Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 60 of the 61 references it cites were found in a registry or an index.

Evaluating the impact of prediction models: lessons learned, challenges, and recommendations

Open access
Kappen, Teus H., van Klei, Wilton A., van Wolfswinkel, Leo, Kalkman, Cor J., Vergouwe, Yvonne, Moons, Karel G. M. · 2018 · Diagnostic and Prognostic Research

Abstract

An important aim of clinical prediction models is to positively impact clinical decision making and subsequent patient outcomes. The impact on clinical decision making and patient outcome can be quantified in prospective comparative-ideally cluster-randomized-studies, known as 'impact studies'. However, such impact studies often require a lot of time and resources, especially when they are (cluster-)randomized studies. Before envisioning such large-scale randomized impact study, it is important to ensure a reasonable chance that the use of the prediction model by the targeted healthcare professionals and patients will indeed have a positive effect on both decision making and subsequent outcomes. We recently performed two differently designed, prospective impact studies on a clinical prediction model to be used in surgical patients. Both studies taught us new valuable lessons on several aspects of prediction model impact studies, and which considerations may guide researchers in their decision to conduct a prospective comparative impact study. We provide considerations on how to prepare a prediction model for implementation in practice, how to present the model predictions, and how to choose the proper design for a prediction model impact study.

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 · 10.1186/s41512-018-0033-6

Cites

60 of 60 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Methodological similarities and differences between our cluster-randomized trial with an assistive prediction tool (first study) and the before-after study with a directive prediction tool (second study)
Fig. 1 Methodological similarities and differences between our cluster-randomized trial with an assistive prediction tool (first study) and the before-after study with a directive prediction tool (second study)CC BY · PubMed Central
Fig. 2 Graphical representation of the mixed effects regression analysis on the pooled dataset of the two impact studies. In both studies, a prediction model for postoperative nausea and vomiting (PONV) was implemented (red colors) and compared to care-as-usual (blue colors). In one study, the probabilities of the model were simply presented to physicians who implemented without a recommendation (i.e. an assistive format; less saturated colors). The other study also included an actionable recommendation (i.e. a directive format; more saturated colors). Both studies compared the impact on the physicians’ administration of antiemetic prophylaxis (a) and on the incidence of PONV (b). The bars and their 95% confidence intervals (CI) represent the fixed effects of the mixed effects regression analyses. The mixed effects models included fixed effects for the following variables: study, allocation group, predicted probability of PONV, and all interaction term between these variables. Because of the similarity of the results, the bars were calculated from the unadjusted analysis after multiple imputations. The 95% CIs were calculated from the covariance matrix for the variable study, allocation group, predicted probability, and their interaction terms. Further methodologic information and the numerical results of the regression models are available in Additional file 1
Fig. 2 Graphical representation of the mixed effects regression analysis on the pooled dataset of the two impact studies. In both studies, a prediction model for postoperative nausea and vomiting (PONV) was implemented (red colors) and compared to care-as-usual (blue colors). In one study, the probabilities of the model were simply presented to physicians who implemented without a recommendation (i.e. an assistive format; less saturated colors). The other study also included an actionable recommendation (i.e. a directive format; more saturated colors). Both studies compared the impact on the physicians’ administration of antiemetic prophylaxis (a) and on the incidence of PONV (b). The bars and their 95% confidence intervals (CI) represent the fixed effects of the mixed effects regression analyses. The mixed effects models included fixed effects for the following variables: study, allocation group, predicted probability of PONV, and all interaction term between these variables. Because of the similarity of the results, the bars were calculated from the unadjusted analysis after multiple imputations. The 95% CIs were calculated from the covariance matrix for the variable study, allocation group, predicted probability, and their interaction terms. Further methodologic information and the numerical results of the regression models are available in Additional file 1CC 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?

11 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

1 retracted

Show all 61 references

Cited by

See all 220

Metadata

Authors
Kappen, T. H., van Klei, W. A., van Wolfswinkel, L., Kalkman, C. J., Vergouwe, Y., & Moons, K. G. M.
Affiliations
Utrecht University (NL)
Corresponding author
Kappen, Teus H.
Venue
Diagnostic and Prognostic Research
Published
2018-06-12
Volume
2
Issue
1
Pages
11-11
ISSN
2397-7523 (ISSN-L)
OpenAlex
W2808649887
Cited by
215
References
61
Citations by year
2026: 35 · 2025: 29 · 2024: 37 · 2023: 28 · 2022: 30 · 2021: 24 · 2020: 15 · 2019: 14 · 2018: 2
FWCI
11.41
Type
journal article
Language
en
Open access
Licence
  • cc-by
  • creativecommons.org/licenses/by/4.0/ (tdm)
Locations
  • Diagnostic and Prognostic Research (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Utrecht University Repository (Utrecht University) (submittedVersion, other-oa)
Funders
ZonMw (945.16.202, 912.08.004, 918.10.615)
Topics
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
  • Health Sciences › Medicine › Family Practice › Clinical Reasoning and Diagnostic Skills
  • Health Sciences › Health Professions › General Health Professions › Health Policy Implementation Science
Keywords
clinical prediction model, impact studies, clinical decision-making, patient outcomes, surgical patients

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: Evaluating the impact of prediction models: lessons learned, challenges, and recommendations. https://app.cochat.ai/papers/10.1186/s41512-018-0033-6
The paper
Kappen, T. H., van Klei, W. A., van Wolfswinkel, L., Kalkman, C. J., Vergouwe, Y., & Moons, K. G. M. (2018). Evaluating the impact of prediction models: lessons learned, challenges, and recommendations. Diagnostic and Prognostic Research. https://doi.org/10.1186/s41512-018-0033-6

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.