Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a sco** review

AAH de Hond, AM Leeuwenberg, L Hooft… - NPJ digital …, 2022‏ - nature.com
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 …

Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal

L Wynants, B Van Calster, GS Collins, RD Riley… - bmj, 2020‏ - bmj.com
Objective To review and appraise the validity and usefulness of published and preprint
reports of prediction models for prognosis of patients with covid-19, and for detecting people …

Calculating the sample size required for develo** a clinical prediction model

RD Riley, J Ensor, KIE Snell, FE Harrell, GP Martin… - Bmj, 2020‏ - bmj.com
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 …

PROBAST: a tool to assess risk of bias and applicability of prediction model studies: explanation and elaboration

KGM Moons, RF Wolff, RD Riley, PF Whiting… - Annals of internal …, 2019‏ - acpjournals.org
Prediction models in health care use predictors to estimate for an individual the probability
that a condition or disease is already present (diagnostic model) or will occur in the future …

Minimum sample size for external validation of a clinical prediction model with a binary outcome

RD Riley, TPA Debray, GS Collins, L Archer… - Statistics in …, 2021‏ - Wiley Online Library
In prediction model research, external validation is needed to examine an existing model's
performance using data independent to that for model development. Current external …

The importance of being external. methodological insights for the external validation of machine learning models in medicine

F Cabitza, A Campagner, F Soares… - Computer Methods and …, 2021‏ - Elsevier
Abstract Background and Objective Medical machine learning (ML) models tend to perform
better on data from the same cohort than on new data, often due to overfitting, or co-variate …

Comparison of eight prehospital stroke scales to detect intracranial large-vessel occlusion in suspected stroke (PRESTO): a prospective observational study

MHC Duvekot, E Venema, AD Rozeman… - The Lancet …, 2021‏ - thelancet.com
Background Due to the time-sensitive effect of endovascular treatment, rapid prehospital
identification of large-vessel occlusion in individuals with suspected stroke is essential to …

Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): explanation and elaboration

KGM Moons, DG Altman, JB Reitsma… - Annals of internal …, 2015‏ - acpjournals.org
The TRIPOD (Transparent Reporting of a multivariable prediction model for Individual
Prognosis Or Diagnosis) Statement includes a 22-item checklist, which aims to improve the …

A calibration hierarchy for risk models was defined: from utopia to empirical data

B Van Calster, D Nieboer, Y Vergouwe… - Journal of clinical …, 2016‏ - Elsevier
Objective Calibrated risk models are vital for valid decision support. We define four levels of
calibration and describe implications for model development and external validation of …

Validation of a prediction tool for chemotherapy toxicity in older adults with cancer

A Hurria, S Mohile, A Gajra, H Klepin… - Journal of Clinical …, 2016‏ - ascopubs.org
Purpose Older adults are at increased risk for chemotherapy toxicity, and standard oncology
assessment measures cannot identify those at risk. A predictive model for chemotherapy …