Browsing by Subject "Computer neural networks"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Assessing the utility of deep neural networks in predicting postoperative surgical complications: a retrospective study
    (Elsevier, 2021) Bonde, Alexander; Varadarajan, Kartik M.; Bonde, Nicholas; Troelsen, Anders; Muratoglu, Orhun K.; Malchau, Henrik; Yang, Anthony D.; Alam, Hasan; Sillesen, Martin; Surgery, School of Medicine
    Background: Early detection of postoperative complications, including organ failure, is pivotal in the initiation of targeted treatment strategies aimed at attenuating organ damage. In an era of increasing health-care costs and limited financial resources, identifying surgical patients at a high risk of postoperative complications and providing personalised precision medicine-based treatment strategies provides an obvious pathway for reducing patient morbidity and mortality. We aimed to leverage deep learning to create, through training on structured electronic health-care data, a multilabel deep neural network to predict surgical postoperative complications that would outperform available models in surgical risk prediction. Methods: In this retrospective study, we used data on 58 input features, including demographics, laboratory values, and 30-day postoperative complications, from the American College of Surgeons (ACS) National Surgical Quality Improvement Program database, which collects data from 722 hospitals from around 15 countries. We queried the entire adult (≥18 years) database for patients who had surgery between Jan 1, 2012, and Dec 31, 2018. We then identified all patients who were treated at a large midwestern US academic medical centre, excluded them from the base dataset, and reserved this independent group for final model testing. We then randomly created a training set and a validation set from the remaining cases. We developed three deep neural network models with increasing numbers of input variables and so increasing levels of complexity. Output variables comprised mortality and 18 different postoperative complications. Overall morbidity was defined as any of 16 postoperative complications. Model performance was evaluated on the test set using the area under the receiver operating characteristic curve (AUC) and compared with previous metrics from the ACS-Surgical Risk Calculator (ACS-SRC). We evaluated resistance to changes in the underlying patient population on a subset of the test set, comprising only patients who had emergency surgery. Results were also compared with the Predictive OpTimal Trees in Emergency Surgery Risk (POTTER) calculator. Findings: 5 881 881 surgical patients, with 2941 unique Current Procedural Terminology codes, were included in this study, with 4 694 488 in the training set, 1 173 622 in the validation set, and 13 771 in the test set. The mean AUCs for the validation set were 0·864 (SD 0·053) for model 1, 0·871 (0·055) for model 2, and 0·882 (0·053) for model 3. The mean AUCs for the test set were 0·859 (SD 0·063) for model 1, 0·863 (0·064) for model 2, and 0·874 (0·061) for model 3. The mean AUCs of each model outperformed previously published performance metrics from the ACS-SRC, with a direct correlation between increasing model complexity and performance. Additionally, when tested on a subgroup of patients who had emergency surgery, our models outperformed previously published POTTER metrics. Interpretation: We have developed unified prediction models, based on deep neural networks, for predicting surgical postoperative complications. The models were generally superior to previously published surgical risk prediction tools and appeared robust to changes in the underlying patient population. Deep learning could offer superior approaches to surgical risk prediction in clinical practice.
  • Thumbnail Image
    Item
    scGNN 2.0: a graph neural network tool for imputation and clustering of single-cell RNA-Seq data
    (Oxford University Press, 2022) Gu, Haocheng; Cheng, Hao; Ma, Anjun; Li, Yang; Wang, Juexin; Xu, Dong; Ma, Qin; Biostatistics and Health Data Science, Richard M. Fairbanks School of Public Health
    Motivation: Gene expression imputation has been an essential step of the single-cell RNA-Seq data analysis workflow. Among several deep-learning methods, the debut of scGNN gained substantial recognition in 2021 for its superior performance and the ability to produce a cell-cell graph. However, the implementation of scGNN was relatively time-consuming and its performance could still be optimized. Results: The implementation of scGNN 2.0 is significantly faster than scGNN thanks to a simplified close-loop architecture. For all eight datasets, cell clustering performance was increased by 85.02% on average in terms of adjusted rand index, and the imputation Median L1 Error was reduced by 67.94% on average. With the built-in visualizations, users can quickly assess the imputation and cell clustering results, compare against benchmarks and interpret the cell-cell interaction. The expanded input and output formats also pave the way for custom workflows that integrate scGNN 2.0 with other scRNA-Seq toolkits on both Python and R platforms. Availability and implementation: scGNN 2.0 is implemented in Python (as of version 3.8) with the source code available at https://github.com/OSU-BMBL/scGNN2.0.
  • Thumbnail Image
    Item
    Understanding Cortical Streams from a Computational Perspective
    (MIT Press, 2024) Han, Zhixian; Sereno, Anne B.; Psychology, School of Science
    The two visual cortical streams hypothesis, which suggests object properties (what) are processed separately from spatial properties (where), has a longstanding history, and much evidence has accumulated to support its conjectures. Nevertheless, in the last few decades, conflicting evidence has mounted that demands some explanation and modification. For example, existence of (1) shape activities (fMRI) or shape selectivities (physiology) in dorsal stream, similar to ventral stream; likewise, spatial activations (fMRI) or spatial selectivities (physiology) in ventral stream, similar to dorsal stream; (2) multiple segregated subpathways within a stream. In addition, the idea of segregation of various aspects of multiple objects in a scene raises questions about how these properties of multiple objects are then properly re-associated or bound back together to accurately perceive, remember, or make decisions. We will briefly review the history of the two-stream hypothesis, discuss competing accounts that challenge current thinking, and propose ideas on why the brain has segregated pathways. We will present ideas based on our own data using artificial neural networks (1) to reveal encoding differences for what and where that arise in a two-pathway neural network, (2) to show how these encoding differences can clarify previous conflicting findings, and (3) to elucidate the computational advantages of segregated pathways. Furthermore, we will discuss whether neural networks need to have multiple subpathways for different visual attributes. We will also discuss the binding problem (how to correctly associate the different attributes of each object together when there are multiple objects each with multiple attributes in a scene) and possible solutions to the binding problem. Finally, we will briefly discuss problems and limitations with existing models and potential fruitful future directions.