Artificial or intelligent? Machine learning and medical selection: possibilities and risks

Machine Learning to Predict Prostate Artery Embolization Outcomes

PURPOSE

This study leverages pre-procedural data and machine learning (ML) techniques to predict outcomes at one year following prostate artery embolization (PAE).

MATERIALS AND METHODS

This retrospective analysis combines data from the UK-ROPE registry and patients that underwent PAE at our institution between 2012 and 2023. Traditional ML approaches, including linear regression, lasso regression, ridge regression, decision trees and random forests, were used with leave-one-out cross-validation to predict international prostate symptom score (IPSS) at baseline and change at 1 year. Predictors included age, prostate volume, Qmax (maximum urinary flow rate), post-void residual volume, Abrams-Griffiths number (urodynamics score) and baseline IPSS (for change at 1 year). We also independently confirmed our findings using a separate dataset. An interactive digital user interface was developed to facilitate real-time outcome prediction.

RESULTS

Complete data were available in 128 patients (66.7 ± 6.9 years). All models predicting IPSS demonstrated reasonable performance, with mean absolute error ranging between 4.9-7.3 for baseline IPSS and 5.2-8.2 for change in IPSS. These numbers represent the differences between the patient-reported and model-predicted IPSS scores. Interestingly, the model error in predicting baseline IPSS (based on objective measures alone) significantly correlated with the change in IPSS at 1-year post-PAE (R2 = 0.2, p < 0.001), forming the basis for our digital user interface.

CONCLUSION

This study uses ML methods to predict IPSS improvement at 1 year, integrated into a user-friendly interface for real-time prediction. This tool could be used to counsel patients prior to treatment.

Artificial intelligence in emergency medicine: A scoping review

INTRODUCTION

Despite the growing investment in and adoption of artificial intelligence (AI) in medicine, the applications of AI in an emergency setting remain unclear. This scoping review seeks to identify available literature regarding the applications of AI in emergency medicine.

METHODS

The scoping review was conducted according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines for scoping reviews using Medline-OVID, EMBASE, CINAHL, and IEEE, with a double screening and extraction process. The search included articles published until February 28, 2020. Articles were excluded if they did not self-classify as studying an AI intervention, were not relevant to the emergency department (ED), or did not report outcomes or evaluation.

RESULTS

Of the 1483 original database citations, 395 were eligible for full-text evaluation. Of these articles, a total of 150 were included in the scoping review. The majority of included studies were retrospective in nature (n = 124, 82.7%), with only 3 (2.0%) prospective controlled trials. We found 37 (24.7%) interventions aimed at improving diagnosis within the ED. Among the 150 studies, 19 (12.7%) focused on diagnostic imaging within the ED. A total of 16 (10.7%) studies were conducted in the out-of-hospital environment (eg, emergency medical services, paramedics) with the remainder occurring either in the ED or the trauma bay. Of the 24 (16%) studies that had human comparators, there were 12 (8%) studies in which AI interventions outperformed clinicians in at least 1 measured outcome.

CONCLUSION

AI-related research is rapidly increasing in emergency medicine. There are several promising AI interventions that can improve emergency care, particularly for acute radiographic imaging and prediction-based diagnoses. Higher quality evidence is needed to further assess both short- and long-term clinical outcomes.

Closing Editorial: New insights and reflections on the science of selection and recruitment

This article was migrated. The article was marked as recommended. In this closing editorial we reflect on key topics presented in this special issue on selection and recruitment, with a view to identifying gaps in the literature, and exploring where next. Four key themes have emerged including; (1) the impact of using new technologies in selection and recruitment; (2) addressing social accountability, diversity and fairness issues in selection; (3) increased emphasis on non-academic personal attributes in selection, and (4) attraction and recruitment in postgraduate recruitment. The implications of findings from this collection of studies and opinion pieces are discussed in relation to future research, policy and practice.