Using Transfer Learning for Improved Mortality Prediction in a Data-Scarce Hospital Setting

Abstract

Algorithm–based clinical decision support (CDS) systems associate patient-derived health data with outcomes of interest, such as in-hospital mortality. However, the quality of such associations often depends on the availability of site-specific training data. Without sufficient quantities of data, the underlying statistical apparatus cannot differentiate useful patterns from noise and, as a result, may underperform. This initial training data burden limits the widespread, out-of-the-box, use of machine learning–based risk scoring systems. In this study, we implement a statistical transfer learning technique, which uses a large “source” data set to drastically reduce the amount of data needed to perform well on a “target” site for which training data are scarce. We test this transfer technique with AutoTriage, a mortality prediction algorithm, on patient charts from the Beth Israel Deaconess Medical Center (the source) and a population of 48 249 adult inpatients from University of California San Francisco Medical Center (the target institution). We find that the amount of training data required to surpass 0.80 area under the receiver operating characteristic (AUROC) on the target set decreases from more than 4000 patients to fewer than 220. This performance is superior to the Modified Early Warning Score (AUROC: 0.76) and corresponds to a decrease in clinical data collection time from approximately 6 months to less than 10 days. Our results highlight the usefulness of transfer learning in the specialization of CDS systems to new hospital sites, without requiring expensive and time-consuming data collection efforts.

Prediction of early unplanned intensive care unit readmission in a UK tertiary care hospital: a cross-sectional machine learning approach

“…However, very similar results can be obtained by nesting another cross-validation inside the training to select the transfer weight. 25 …”

Mortality prediction model for the triage of COVID-19, pneumonia, and mechanically ventilated ICU patients: A retrospective study

“…Mortality prediction tools aid in triage and resource allocation by providing advance warning of patient deterioration. Our prior work has validated machine-learning (ML) algorithms for their ability to predict mortality and patient stability in a variety of settings and on diverse patient populations [ [20] , [21] , [22] , [23] , [24] ].…”

Deep learning enables automated scoring of liver fibrosis stages

“…This network was made up of 1 input layer, 7 hidden layers (5 convolution layers and 2 fully connected layers) and 1 output layer using batch stochastic gradient descent, with specific values for momentum and weight decay 17 . The input and output layers of the original AlexNet-CNN network were replaced accordingly for liver fibrosis assessment as previously reported 15 , 16 , where the processed SHG images were first resized and duplicated to 224 × 224 × 3 pixels to fit into the model as input images. There were 2 max pooling layers of size 2 × 2 pixels after the first and second convolution layer where the size and number of filters are 11 × 11 × 3 pixels, 96 and 5 × 5 × 96 pixels, 256, respectively.…”

“…However, they demand the use of a large training dataset and biopsy sample images typically do not meet this need. Based on transfer learning being a variant of the typical deep learning-based algorithms - in that the neural network is pre-trained by a very large number of training datasets worldwide using weakly or even irrelevant image sources 15 , 16 - we hypothesized that the pre-trained deep learning neural network in transfer learning approach can accurately stage liver fibrosis in a fully automated manner. Here, we validated our hypothesis by inheriting and adapting the most studied seven-layered AlexNet 17 algorithm for computer-aided liver fibrosis scoring.…”