2017
DOI: 10.1177/1178222617712994
|View full text |Cite
|
Sign up to set email alerts
|

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 learnin… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
28
0

Year Published

2017
2017
2024
2024

Publication Types

Select...
6
2

Relationship

2
6

Authors

Journals

citations
Cited by 40 publications
(28 citation statements)
references
References 29 publications
0
28
0
Order By: Relevance
“…However, very similar results can be obtained by nesting another cross-validation inside the training to select the transfer weight. 25 …”
Section: Discussionmentioning
confidence: 99%
“…However, very similar results can be obtained by nesting another cross-validation inside the training to select the transfer weight. 25 …”
Section: Discussionmentioning
confidence: 99%
“…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] ].…”
Section: Introductionmentioning
confidence: 99%
“…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.…”
Section: Methodsmentioning
confidence: 99%
“…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.…”
Section: Introductionmentioning
confidence: 99%