MétaCan
Menu
← Back to cohort
Record W7117163620 · doi:10.2196/81824

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

2025· article· en· W7117163620 on OpenAlexvenueno aff
Johanna Sadel, Natalie Victoria Grant, Heinrich Burkhardt, Christophe Kunze

Bibliographic record

VenueJMIR Formative Research · 2025
Typearticle
Languageen
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsnot available
Fundersnot available
KeywordsHospital dischargeEmpirical researchQuality (philosophy)Work (physics)Key (lock)

Abstract

fetched live from OpenAlex

Background: 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. Objective: 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. Methods: 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. Results: 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. Conclusions: 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.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.074
metaresearch head score (Gemma)0.093
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Qualitative · Consensus signal: Qualitative
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.074
Threshold uncertainty score0.389

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0740.093
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0030.003
Science and technology studies0.0040.003
Scholarly communication0.0060.005
Open science0.0020.005
Research integrity0.0020.001
Insufficient payload (model declined to judge)0.0020.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.392
GPT teacher head0.631
Teacher spread0.239 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designQualitative
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueJMIR Formative Research→Same topicArtificial Intelligence in Healthcare and Education→French-language works237,207→