Dataset Information

Spatio-temporal hybrid neural networks reduce erroneous human "judgement calls" in the diagnosis of Takotsubo syndrome.

ABSTRACT:

Background

We investigate whether deep learning (DL) neural networks can reduce erroneous human "judgment calls" on bedside echocardiograms and help distinguish Takotsubo syndrome (TTS) from anterior wall ST segment elevation myocardial infarction (STEMI).

Methods

We developed a single-channel (DCNN[2D SCI]), a multi-channel (DCNN[2D MCI]), and a 3-dimensional (DCNN[2D+t]) deep convolution neural network, and a recurrent neural network (RNN) based on 17,280 still-frame images and 540 videos from 2-dimensional echocardiograms in 10 years (1 January 2008 to 1 January 2018) retrospective cohort in University of Iowa (UI) and eight other medical centers. Echocardiograms from 450 UI patients were randomly divided into training and testing sets for internal training, testing, and model construction. Echocardiograms of 90 patients from the other medical centers were used for external validation to evaluate the model generalizability. A total of 49 board-certified human readers performed human-side classification on the same echocardiography dataset to compare the diagnostic performance and help data visualization.

Findings

The DCNN (2D SCI), DCNN (2D MCI), DCNN(2D+t), and RNN models established based on UI dataset for TTS versus STEMI prediction showed mean diagnostic accuracy 73%, 75%, 80%, and 75% respectively, and mean diagnostic accuracy of 74%, 74%, 77%, and 73%, respectively, on the external validation. DCNN(2D+t) (area under the curve [AUC] 0·787 vs. 0·699, P = 0·015) and RNN models (AUC 0·774 vs. 0·699, P = 0·033) outperformed human readers in differentiating TTS and STEMI by reducing human erroneous judgement calls on TTS.

Interpretation

Spatio-temporal hybrid DL neural networks reduce erroneous human "judgement calls" in distinguishing TTS from anterior wall STEMI based on bedside echocardiographic videos.

Funding

University of Iowa Obermann Center for Advanced Studies Interdisciplinary Research Grant, and Institute for Clinical and Translational Science Grant. National Institutes of Health Award (1R01EB025018-01).

SUBMITTER: Zaman F

PROVIDER: S-EPMC8426197 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Despite its high ecological importance, the commensal interactions at community level are poorly studied. In tropical dry forests (TDF) there is a great diversity of species adapted to the high seasonality that characterizes them; however, little is known regarding how the spatial and temporal availability of resources generates changes in the pattern of commensal interactions. We experimentally studied changes in the diversity, composition, and pattern of interactions in spatio-temporal associations between the saproxylophagous beetles and their host trees in a TDF in Morelos, Mexico. A total of 65 host tree species were selected, from which 16 wood sections were obtained per species. These sections were exposed in the field to allow oviposition by the cerambycids under four different (spatio-temporal) treatments. We analyzed the network structure and generated indices at species level (i.e., specialization, species strength, and effective partners) and those related to physical characteristics of the wood (hardness and degradation rate) and the cerambycids (body size). In total, 1,323 individuals of 57 species of cerambycids emerged. Our results showed that, independently of the space and time, the network presented a nested and modular structure, with a high specialization degree and a high turnover of cerambycid species and their interactions. In general, we found that the cerambycids are mostly associated with softwood species with a lower decomposition rate of wood, as well as with the most abundant host species. The commensalistic interactions between the cerambycids and their host trees are highly specialized but are not spatio-temporally static. The high turnover in the interactions is caused by the emergence patterns of cerambycids, which seem to restrict their use to certain species. The knowledge of the spatio-temporal variation in Cerambycidae-host tree interactions allows us to predict how environmental and structural changes in the habitat can modify the species ensemble, and therefore its interactions.