Using IoT and machine learning to track the progression of lung disease

Using IoT and machine learning to track the progression of lung disease

IBM scientists Thomas Brunschwiler and Rahel Straessle are developing machine learning algorithms to interpret the IoT data.

Chronic obstructive pulmonary disease, a.k.a. COPD, is a progressive lung disease which causes breathlessness and is often caused by cigarette smoke and air pollution.

By 2030, it is expected to be the third leading cause of death worldwide, with 90% occurring in low and middle-income countries, according to the World Health Organization.

The Centers for Disease Control and Prevention reports that by 2020 the expected cost of medical care for adults in the US with COPD will be more than $90 billion, mainly due to complications and multiple hospitalizations, many of which are preventable with better healthcare management and more personalized and frequent patient support.

Technology to manage COPD

Management and prevention of COPD is the focus of a new research project presented today at the 19th annual IEEE Healthcom Conference, in Dalian, China. IBM researchers in Zurich are collaborating with Swiss start-up docdok.health to develop a set of sensor and machine learning technologies that aim to improve the life quality of COPD patients, facilitate patient-physician communication and simultaneously reduce the financial burden on healthcare systems.

“As most chronic diseases progress outside the hospital we need a secure way to monitor patients when they are discharged,” said Dr. Ulrich Muehlner, CEO, docdok.health. “In this project we are demonstrating that mobile-health technologies have the potential to not only offer frequent patient support at scale and low cost, but also to provide health care that is tailored specifically to individual patient needs.”

Clinical trials are expected to begin in early 2018 at the Zurich University Hospital and will initially involve up to 100 participants wearing Internet of Things (IoT) devices, which will record their symptoms and vital-signs, such as cough intensity, sputum (salvia and mucus) color, lung function, breath rate and heart rate, oxygen saturation, as well as their activity. The wearable devices are being provided by Biovotion, Foobot and Nuvoair.

COPD patient app, depicting the patient-physician disease-related communication (Courtesy of docdok.health Ltd.)

Post-trial analysis

Upon completion of the trial, docdok.health will analyze multi-sensor data using machine learning algorithms developed by IBM scientists to derive correlations and patterns. In the future, the algorithms derived from these patterns could be useful to identify the status and progression of the disease and to predict acute events, called exacerbations, where patients nearly suffocate and require re-hospitalization. Future applications may also allow predictions to be shared via the docdok.health communication platform with treating physicians, who could then intervene in a patient-specific way and alter the patient’s medication to reduce the risk of  such acute events from occurring again.

“As doctors are confronted with increasing chronic illness in an aging population, we want to challenge the traditional physician office visits and encourage self-care by providing easy-to-use technology. We must be able to detect pre-acute conditions before the patient clinically decompensates and shows up in the emergency room,” said Dr. Christian Clarenbach, an attending physician in the department of pulmonology at the Zurich University Hospital. (Switzerland-based patients interested in the trial should contact Dr. Clarenbach)

Coaching

As per the peer-reviewed journal BMC Pulmonary Medicine, inactive COPD patients tend to be at an increased risk of exacerbations, hospitalizations and mortality. To motivate patients to become more active, the docdok.health communication platform could expand to include reminder messages, information material and activity scores to be shared with patients and doctors. Activity targets could also be personalized, based on individual patient status including physiological, psychological and societal conditions, such as support from friends and family.

“We believe that machine learning algorithms may someday be able to help doctors and patients predict and prevent exacerbations of the disease and also provide personalized virtual coaching to improve medication adherence and activity level,” states Thomas Brunschwiler, IBM Research scientist and project leader. “If a virtual coach can motivate patients to be more active it would not only improve their quality of life, it could also reduce the cost burden on healthcare systems which are increasingly becoming overwhelmed.”

Save

Save

Save

The post Using IoT and machine learning to track the progression of lung disease appeared first on IBM Blog Research.

#bluemix,#awvi,#ibm

IBM

via IBM Blog Research https://ibm.co/2cYaEHU

October 13, 2017 at 06:33AM

Leave a Reply

Please log in using one of these methods to post your comment:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s