用于预测重症监护病房医院感染风险的人工神经网络：教学性初步模型

数据集获取（Figshare）

• 源站标题：A neural network for prediction of risk of nosocomial infection at intensive care units: a didactic preliminary model
• DOI：10.6084/m9.figshare.14322394.v1
• 发布日期：2021-03-26
• 文件数：9 个
• 文件总体积：1.27 MB
• 源站页面：https://scielo.figshare.com/articles/dataset/A_neural_network_for_prediction_of_risk_of_nosocomial_infection_at_intensive_care_units_a_didactic_preliminary_model/14322394

命令行下载

curl -L -o "2317-6385-eins-18-eAO5480-gf01.jpg" "https://ndownloader.figshare.com/files/27284023"
curl -L -o "2317-6385-eins-18-eAO5480-gf02.jpg" "https://ndownloader.figshare.com/files/27284026"
curl -L -o "2317-6385-eins-18-eAO5480-gf03.jpg" "https://ndownloader.figshare.com/files/27284029"
curl -L -o "2317-6385-eins-18-eAO5480-gf04.jpg" "https://ndownloader.figshare.com/files/27284032"
curl -L -o "Table_1.xls" "https://ndownloader.figshare.com/files/27284041"
curl -L -o "Table_2.xls" "https://ndownloader.figshare.com/files/27284044"
curl -L -o "Table_3.xls" "https://ndownloader.figshare.com/files/27284047"
curl -L -o "Table_4.xls" "https://ndownloader.figshare.com/files/27284050"

文件清单

• 2317-6385-eins-18-eAO5480-gf01.jpg（157.09 KB）
• 2317-6385-eins-18-eAO5480-gf02.jpg（259.87 KB）
• 2317-6385-eins-18-eAO5480-gf03.jpg（266.62 KB）
• 2317-6385-eins-18-eAO5480-gf04.jpg（559.84 KB）
• Table_1.xls（5.63 KB）
• Table_2.xls（5.63 KB）
• Table_3.xls（5.63 KB）
• Table_4.xls（5.63 KB）
• Table_5.xls（5.63 KB）

文件总体积 1.27 MB（源站 API 实测）。

数据加载示例（图像类）

from PIL import Image
import glob, os

files = (glob.glob(os.path.join(path, "**", "*.png"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.jpg"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.tif"), recursive=True))
print("图像文件数:", len(files))
img = Image.open(files[0]); print("尺寸/模式:", img.size, img.mode)

# torchvision Dataset 方式:
# from torchvision import datasets
# ds = datasets.ImageFolder(path)  # 要求 子目录=类别

目录组织与标注格式以源站说明和下载后实际文件为准。

数据说明

ABSTRACT Objective: To propose a preliminary artificial intelligence model, based on artificial neural networks, for predicting the risk of nosocomial infection at intensive care units. Methods: An artificial neural network is designed that employs supervised learning. The generation of the datasets was based on data derived from the Japanese Nosocomial Infection Surveillance system. It is studied how the Java Neural Network Simulator learns to categorize these patients to predict their risk of nosocomial infection. The simulations are performed with several backpropagation learning algorithms and with several groups of parameters, comparing their results through the sum of the squared errors and mean errors per pattern. Results: The backpropagation with momentum algorithm showed better performance than the backpropagation algorithm. The performance improved with the xor. README file parameter values compared to the default parameters. There were no failures in the categorization of the patients into their risk of nosocomial infection. Conclusion: While this model is still based on a synthetic dataset, the excellent performance observed with a small number of patterns suggests that using higher numbers of variables and network layers to analyze larger volumes of data can create powerful artificial neural networks, potentially capable of precisely anticipating nosocomial infection at intensive care units. Using a real database during the simulations has the potential to realize the predictive ability of this model.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.6084/m9.figshare.14322394.v1（source: https://scielo.figshare.com/articles/dataset/A_neural_network_for_prediction_of_risk_of_nosocomial_infection_at_intensive_care_units_a_didactic_preliminary_model/14322394）。