Michael S Avidan

Sandhya Tripathi, Bradley A Fritz, Michael S Avidan et al.

Although prediction models for delirium, a commonly occurring condition during general hospitalization or post-surgery, have not gained huge popularity, their algorithmic bias evaluation is crucial due to the existing association between social determinants of health and delirium risk. In this context, using MIMIC-III and another academic hospital dataset, we present some initial experimental evidence showing how sociodemographic features such as sex and race can impact the model performance across subgroups. With this work, our intent is to initiate a discussion about the intersectionality effects of old age, race and socioeconomic factors on the early-stage detection and prevention of delirium using ML.

Mohamed Abdelhack, Jiaming Zhang, Sandhya Tripathi et al.

Data missingness and quality are common problems in machine learning, especially for high-stakes applications such as healthcare. Developers often train machine learning models on carefully curated datasets using only high quality data; however, this reduces the utility of such models in production environments. We propose a novel neural network modification to mitigate the impacts of low quality and missing data which involves replacing the fixed weights of a fully-connected layer with a function of an additional input. This is inspired from neuromodulation in biological neural networks where the cortex can up- and down-regulate inputs based on their reliability and the presence of other data. In testing, with reliability scores as a modulating signal, models with modulating layers were found to be more robust against degradation of data quality, including additional missingness. These models are superior to imputation as they save on training time by completely skipping the imputation process and further allow the introduction of other data quality measures that imputation cannot handle. Our results suggest that explicitly accounting for reduced information quality with a modulating fully connected layer can enable the deployment of artificial intelligence systems in real-time applications.

Zhicheng Cui, Bradley A Fritz, Christopher R King et al.

Logistic regression (LR) is widely used in clinical prediction because it is simple to deploy and easy to interpret. Nevertheless, being a linear model, LR has limited expressive capability and often has unsatisfactory performance. Generalized additive models (GAMs) extend the linear model with transformations of input features, though feature interaction is not allowed for all GAM variants. In this paper, we propose a factored generalized additive model (F-GAM) to preserve the model interpretability for targeted features while allowing a rich model for interaction with features fixed within the individual. We evaluate F-GAM on prediction of two targets, postoperative acute kidney injury and acute respiratory failure, from a single-center database. We find superior model performance of F-GAM in terms of AUPRC and AUROC compared to several other GAM implementations, random forests, support vector machine, and a deep neural network. We find that the model interpretability is good with results with high face validity.