A study of longitudinal mobile health data through fuzzy clustering methods for functional data: The case of allergic rhinoconjunctivitis in childhood

Abstract

The use of mobile communication devices in health care is spreading worldwide. A huge amount of health data collected by these devices (mobile health data) is nowadays available. Mobile health data may allow for real-time monitoring of patients and delivering ad-hoc treatment recommendations. This paper aims at showing how this may be done by exploiting the potentialities of fuzzy clustering techniques. In fact, such techniques can be fruitfully applied to mobile health data in order to identify clusters of patients for diagnostic classification and cluster-specific therapies. However, since mobile health data are full of noise, fuzzy clustering methods cannot be directly applied to mobile health data. Such data must be denoised prior to analyzing them. When longitudinal mobile health data are available, functional data analysis represents a powerful tool for filtering out the noise in the data. Fuzzy clustering methods for functional data can then be used to determine groups of patients. In this work we develop a fuzzy clustering method, based on the concept of medoid, for functional data and we apply it to longitudinal mHealth data on daily symptoms and consumptions of anti-symptomatic drugs collected by two sets of patients in Berlin (Germany) and Ascoli Piceno (Italy) suffering from allergic rhinoconjunctivitis. The studies showed that clusters of patients with similar changes in symptoms were identified opening the possibility of precision medicine.

Digitally‐enabled, patient‐centred care in rhinitis and asthma multimorbidity: The ARIA‐MASK‐air®approach

“…Apps were eligible if symptoms were evaluated. Three apps could be used in 2021, according to criteria required for the study, and two for the purposes of the Combined Symptom‐Medication Score (CSMS) (AllergyMonitor 27 , 28 and MASK‐air ® ).…”

Real‐world data using mHealth apps in rhinitis, rhinosinusitis and their multimorbidities

“…By the B-spline basis system, these coefficients allowed continuous smoothing functions to be found, synthesising the general trend of the observed data. 23 3.1.2 | MASK-air ® MASK, the Phase 3 ARIA (Allergic Rhinitis and its Impact on Asthma) initiative, is a Good Practice of DG Santé for digitallyenabled, patient-centred care. 65,66 It aims to improve the management of AR and asthma multimorbidity in a patient-centred approach and to facilitate shared decision-making.…”

“…Using automatic and manual search methods, we identified six relevant apps for AR for which data have been published in the literature: AllergyMonitor ® , 21 , 22 , 23 , 24 , 25 AirRater ® , 26 MASK‐air ® , 12 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 , 44 , 45 Pollen App (patient's hay fever diary, developed in Austria), 46 , 47 , 48 Husteblume (a mobile phone health app developed in Germany as a spin‐off of Pollen App including the patient hay fever diary) and AllerSearch (Table 1 ). 55 Galenus Health did not have any published data on AR and could therefore not be considered in this section for AR, but will be discussed in the subsection of CRS apps.…”

“…By the B‐spline basis system, these coefficients allowed continuous smoothing functions to be found, synthesising the general trend of the observed data. 23 …”

“…To account for noise when identifying clusters of homogenous patients, the authors applied the fuzzy k ‐medoids algorithm to the obtained functional coefficients. By the B‐spline basis system, these coefficients allowed continuous smoothing functions to be found, synthesising the general trend of the observed data 23 …”