For the first time in a telemonitoring context, we apply the Rome Proposal (RP), recently adopted by GOLD 2023, to assess the severity of exacerbations (ECOPD). So far, we have analysed 387 study weeks, which include only 18 ECOPDs; 4 mild, 13 moderate and 1 severe according to the criteria from RP. There is a promising potential of telemonitoring based on the RP.

Background: Chronic heart failure (CHF) is a common comorbidity among patients with chronic obstructive pulmonary disease (COPD). Both exacerbations of COPD (ECOPDs) and exacerbations of CHF (ECHFs) display worsening of breathlessness at rest (BaR) and breathlessness at physical activity (BaPA). Comorbid CHF may have an impact on the vital signs assessed, when the Rome proposal (adopted by GOLD 2023) is applied on ECOPDs. Thus, the aim of the present study was to investigate the impact of comorbid CHF on ECOPDs severity, particularly focusing on the influence of comorbid CHF on BaR and BaPA. Methods: We analysed data on COPD symptoms collected from the telehealth study The eHealth Diary. Patients with COPD (n = 43) and patients with CHF (n = 41) were asked to daily monitor BaR and BaPA, employing a digital pen and scales for BaR and BaPA (from 0 to 10). Twenty-eight patients of the COPD patients presented with comorbid CHF. Totally, 125 exacerbations were analysed. Results: Exacerbations in the group with COPD patients and comorbid CHF were compared to the group with COPD patients without comorbid CHF and the group with CHF patients. Compared with GOLD 2022, the GOLD 2023 (the Rome proposal) significantly downgraded the ECOPD severity. Comorbid CHF did not interfere significantly on the observed difference. Comorbid CHF did not worsen BaR scores, assessed at inclusion and at the symptom peak of the exacerbations. Conclusion: In the present study, we find no evidence that comorbid CHF would interfere significantly with the parameters included in the Rome proposal (GOLD 2023). We conclude that the Rome proposal can be safely applied even on COPD patients with very advanced comorbid CHF.

Background: GOLD 2023 defines an exacerbation of COPD (ECOPD) by a deterioration of breathlessness at rest (BaR), mucus and cough. The severity of an ECOPD is determined by the degree of BaR, ranging from 0 to 10. However, it is not known which symptom is the most important one to detect early of an ECOPD, and which symptom that predicts future ECOPDs best. Thus, the purpose of the present study was to find out which symptom is the most important one to monitor. Methods: We analysed data on COPD symptoms from the telehealth study The eHealth Diary. Frequent exacerbators (n = 27) were asked to daily monitor BaR and breathlessness at physical activity (BaPA), mucus and cough, employing a digital pen and symptom scales (0–10). Twenty-seven patients with 105 ECOPDs were analysed. The association between symptom development and the occurrence of exacerbations was evaluated using the Andersen–Gill formulation of the Cox proportional hazards model for the analysis of recurrent time-to-event data with time-varying predictors. Results: According to the criteria proposed by GOLD 2023, 42% ECOPDs were mild, 48% were moderate and 5% were severe, while 6% were undefinable. Mucus and cough improved over study time, while BaR and BaPA deteriorated. Mucus appeared earliest, which was the most prominent feature of the average exacerbation, and worsening of mucus increased the risk for a future ECOPD. There was a 58% increase in the risk of exacerbation per unit increase in mucus score. Conclusion: This study suggests that mucus worsening is the most important COPD symptom to monitor to detect ECOPDs early and to predict future risk för ECOPDs. In the present study, we also noticed a pronounced difference between GOLD 2022 and 2023. Hence, GOLD 2023 defined the ECOPD severity much lower than GOLD 2022 did. © 2023 Jacobson et al.

Introduction: In this article, we explore to what extent it is possible to leverage on very small data to build machine learning (ML) models that predict acute exacerbations of chronic obstructive pulmonary disease (AECOPD). Methods: We build ML models using the small data collected during the eHealth Diary telemonitoring study between 2013 and 2017 in Sweden. This data refers to a group of multimorbid patients, namely 18 patients with chronic obstructive pulmonary disease (COPD) as the major reason behind previous hospitalisations. The telemonitoring was supervised by a specialised hospital-based home care (HBHC) unit, which also was responsible for the medical actions needed. Results: We implement two different ML approaches, one based on time-dependent covariates and the other one based on time-independent covariates. We compare the first approach with standard COX Proportional Hazards (CPH). For the second one, we use different proportions of synthetic data to build models and then evaluate the best model against authentic data. Discussion: To the best of our knowledge, the present ML study shows for the first time that the most important variable for an increased risk of future AECOPDs is “maintenance medication changes by HBHC”. This finding is clinically relevant since a sub-optimal maintenance treatment, requiring medication changes, puts the patient in risk for future AECOPDs. Conclusion: The experiments return useful insights about the use of small data for ML. © 2023 Jacobson et al.

Introduction: Growing populations of elderly patients with chronic obstructive pulmonary disease (COPD) or heart failure (HF) require more healthcare. A four-year telehealth intervention – the Health Diary system based on digital pen technology – was implemented. We hypothesized that study patients with advanced COPD or HF would have lower rates of hospitalization when using the Health Diary. The aim was to investigate the effects of the intervention on healthcare costs and the number of hospitalizations, as well as other care required in COPD and HF patients. Methods: Patients were introduced to the telemonitoring system which was supervised by a specialized hospital-based home care (HBHC) unit. Staff associated with this unit were responsible for the healthcare provided. The study included patients with COPD or HF, aged ≥ 65 years who were frequently hospitalized due to exacerbations – at least two inpatient episodes within the last 12 months. Observed number of hospitalizations and total healthcare costs were compared with the expected values, which were calculated using the generalized estimating equations (GEE) method. Results: A total of 36 COPD and 58 HF patients with advanced stages of disease were included. The number of hospitalizations was significantly reduced for both HF and COPD patients participating in telemonitoring. Accordingly, hospitalization costs were significantly reduced for both groups, but the total healthcare cost was not significantly different from the expected costs. Conclusion: A telemonitoring system, the Health Diary, combined with a specialized HBHC unit significantly decreases the need for hospital care in elderly patients with advanced HF or COPD without increasing total healthcare costs.

RDF Stream Processing (RSP) has been proposed as a candidate for bringing together the Complex Event Processing (CEP) paradigm and the Semantic Web standards. In this paper, we investigate the impact of explicitly representing and processing uncertainty in RSP for the use in CEP. Additionally, we provide a representation for capturing the relevant notions of uncertainty in the RSP-QL data model and describe query functions that can operate on this representation. The impact evaluation is based on a use-case within electronic healthcare, where we compare the query execution overhead of different uncertainty options in a prototype implementation. The experiments show that the influence on query execution performance varies greatly, but that uncertainty can have noticeable impact on query execution performance. On the other hand, the overhead grows linearly with respect to the stream rate for all uncertainty options in the evaluation, and the observed performance is sufficient for many use-cases. Extending the representation and operations to support more uncertainty options and investigating different query optimization strategies to reduce the impact on execution performance remain important areas for future research.

Background: Elderly, multimorbid patients with advanced chronic obstructive pulmonary disease (COPD) and/or chronic heart failure (CHF) exhibit poor health-related quality of life (HRQoL). Telemonitoring, based on digital pen technology, supported by hospital-based home care (HBHC) significantly reduces the number of hospitalizations. We hypothesized that the same intervention would prevent the deterioration of HRQoL that follows upon disease progression. Methods: Elderly computer-illiterate subjects with ≥2 hospitalizations the previous year were included. HRQoL was assessed at inclusion (baseline) and at 1, 6 and 12 months employing EuroQol-5 Dimensions (EQ-5D) and RAND-36 for general HRQoL, and Minnesota Living with Heart Failure Questionnaire (MLHFQ) and St. Georges Respiratory Questionnaire (SGRQ) for disease-specific HRQoL. Healthcare contacts, hospitalizations, as-needed medications, prescription changes and healthcare costs were registered. Results: Ninety-four patients were enrolled of which 53 subjects completed the 12-month study period. Compared to baseline, most domains of RAND-36 were improved significantly at 1 time-point or more. Only among COPD subjects, the disease-specific HRQoL was worsened at the 12 month evaluation. Measures of healthcare dependency were associated with poor HRQoL. Conclusion: The Health Diary system and HBHC together improve general HRQoL, and measures of healthcare dependency are associated with HRQoL variables. © 2020 Persson et al.

In the era of data-driven science, corpus-based language technology is an essential part of cyber physicalsystems. In this chapter, the authors describe the design and the development of an extensible domainspecificweb corpus to be used in a distributed social application for the care of the elderly at home.The domain of interest is the medical field of chronic diseases. The corpus is conceived as a flexible andextensible textual resource, where additional documents and additional languages will be appendedover time. The main purpose of the corpus is to be used for building and training language technologyapplications for the “layfication” of the specialized medical jargon. “Layfication” refers to the automaticidentification of more intuitive linguistic expressions that can help laypeople (e.g., patients, familycaregivers, and home care aides) understand medical terms, which often appear opaque. Exploratoryexperiments are presented and discussed.

BACKGROUND: Elderly patients with advanced stages of COPD or chronic heart failure (CHF) often require hospitalization due to exacerbations. We hypothesized that telemonitoring supported by hospital-based home care (HBHC) would detect exacerbations early, thus, reducing the number of hospitalization. We also speculated that patients with advanced COPD or CHF would present differences regarding exacerbation frequency and the need of HBHC. METHODS: The Health Diary system, based on digital pen technology, was employed. Patients aged ≥65 years with ≥2 hospitalizations the previous year were included. Exacerbations were categorized and treated as either COPD or CHF exacerbation by an experienced physician. All HBHC contacts (home visits or telephone consultations) were registered. RESULTS: Ninety-four patients with advanced diseases were enrolled (36 COPD and 58 CHF subjects) of which 53 subjects (19 COPD and 34 CHF subjects) completed the 1-year study period. Death was the major reason for not finalizing the study. Compared to the 1-year prior inclusion, the intervention significantly reduced hospitalization. Although COPD subjects were younger with less comorbidity, exacerbations and HBHC contacts were significantly greater in this group. CONCLUSIONS: COPD subjects exhibit exacerbations more frequently, mainly due to disease characteristics, thus, demanding much more HBHC.

RSP-QL was developed by the W3C RDF Stream Processing (RSP) community group as a common way to express and query RDF streams. However, RSP-QL does not provide any way of annotating data on the statement level, for example, to express the uncertainty that is often associated with streaming information. Instead, the only way to provide such information has been to use RDF reification, which adds additional complexity to query processing, and is syntactically verbose. In this paper, we define an extension of RSP-QL, called RSP-QL⋆⋆, that provides an intuitive way for supporting statement-level annotations in RSP. The approach leverages the concepts previously described for RDF* and SPARQL*. We illustrate the proposed approach based on a scenario from a research project in e-health. An open-source implementation of the proposal is provided and compared to the baseline approach of using RDF reification. The results show that this way of dealing with statement-level annotations offers advantages with respect to both data transfer bandwidth and query execution performance.