Clinical validation of smartphone-based activity tracking in peripheral artery disease patients

Ata, Raheel; Gandhi, Neil; Rasmussen, Hannah; El-Gabalawy, Osama; Gutierrez, Santiago Ortega; Ahmad, Alizeh; Suresh, Siddharth; Ravi, Roshini; Rothenberg, Kara A.; Aalami, Oliver

doi:10.1038/s41746-018-0073-x

Cited by 44 publications

(60 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Community-based 6MWTs have been performed in chronic stroke patients using a GPS tracker [10] and in heart failure patients using accelerometers and step counters [11]. A smartphone-based method was used by Ata et al [12] for assessing patients with peripheral artery disease, but it relied on the embedded distance measurement of the iPhone and proved to have low accuracy. More promising results were achieved using a custom smartphone app in congestive heart failure and pulmonary hypertension participants [13] or our app, named SMWT, which demonstrated high accuracy and user acceptance in lab tests [14].…”

Section: Introductionmentioning

confidence: 99%

App-Based Versus Standard Six-Minute Walk Test in Pulmonary Hypertension: Mixed Methods Study

Salvi

Poffley

Tarassenko

et al. 2021

JMIR Mhealth Uhealth

View full text Add to dashboard Cite

Background Pulmonary arterial hypertension (PAH) is a chronic disease of the pulmonary vasculature that can lead to heart failure and premature death. Assessment of patients with PAH includes performing a 6-minute walk test (6MWT) in clinics. We developed a smartphone app to compute the walked distance (6MWD) indoors, by counting U-turns, and outdoors, by using satellite positioning. Objective The goal of the research was to assess (1) accuracy of the indoor 6MWTs in clinical settings, (2) validity and test-retest reliability of outdoor 6MWTs in the community, (3) compliance, usability, and acceptance of the app, and (4) feasibility of pulse oximetry during 6MWTs. Methods We tested the app on 30 PAH patients over 6 months. Patients were asked to perform 3 conventional 6MWTs in clinic while using the app in the indoor mode and one or more app-based 6MWTs in outdoor mode in the community per month. Results Bland-Altman analysis of 70 pairs of conventional versus app-based indoor 6MWDs suggests that the app is sometimes inaccurate (14.6 m mean difference, lower and upper limit of agreement: –133.35 m to 162.55 m). The comparison of 69 pairs of conventional 6MWDs and community-based outdoor 6MWDs within 7 days shows that community tests are strongly related to those performed in clinic (correlation 0.89), but the interpretation of the distance should consider that differences above the clinically significant threshold are not uncommon. Analysis of 89 pairs of outdoor tests performed by the same patient within 7 days shows that community-based tests are repeatable (intraclass correlation 0.91, standard error of measurement 36.97 m, mean coefficient of variation 12.45%). Questionnaires and semistructured interviews indicate that the app is usable and well accepted, but motivation to use it could be affected if the data are not used for clinical decision, which may explain low compliance in 52% of our cohort. Analysis of pulse oximetry data indicates that conventional pulse oximeters are unreliable if used during a walk. Conclusions App-based outdoor 6MWTs in community settings are valid, repeatable, and well accepted by patients. More studies would be needed to assess the benefits of using the app in clinical practice. Trial Registration ClinicalTrials.gov NCT04633538; https://clinicaltrials.gov/ct2/show/NCT04633538

show abstract

Section: Introductionmentioning

confidence: 99%

App-Based Versus Standard Six-Minute Walk Test in Pulmonary Hypertension: Mixed Methods Study

Salvi

Poffley

Tarassenko

et al. 2021

JMIR Mhealth Uhealth

View full text Add to dashboard Cite

show abstract

“…Observational health data sources have shed light on individual clinical trajectories 36 , increased self-awareness about individual health 37 , and helped deliver on the promise of precision medicine 38 . Mobile-health solutions enable a high-resolution view of a large, highly diverse range of individuals over time [39][40][41][42] , and can provide insights into chronic diseases and behaviors [43][44][45][46][47][48][49][50][51][52] . Menstrual trackers in particular have become increasingly common: they are the second most popular app for adolescent girls and the fourth most popular for adult women 53,54 .…”

Section: Introductionmentioning

confidence: 99%

Characterizing physiological and symptomatic variation in menstrual cycles using self-tracked mobile-health data

Urteaga

Wiggins

et al. 2020

npj Digit. Med.

View full text Add to dashboard Cite

The menstrual cycle is a key indicator of overall health for women of reproductive age. Previously, menstruation was primarily studied through survey results; however, as menstrual tracking mobile apps become more widely adopted, they provide an increasingly large, content-rich source of menstrual health experiences and behaviors over time. By exploring a database of usertracked observations from the Clue app by BioWink GmbH of over 378,000 users and 4.9 million natural cycles, we show that selfreported menstrual tracker data can reveal statistically significant relationships between per-person cycle length variability and selfreported qualitative symptoms. A concern for self-tracked data is that they reflect not only physiological behaviors, but also the engagement dynamics of app users. To mitigate such potential artifacts, we develop a procedure to exclude cycles lacking user engagement, thereby allowing us to better distinguish true menstrual patterns from tracking anomalies. We uncover that women located at different ends of the menstrual variability spectrum, based on the consistency of their cycle length statistics, exhibit statistically significant differences in their cycle characteristics and symptom tracking patterns. We also find that cycle and period length statistics are stationary over the app usage timeline across the variability spectrum. The symptoms that we identify as showing statistically significant association with timing data can be useful to clinicians and users for predicting cycle variability from symptoms, or as potential health indicators for conditions like endometriosis. Our findings showcase the potential of longitudinal, high-resolution self-tracked data to improve understanding of menstruation and women's health as a whole.

show abstract

“…Digital phenotyping aims at the automatic characterization of a patient's phenotype using electronic data. In conjunction with the advance of data science and machine learning techniques, along with the pervasive use of smartphones, other personal digital devices and wearables, it holds considerable potential for analyzing patient-generated data 20,23 for medical research purposes 12,13,16,[24][25][26][27] .…”

Section: Introductionmentioning

confidence: 99%

Learning endometriosis phenotypes from patient-generated data

2020

View full text Add to dashboard Cite

Endometriosis is a systemic and chronic condition in women of childbearing age, yet a highly enigmatic disease with unresolved questions: there are no known biomarkers, nor established clinical stages. We here investigate the use of patient-generated health data and data-driven phenotyping to characterize endometriosis patient subtypes, based on their reported signs and symptoms. We aim at unsupervised learning of endometriosis phenotypes using self-tracking data from personal smartphones. We leverage data from an observational research study of over 4000 women with endometriosis that track their condition over more than 2 years. We extend a classical mixed-membership model to accommodate the idiosyncrasies of the data at hand, i.e., the multimodality and uncertainty of the self-tracked variables. The proposed method, by jointly modeling a wide range of observations (i.e., participant symptoms, quality of life, treatments), identifies clinically relevant endometriosis subtypes. Experiments show that our method is robust to different hyperparameter choices and the biases of self-tracking data (e.g., the wide variations in tracking frequency among participants). With this work, we show the promise of unsupervised learning of endometriosis subtypes from self-tracked data, as learned phenotypes align well with what is already known about the disease, but also suggest new clinically actionable findings. More generally, we argue that a continued research effort on unsupervised phenotyping methods with patient-generated health data via new mobile and digital technologies will have significant impact on the study of enigmatic diseases in particular, and health in general.

show abstract

Clinical validation of smartphone-based activity tracking in peripheral artery disease patients

Cited by 44 publications

References 30 publications

App-Based Versus Standard Six-Minute Walk Test in Pulmonary Hypertension: Mixed Methods Study

App-Based Versus Standard Six-Minute Walk Test in Pulmonary Hypertension: Mixed Methods Study

Characterizing physiological and symptomatic variation in menstrual cycles using self-tracked mobile-health data

Learning endometriosis phenotypes from patient-generated data

Contact Info

Product

Resources

About