CoChat

Solving the explainable AI conundrum by bridging clinicians’ needs and developers’ goals

Open access

Published version of a preprint

The DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.

Abstract

Explainable artificial intelligence (XAI) has emerged as a promising solution for addressing the implementation challenges of AI/ML in healthcare. However, little is known about how developers and clinicians interpret XAI and what conflicting goals and requirements they may have. This paper presents the findings of a longitudinal multi-method study involving 112 developers and clinicians co-designing an XAI solution for a clinical decision support system. Our study identifies three key differences between developer and clinician mental models of XAI, including opposing goals (model interpretability vs. clinical plausibility), different sources of truth (data vs. patient), and the role of exploring new vs. exploiting old knowledge. Based on our findings, we propose design solutions that can help address the XAI conundrum in healthcare, including the use of causal inference models, personalized explanations, and ambidexterity between exploration and exploitation mindsets. Our study highlights the importance of considering the perspectives of both developers and clinicians in the design of XAI systems and provides practical recommendations for improving the effectiveness and usability of XAI in healthcare.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41746-023-00837-4

Cites

34 of 34 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Clinician assessment of the risk of DCI in a patient with or without the use of the DCIP. a–c Frequencies (in %) of multiple response answers for survey Q 1–3. Responses from physicians are displayed in orange and from nurses in blue.
Fig. 1 Clinician assessment of the risk of DCI in a patient with or without the use of the DCIP. a–c Frequencies (in %) of multiple response answers for survey Q 1–3. Responses from physicians are displayed in orange and from nurses in blue.CC BY · PubMed Central
Fig. 2 Screenshot of the DCIP system user interface prototype. The DCIP user interface aims to facilitate clinicians’ understanding of the ML model’s predictions with minimal time and effort. The header menu (A) displays information about the selected patient. In the overview frame (B), the current combined DCI risk score (0.8) is displayed, based on dynamic (0.72) and static (0.91) contributors (pink vs. blue hues indicating higher vs. lower risk). The static contributor view (C) displays Shapley values of static contributors assessed at the time of patient admission, including reference values for cohort-level evidence based on clinical norms such as the Barrow Neurological Institute Grading Scale (BNI), Hunt & Hess Grade, Modified Fisher Grade (MFS), Fisher Grade, and World Federation of Neurological Surgeons Grade (WFNS). The horizontal bar chart displays how the values below/above 0.5 decrease or increase the DCI risk score (in order of importance) The DCI probability frame (D) displays periods of high risk for DCI as colored areas under the curve, allowing clinicians to probe exact numeric values at each point in time. The solid line represents the combined risk fluctuating over time and the dashed line indicates the constant static probability (0.9). The Dynamic Contributors frame (E) displays a heatmap of Shapley values of dynamic contributors over time. Each heatmap lane shows how much a given signal (e.g., mOsm = Serum osmolality) contributes to the DCI risk at a given point in time (hover) and can be added (double-click) as an additional timeline displaying raw values below (F). Additional timelines can be added on demand to provide context for feature-level explanations (e.g., Heart Rate [bpm], intracranial pressure [mmHg], pupil reaction time). All timelines are in synch and can be zoomed/panned as desired. Individual points in time can be probed to reveal exact numeric values across all charts. For context information outside of the DCIP, clinicians can access the target patient’s complete health records (via the separate Electronic Health Record [EHR] system). Numbers 1–5 highlight the specific features referred to by interviewees when searching for model explanations (see Interview results).
Fig. 2 Screenshot of the DCIP system user interface prototype. The DCIP user interface aims to facilitate clinicians’ understanding of the ML model’s predictions with minimal time and effort. The header menu (A) displays information about the selected patient. In the overview frame (B), the current combined DCI risk score (0.8) is displayed, based on dynamic (0.72) and static (0.91) contributors (pink vs. blue hues indicating higher vs. lower risk). The static contributor view (C) displays Shapley values of static contributors assessed at the time of patient admission, including reference values for cohort-level evidence based on clinical norms such as the Barrow Neurological Institute Grading Scale (BNI), Hunt & Hess Grade, Modified Fisher Grade (MFS), Fisher Grade, and World Federation of Neurological Surgeons Grade (WFNS). The horizontal bar chart displays how the values below/above 0.5 decrease or increase the DCI risk score (in order of importance) The DCI probability frame (D) displays periods of high risk for DCI as colored areas under the curve, allowing clinicians to probe exact numeric values at each point in time. The solid line represents the combined risk fluctuating over time and the dashed line indicates the constant static probability (0.9). The Dynamic Contributors frame (E) displays a heatmap of Shapley values of dynamic contributors over time. Each heatmap lane shows how much a given signal (e.g., mOsm = Serum osmolality) contributes to the DCI risk at a given point in time (hover) and can be added (double-click) as an additional timeline displaying raw values below (F). Additional timelines can be added on demand to provide context for feature-level explanations (e.g., Heart Rate [bpm], intracranial pressure [mmHg], pupil reaction time). All timelines are in synch and can be zoomed/panned as desired. Individual points in time can be probed to reveal exact numeric values across all charts. For context information outside of the DCIP, clinicians can access the target patient’s complete health records (via the separate Electronic Health Record [EHR] system). Numbers 1–5 highlight the specific features referred to by interviewees when searching for model explanations (see Interview results).CC BY · PubMed Central
Fig. 3 Framework of XAI mental model differences and recommendations how to reduce the differences (see textbox). ML Developers’ mental models (left) relate to model interpretability, a data-centered assessment, and an exploration mindset. Clinician’s mental models (right) aim for clinical plausibility, a patient-centered assessment, and an exploitation mindset.
Fig. 3 Framework of XAI mental model differences and recommendations how to reduce the differences (see textbox). ML Developers’ mental models (left) relate to model interpretability, a data-centered assessment, and an exploration mindset. Clinician’s mental models (right) aim for clinical plausibility, a patient-centered assessment, and an exploitation mindset.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

10 more claims about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 34 references

Research works printed but not linked: 1

  1. Tabachnick, B. G., Fidell, L. S. & Ullman, J. B. Using multivariate statistics. (Pearson, 2019).

Cited by

See all 200

Metadata

Authors
Bienefeld, N., Boss, J. M., Lüthy, R., Brodbeck, D., Azzati, J., Blaser, M., Willms, J., & Keller, E.
Affiliations
  • ETH Zurich (CH)
  • University of Zurich (CH)
  • FHNW University of Applied Sciences and Arts Northwestern Switzerland (CH)
Corresponding author
Bienefeld, Nadine
Venue
npj Digital Medicine
Published
2023-05-22
Volume
6
Issue
1
Pages
94-94
ISSN
2398-6352 (ISSN-L)
OpenAlex
W4377289493
Cited by
159
References
32
Citations by year
2026: 68 · 2025: 52 · 2024: 31 · 2023: 8
FWCI
14.99
Type
journal article
Language
en
Open access
Licence
Locations
  • npj Digital Medicine (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Zurich Open Repository and Archive (University of Zurich) (acceptedVersion, cc-by-nc-nd)
  • Repository for Publications and Research Data (ETH Zurich) (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Zurich Open Repository and Archive (University of Zurich) (submittedVersion, cc-by)
  • ETH Zürich Research Collection
  • Zurich Open Repository and Archive (University of Zurich)
Funders
Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (187331, 52441_1)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
Keywords
explainable AI, clinical decision support systems, co-design, model interpretability, exploration and exploitation, ambidexterity, causal inference, personalized explanations, clinical implementation of AI

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Solving the explainable AI conundrum by bridging clinicians’ needs and developers’ goals. https://app.cochat.ai/papers/10.1038/s41746-023-00837-4
The paper
Bienefeld, N., Boss, J. M., Lüthy, R., Brodbeck, D., Azzati, J., Blaser, M., Willms, J., & Keller, E. (2023). Solving the explainable AI conundrum by bridging clinicians’ needs and developers’ goals. npj Digital Medicine. https://doi.org/10.1038/s41746-023-00837-4

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.