While the opportunities of ML and AI in healthcare are promising, the growth of complex data-driven prediction models requires careful quality and applicability assessment before they are applied and disseminated in daily practice. This scoping review aimed to identify actionable guidance for those closely involved in AI-based prediction model (AIPM) development, evaluation and implementation including software engineers, data scientists, and healthcare professionals and to identify potential gaps in this guidance. We performed a scoping review of the relevant literature providing guidance or quality criteria regarding the development, evaluation, and implementation of AIPMs using a comprehensive multi-stage screening strategy. PubMed, Web of Science, and the ACM Digital Library were searched, and AI experts were consulted. Topics were extracted from the identified literature and summarized across the six phases at the core of this review: (1) data preparation, (2) AIPM development, (3) AIPM validation, (4) software development, (5) AIPM impact assessment, and (6) AIPM implementation into daily healthcare practice. From 2683 unique hits, 72 relevant guidance documents were identified. Substantial guidance was found for data preparation, AIPM development and AIPM validation (phases 1–3), while later phases clearly have received less attention (software development, impact assessment and implementation) in the scientific literature. The six phases of the AIPM development, evaluation and implementation cycle provide a framework for responsible introduction of AI-based prediction models in healthcare. Additional domain and technology specific research may be necessary and more practical experience with implementing AIPMs is needed to support further guidance.

The generalizability of predictive algorithms is of key relevance to application in clinical practice. We provide an overview of three types of generalizability, based on existing literature: temporal, geographical, and domain generalizability. These generalizability types are linked to their associated goals, methodology, and stakeholders.

Clinical prediction models provide risks of health outcomes that can inform patients and support medical decisions. However, most models never make it to actual implementation in practice. A commonly heard reason for this lack of implementation is that prediction models are often not externally validated. While we generally encourage external validation, we argue that an external validation is often neither sufficient nor required as an essential step before implementation. As such, any available external validation should not be perceived as a license for model implementation. We clarify this argument by discussing 3 common misconceptions about external validation. We argue that there is not one type of recommended validation design, not always a necessity for external validation, and sometimes a need for multiple external validations. The insights from this paper can help readers to consider, design, interpret, and appreciate external validation studies.

Early identification of emergency department (ED) patients who need hospitalization is essential for quality of care and patient safety. We aimed to compare machine learning (ML) models predicting the hospitalization of ED patients and conventional regression techniques at three points in time after ED registration. We analyzed consecutive ED patients of three hospitals using the Netherlands Emergency Department Evaluation Database (NEED). We developed prediction models for hospitalization using an increasing number of data available at triage, ∼30 min (including vital signs) and ∼2 h (including laboratory tests) after ED registration, using ML (random forest, gradient boosted decision trees, deep neural networks) and multivariable logistic regression analysis (including spline transformations for continuous predictors). Demographics, urgency, presenting complaints, disease severity and proxies for comorbidity, and complexity were used as covariates. We compared the performance using the area under the ROC curve in independent validation sets from each hospital. We included 172,104 ED patients of whom 66,782 (39 %) were hospitalized. The AUC of the multivariable logistic regression model was 0.82 (0.78-0.86) at triage, 0.84 (0.81-0.86) at ∼30 min and 0.83 (0.75-0.92) after ∼2 h. The best performing ML model over time was the gradient boosted decision trees model with an AUC of 0.84 (0.77-0.88) at triage, 0.86 (0.82-0.89) at ∼30 min and 0.86 (0.74-0.93) after ∼2 h. Our study showed that machine learning models had an excellent but similar predictive performance as the logistic regression model for predicting hospital admission. In comparison to the 30-min model, the 2-h model did not show a performance improvement. After further validation, these prediction models could support management decisions by real-time feedback to medical personal.

OBJECTIVES: Many machine learning (ML) models have been developed for application in the ICU, but few models have been subjected to external validation. The performance of these models in new settings therefore remains unknown. The objective of this study was to assess the performance of an existing decision support tool based on a ML model predicting readmission or death within 7 days after ICU discharge before, during, and after retraining and recalibration. DESIGN: A gradient boosted ML model was developed and validated on electronic health record data from 2004 to 2021. We performed an independent validation of this model on electronic health record data from 2011 to 2019 from a different tertiary care center. SETTING: Two ICUs in tertiary care centers in The Netherlands. PATIENTS: Adult patients who were admitted to the ICU and stayed for longer than 12 hours. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We assessed discrimination by area under the receiver operating characteristic curve (AUC) and calibration (slope and intercept). We retrained and recalibrated the original model and assessed performance via a temporal validation design. The final retrained model was cross-validated on all data from the new site. Readmission or death within 7 days after ICU discharge occurred in 577 of 10,052 ICU admissions (5.7%) at the new site. External validation revealed moderate discrimination with an AUC of 0.72 (95% CI 0.67–0.76). Retrained models showed improved discrimination with AUC 0.79 (95% CI 0.75–0.82) for the final validation model. Calibration was poor initially and good after recalibration via isotonic regression. CONCLUSIONS: In this era of expanding availability of ML models, external validation and retraining are key steps to consider before applying ML models to new settings. Clinicians and decision-makers should take this into account when considering applying new ML models to their local settings.