Novel methods of ambulatory physiologic monitoring in patients with neuromuscular disease

Machine learning for automatic identification of thoracoabdominal asynchrony in children

BACKGROUND

The current methods for assessment of thoracoabdominal asynchrony (TAA) require offline analysis on the part of physicians (respiratory inductance plethysmography (RIP)) or require experts for interpretation of the data (sleep apnea detection).

METHODS

To assess synchrony between the thorax and abdomen, the movements of the two compartments during quiet breathing were measured using pneuRIP. Fifty-one recordings were obtained: 20 were used to train a machine-learning (ML) model with elastic-net regularization, and 31 were used to test the model's performance. Two feature sets were explored: (1) phase difference (ɸ) between the thoracic and abdominal signals and (2) inverse cumulative percentage (ICP), which is an alternate measure of data distribution. To compute accuracy of training, the model outcomes were compared with five experts' assessments.

RESULTS

Accuracies of 61.3% and 90.3% were obtained using ɸ and ICP features, respectively. The inter-rater reliability (i.r.r.) of the assessments of experts was 0.402 and 0.684 when they used ɸ and ICP to identify TAA, respectively.

CONCLUSIONS

With this pilot study, we show the efficacy of the ICP feature and ML in developing an accurate automated approach to identifying TAA that reduces time and effort for diagnosis. ICP also helped improve consensus among experts.

IMPACT

Our article presents an automated approach to identifying thoracic abdominal asynchrony using machine learning and the pneuRIP device. It also shows how a modified statistical measure of cumulative frequency can be used to visualize the progression of the pulmonary functionality along time. The pulmonary testing method we developed gives patients and doctors a noninvasive and easy to administer and diagnose approach. It can be administered remotely, and alerts can be transmitted to the physician. Further, the test can also be used to monitor and assess pulmonary function continuously for prolonged periods, if needed.

Measures of respiratory inductance plethysmography (RIP) in children with neuromuscular disease

BACKGROUND

Pulmonary function testing (PFT) is essential for the clinical assessment of respiratory problems. Respiratory inductance plethysmography (RIP) is a non-invasive method of PFT requiring minimal patient cooperation. RIP measures the volumetric change in the ribcage and abdomen, from which work of breathing (WOB) indices are derived. WOB indices include: phase angle (Ф), percent ribcage (RC%), respiratory rate (RR), and labored breathing index (LBI). Heart rate (HR) is collected separately.

AIM

The goal of this study was to assess the utility of a newly developed RIP system, the pneuRIP, in an outpatient clinic setting in children with neuromuscular (NM) disease.

METHOD

The pneuRIP system measures and displays the WOB indices in real-time on an iPad display. Forty-three subjects, 22 NM patients and 21 healthy children (ages: 5-18 years) were enrolled.

RESULTS

Patients' means showed an increase of 119.8% for Ф, 15.7% for LBI, and 19.9% for HR compared with healthy subjects, when adjusted for age and gender. The study found significant differences between the mean values of the healthy subjects and patients in Ф (P = 0.000), LBI (P = 0.001), and HR (P = 0.001). No differences were noted for RC% and RR between groups. Data for Ф in NM patients were diffusely distributed as compared with healthy subjects based on analysis of histograms.

CONCLUSION

Non-invasive pneuRIP testing provided instantaneous PFT results. As compared to healthy subjects, NM patients showed abnormal results with increased markers of thoracoabdominal asynchrony, WOB indices, and biphasic breathing patterns likely resulting from NM weakness.

Quantitative Analysis of Thoracoabdominal Asynchrony in Pediatric Polysomnography

STUDY OBJECTIVES

Objective measurements of thoracoabdominal asynchrony (TAA), such as average phase angle (θavg), can quantify airway obstruction. This study demonstrates and evaluates use of θavg for predicting obstructive sleep apnea (OSA) in pediatric polysomnography (PSG).

METHODS

This prospective observational study recruited otherwise healthy 3- to 8-year-old children presenting for PSG due to snoring, behavioral problems, difficulty sleeping, and/or enlarged tonsils. Respiratory inductance plethysmography (RIP) was directly monitored and data were collected during each PSG. θavg and average labored breathing index (LBIavg) were calculated for earliest acceptable 5-minute periods of stage N3 sleep and stage R sleep. Associations between θavg and obstructive apnea index (OAI) and obstructive apnea-hypopnea index (OAHI), as well as between LBIavg and OAI and OAHI, were examined.

RESULTS

Forty patients undergoing PSG were analyzed. Thirty percent of patients had OSA, 57.5% had enlarged tonsils, and 17.5% were obese. θavg during stage N3 sleep and stage R sleep had significant positive correlations with OAI (Spearman r = .35 [P = .03] and .40 [P = .01], respectively) and θavg during stage N3 sleep with OAHI (r = .35 [P = .03]). LBIavg showed lower correlations. Median θavg during stage R sleep (33.1) was significantly greater than during stage N3 sleep (13.7, P = .0005).

CONCLUSIONS

Association of θavg with OAI and OAHI shows that θavg reflects airway obstruction and has potential use as a quantitative indicator of OSA. RIP provides valuable information that is readily available in PSG. The significant difference between θavg in stage N3 sleep and stage R sleep confirms the clinical observation that there is more asynchrony during rapid eye movement sleep than non-rapid eye movement sleep.

Non-pharmaceutical management of respiratory morbidity in children with severe global developmental delay

BACKGROUND

Children with severe global developmental delay (SGDD) have significant intellectual disability and severe motor impairment; they are extremely limited in their functional movement and are dependent upon others for all activities of daily living. SGDD does not directly cause lung dysfunction, but the combination of immobility, weakness, skeletal deformity and parenchymal damage from aspiration can lead to significant prevalence of respiratory illness. Respiratory pathology is a significant cause of morbidity and mortality for children with SGDD; it can result in frequent hospital admissions and impacts upon quality of life. Although many treatment approaches are available, there currently exists no comprehensive review of the literature to inform best practice. A broad range of treatment options exist; to focus the scope of this review and allow in-depth analysis, we have excluded pharmaceutical interventions.

OBJECTIVES

To assess the effects of non-pharmaceutical treatment modalities for the management of respiratory morbidity in children with severe global developmental delay.

SEARCH METHODS

We conducted comprehensive searches of the following databases from inception to November 2013: the Cochrane Central Register of Controlled Trials (CENTRAL), MEDLINE, EMBASE, the Allied and Complementary Medicine Database (AMED) and the Cumulative Index to Nursing and Allied Health Literature (CINAHL). We searched the Web of Science and clinical trials registries for grey literature and for planned, ongoing and unpublished trials. We checked the reference lists of all primary included studies for additional relevant references.

SELECTION CRITERIA

Randomised controlled trials, controlled trials and cohort studies of children up to 18 years of age with a diagnosis of severe neurological impairment and respiratory morbidity were included. Studies of airways clearance techniques, suction, assisted coughing, non-invasive ventilation, tracheostomy and postural management were eligible for inclusion.

DATA COLLECTION AND ANALYSIS

We used standard methodological procedures as expected by The Cochrane Collaboration. As the result of heterogeneity, we could not perform meta-analysis. We have therefore presented our results using a narrative approach.

MAIN RESULTS

Fifteen studies were included in the review. Studies included children with a range of severe neurological impairments in differing settings, for example, home and critical care. Several different treatment modalities were assessed, and a wide range of outcome measures were used. Most studies used a non-randomised design and included small sample groups. Only four randomised controlled trials were identified. Non-randomised design, lack of information about how participants were selected and who completed outcome measures and incomplete reporting led to high or unclear risk of bias in many studies. Results from low-quality studies suggest that use of non-invasive ventilation, mechanically assisted coughing, high-frequency chest wall oscillation (HFCWO), positive expiratory pressure and supportive seating may confer potential benefits. No serious adverse effects were reported for ventilatory support or airway clearance interventions other than one incident in a clinically unstable child following mechanically assisted coughing. Night-time positioning equipment and spinal bracing were shown to have a potentially negative effect for some participants. However, these findings must be considered as tentative and require testing in future randomised trials.

AUTHORS' CONCLUSIONS

This review found no high-quality evidence for any single intervention for the management of respiratory morbidity in children with severe global developmental delay. Our search yielded data on a wide range of interventions of interest. Significant differences in study design and in outcome measures precluded the possibility of meta-analysis. No conclusions on efficacy or safety of interventions for respiratory morbidity in children with severe global developmental delay can be made based upon the findings of this review.A co-ordinated approach to future research is vital to ensure that high-quality evidence becomes available to guide treatment for this vulnerable patient group.