Use of predictive algorithms in-home monitoring of chronic obstructive pulmonary disease and asthma

Abstract

Major reported factors associated with the limited effectiveness of home telemonitoring interventions in chronic respiratory conditions include the lack of useful early predictors, poor patient compliance and the poor performance of conventional algorithms for detecting deteriorations. This article provides a systematic review of existing algorithms and the factors associated with their performance in detecting exacerbations and supporting clinical decisions in patients with chronic obstructive pulmonary disease (COPD) or asthma. An electronic literature search in Medline, Scopus, Web of Science and Cochrane library was conducted to identify relevant articles published between 2005 and July 2015. A total of 20 studies (16 COPD, 4 asthma) that included research about the use of algorithms in telemonitoring interventions in asthma and COPD were selected. Differences on the applied definition of exacerbation, telemonitoring duration, acquired physiological signals and symptoms, type of technology deployed and algorithms used were found. Predictive models with good clinically reliability have yet to be defined, and are an important goal for the future development of telehealth in chronic respiratory conditions. New predictive models incorporating both symptoms and physiological signals are being tested in telemonitoring interventions with positive outcomes. However, the underpinning algorithms behind these models need be validated in larger samples of patients, for longer periods of time and with wellestablished protocols. In addition, further research is needed to identify novel predictors that enable the early detection of deteriorations, especially in COPD. Only then will telemonitoring achieve the aim of preventing hospital admissions, contributing to the reduction of health resource utilization and improving the quality of life of patients.

Feasibility of Using a Smartwatch to Intensively Monitor Patients With Chronic Obstructive Pulmonary Disease: Prospective Cohort Study (Preprint)

“…While most previous COPD telemonitoring studies collected data daily, [11] the one study with more frequent collection used a custom wristband that was designed to perform 5 measurements of their oxygen saturation, heart rate, body temperature, and physical activity every 3 hours. [18] However, they obtained on average only 4 recordings per patient day, and data was available for only 60% of patient days, seemingly due to lack of use of their system.…”

“…A recent systematic review examined the effectiveness of home telemonitoring of people with COPD in predicting AECOPD. [11] Of the 16 studies that evaluated the predictive ability of systems that recorded physiologic parameters and/or symptoms, none appeared to be clinically reliable in predicting AECOPDs. One reason may be that most data is collected too infrequently.…”

“…Most systems collected data once daily, potentially missing the sensitivity required to detect AECOPDs early. [11] The emergence of consumer wearables such as smartwatches offers a potential practical and affordable method to monitor and collect early signs frequently, even continuously, to detect concerning symptoms. However, such devices can only work if they are worn and maintained.…”

“…[13;14] The difficulty in reliably measuring physiologic data has been another reason attributed to the inability for telemonitoring to predict AECOPDs. [11] Our goal is to improve the care of people with COPD and reduce hospitalizations by providing patients with a practical way to monitor their condition to detect early exacerbations, allowing for timely intervention. In this study, we sought to determine whether patients with COPD would use, wear, and maintain a smartwatch for extended periods of time and whether such a device could reliably capture near-continuous sensor data.…”

Improving prediction of risk of hospital admission in chronic obstructive pulmonary disease: application of machine learning to telemonitoring data (Preprint)

“…There is increasing interest in the development of more accurate predictive algorithms using machine learning; Sanchez-Morillo [ 38 ] and colleagues in a recent review concluded that while some of these show promise that they have been based on relatively small numbers of patients and events. [ , who used logistic regression to predict future exacerbations and showed that using pulse rate, oxygen saturation, and respiratory rate (from a pulse oximeter) showed improved predictivity when compared with traditional algorithms of COPD exacerbations.…”