# Optimizing Hospital Discharge Planning: Empirical Insights and Requirements of AI-Based Technologies From an Explorative Mixed Methods Field Study

## TL;DR

This study explores how AI can better support hospital discharge planning by understanding real-world challenges and user needs in two German hospitals.

## Contribution

The paper provides empirical insights and design requirements for integrating AI into discharge planning through a mixed methods field study.

## Key findings

- Persistent challenges in interdisciplinary communication and documentation were identified in discharge planning.
- Participants emphasized the need for transparent and explainable AI systems aligned with clinical roles.
- Quantitative data confirmed high administrative workload and bottlenecks in information transfer.

## Abstract

Discharge planning (DP) is crucial for care continuity after a hospital stay but remains complex due to organizational constraints, interprofessional coordination, and administrative demands. Despite ongoing digitalization efforts, many health technologies overlook the sociotechnical nature of discharge processes, limiting acceptance and integration into clinical workflows.

This study aimed to examine real-world DP practices in 2 German university hospitals, identify user-centered needs, and derive design implications for responsibly integrating artificial intelligence (AI)–based systems into DP.

A mixed methods field study was conducted combining qualitative and quantitative approaches. In the qualitative phase, DP employees participated in workshops (n=33). Additionally, expert interviews were conducted with 2 physicians and 3 nurses (n=5). Activities explored understanding of AI, challenges in DP workflows, and best-case process scenarios; existing processes were collaboratively modeled to identify potential intervention points for technological support. Transcripts were analyzed inductively following Mayring’s qualitative content analysis. Quantitative data were collected through a standardized questionnaire (n=23), focusing on workload distribution, process inefficiencies, and openness to using AI in the DP context. Descriptive statistics were used to identify high-burden segments. Findings were integrated through methodological triangulation.

Persistent challenges emerged in interdisciplinary communication, documentation practices, and information continuity. Participants expressed uncertainty about the value of AI in DP, emphasizing the need for transparency, explainability, and role alignment. Questionnaire data confirmed bottlenecks in information transfer and high administrative workload. Design requirements for future systems include process transparency, support for coordination tasks, and adaptability to clinical roles.

DP is a sociotechnical process in which human expertise and organizational context must guide system design. Participatory, context-aware design approaches are essential for integrating AI into clinical practice. Aligning technology with everyday workflows can increase acceptance and yield more effective digital interventions.