Elena Heber

Elena Heber

Auto-generated profile, based on publicly available information

Elena Heber

Department of Psychology, University of Southampton, Southampton, UK

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
17 February 2017 in Journal of Medical Internet Research
Verified
Journal Article
Open access
EHElena Heber
Elena Heber
DEDavid Daniel Ebert
David Daniel Ebert
DLDirk Lehr
Dirk Lehr
PCPim Cuijpers
Pim Cuijpers
MBMatthias Berking
Matthias Berking
HRHeleen Riper
Heleen Riper
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet

27 January 2016 in Journal of Medical Internet Research
Verified
Journal Article
Open access
EHElena Heber
Elena Heber
DLDirk Lehr
Dirk Lehr
DEDavid Daniel Ebert
David Daniel Ebert
MBMatthias Berking
Matthias Berking
HRHeleen Riper
Heleen Riper
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet

18 November 2022 in Frontiers in Digital Health
Verified
Journal Article
Open access
AKAlexander Kathan
Alexander Kathan
MHMathias Harrer
Mathias Harrer
LKLudwig Küster
Ludwig Küster
ATAndreas Triantafyllopoulos
Andreas Triantafyllopoulos
XHXiangheng He
Xiangheng He
BSBjörn W. Schuller
Björn W. Schuller
Introduction: Digital health interventions are an effective way to treat depression, but it is still largely unclear how patients’ individual symptoms evolve dynamically during such treatments. Data-driven forecasts of depressive symptoms would allow to greatly improve the personalisation of treatments. In current forecasting approaches, models are often trained on an entire population, resulting in a general model that works overall, but does not translate well to each individual in clinically heterogeneous, real-world populations. Model fairness across patient subgroups is also frequently overlooked. Personalised models tailored to the individual patient may therefore be promising.Methods: We investigate different personalisation strategies using transfer learning, subgroup models, as well as subject-dependent standardisation on a newly-collected, longitudinal dataset of depression patients undergoing treatment with a digital intervention (N=65 patients recruited). Both passive mobile sensor data as well as ecological momentary assessments were available for modelling. We evaluated the models’ ability to predict symptoms of depression (Patient Health Questionnaire-2; PHQ-2) at the end of each day, and to forecast symptoms of the next day.Results: In our experiments, we achieve a best mean-absolute-error (MAE) of 0.801 (25% improvement) for predicting PHQ-2 values at the end of the day with subject-dependent standardisation compared to a non-personalised baseline (MAE=1.062). For one day ahead-forecasting, we can improve the baseline of 1.539 by 12% to a MAE of 1.349 using a transfer learning approach with shared common layers. In addition, personalisation leads to fairer models at group-level.Discussion: Our results suggest that personalisation using subject-dependent standardisation and transfer learning can improve predictions and forecasts, respectively, of depressive symptoms in participants of a digital depression intervention. We discuss technical and clinical limitations of this approach, avenues for future investigations, and how personalised machine learning architectures may be implemented to improve existing digital interventions for depression.

19 June 2018 in Journal of Medical Internet Research
Verified
Journal Article
Open access
KWKiona Krueger Weisel
Kiona Krueger Weisel
DLDirk Lehr
Dirk Lehr
EHElena Heber
Elena Heber
AZAnna-Carlotta Zarski
Anna-Carlotta Zarski
MBMatthias Berking
Matthias Berking
DEDavid Daniel Ebert
David Daniel Ebert
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet

15 May 2019 in JMIR Mental Health
Verified
Journal Article
Open access
FKFanny Kählke
Fanny Kählke
CBClaudia Buntrock
Claudia Buntrock
FSFilip Smit
Filip Smit
MBMatthias Berking
Matthias Berking
DLDirk Lehr
Dirk Lehr
DEDavid Daniel Ebert
David Daniel Ebert
Background: Work-related stress is widespread among employees and associated with high costs for German society. Internet-based stress management interventions (iSMIs) are effective in reducing such stress. However, evidence for their cost-effectiveness is scant. Objective: The aim of this study was to assess the cost-effectiveness of a guided iSMI for employees. Methods: A sample of 264 employees with elevated symptoms of perceived stress (Perceived Stress Scale≥22) was assigned to either the iSMI or a waitlist control condition (WLC) with unrestricted access to treatment as usual. Participants were recruited in Germany in 2013 and followed through 2014, and data were analyzed in 2017. The iSMI consisted of 7 sessions plus 1 booster session. It was based on problem-solving therapy and emotion regulation techniques. Costs were measured from the societal perspective, including all direct and indirect medical costs. We performed a cost-effectiveness analysis and a cost-utility analysis relating costs to a symptom-free person and quality-adjusted life years (QALYs) gained, respectively. Sampling uncertainty was handled using nonparametric bootstrapping (N=5000). Results: When the society is not willing to pay anything to get an additional symptom-free person (eg, willingness-to-pay [WTP]=€0), there was a 70% probability that the intervention is more cost-effective than WLC. This probability rose to 85% and 93% when the society is willing to pay €1000 and €2000, respectively, for achieving an additional symptom-free person. The cost-utility analysis yielded a 76% probability that the intervention is more cost-effective than WLC at a conservative WTP threshold of €20,000 (US $25,800) per QALY gained. Conclusions: Offering an iSMI to stressed employees has an acceptable likelihood of being cost-effective compared with WLC. Trial Registration: German Clinical Trials Register DRKS00004749; https://www.drks.de/DRKS00004749 International Registered Report Identifier (IRRID): RR2-10.1186/1471-2458-13-655

25 January 2019 in JMIR Research Protocols
Verified
Journal Article
Open access
DJDilfa Juniar
Dilfa Juniar
WBWouter van Ballegooijen
Wouter van Ballegooijen
EKEirini Karyotaki
Eirini Karyotaki
ASAnneke Van Schaik
Anneke Van Schaik
JPJan Passchier
Jan Passchier
HRHeleen Riper
Heleen Riper
The number of university students experiencing stress is increasing, which often leads to adverse effects such as poor grades, academic probation, and emotional problems. Unfortunately, most of these problems remain untreated because of limited professional resources and fear of stigma. Several Web-based stress management interventions are now available for student populations, but these treatments are not yet available in Indonesia. To make treatment for stress more acceptable in Indonesia, a cultural adaptation process is needed, and part of the process is assessing the feasibility of the adapted intervention. This paper describes the first two stages of a cultural adaptation process and the protocol of a feasibility study that will assess the acceptability of a culturally adapted stress management intervention for university students in Indonesia. Focus group discussions with Indonesian university students were held, and input from Indonesian psychologists was gathered for developing the adapted intervention. A single-group feasibility study with a pre-post design will be conducted. We will recruit at minimum 50 university students who have an elevated level of stress (Depression, Anxiety, and Stress Scales-42 stress subscale score ≥15), identify themselves as being of Indonesian culture (eg, able to speak Bahasa Indonesia fluently), and are studying at a university in Indonesia. The primary endpoints of this study will be rates of participant satisfaction, system usability, dropout rates, and level of adherence. We will also use qualitative data to assess the adapted intervention more thoroughly. Secondary study endpoints will be quality of life, stress, anxiety, and depression levels. Feasibility parameters (eg, participant satisfaction, system usability, and level of adherence) will be summarized with descriptive statistics. Two-tailed paired within-group t tests will be used to analyze stress, anxiety, depression, and quality of life. The enrollment of pilot study is currently ongoing. First results are expected to be ready for analysis in the second half of 2019. The project was funded as part of a PhD trajectory in 2015 by the Indonesian Endowment Fund for Education. This is one of the first studies to assess the feasibility of a culturally adapted Web-based stress management intervention for university students in Indonesia. Strengths and limitations of the study are discussed. DERR1-10.2196/11493.