loop cueing) which may help to improve movement patterns. Some studies that used closed-loop cueing observed improvements in gait and posture in PD, but the treadmill-based setup in a laboratory would not be accessible outside of a research setting, and the skills learned may not readily and completely transfer to overground locomotion in the community. Technologies suitable for cueing outside of laboratory environments could facilitate movement practice during daily activities at home or in the community and could strongly reinforce movement patterns and improve clinical outcomes. This narrative review presents an overview of cueing paradigms that have been utilized to improve gait and posture in people with PD and recommends development of closed-loop wearable systems that can be used at home or in the community to improve gait and posture in PD.

Polestriding Intervention Improves Gait and Axial Symptoms in Mild to Moderate Parkinson Disease.

OBJECTIVE: To evaluate the effects of 12-week polestriding intervention on gait and disease severity in people with mild to moderate Parkinson disease (PD). DESIGN: A-B-A withdrawal study design. SETTING: Outpatient movement disorder center and community facility. PARTICIPANTS: Individuals (N=17; 9 women [53%] and 8 men [47%]; mean age, 63.7±4.9y; range, 53-72y) with mild to moderate PD according to United Kingdom brain bank criteria with Hoehn & Yahr score ranging from 2.5 to 3.0 with a stable medication regimen and ability to tolerate "off" medication state. INTERVENTIONS: Twelve-week polestriding intervention with 12-week follow-up. MAIN OUTCOME MEASURES: Gait was evaluated using several quantitative temporal, spatial, and variability measures. In addition, disease severity was assessed using clinical scales such as Unified Parkinson's Disease Rating Scale (UPDRS), Hoehn & Yahr scale, and Parkinson's Disease Questionnaire-39. RESULTS: Step and stride lengths, gait speed, and step-time variability were improved significantly (P<.05) because of 12-week polestriding intervention. Also, the UPDRS motor score, the UPDRS axial score, and the scores of UPDRS subscales on walking and balance improved significantly after the intervention. CONCLUSIONS: Because increased step-time variability and decreased step and stride lengths are associated with PD severity and an increased risk of falls in PD, the observed improvements suggest that regular practice of polestriding may reduce the risk of falls and improve mobility in people with PD.

Attractor-shape descriptors for balance impairment assessment in Parkinson's disease.

In this paper, we propose a computational framework using high-dimensional shape descriptors of reconstructed attractors of center-of-pressure (CoP) tracings collected from subjects with Parkinson's disease while performing dynamical posture shifts, to quantitatively assess balance impairment. Using a dataset collected from 60 subjects, we demonstrated that the proposed method outperforms traditional methods, such as dynamical shift indices and use of chaotic invariants, in assessment of balance impairment.

A System for Real-Time Feedback to Improve Gait and Posture in Parkinson's Disease.

For people with Parkinson's disease (PD), gait and postural impairments can significantly affect their ability to perform activities of daily living. Presentation of appropriate cues has been shown to improve gait in PD. Based on this, a treadmill-based system and experimental paradigm were developed to determine if people with PD can utilize real-time feedback (RTFB) of step length or back angle (uprightness) to improve gait and posture. Eleven subjects (mean age 67 ± 8 years) with mild-to-moderate PD (Hoehn and Yahr stage I-III) were evaluated regarding their ability to successfully utilize RTFB of back angle or step length during quiet standing and treadmill walking tasks during a single session in their medication-on state. Changes in back angle and step length due to feedback were compared using Friedman nonparametric tests with Wilcoxon Signed-Rank tests for post-hoc comparisons. Improvements in uprightness were observed as an increase in back angle during quiet standing (p = 0.005) and during treadmill walking (p = 0.005) with back angle feedback when compared to corresponding tasks without feedback. Improvements in gait were also observed as an increase in step length (p = 0.005) during step length feedback compared to tasks without feedback. These results indicate that people with mild-to-moderate PD can utilize RTFB to improve upright posture and gait. Future work will investigate the long-term effects of this RTFB paradigm and the development of systems for clinical or home-based use.

Distinguishing the tremor of Parkinson's disease from essential tremor: finger displacement.

Although, the tremor of Parkinson's disease (PD) usually, but not always, differs from essential tremor (ET), there is no simple bedside test to distinguish PD from ET. We believe we have made such an observation. We studied 50 consecutive tremor-dominant PD patients (mean age: 63.4 years; mean disease duration: 4.9 years) and 35 consecutive ET patients (mean age: 64.1 years; mean disease duration: 12.5 years). Among PD patients, 31 had a bilateral tremor and among ET patients, 29 patients had a bilateral tremor. Patients sat opposite the examiner and pointed both index fingers at the examiner's index fingers. Then they closed their eyes. Within 15 s, one or rarely both of the patient's index fingers moved, was displaced, either upward or laterally. Finger displacement occurred only with bilateral simultaneous pointing with the patient's eyes closed. All the tremor-dominant PD patients exhibited displacement of an index finger. In 46 patients, it occurred on the side of dominant tremor, in 4, it occurred bilaterally. In 31 of 35 ET patients, no displacement occurred. In 4 of 35 ET patients, it occurred unilaterally on the side of dominant tremor. Odds ratio of distinguishing PD from ET: 89.62 at 95% confidence limits (5.31-1513.4), p = 0. 0018. Sensitivity 100% (0.91-1), specificity 89% (0.72-0.96). Finger displacement can distinguish the tremor of PD from ET. The unilateral movement with eyes closed suggests the tremor of PD unlike ET may impact circuits involving the parietal and supplementary motor cortices.

Finger displacement in Parkinson disease: up? down? sideways?

We previously reported that patients with tremor preponderant Parkinson disease (PD) displayed upward or lateral displacement of their more tremulous finger when they pointed both their index fingers at a target and closed their eyes for 15 seconds. In this study, we examined the phenomenon in 104 PD patients: 72 patients without tremor and 32 with minimal tremor to see if the displacement is related to the disease or the tremor. Sixty-eight of the 72 patients without tremor, 94%, exhibited finger displacement suggesting the phenomenon is related to the disease. None of the 104 patients were demented: mini-mental status examination (MMSE) score 29.0 ± 0. 75. Ninety patients displayed upward displacement (56 patients) or lateral or medial displacement (34 patients). MMSE score of the 90 patients: 29.2 ± 0.74 with no score < 28. Eight patients (6 without tremor) displayed downward displacement. MMSE score of the 8 patients: 27.5 ± 0.35 with 5 having MMSE score of 27. Although not significant the results suggest that patients with downward displacement and lower MMSE score may be evolving a dementia. Upward displacement with eyes closed for 15 seconds requires an ability to "remember" the position of the finger in space and to alter tone to overcome gravity. Downward displacement implies an inability to "remember" the position of the finger in space an inability to overcome the effects of gravity. This may be more likely in patients who are evolving a dementia. Two patients, with PD-like symptoms, and specific anatomical abnormalities are also presented as they illustrate the anatomy of finger displacement.

Is there room for non-dopaminergic treatment in Parkinson disease?

Although levodopa and dopaminergic drugs remain the mainstay of therapy for the motor symptoms of Parkinson disease (PD), they fail to address many of the non-motor symptoms of PD including orthostatic hypotension, freezing of gait (FOG) and difficulty with balance, drug-induced paranoia and hallucinations, and drug-induced dyskinesias. Droxidopa, a drug that increases norepinephrine, treats orthostatic hypotension, cholinomimetic drugs sometimes help with FOG and difficulty with balance, pimavanserin, a drug that blocks serotonin receptors, treats paranoia and hallucinations, and anti-glutaminergic drugs treat dyskinesias. Thus, there are ample opportunities for non-dopaminergic drugs in PD.

A simple question about falls to distinguish balance and gait difficulties in Parkinson's disease.

Although gait and balance difficulties often occur together in Parkinson's disease (PD) patients, it is believed that they are actually two eparate symptoms. However, there are no simple tests to distinguish them. We have developed the self-administered Barrow Neurological Institute (BNI) question to distinguish between gait and balance issues in PD and it was tested in 102 consecutive PD patients. The responses were compared with those of the walking and balance question (item # 2.12) of the Movement Disorder Society-sponsored revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS), and the MDS-UPDRS motor examination and its subsets such as gait and postural stability (PS). Fifty-five patients reported balance difficulty on the BNI question and 64 reported walking and balance difficulty on the MDS-UPDRS question. Of the patients who reported balance difficulty on the BNI question, 74.5% had a PS score ≥2 and 25.4% fell at least three times per month. Of the patients who reported walking and balance difficulty on the MDS-UPDRS question, only 59.4% had a PS score ≥2 and only 10.9% fell three or more times per month. These statistically significant results suggest that the BNI question is better able to detect balance difficulty and its associated falls in PD and can be a supplement to the MDS-UPDRS or a stand-alone question to evaluate balance difficulty and its associated falls in PD.

Deep brain stimulation amplitude alters posture shift velocity in Parkinson's disease.

Deep brain stimulation (DBS) of the subthalamic nucleus (STN) is now widely used to alleviate symptoms of Parkinson's disease (PD). The specific aim of this study was to identify posture control measures that may be used to improve selection of DBS parameters in the clinic and this was carried out by changing the DBS stimulation amplitude. A dynamic posture shift paradigm was used to assess posture control in 4 PD STN-DBS subjects. Each subject was tested at 4 stimulation amplitude settings. Movements of the center of pressure and the position of the pelvis were monitored and several quantitative indices were calculated. The presence of any statistically significant changes in several normalized indices due to reduced/no stimulation was tested using the one-sample t test. The peak velocity and the average movement velocity during the initial and mid phases of movement towards the target posture were substantially reduced. These results may be explained in terms of increased akinesia and bradykinesia due to altered stimulation conditions. Thus, the dynamic posture shift paradigm may be an effective tool to quantitatively characterize the effects of DBS on posture control and should be further investigated as a tool for selection of DBS parameters in the clinic.