PREDICT-GTN 1: Can we improve the FIGO scoring system in gestational trophoblastic neoplasia?

Gestational trophoblastic neoplasia (GTN) patients are treated according to the eight-variable International Federation of Gynaecology and Obstetrics (FIGO) scoring system, that aims to predict first-line single-agent chemotherapy resistance. FIGO is imperfect with one-third of low-risk patients developing disease resistance to first-line single-agent chemotherapy. We aimed to generate simplified models that improve upon FIGO. Logistic regression (LR) and multilayer perceptron (MLP) modelling (n = 4191) generated six models (M1-6). M1, all eight FIGO variables (scored data); M2, all eight FIGO variables (scored and raw data); M3, nonimaging variables (scored data); M4, nonimaging variables (scored and raw data); M5, imaging variables (scored data); and M6, pretreatment hCG (raw data) + imaging variables (scored data). Performance was compared to FIGO using true and false positive rates, positive and negative predictive values, diagnostic odds ratio, receiver operating characteristic (ROC) curves, Bland-Altman calibration plots, decision curve analysis and contingency tables. M1-6 were calibrated and outperformed FIGO on true positive rate and positive predictive value. Using LR and MLP, M1, M2 and M4 generated small improvements to the ROC curve and decision curve analysis. M3, M5 and M6 matched FIGO or performed less well. Compared to FIGO, most (excluding LR M4 and MLP M5) had significant discordance in patient classification (McNemar's test P < .05); 55-112 undertreated, 46-206 overtreated. Statistical modelling yielded only small gains over FIGO performance, arising through recategorisation of treatment-resistant patients, with a significant proportion of under/overtreatment as the available data have been used a priori to allocate primary chemotherapy. Streamlining FIGO should now be the focus.     

Humans and machines: Moving towards a more symbiotic approach to learning clinical reasoning

Abstract

Artificial intelligence is a growing phenomenon that is driving major changes to how we deliver healthcare. One of its most significant and challenging contributions is likely to be in diagnosis. Artificial intelligence is challenging the physician’s exclusive role in diagnosis and in some areas, its diagnostic accuracy exceeds that of humans. We argue that we urgently need to consider how we will incorporate AI into our teaching of clinical reasoning in the undergraduate curriculum; students need to successfully navigate the benefits and potential issues of new and developing approaches to AI in clinical diagnosis. We offer a pedagogical framework for this challenging change to our curriculum.