Explore the vast range of titles available.

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.

Natural language processing (NLP) of clinical notes in electronic medical records is increasingly used to extract otherwise sparsely available patient characteristics, to assess their association with relevant health outcomes. Manual data curation is resource intensive and NLP methods make these studies more feasible. However, the methodology of using NLP methods reliably in clinical research is understudied. The objective of this study is to investigate how NLP models could be used to extract study variables (specifically exposures) to reliably conduct exposure-outcome association studies. In a convenience sample of patients admitted to the intensive care unit of a US academic health system, multiple association studies are conducted, comparing the association estimates based on NLP-extracted vs. manually extracted exposure variables. The association studies varied in NLP model architecture (Bidirectional Encoder Decoder from Transformers, Long Short-Term Memory), training paradigm (training a new model, fine-tuning an existing external model), extracted exposures (employment status, living status, and substance use), health outcomes (having a do-not-resuscitate/intubate code, length of stay, and in-hospital mortality), missing data handling (multiple imputation vs. complete case analysis), and the application of measurement error correction (via regression calibration). The study was conducted on 1,174 participants (median [interquartile range] age, 61 [50, 73] years; 60.6% male). Additionally, up to 500 discharge reports of participants from the same health system and 2,528 reports of participants from an external health system were used to train the NLP models. Substantial differences were found between the associations based on NLP-extracted and manually extracted exposures under all settings. The error in association was only weakly correlated with the overall F1 score of the NLP models. Associations estimated using NLP-extracted exposures should be interpreted with caution. Further research is needed to set conditions for reliable use of NLP in medical association studies. [Display omitted]

To develop a framework to identify and evaluate spin practices and its facilitators in studies on clinical prediction model regardless of the modeling technique. We followed a three-phase consensus process: (1) premeeting literature review to generate items to be included; (2) a series of structured meetings to provide comments discussed and exchanged viewpoints on items to be included with a panel of experienced researchers; and (3) postmeeting review on final list of items and examples to be included. Through this iterative consensus process, a framework was derived after all panel's researchers agreed. This consensus process involved a panel of eight researchers and resulted in SPIN-Prediction Models which consists of two categories of spin (misleading interpretation and misleading transportability), and within these categories, two forms of spin (spin practices and facilitators of spin). We provide criteria and examples. We proposed this guidance aiming to facilitate not only the accurate reporting but also an accurate interpretation and extrapolation of clinical prediction models which will likely improve the reporting quality of subsequent research, as well as reduce research waste.

Cardiovascular disease (CVD) risk scores provide point estimates of individual risk without uncertainty quantification. The objective of the current study was to demonstrate the feasibility and clinical utility of calculating uncertainty surrounding individual CVD-risk predictions using Bayesian methods. Individuals with established atherosclerotic CVD were included from the Utrecht Cardiovascular Cohort—Secondary Manifestations of ARTerial disease (UCC-SMART). In 8,355 individuals, followed for median of 8.2 years (IQR 4.2–12.5), a Bayesian Weibull model was derived to predict the 10-year risk of recurrent CVD events. Model coefficients and individual predictions from the Bayesian model were very similar to that of a traditional (‘frequentist’) model but the Bayesian model also predicted 95% credible intervals (CIs) surrounding individual risk estimates. The median width of the individual 95%CrI was 5.3% (IQR 3.6–6.5) and 17% of the population had a 95%CrI width of 10% or greater. The uncertainty decreased with increasing sample size used for derivation of the model. Combining the Bayesian Weibull model with sampled hazard ratios based on trial reports may be used to estimate individual estimates of absolute risk reduction with uncertainty measures and the probability that a treatment option will result in a clinically relevant risk reduction. Estimating uncertainty surrounding individual CVD risk predictions using Bayesian methods is feasible. The uncertainty regarding individual risk predictions could have several applications in clinical practice, like the comparison of different treatment options or by calculating the probability of the individual risk being below a certain treatment threshold. However, as the individual uncertainty measures only reflect sampling error and no biases in risk prediction, physicians should be familiar with the interpretation before widespread clinical adaption. [Display omitted] •It is feasible to estimate uncertainty surrounding individual CVD risk predictions.•Calculating uncertainty with Bayesian methods may have several applications.•One example is calculating the probability of being above risk thresholds.•Individual uncertainty only reflects sampling error and no biases in risk prediction.

Clinical prediction models aim to predict outcomes in individuals, to inform diagnosis or prognosis in healthcare. Hundreds of prediction models are published in the medical literature each year, yet many are developed using a dataset that is too small for the total number of participants or outcome events. This leads to inaccurate predictions and consequently incorrect healthcare decisions for some individuals. In this article, the authors provide guidance on how to calculate the sample size required to develop a clinical prediction model.

Background Clinical prediction models should be validated before implementation in clinical practice. But is favorable performance at internal validation or one external validation sufficient to claim that a prediction model works well in the intended clinical context? Main body We argue to the contrary because (1) patient populations vary, (2) measurement procedures vary, and (3) populations and measurements change over time. Hence, we have to expect heterogeneity in model performance between locations and settings, and across time. It follows that prediction models are never truly validated. This does not imply that validation is not important. Rather, the current focus on developing new models should shift to a focus on more extensive, well-conducted, and well-reported validation studies of promising models. Conclusion Principled validation strategies are needed to understand and quantify heterogeneity, monitor performance over time, and update prediction models when appropriate. Such strategies will help to ensure that prediction models stay up-to-date and safe to support clinical decision-making.

The TRIPOD (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis) statement was published in 2015 to provide the minimum reporting recommendations for studies developing or evaluating the performance of a prediction model. Methodological advances in the field of prediction have since included the widespread use of artificial intelligence (AI) powered by machine learning methods to develop prediction models. An update to the TRIPOD statement is thus needed. TRIPOD+AI provides harmonised guidance for reporting prediction model studies, irrespective of whether regression modelling or machine learning methods have been used. The new checklist supersedes the TRIPOD 2015 checklist, which should no longer be used. This article describes the development of TRIPOD+AI and presents the expanded 27 item checklist with more detailed explanation of each reporting recommendation, and the TRIPOD+AI for Abstracts checklist. TRIPOD+AI aims to promote the complete, accurate, and transparent reporting of studies that develop a prediction model or evaluate its performance. Complete reporting will facilitate study appraisal, model evaluation, and model implementation.

Background The assessment of calibration performance of risk prediction models based on regression or more flexible machine learning algorithms receives little attention. Main text Herein, we argue that this needs to change immediately because poorly calibrated algorithms can be misleading and potentially harmful for clinical decision-making. We summarize how to avoid poor calibration at algorithm development and how to assess calibration at algorithm validation, emphasizing balance between model complexity and the available sample size. At external validation, calibration curves require sufficiently large samples. Algorithm updating should be considered for appropriate support of clinical practice. Conclusion Efforts are required to avoid poor calibration when developing prediction models, to evaluate calibration when validating models, and to update models when indicated. The ultimate aim is to optimize the utility of predictive analytics for shared decision-making and patient counseling.

Evaluating the performance of a clinical prediction model is crucial to establish its predictive accuracy in the populations and settings intended for use. In this article, the first in a three part series, Collins and colleagues describe the importance of a meaningful evaluation using internal, internal-external, and external validation, as well as exploring heterogeneity, fairness, and generalisability in model performance.

An external validation study evaluates the performance of a prediction model in new data, but many of these studies are too small to provide reliable answers. In the third article of their series on model evaluation, Riley and colleagues describe how to calculate the sample size required for external validation studies, and propose to avoid rules of thumb by tailoring calculations to the model and setting at hand.