Keesense
Heart Failure (HF) is a global health concern that’s affecting over 64 million people around the world. In the USA for example, the total healthcare cost for HF in 2020 was estimated at $43.6 bilion, with more than 70% coming from inpatient medical expenditures. Research has found that HF patients with a history of hospitalization experienced 80.4% “all-cause readmission”, 43.3% HF-specific readmissions and 75.4% mortality rates.
With the global shortage of healthcare resources especially hospital bed units and the growing number of patients suffering from heart failure (46% increase by 2030), innovative solutions are urgently needed to monitor HF patients post-discharge and prevent worsening events. Thanks to the increasing adoption of remote patient monitoring (RPM) solutions, HF patients can safely and reliably have their heart conditions continuously monitored as they recover from the comfort of their homes.
The accurate monitoring and prediction of worsening heart failure events is complicated as it requires a sophisticated set of data analysis into key clinical features that positively correlate with cardiac exacerbations. Therefore, relying on basic, singular methods such as weights monitoring and symptoms checking are simply not adequate. More importantly, commodity consumer-grade wearable sensors have not been scientifically configured to monitor complex physiological signals such as thoracic impedance, which is a significant indicator of potential heart failure exacerbation.
Chronolife’s HF prediction solution is based on a multiparametric remote patient monitoring solution featuring multifactorial algorithms combining thoracic impedance and abdominal respiration with a holistic set of biometrics including heart rate, electrocardiogram, physical activity, and skin temperature, to detect HF clinical decompensation. The comprehensive nature of the medical-grade device allows it to monitor all interrelated symptoms and physiological indicators for HF, including increased lung fluid content, shortness of breath, palpitations, electrical heart signals, and so forth.
According to the International Journal of Heart Failure’s review of existing evidence regarding RPM in HF management, enhancing patient adherence is key to clinical efficacy. Several numbers of existing trials on HF telemonitoring have shown high degrees of patient nonadherence or drop off rates over time. Among the studies of noninvasive biometric sensing demonstrating clinical efficacy, higher patient adherence to data collection and transmission was observed. The study also notes that “automated data transmission via Bluetooth-enabled devices to a central hub has also become an often-employed strategy across many digital RPMs to prevent the need for manual input by patients.”
Chronolife’s HF predictive solution is based on a 100% machine-washable smart t-shirt that wears like any other daily undergarments. It has been shown to achieve a patient compliance rate of 97% because it’s intuitive to use, nonobstructive to patients, and doesn’t require any manual data intake thanks to our machine learning algorithm that is capable of extracting, processing, and analyzing complex data streams on low bandwidth such as smartphones or tablets via bluetooth.
The multiparametric algorithm and the high adherence nature of Chronolife’s HF predictive solution means that all patient data feeding into the predictive algorithm is reliable and comprehensive to generate as accurate alerts as possible regarding potential exacerbation events.
The algorithm can also be embedded with a wide variety of connected devices (such as smart weights and blood pressure monitors) to customize patients’ health status monitoring and prediction programs based on their unique medical history, doctors’ prescriptions, and other lifestyle peculiarities.
