Mining telemonitored physiological data and patient-reported outcomes of congestive heart failure patients

Abstract

This paper addresses patient-reported outcomes (PROs) and telemonitoring in congestive heart failure (CHF), both increasingly important topics. The interest in CHF trials is shifting from hard end-points such as hospitalization and mortality, to softer end-points such health-related quality of life. However, the relation of these softer end-points to objective parameters is not well studied. Telemonitoring is suitable for collecting both patient-reported outcomes and objective parameters. Most telemonitoring studies, however, do not take full advantage of the available sensor technology and intelligent data analysis. The Chiron clinical observational study was performed among 24 CHF patients (17 men and 7 women, age 62.9 ± 9.4 years, 15 NYHA class II and 9 class III, 10 of ishaemic, aetiology, 6 dilated, 2 valvular, and 6 of multiple aetiologies or cardiomyopathy) in Italy and UK. A large number of physiological and ambient parameters were collected by wearable and other devices, together with PROs describing how well the patients felt, over 1,086 days of observation. The resulting data were mined for relations between the objective parameters and the PROs. The objective parameters (humidity, ambient temperature, blood pressure, SpO2, and sweeting intensity) could predict the PROs with accuracies up to 86% and AUC up to 0.83, making this the first report providing evidence for ambient and physiological parameters to be objectively related to PROs in CHF patients. We also analyzed the relations in the predictive models, gaining some insights into what affects the feeling of health, which was also generally not attempted in previous investigations. The paper strongly points to the possibility of using PROs as primary end-points in future trials.

Association of patient-reported outcomes and heart rate trends in heart failure: a report from the Chiron project

“…Our findings are explorative and hypothesis generating only. In fact, although Chiron study generated an enormous and refined quantity of data due to the large number of measurements and their quality, the absolute number of patients was small and does not allow any definitive conclusion about the investigated topic 13,14,16,17 . Our results were obtained in patients with chronic stable mild to moderate HF and low ejection fraction and generalizations are not possible out of this HF subgroup.…”

“…The clinical characteristics and variables' selection, primary objectives, the telemonitoring system, the protocol and the gross outcomes of this study have been previously described in detail 13 . In brief, the Chiron project conducted a clinical observational study in two countries (Italy and UK) among patients in sinus rhythm with chronic systolic HF and moderate symptoms (NYHA class II or III) with the aim of developing a comprehensive framework for personalized health management including mobile, home and hospital services 13,14 . The study was conducted in accordance with the Declaration of Helsinki and approved by site ethics committees 13 .…”

“…In brief, the Chiron project conducted a clinical observational study in two countries (Italy and UK) among patients in sinus rhythm with chronic systolic HF and moderate symptoms (NYHA class II or III) with the aim of developing a comprehensive framework for personalized health management including mobile, home and hospital services 13,14 . The study was conducted in accordance with the Declaration of Helsinki and approved by site ethics committees 13 . All participants gave written informed consent to participate in the trial.…”

“…Therefore, in order to make the difference among classes as larger as possible we decided to use only two classes corresponding to good and bad feeling of health. To identify which of the feelings should be included in the two classes, we tested nine different class definitions that included different combinations of reported feelings for different periods (i.e 1 vs 5 for one day; 1 and 2 vs 4 and 5 for two out of last three days; ect), obtaining the best differentiation between the extreme classes when patients reported to feel worse (options 1 and 2) or better (options 4 and 5) for three out of the last three to five days 13 .…”

A Personal Decision Support System for Heart Failure Management (HeartMan): study protocol of the HeartMan randomized controlled trial

“…HRQoL and perceived health status, both patient-reported outcomes (PROs), have increasingly been recognized as outcomes of interest in HF and coronary patients [ 12 , 13 ]. PROs are not surrogates for harder endpoints such as mortality, but rather represent independent outcomes [ 14 ].…”