Simplification of Mobility Tests and Data Processing to Increase Applicability of Wearable Sensors as Diagnostic Tools for Parkinson's Disease.

Quantitative mobility analysis using wearable sensors, while promising as a diagnostic tool for Parkinson's disease (PD), is not commonly applied in clinical settings. Major obstacles include uncertainty regarding the best protocol for instrumented mobility testing and subsequent data processing, as well as the added workload and complexity of this multi-step process. To simplify sensor-based mobility testing in diagnosing PD, we analyzed data from 262 PD participants and 50 controls performing several motor tasks wearing a sensor on their lower back containing a triaxial accelerometer and a triaxial gyroscope. Using ensembles of heterogeneous machine learning models incorporating a range of classifiers trained on a set of sensor features, we show that our models effectively differentiate between participants with PD and controls, both for mixed-stage PD (92.6% accuracy) and a group selected for mild PD only (89.4% accuracy). Omitting algorithmic segmentation of complex mobility tasks decreased the diagnostic accuracy of our models, as did the inclusion of kinesiological features. Feature importance analysis revealed that Timed Up and Go (TUG) tasks to contribute the highest-yield predictive features, with only minor decreases in accuracy for models based on cognitive TUG as a single mobility task. Our machine learning approach facilitates major simplification of instrumented mobility testing without compromising predictive performance.

Adverse Effects After Prehospital Administration of Naloxone by Bystanders: A Preliminary Study.

OBJECTIVE: Opioid use disorder is a cause of significant morbidity and mortality. In order to reverse opioid overdose as quickly as possible, many institutions and municipalities have encouraged people with no professional medical training to carry and administer naloxone. This study sought to provide preliminary data for research into the rates of adverse effects of naloxone when administered by bystanders compared to Emergency Medical Services (EMS) personnel, since this question has not been studied previously. METHODS: This was a retrospective cohort study performed at an urban, tertiary, academic medical center that operates its own EMS service. A consecutive sample of patients presenting to EMS with opioid overdose requiring naloxone was separated into two groups based on whether naloxone was administered by bystanders or by EMS personnel. Each group was analyzed to determine the incidence of four pre-specified adverse events. RESULTS: There was no significant difference in the rate of adverse events between the bystander (19%) and EMS (16%) groups (OR = 1.23; 95% CI, 0.63 - 2.32; P = .499) in this small sample. Based on these initial results, a study would need a sample size of 6,188 in order to reach this conclusion with 80% power. Similarly, there were no significant differences in the rates of any of the individual adverse events. Secondary analysis of patients' demographics showed differences between the two groups which generate hypotheses for further investigation of disparities in naloxone administration. CONCLUSIONS: This preliminary study provides foundational data for further investigation of naloxone administration by bystanders. Adverse events after the prehospital administration of naloxone are rare, and future studies will require large sample sizes. These preliminary data did not demonstrate a statistically significant difference in adverse event rates when comparing naloxone administration by bystanders and EMS clinicians. This study provides data that will be useful for conducting further research on multiple facets of this topic.

Parental Concordance Regarding Problems and Hopes for Seriously Ill Children: A Two-Year Cohort Study.

CONTEXT: Parents of a seriously ill child may have different concerns and hopes for their child, and these concerns and hopes may change over time. OBJECTIVES: In a mixed-method prospective cohort of parental dyads of children with serious illness, to describe the major problems and hopes perceived for their child, examine the degree of concordance between parents, and assess whether prevalence and concordance change over time. METHODS: Eighty-four parents (42 dyads) of seriously ill children reported the major problems and hopes for their children at baseline. Thirty-two parents (16 dyads) answered the same questions at 24 months. Problems and hopes were classified into nine domains. Observed concordance was calculated between parents on each domain. Data for parents of 11 children who died are reported separately. RESULTS: The most common major problem and hope domains at baseline were physical body, quality of life, future health and well-being, and medical care. Parental dyads demonstrated a moderately high percentage of concordance (69%) regarding reported problem domains and a slightly lower percentage of concordance on hopes (61%), with higher concordance for more common domains. Domain prevalence and concordance changed considerably at 24 months. Parents of children who later died showed markedly different patterns of domain prevalence and more extreme patterns of concordance. CONCLUSION: Parents of children with serious illness may have different perspectives regarding major problems and hopes, and these perspectives change over time. Parents of sicker children are more likely to be in either complete agreement or disagreement regarding the problems and hopes they identify.