Sevda Ece Kizilkilic

Sevda Ece Kizilkilic

Auto-generated profile, based on publicly available information

Sevda Ece Kizilkilic

Hasselt University

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 February 2024 in European Heart Journal - Digital Health
Verified
Journal Article
Open access
PDF file
MFMaarten Falter
Maarten Falter
DGDries Godderis
Dries Godderis
MSMartijn Scherrenberg
Martijn Scherrenberg
SKSevda Ece Kizilkilic
Sevda Ece Kizilkilic
LXLinqi Xu
Linqi Xu
PDPaul Dendale
Paul Dendale
ICD codes are used for classification of hospitalizations. The codes are used for administrative, financial, and research purposes. It is known, however, that errors occur. Natural language processing (NLP) offers promising solutions for optimizing the process. To investigate methods for automatic classification of disease in unstructured medical records using NLP and to compare these to conventional ICD coding. Two datasets were used: the open-source Medical Information Mart for Intensive Care (MIMIC)-III dataset (n = 55.177) and a dataset from a hospital in Belgium (n = 12.706). Automated searches using NLP algorithms were performed for the diagnoses ‘atrial fibrillation (AF)’ and ‘heart failure (HF)’. Four methods were used: rule-based search, logistic regression, term frequency-inverse document frequency (TF-IDF), Extreme Gradient Boosting (XGBoost), and Bio-Bidirectional Encoder Representations from Transformers (BioBERT). All algorithms were developed on the MIMIC-III dataset. The best performing algorithm was then deployed on the Belgian dataset. After preprocessing a total of 1438 reports was retained in the Belgian dataset. XGBoost on TF-IDF matrix resulted in an accuracy of 0.94 and 0.92 for AF and HF, respectively. There were 211 mismatches between algorithm and ICD codes. One hundred and three were due to a difference in data availability or differing definitions. In the remaining 108 mismatches, 70% were due to incorrect labelling by the algorithm and 30% were due to erroneous ICD coding (2% of total hospitalizations). A newly developed NLP algorithm attained a high accuracy for classifying disease in medical records. XGBoost outperformed the deep learning technique BioBERT. NLP algorithms could be used to identify ICD-coding errors and optimize and support the ICD-coding process.

28 August 2025 in European Journal of Preventive Cardiology
Verified
Journal Article
Closed access
SKSevda Ece Kizilkilic
Sevda Ece Kizilkilic
WRWim Ramakers
Wim Ramakers
MFMaarten Falter
Maarten Falter
MSMartijn Scherrenberg
Martijn Scherrenberg
CBCindel Bonneux
Cindel Bonneux
PDPaul Dendale
Paul Dendale
Aims: The aim of the study is to evaluate the effectiveness of combining centre-based cardiac rehabilitation (CR) with shared decision-making (SDM) based telerehabilitation (TR) on patients’ quality of life, cardiorespiratory fitness, and physical activity level. Methods and results: A randomized controlled trial (NCT05026957) was conducted with 80 patients with heart disease recruited from Jessa Hospital, Hasselt. Patients were randomized to either a control group receiving standard CR or an intervention group receiving standard CR with additional SDM-based TR via the SharedHeart smartphone application. Primary outcome was quality of life (HeartQoL), while secondary outcomes included cardiorespiratory fitness (VO2peak) and physical activity levels. Data were analysed using a linear mixed model. The intervention group showed a greater improvement in quality of life [4.15 points, 95% confidence interval (CI): 0.7–7.6; P = 0.02], peak oxygen uptake (VO2peak) (1.1 mL/kg/min, 95% CI: 0.04–2.1; P = 0.04), and number of step count [14 788 more steps/7 days (95% CI: 4,2–25,3; P < 0.01)] over a 12-week intervention, compared with the control group. Conclusion: This study demonstrated that the addition of SDM-based TR programme to centre-based CR significantly improved patients’ quality of life, cardiorespiratory fitness, and physical activity levels compared with centre-based CR alone. The SharedHeart study stands out as one of the first to integrate a digitally supported SDM approach in CR, empowering patients to take an active role in their rehabilitation. Future research should focus on the long-term impact of digital interventions, particularly in reducing adverse cardiovascular events and enhancing patient self-management.

15 July 2025 in European Journal of Preventive Cardiology
Verified
Journal Article
Closed access
SKSevda Ece Kizilkilic
Sevda Ece Kizilkilic
LXLinqi Xu
Linqi Xu
BABuket Akinci
Buket Akinci
GBGunhild Brørs
Gunhild Brørs
MBMaria Bäck
Maria Bäck
PDPaul Dendale
Paul Dendale
Aims: Digital health literacy (DHL) is essential for managing chronic diseases and promoting healthy aging. Despite its importance, evidence on how to improve DHL remains limited. This systematic review and meta-analysis assessed the impact of educational interventions on DHL among adults with chronic diseases and healthy older adults, with implications for both primary and secondary prevention. Methods and results: This review followed PRISMA guidelines and was registered in PROSPERO (CRD42024592890). Studies from 2000–24 targeting adults (≥18 years) with chronic diseases or healthy individuals (≥65 years) and evaluating educational interventions to improve DHL were included. Nine databases were searched. Outcomes were assessed using validated tools (e.g. eHEALS). Follow-up was categorized as short-term (T1) and long-term (T2), with durations ranging from 3 to 12 months, depending on the study. Risk of bias was evaluated with ROB 2 and ROBINS-I. Twenty-one studies (n = 4195) were included: 14 randomized controlled trials and 7 pre–post studies. Most interventions (n = 17) were in-person programmes. Meta-analysis revealed significant eHEALS score improvements at short-term {T1: [mean difference (MD) 3.30, 95% confidence interval (CI): 1.21–5.40, I² = 0%, P = 0.03]} and long-term (T2: MD 2.18, 95% CI: 1.42–2.95, I² = 1%, P = 0.007). In-person and interactive interventions were most effective; app-based and online-only approaches showed limited benefit. Learning-by-doing interventions had limited impact on DHL but reduced clinical events. Conclusion: Educational interventions, especially in-person, improve DHL among older adults and individuals with chronic disease. Given the high heterogeneity among studies, standardized methodologies and tailored educational strategies are needed to maximize effectiveness and ensure equitable access. Addressing foundational digital skills and bridging the digital health divide remain crucial priorities in secondary prevention care.

21 April 2023 in European Journal of Preventive Cardiology
Verified
Journal Article
Closed access
PDF file
SKSevda Ece Kizilkilic
Sevda Ece Kizilkilic
MFMaarten Falter
Maarten Falter
PDPaul Dendale
Paul Dendale
Sevda Ece Kizilkilic, Maarten Falter, Paul Dendale; The power of movement: how physical activity can mitigate the risks of inadequate sleep, European Journal of

1 January 2025 in Arquivos Brasileiros de Cardiologia
Verified
Journal Article
Open access
SKSevda Ece Kizilkilic
Sevda Ece Kizilkilic
JMJuliana Goulart Prata Oliveira Milani
Juliana Goulart Prata Oliveira Milani
GJGerson Cipriano Junior
Gerson Cipriano Junior
PDPaul Dendale
Paul Dendale
MMMauricio Milani
Mauricio Milani
A reabilitação cardíaca (RC) desempenha um papel central na prevenção secundária da doença arterial coronariana (DAC) e é classificada como uma recomendação Classe IA nas diretrizes clínicas. No entanto, apesar de seus benefícios comprovados, as taxas de participação permanecem desanimadoramente baixas. Diante disso, a telerreabilitação (TR) tem ganhado atenção como uma alternativa prática, oferecendo melhorias clínicas semelhantes às dos programas tradicionais baseados em centros especializados. Paralelamente, a integração da inteligência artificial (IA) tem despertado crescente interesse na área da saúde

28 May 2026 in European Journal of Preventive Cardiology
Verified
Journal Article
Closed access
SKSevda Ece Kizilkilic
Sevda Ece Kizilkilic
JRJovana Ristic
Jovana Ristic
GBGunhild Brors
Gunhild Brors
LXLinqi Xu
Linqi Xu
MBMaria Bäck
Maria Bäck
PDPaul Dendale
Paul Dendale
Aims: Coronary heart disease (CHD) is the leading cause of death globally. Cardiac rehabilitation (CR) reduces cardiovascular mortality, hospital readmissions, and improves quality of life, yet participation in centre-based programmes remains low. Therefore, the aim of this systematic review and meta-analysis was to evaluate the clinical benefits of cardiac telerehabilitation (CTR), using exercise as the primary intervention, on physical capacity compared with centre-based cardiac rehabilitation (CBCR) or usual care in patients with CHD. Methods and results: This review followed PRISMA guidelines and was registered in PROSPERO (CRD420251160310). Five databases (PubMed, Embase, Scopus, CINAHL, CENTRAL) were searched from January 2000 to 15 October 2025. Eligible studies were randomized controlled trials (RCTs) enrolling adults with CHD in phase II CTR, with exercise training as a mandatory core component, optionally supplemented by other CR elements. Outcomes were cardiorespiratory fitness (CRF) (peak VO2) and functional capacity (6MWT, ISWT) between CTR and CBCR or usual care. For outcomes with substantial heterogeneity (I2 > 50%), random-effects meta-analyses were conducted using inverse-variance weighting, restricted maximum-likelihood estimation, and Knapp–Hartung adjustment. Twenty-five studies (n = 2717) were included. Compared with CBCR, no statistically significant difference was observed between CTR and CBCR in improvements VO2peak (mean difference (MD): 1.55, 95% CI: −1.60 to 4.70; I2 = 83.7%; P = 0.168) and 6MWT (MD: 15.01, 95% CI: −7.30 to 37.33; I2 = 0.0%; P = 0.187) at short-term (ST; 3 months). These comparable improvements persisted long-term (LT; 6–12 months). By contrast, CTR led to a significantly greater improvement compared with usual care in VO2peak (MD: 3.86, 95% CI: 3.03–4.69; I2 = 0.0%; P < 0.0001) and 6MWT (MD: 37.83, 95% CI: 22.12–53.53; I2 = 62.3%; P = 0.001) in the short term. Conclusion: CTR provides improvements in CRF and functional capacity with no statistically significant difference compared with CBCR, and significantly greater improvements compared with usual care.