Artificial intelligence based data curation: enabling a patient-centric European health data space.

The emerging European Health Data Space (EHDS) Regulation opens new prospects for large-scale sharing and re-use of health data. Yet, the proposed regulation suffers from two important limitations: it is designed to benefit the whole population with limited consideration for individuals, and the generation of secondary datasets from heterogeneous, unlinked patient data will remain burdensome. AIDAVA, a Horizon Europe project that started in September 2022, proposes to address both shortcomings by providing patients with an AI-based virtual assistant that maximises automation in the integration and transformation of their health data into an interoperable, longitudinal health record. This personal record can then be used to inform patient-related decisions at the point of care, whether this is the usual point of care or a possible cross-border point of care. The personal record can also be used to generate population datasets for research and policymaking. The proposed solution will enable a much-needed paradigm shift in health data management, implementing a 'curate once at patient level, use many times' approach, primarily for the benefit of patients and their care providers, but also for more efficient generation of high-quality secondary datasets. After 15 months, the project shows promising preliminary results in achieving automation in the integration and transformation of heterogeneous data of each individual patient, once the content of the data sources managed by the data holders has been formally described. Additionally, the conceptualization phase of the project identified a set of recommendations for the development of a patient-centric EHDS, significantly facilitating the generation of data for secondary use.

Evaluation of frailty in geriatric patients undergoing cardiac rehabilitation after cardiac procedure: results of a prospective, cross-sectional study.

BACKGROUND: Frailty is an indicator of a decline in quality of life and functional capacity in cardiac rehabilitation (CR) patients. Currently, there is no standardized assessment tool for frailty used in CR. The aim of this study was to determine if the Clinical Frailty Scale (CFS) is feasible for assessing frailty in CR. METHODS: Prospective, cross-sectional study within the framework of the ongoing multicenter prehabilitation study "PRECOVERY". Patients ≥75 years undergoing CR after cardiac procedure (n=122) were recruited in four German inpatient CR facilities. Assessments included: CFS, Katz-Index, hand grip strength (HGS), Short Physical Performance Battery (SPPB) and six-minute-walk test (6MWT). Outcomes were frailty (CFS≥4) and the correlation of frailty with assessments of functional capacity, activities of daily living and clinical parameters. Statistical analysis included descriptive statistics and correlations, using the spearman correlation coefficient and chi-square test to test for significance. RESULTS: Data from 101 patients (79.9±4.0 years; 63% male) were analyzed. The mean CFS score was 3.2±1.4; 41.6% were defined as frail (CFS≥4). The mean time required to assess the CFS was 0.20 minutes. The findings show that CFS correlates significantly (p<0.001) with the following factors: Katz-Index, HGS, SPPB-Score and 6MWT (r≤-0.575). In addition, CFS correlated with small to moderate effects with co-morbidities (r=0.250), as-needed medications and need for nursing assistance (r≤0.248). CONCLUSIONS: The CFS assessment can be performed in under one minute and it correlates significantly with assessments of functional capacity, activities of daily living and clinical parameters in the CR setting. TRIAL REGISTRATION: German Clinical Trials Register (DRKS; http:// www. drks. de; DRKS00032256). Retrospectively registered on 13 July 2023.

Cocreation to Facilitate Communication and Collaboration Between Multidisciplinary Stakeholders in eHealth Research and Development: Case Study of the CARRIER (Coronary Artery Disease: Risk Estimations and Interventions for Prevention and Early Detection) Consortium.

BACKGROUND: Collaboration with diverse stakeholders in eHealth research is fundamental yet complex. Stakeholders from various disciplines do not "speak the same language" and have different levels of power and interest, resulting in contrasting objectives, priorities, and expectations. An approach to constructive communication and collaboration is necessary to overcome this complex dynamic. Cocreation, known in the field of eHealth most often to involve end users, may also be suitable for facilitating stakeholder engagement and alignment. OBJECTIVE: This paper provides insights into the application of cocreation, specifically in the early phases of research that focus on involving and aligning relevant stakeholders from different academic and professional backgrounds. METHODS: The case for this study was a group discussion with members of a multidisciplinary consortium that works on developing a personalized eHealth intervention for atherosclerotic cardiovascular disease. Using stakeholder mapping, health and medicine experts, big data scientists, software developers, and an innovation manager (N=8) were invited to participate. The discussion was based on a user scenario and structured according to the Six Thinking Hats of de Bono, representing 6 different types of thinking. The discussion was recorded, transcribed verbatim, and analyzed thematically with the use of ATLAS.ti software. RESULTS: First, informative and intuitive thinking served the preparatory purpose of familiarization with the project details and other participants. Second, positive and critical thinking constituted the body of the discussion and resulted in an in-depth conversation. Third, creative and organizational thinking were action oriented and focused on solutions and planning to safeguard future progress. The participants repeatedly reflected on various intervention-related themes, ranging from intervention content to technical functionalities and from legal requirements to implementation in practice. Moreover, project-related matters were discussed, including stakeholder management and time and budget constraints. CONCLUSIONS: This paper demonstrates how cocreation can be of value for multidisciplinary stakeholder engagement and alignment. Based on stakeholder mapping (with whom to discuss), a dream user scenario (what to discuss), and the Six Thinking Hats of de Bono (how to discuss), the participants shared information, discussed differences, searched for solutions, and moved toward a collective approach regarding intervention development. The lessons learned may further improve the understanding of how cocreation can contribute to multidisciplinary collaboration.

Reasons and predictors of non-participation in a personalized digital prehabilitation care trial for patients undergoing elective cardiothoracic surgery.

OBJECTIVES: Prehabilitation through a digital platform could preoperatively improve the physical and mental fitness of patients undergoing cardiothoracic surgery, thereby improving treatment outcomes. This study aimed to describe the reasons and predictors of non-participation in a personalized digital prehabilitation care trial (Digital Cardiac Counseling randomized controlled trial) for patients undergoing elective cardiothoracic surgery. METHODS: Adult patients scheduled for elective cardiothoracic surgery at the Maastricht University Medical Center+ were approached to participate in a digital prehabilitation care trial, in which patients were informed about their care pathway, monitored for symptom progression and screened for preoperative modifiable risk factors. Baseline characteristics of all eligible patients and reasons of non-participation were registered prospectively. Predictors of non-participation were determined using logistic regression. RESULTS: Between May 2020 and August 2022, 815 patients were eligible for participation; 421 (52%) did not participate in the personalized digital prehabilitation care trial. Reasons for non-participation were 'lack of internet access or insufficient digital skills' (32%), 'wishing no participation' (39%) and 'other reasons' (30%; e.g. vision or hearing impairments, analphabetism, language barriers). Independent predictors of non-participation were age [odds ratio (OR) 1.024 (1.003-1.046), P = 0.024], socioeconomic status [OR 0.267 (0.133-0.536), P < 0.001], current smoker [OR 1.823 (1.124-2.954), P = 0.015] and EuroSCORE II [OR 1.160 (1.042-1.292), P = 0.007]. CONCLUSIONS: Half of the eligible patients did not participate in a personalized digital prehabilitation care trial. Non-participants were vulnerable patients, with a more unfavourable risk profile and more modifiable risk factors, who could potentially benefit the most from prehabilitation.

Using clinical prediction models to personalise lifestyle interventions for cardiovascular disease prevention: A systematic literature review.

This study aimed to systematically review the use of clinical prediction models (CPMs) in personalised lifestyle interventions for the prevention of cardiovascular disease. We searched PubMed and PsycInfo for articles describing relevant studies published up to August 1, 2021. These were supplemented with items retrieved via screening references of citations and cited by references. In total, 32 studies were included. Nineteen different CPMs were used to guide the intervention. Most frequently, a version of the Framingham risk score was used. The CPM was used to inform the intensity of the intervention in five studies (16 %), and the intervention's type in 31 studies (97 %). The CPM was supplemented with relative risk estimates for additional risk factors in three studies (9 %), and relative risk estimates for intervention effects in four (13 %). In addition to the estimated risk, the personalisation was determined using criteria based on univariable risk factors in 18 studies (56 %), a lifestyle score in three (9 %), and a physical examination index in one (3 %). We noted insufficient detail in reporting regarding the CPM's use in 20 studies (63 %). In 15 studies (47 %), the primary outcome was a CPM estimate. A statistically significant effect favouring the intervention to the comparator arm was reported in four out of eight analyses (50 %), and a statistically significant improvement compared to baseline in five out of seven analyses (71 %). Due to the design of the included studies, the effect of the use of CPMs is still unclear. Therefore, we see a need for future research.

Digital Health Solutions to Reduce the Burden of Atherosclerotic Cardiovascular Disease Proposed by the CARRIER Consortium.

Digital health is a promising tool to support people with an elevated risk for atherosclerotic cardiovascular disease (ASCVD) and patients with an established disease to improve cardiovascular outcomes. Many digital health initiatives have been developed and employed. However, barriers to their large-scale implementation have remained. This paper focuses on these barriers and presents solutions as proposed by the Dutch CARRIER (ie, Coronary ARtery disease: Risk estimations and Interventions for prevention and EaRly detection) consortium. We will focus in 4 sections on the following: (1) the development process of an eHealth solution that will include design thinking and cocreation with relevant stakeholders; (2) the modeling approach for two clinical prediction models (CPMs) to identify people at risk of developing ASCVD and to guide interventions; (3) description of a federated data infrastructure to train the CPMs and to provide the eHealth solution with relevant data; and (4) discussion of an ethical and legal framework for responsible data handling in health care. The Dutch CARRIER consortium consists of a collaboration between experts in the fields of eHealth development, ASCVD, public health, big data, as well as ethics and law. The consortium focuses on reducing the burden of ASCVD. We believe the future of health care is data driven and supported by digital health. Therefore, we hope that our research will not only facilitate CARRIER consortium but may also facilitate other future health care initiatives.

Corrigendum to: Personalized teleprehabilitation in elective cardiac surgery: a study protocol of the Digital Cardiac Counselling randomized controlled trial.

[This corrects the article DOI: 10.1093/ehjdh/ztab041.].

Last-minute cancellation of adult patients scheduled for cardiothoracic surgery in a large Dutch tertiary care centre.

OBJECTIVES: Unanticipated cancellation of a surgical procedure is a common problem, causing distress to the patient and increases in healthcare costs. However, limited evidence exists on the effects of last-minute cancellations of cardiothoracic surgical procedures in particular. The goal of this study was to gain insight into the prevalence of and the reasons for last-minute cancellations and to examine whether cancellation is associated with adverse medical outcomes. METHODS: Patients who were scheduled for elective cardiothoracic surgical procedures between January 2017 and June 2019 were evaluated. The reasons for the cancellations were assigned to the categories medically related or process related. We examined the differences in patient characteristics between those designated as no cancellation, medically related cancellations and process-related cancellations. Lastly, we examined the outcomes of patients who experienced a last-minute cancellation of a scheduled operation. RESULTS: A total of 2111 patients were included; of these, 301 (14.3%) had last-minute cancellations. In 78 (26%) cases, the cancellations were attributable to medical reasons (e.g. infection, comorbidities); 215 (71%) of the cancellations were process related (e.g. another patient in more urgent need of surgery, lack of staff). Almost 99% of the operations with a process-related cancellation were rescheduled compared to only 71.8% of the medically related cancelled operations (P < 0.001). Patients with a medically related cancellation had significantly higher 1-year mortality than patients who had no cancellation (unadjusted hazard ratio 2.50; 95% confidence interval, 1.30-4.78; P = 0.006); after adjustment for the EuroSCORE II, this effect remained significant. CONCLUSIONS: Last-minute cancellations were commonly seen in our cohort, and the reasons for cancellation were significantly related to adverse medical outcomes.

Personalized teleprehabilitation in elective cardiac surgery: a study protocol of the Digital Cardiac Counselling randomized controlled trial.

Aims: Previous research has shown the possibility to use the pre-operative period to improve a patient's tolerance for surgery. However, there is limited experience with prehabilitation in cardiac surgery. The aim of this study is to evaluate the effect of a comprehensive personalized teleprehabilitation programme on major adverse cardiac events (MACE) in patients scheduled for elective cardiac surgery. Secondary outcomes are post-operative complications, cardiovascular risk factors, quality of life, and cost-effectiveness. Methods and results: In this single-centre randomized controlled trial, patients are eligible for inclusion when they are ≥18 years of age and cardiac surgery is scheduled at least 8 weeks from informed consent. Participants will be randomized to the teleprehabilitation group or the control group. After a digital baseline screening for perioperative risk factors, patients in the intervention arm can pre-operatively be referred to one or more of the prehabilitation modules (functional exercise training, inspiratory muscle training, psychological support, nutritional support, and/or smoking cessation). The programme is targeted at a duration of at least 6 weeks. It is executed by a multidisciplinary team using (video)calls and supported by a custom-made digital platform. During the pre-operative period, the platform is also used to inform patients about their upcoming surgery and for telemonitoring. Conclusion: Reducing perioperative risk factors might result in a reduction of MACE, post-operative complications, length of stay, and cardiovascular risk factors, as well as improved quality of life. Cost-effectiveness will be evaluated.