A hierarchical expert-guided machine learning framework for clinical decision support systems: an application to traumatic brain injury prognostication

Abstract

Prognosis of the long-term functional outcome of traumatic brain injury is essential for personalized management of that injury. Nonetheless, accurate prediction remains unavailable. Although machine learning has shown promise in many fields, including medical diagnosis and prognosis, such models are rarely deployed in real-world settings due to a lack of transparency and trustworthiness. To address these drawbacks, we propose a machine learning-based framework that is explainable and aligns with clinical domain knowledge. To build such a framework, additional layers of statistical inference and human expert validation are added to the model, which ensures the predicted risk score’s trustworthiness. Using 831 patients with moderate or severe traumatic brain injury to build a model using the proposed framework, an area under the receiver operating characteristic curve (AUC) and accuracy of 0.8085 and 0.7488 were achieved, respectively, in determining which patients will experience poor functional outcomes. The performance of the machine learning classifier is not adversely affected by the imposition of statistical and domain knowledge “checks and balances”. Finally, through a case study, we demonstrate how the decision made by a model might be biased if it is not audited carefully.

Predicting outcome of patients with prolonged disorders of consciousness using machine learning models based on medical complexity

“…Moreover, the authors reached similar results targeting the dichotomized version of the GOS-E scale and reporting a validation area under the curve of 0.78 with models trained with data taken at admission 63 . It must be mentioned, though, that our case mix included TBIs, anoxic and vascular etiologies notably increasing the complexity of the prediction task with respect to only TBIs, as in Farzaneh et al 65 .…”

“…In conclusion, ML offers promising and automated medical reporting and prognosis algorithms, but at the moment such models are rarely deployed in daily clinical settings 65 . To improve transparency and practicality, we proposed a machine learning-based framework that is explainable and that is based on affordable features, with no instrumental requirements.…”

Restoring and attributing ancient texts using deep neural networks

“…Most importantly, this work shows how matching human experts with deep learning architectures to tackle tasks collaboratively can surpass the individual (unaided) performance of both humans and model on the same tasks. Indeed, recent medical research 68,69 further confirms the importance of hybrid architectures in addressing real-world problems. The present work makes human expert interaction possible by visualizing the output probability distributions for all tasks using multiple charts and maps, and augmenting their interpretability by means of saliency maps.…”

The leap to ordinal: Detailed functional prognosis after traumatic brain injury with a flexible modelling approach

“…SHAP values are visualised ( Fig 4 ) solely to globally interpret APM MN predictions and to form the extended concise predictor set. Risk factor validation, which falls out of the scope of this work, would require investigating the robustness and clinical plausibility of the relationship between predictor values and their corresponding SHAP values [ 54 ]. Moreover, causal analysis with apt consideration of confounding factors or dataset biases would be necessary before commenting on the potential effects or mechanisms of individual predictors.…”