Hasso Plattner Institute

Scholarly ties in innovation and entrepreneurship: a social network perspective

Purpose This study examines the patterns of scholarly communication on social media, specifically Twitter (now “X”), among researchers in innovation management and entrepreneurship. The research aims to identify how these communities interact and share knowledge, revealing their...

AICO: Feature significance tests for supervised learning

Machine learning is central to modern science, industry, and policy, yet its predictive power often comes at the cost of transparency: We rarely know which input features drive a model’s predictions. Without such understanding, researchers cannot draw reliable conclusions, practi...

Agentic AI, medical morality and the transformation of the patient–physician relationship

Agentic artificial intelligence (AI) is an emerging development in the digital transformation of healthcare. Unlike conventional generative AI, agentic AI systems can perform autonomous, goal-directed actions and coordinate complex tasks. They promise to support or even collabora...

Machine learning-based rescoring with MS²Rescore boosts peptide identification and taxonomic specificity in metaproteomics

Abstract Background Metaproteomics, the study of the collective proteome within microbial ecosystems, has gained increasing interest over the past decade. However, peptide identification rates in metaproteomics remain low compared to single-species proteomics. A key challenge is...

Developers’ Experience with Generative AI Beyond Productivity Assessment – Insights from an Empirical Mixed-Methods Field Study

With the growing adoption of AI-powered coding assistants, organizations and developers are increasingly seeking to optimize their interaction with these tools. Prior research has largely focused on output quality and productivity gains, with limited attention paid to developers’...

HBV re-activation is associated with increased mortality and dysregulation of oxidative and polyamine metabolism in pre-acute-on-chronic liver failure

Abstract Background/Aims Acute-on-chronic liver failure (ACLF) is one of the deadliest complications of chronic liver disease yet treatment options are sparse. In Asia, HBV-reactivation (HBVr) is one of the most common triggers. Recently, HBV-associated ACLF was associated with d...

Care Team Response to Patient Portal Message Content and Writing Style

Importance Patient portal messages are an increasingly central channel for patient-clinician communication, but there are inequities in how responsive care teams are to messages sent by patients from historically marginalized groups. The reasons driving these disparities are not...

Cutting chart-review time and improving database accuracy in inflammatory bowel disease with human-in-the-loop large language models

Abstract Background Manual abstraction of electronic health records into research databases is a major bottleneck in clinical research, limiting scalability and introducing error. This challenge is particularly acute in inflammatory bowel disease surveillance, where clinically re...

Investigating the role of serum IL-6 in predicting outcomes of b-cell depleting therapy in multiple sclerosis: a retrospective cohort study

Abstract Background Interleukin-6 (IL-6) plays a pivotal role in autoimmune inflammation through its effects on B-cell differentiation, Th17 expansion, and regulatory T-cell suppression. Given ocrelizumab’s (OCR) mechanism of selective CD20 + B-cell depletion, baseline IL-6 level...

How to Benchmark Post-Quantum Accelerators

With the recent standardisation of several post-quantum cryptographic (PQC) algorithms, there is an increased focus within the hardware research community to investigate efficient accelerator designs. However, it is difficult to determine whether the reported results are directly...