Julie Vranken

Mrs. Julie Vranken

Hasselt University, Faculty of Medicine and Life Sciences, Agoralaan gebouw D, 3500 Hasselt
+2
orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
18 November 2020 in Sensors
Verified
Journal Article
Open access
PDF file
AYAhmed Youssef
Ahmed Youssef
FWFemke Wouters
Femke Wouters
JVJulie Vranken
Julie Vranken
DBDianne de Korte-De Boer
Dianne de Korte-De Boer
VSValérie Smit-Fun
Valérie Smit-Fun
Bart VanrumsteBart Vanrumste
Bart Vanrumste
In this prospective, interventional, international study, we investigate continuous monitoring of hospitalised patients’ vital signs using wearable technology as a basis for real-time early warning scores (EWS) estimation and vital signs time-series prediction. The collected continuous monitored vital signs are heart rate, blood pressure, respiration rate, and oxygen saturation of a heterogeneous patient population hospitalised in cardiology, postsurgical, and dialysis wards. Two aspects are elaborated in this study. The first is the high-rate (every minute) estimation of the statistical values (e.g., minimum and mean) of the vital signs components of the EWS for one-minute segments in contrast with the conventional routine of 2 to 3 times per day. The second aspect explores the use of a hybrid machine learning algorithm of kNN-LS-SVM for predicting future values of monitored vital signs. It is demonstrated that a real-time implementation of EWS in clinical practice is possible. Furthermore, we showed a promising prediction performance of vital signs compared to the most recent state of the art of a boosted approach of LSTM. The reported mean absolute percentage errors of predicting one-hour averaged heart rate are 4.1, 4.5, and 5% for the upcoming one, two, and three hours respectively for cardiology patients. The obtained results in this study show the potential of using wearable technology to continuously monitor the vital signs of hospitalised patients as the real-time estimation of EWS in addition to a reliable prediction of the future values of these vital signs is presented. Ultimately, both approaches of high-rate EWS computation and vital signs time-series prediction is promising to provide efficient cost-utility, ease of mobility and portability, streaming analytics, and early warning for vital signs deterioration.

18 March 2020 in JMIR Cardio
Verified
Journal Article
Open access
CSChristophe Smeets
Christophe Smeets
SLSeulki Lee
Seulki Lee
WGWillemijn Groenendaal
Willemijn Groenendaal
GSGabriel Squillace
Gabriel Squillace
JVJulie Vranken
Julie Vranken
PVPieter M Vandervoort
Pieter M Vandervoort
Background: Incomplete relief of congestion in acute decompensated heart failure (HF) is related to poor outcomes. However, congestion can be difficult to evaluate, stressing the urgent need for new objective approaches. Due to its inverse correlation with tissue hydration, continuous bioimpedance monitoring might be an effective method for serial fluid status assessments. Objective: This study aimed to determine whether in-hospital bioimpedance monitoring can be used to track fluid changes (ie, the efficacy of decongestion therapy) and the relationships between bioimpedance changes and HF hospitalization and all-cause mortality. Methods: A wearable bioimpedance monitoring device was used for thoracic impedance measurements. Thirty-six patients with signs of acute decompensated HF and volume overload were included. Changes in the resistance at 80 kHz (R80kHz) were analyzed, with fluid balance (fluid in/out) used as a reference. Patients were divided into two groups depending on the change in R80kHz during hospitalization: increase in R80kHz or decrease in R80kHz. Clinical outcomes in terms of HF rehospitalization and all-cause mortality were studied at 30 days and 1 year of follow-up. Results: During hospitalization, R80kHz increased for 24 patients, and decreased for 12 patients. For the total study sample, a moderate negative correlation was found between changes in fluid balance (in/out) and relative changes in R80kHz during hospitalization (rs=-0.51, P<.001). Clinical outcomes at both 30 days and 1 year of follow-up were significantly better for patients with an increase in R80kHz. At 1 year of follow-up, 88% (21/24) of patients with an increase in R80kHz were free from all-cause mortality, compared with 50% (6/12) of patients with a decrease in R80kHz (P=.01); 75% (18/24) and 25% (3/12) were free from all-cause mortality and HF hospitalization, respectively (P=.01). A decrease in R80kHz resulted in a significant hazard ratio of 4.96 (95% CI 1.82-14.37, P=.003) on the composite endpoint. Conclusions: The wearable bioimpedance device was able to track changes in fluid status during hospitalization and is a convenient method to assess the efficacy of decongestion therapy during hospitalization. Patients who do not show an improvement in thoracic impedance tend to have worse clinical outcomes, indicating the potential use of thoracic impedance as a prognostic parameter.

9 January 2025 in JMIR Formative Research
Verified
Journal Article
Open access
FWFemke Wouters
Femke Wouters
HGHenri Gruwez
Henri Gruwez
CSChristophe Smeets
Christophe Smeets
APAnessa Pijalovic
Anessa Pijalovic
WWWouter Wilms
Wouter Wilms
LPLaurent Pison
Laurent Pison
Background: Consumer-oriented wearable devices (CWDs) such as smartphones and smartwatches have gained prominence for their ability to detect atrial fibrillation (AF) through proprietary algorithms using electrocardiography or photoplethysmography (PPG)–based digital recordings. Despite numerous individual validation studies, a direct comparison of interdevice performance is lacking. Objective: This study aimed to evaluate and compare the ability of CWDs to distinguish between sinus rhythm and AF. Methods: Patients exhibiting sinus rhythm or AF were enrolled through a cardiology outpatient clinic. The participants were instructed to perform heart rhythm measurements using a handheld 6-lead electrocardiogram (ECG) device (KardiaMobile 6L), a smartwatch-derived single-lead ECG (Apple Watch), and two PPG-based smartphone apps (FibriCheck and Preventicus) in a random sequence, with simultaneous 12-lead reference ECG as the gold standard. Results: A total of 122 participants were included in the study: median age 69 (IQR 61-77) years, 63.9% (n=78) men, 25% (n=30) with AF, 9.8% (n=12) without prior smartphone experience, and 73% (n=89) without experience in using a smartwatch. The sensitivity to detect AF was 100% for all devices. The specificity to detect sinus rhythm was 96.4% (95% CI 89.5%-98.8%) for KardiaMobile 6L, 97.8% (95% CI 91.6%‐99.5%) for Apple Watch, 98.9% (95% CI 92.5%‐99.8%) for FibriCheck, and 97.8% (95% CI 91.5%‐99.4%) for Preventicus (P=.50). Insufficient quality measurements were observed in 10.7% (95% CI 6.3%-17.5%) of cases for both KardiaMobile 6L and Apple Watch, 7.4% (95% CI 3.9%‐13.6%) for FibriCheck, and 14.8% (95% CI 9.5%‐22.2%) for Preventicus (P=.21). Participants preferred Apple Watch over the other devices to monitor their heart rhythm. Conclusions: In this study population, the discrimination between sinus rhythm and AF using CWDs based on ECG or PPG was highly accurate, with no significant variations in performance across the examined devices.

5 December 2021 in Sensors
Verified
Journal Article
Open access
PDF file
AYAhmed Youssef
Ahmed Youssef
FWFemke Wouters
Femke Wouters
JVJulie Vranken
Julie Vranken
PDPauline Dreesen
Pauline Dreesen
DBDianne de Korte-De Boer
Dianne de Korte-De Boer
Bart VanrumsteBart Vanrumste
Bart Vanrumste
This study introduces machine learning predictive models to predict the future values of the monitored vital signs of COVID-19 ICU patients. The main vital sign predictors include heart rate, respiration rate, and oxygen saturation. We investigated the performances of the developed predictive models by considering different approaches. The first predictive model was developed by considering the following vital signs: heart rate, blood pressure (systolic, diastolic and mean arterial, pulse pressure), respiration rate, and oxygen saturation. Similar to the first approach, the second model was developed using the same vital signs, but it was trained and tested based on a leave-one-subject-out approach. The third predictive model was developed by considering three vital signs: heart rate (HR), respiration rate (RR), and oxygen saturation (SpO2). The fourth model was a leave-one-subject-out model for the three vital signs. Finally, the fifth predictive model was developed based on the same three vital signs, but with a five-minute observation rate, in contrast with the aforementioned four models, where the observation rate was hourly to bi-hourly. For the five models, the predicted measurements were those of the three upcoming observations (on average, three hours ahead). Based on the obtained results, we observed that by limiting the number of vital sign predictors (i.e., three vital signs), the prediction performance was still acceptable, with the average mean absolute percentage error (MAPE) being 12%,5%, and 21.4% for heart rate, oxygen saturation, and respiration rate, respectively. Moreover, increasing the observation rate could enhance the prediction performance to be, on average, 8%,4.8%, and 17.8% for heart rate, oxygen saturation, and respiration rate, respectively. It is envisioned that such models could be integrated with monitoring systems that could, using a limited number of vital signs, predict the health conditions of COVID-19 ICU patients in real-time.

4 April 2018 in JMIR Cardio
Verified
Journal Article
Open access
CSChristophe Smeets
Christophe Smeets
VSValerie Storms
Valerie Storms
PVPieter M Vandervoort
Pieter M Vandervoort
PDPauline Dreesen
Pauline Dreesen
JVJulie Vranken
Julie Vranken
PDPaul Dendale
Paul Dendale
European Society of Cardiology guidelines for the treatment of heart failure (HF) prescribe uptitration of angiotensin-converting enzyme inhibitors (ACE-I) and β-blockers to the maximum-tolerated, evidence-based dose. Although HF prognosis can drastically improve when correctly implementing these guidelines, studies have shown that they are insufficiently implemented in clinical practice. The aim of this study was to verify whether supplementing the usual care with the CardioCoach follow-up tool is feasible and safe, and whether the tool is more efficient in implementing the guideline recommendations for β-blocker and ACE-I. A total of 25 HF patients were randomly assigned to either the usual care control group (n=10) or CardioCoach intervention group (n=15), and observed for 6 months. The CardioCoach follow-up tool is a two-way communication platform with decision support algorithms for semiautomatic remote medication uptitration. Remote monitoring sensors automatically transmit patient's blood pressure, heart rate, and weight on a daily basis. Patients' satisfaction and adherence for medication intake (10,018/10,825, 92.55%) and vital sign measurements (4504/4758, 94.66%) were excellent. However, the number of technical issues that arose was large, with 831 phone contacts (median 41, IQR 32-65) in total. The semiautomatic remote uptitration was safe, as there were no adverse events and no false positive uptitration proposals. Although no significant differences were found between both groups, a higher number of patients were on guideline-recommended medication dose in both groups compared with previous reports. The CardioCoach follow-up tool for remote uptitration is feasible and safe and was found to be efficient in facilitating information exchange between care providers, with high patient satisfaction and adherence. ClinicalTrials.gov NCT03294811; https://clinicaltrials.gov/ct2/show/NCT03294811 (Archived by WebCite at http://www.webcitation.org/6xLiWVsgM).

27 August 2019 in Applied Sciences
Verified
Journal Article
Open access
PDF file
AAAhmed Y. A. Amer
Ahmed Y. A. Amer
JVJulie Vranken
Julie Vranken
FWFemke Wouters
Femke Wouters
DMDieter Mesotten
Dieter Mesotten
PVPieter Vandervoort
Pieter Vandervoort
Jean-Marie AertsJean-Marie Aerts
Jean-Marie Aerts
Mortality prediction for intensive care unit (ICU) patients is a challenging problem that requires extracting discriminative and informative features. This study presents a proof of concept for exploring features that can provide clinical insight. Through a feature engineering approach, it is attempted to improve ICU mortality prediction in field conditions with low frequently measured data (i.e., hourly to bi-hourly). Features are explored by investigating the vital signs measurements of ICU patients, labelled with mortality or survival at discharge. The vital signs of interest in this study are heart and respiration rate, oxygen saturation and blood pressure. The latter comprises systolic, diastolic and mean arterial pressure. In the feature exploration process, it is aimed to extract simple and interpretable features that can provide clinical insight. For this purpose, a classifier is required that maximises the margin between the two classes (i.e., survival and mortality) with minimum tolerance to misclassification errors. Moreover, it preferably has to provide a linear decision surface in the original feature space without mapping to an unlimited dimensionality feature space. Therefore, a linear hard margin support vector machine (SVM) classifier is suggested. The extracted features are grouped in three categories: statistical, dynamic and physiological. Each category plays an important role in enhancing classification error performance. After extracting several features within the three categories, a manual feature fine-tuning is applied to consider only the most efficient features. The final classification, considering mortality as the positive class, resulted in an accuracy of 91.56 % , sensitivity of 90.59 % , precision of 86.52 % and F 1 -score of 88.50 % . The obtained results show that the proposed feature engineering approach and the extracted features are valid to be considered and further enhanced for the mortality prediction purpose. Moreover, the proposed feature engineering approach moved the modelling methodology from black-box modelling to grey-box modelling in combination with the powerful classifier of SVMs.