Kianush Monschau

Kianush Monschau

Auto-generated profile, based on publicly available information

Kianush Monschau

Department of Methodology and Statistics, Faculty of Social and Behavioural Sciences, Utrecht University, Utrecht, The Netherlands

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
30 September 2025 in Journal of Innovation and Entrepreneurship
Verified
Journal Article
Open access
PDF file
LPLutz Peschke
Lutz Peschke
KMKianush Monschau
Kianush Monschau
FFFrans Folkvord
Frans Folkvord
SPSeldağ Güneş Peschke
Seldağ Güneş Peschke
RSRens Van de Schoot
Rens Van de Schoot
Sustainable research and innovation activities are mainly executed in collaborative networks consisting of stakeholders from academia, the economy, politics, and the media-based public considering the knowledge of the natural environment of societies. AI-based tools play an increasing role in knowledge production processes in all stakeholder communities. However, with a view to Mode 3 knowledge production, the context of the deployment of AI-based tools in a creative knowledge environment is not systematically analyzed. This paper focuses on a so-called Screenathon as a new format of knowledge production and knowledge exchange that integrates AI-based tools as a knowledge-producing entity. It follows the concept of an academic firm where creative knowledge environments are the central aspect in the combination of different principles of knowledge production. The Screenathon was executed for 2 days in Utrecht, The Netherlands, where 26 stakeholders from science, economy, politics, industry, and the professional public came together to screen > 12,000 papers about processes in the context of patient-generated health data (PGHD). The papers are the output of an AI-based literature review tool, ASReview. The Screenathon is, therefore, the second step in which the publications found are sorted by human activity into on-topic and off-topic papers. The screening of the papers were proceeded in different cultural locations in the city of Utrecht. In the present paper, the authors evaluate the interplay of a creative knowledge environment and an AI-based learning environment with the help of the Sociology of Knowledge Approach to Discourse (SKAD). It contributes to the understanding of AI’s impact on Mode 3 knowledge production and how it stimulates new forms of academic and educational systems. It could additionally juxtapose communicating and interpreting action in the context of meaning-making as the basis of social systems and include the discussion about the change of the self-rationale in the system knowledge.

3 December 2024 in PsyArXiv
Verified
Preprint
Open access
KMKianush Monschau
Kianush Monschau
RNRutger Chris Neeleman
Rutger Chris Neeleman
EJElena Jalsovec
Elena Jalsovec
LBLaurens de Bruin
Laurens de Bruin
JBJonathan de Bruin
Jonathan de Bruin
RSRens Van de Schoot
Rens Van de Schoot
Systematic Title-Abstract (TA) screening is an essential but time-intensive task, especially in large-scale collaborations working with large datasets. We introduce the Screenathon Review, a literature screening procedure that adapts to this setting by 1. crowdsourcing the screening using relevant stakeholders, 2. screening literature in a limited amount of time, 3. forming a consensus about inclusion criteria and definitions and 4. building a research community that lasts for the entire project's duration. The procedure involves four phases: Large-scale screening preparation, group calibration and training, crowd-sourced screening, and quality checking. We applied and tested this procedure with 26 attendees as part of the EU-funded IMPROVE project in a four-day design, which included incentives and gamification elements. During the screening phase of the Screenathon event, 12,473 records were screened within two days. Attendees’ confidence, motivation, and satisfaction were high and did not decrease during screening days. Considerations about the procedure and implications for future Screenathon Reviews are discussed.

22 March 2026 in Scientific Reports
Verified
Journal Article
Open access
JBJonas Bergmann
Jonas Bergmann
TATiago Azzi
Tiago Azzi
RNRutger Neeleman
Rutger Neeleman
KMKianush Monschau
Kianush Monschau
BYBerke Yazan
Berke Yazan
RSRens Van de Schoot
Rens Van de Schoot
Systematic reviews are essential for evidence-based research, yet the traditional screening process is time-consuming and difficult to scale. Human-only screening can introduce inconsistency, while fully automated approaches employing Large Language Models often lack the contextual judgement required for complex decisions. To address this, we introduce a crowd-based screening methodology that integrates human expertise with adaptive machine learning. The methods have been applied in the context of a large EU project where experts from 27 collaborating partners jointly screened 5842 papers across eleven disease topics related to patient-generated health data in a span of 2 days. Post-processing played a central role in ensuring data quality, including topic reallocation, targeted full-text verification, and noisy-label filtering. This Screenathon resulted in 487 records being labeled as relevant and 6,463 records as irrelevant. The number of records screened per participant ranged from 3 to 2496, with a mean of 216.4 records per screener ( SE = 95.19). Exploratory analyses using survey results indicated increased trust in AI-assisted systematic reviewing after the event, along with generally positive evaluations of usability. The current Screenathon demonstrates that crowdsourced human–AI collaboration requires thoughtful training and calibration, together with strong post-processing safeguards.

9 January 2026 in PsyArXiv
Verified
Preprint
Open access
JBJonas Bergmann
Jonas Bergmann
TATiago Azzi
Tiago Azzi
RNRutger Chris Neeleman
Rutger Chris Neeleman
KMKianush Monschau
Kianush Monschau
EJElena Jalsovec
Elena Jalsovec
BYBerke Yazan
Berke Yazan
Systematic reviews are essential for evidence-based research, yet the traditional screening process is time-consuming and difficult to scale. Human-only screening can introduce inconsistency, while fully automated approaches employing Large Language Models often lack the contextual judgement required for complex decisions. To address this, we introduce a crowd-based screening methodology that integrates human expertise with adaptive machine learning. The methods have been applied in the context of a large EU project where experts from 27 collaborating partners jointly screened 5,842 papers across eleven disease topics related to patient-generated health data in a span of only 2 days. Post-processing played a central role in ensuring data quality, including topic reallocation, targeted full-text verification, and noisy-label filtering. This Screenathon resulted in 487 records being labeled as relevant and 6,463 records as irrelevant. The number of records screened per participant ranged from 3 to 2,496, with a mean of 216.4 records per screener (SE = 95.19). Survey results indicated increased trust in AI-assisted systematic reviewing after the event, along with generally positive evaluations of usability. The current Screenathon demonstrates that human–AI collaboration can increase efficiency while maintaining rigor, provided that workflows include thoughtful training and calibration together with strong post-processing safeguards.

13 November 2025 in PsyArXiv
Verified
Preprint
Open access
KMKianush Monschau
Kianush Monschau
EWEmily Westerbeek
Emily Westerbeek
QFQixiang Fang
Qixiang Fang
JBJonas Bergmann
Jonas Bergmann
GFGiuseppe Fico
Giuseppe Fico
RSRens Van de Schoot
Rens Van de Schoot
The EU-funded IMPROVE project seeks to build a platform that enables the smart use of patient-generated health data (PGHD), thereby enhancing digital healthcare efficiency. This paper introduces a dataset directly resulting from a large-scale systematic literature search carried out within the IMPROVE project, concerning the use of PGHD in treatments of five categories of chronic diseases: cardiovascular disease, chronic inflammation, neurology, oncology, and ophthalmology. Specifically, the dataset contains the metadata of 12.473 studies returned by databases, such as title, abstract and DOI, as well as inclusion decisions. The dataset is stored in both excel and csv format. It can be used to aid the understanding of PGHD use in healthcare and the development of AI-assisted systematic review tools.