Applying artificial intelligence to predict falls for inpatient.

Objective: Falls are adverse events which commonly occur in hospitalized patients. Inpatient falls may cause bruises or contusions and even a fractures or head injuries, which can lead to significant physical and economic burdens for patients and their families. Therefore, it is important to predict the risks involved surrounding hospitalized patients falling in order to better provide medical personnel with effective fall prevention measures. Setting: This study retrospectively used EHR data taken from the Taichung Veterans General Hospital clinical database between January 2015 and December 2019. Participants: A total of 53,122 patient records were collected in this study, of which 1,157 involved fall patients and 51,965 were non-fall patients. Primary and secondary outcome measure: This study integrated the characteristics and clinical data of patients with falls and without falls using RapidMiner Studio as an analysis tool for various models of artificial intelligence. Utilization of 8 differ models to identify the most important factors surrounding inpatient fall risk. This study used the sensitivity, specificity, and area under the ROC curve to compute the data by 5-fold cross-validation and then compared them by pairwise t-tests. Results: The predictive classifier was developed based upon the gradient boosted trees (XGBoost) model which outperformed the other seven baseline models and achieved a cross-validated ACC of 95.11%, AUC of 0.990, F1 score of 95.1%. These results show that the XGBoost model was used when dealing with multisource patient data, which in this case delivered a highly predictive performance on the risk of inpatient falls. Conclusion: Machine learning methods identify the most important factors regarding the detection of inpatients who are at risk of falling, which in turn would improve the quality of patient care and reduce the workloads of the nursing staff when making fall assessments.

Developing a machine-learning model for real-time prediction of successful extubation in mechanically ventilated patients using time-series ventilator-derived parameters.

Background: Successful weaning from mechanical ventilation is important for patients admitted to intensive care units. However, models for predicting real-time weaning outcomes remain inadequate. Therefore, this study aimed to develop a machine-learning model for predicting successful extubation only using time-series ventilator-derived parameters with good accuracy. Methods: Patients with mechanical ventilation admitted to the Yuanlin Christian Hospital in Taiwan between August 2015 and November 2020 were retrospectively included. A dataset with ventilator-derived parameters was obtained before extubation. Recursive feature elimination was applied to select the most important features. Machine-learning models of logistic regression, random forest (RF), and support vector machine were adopted to predict extubation outcomes. In addition, the synthetic minority oversampling technique (SMOTE) was employed to address the data imbalance problem. The area under the receiver operating characteristic (AUC), F1 score, and accuracy, along with the 10-fold cross-validation, were used to evaluate prediction performance. Results: In this study, 233 patients were included, of whom 28 (12.0%) failed extubation. The six ventilatory variables per 180 s dataset had optimal feature importance. RF exhibited better performance than the others, with an AUC value of 0.976 (95% confidence interval [CI], 0.975-0.976), accuracy of 94.0% (95% CI, 93.8-94.3%), and an F1 score of 95.8% (95% CI, 95.7-96.0%). The difference in performance between the RF and the original and SMOTE datasets was small. Conclusion: The RF model demonstrated a good performance in predicting successful extubation in mechanically ventilated patients. This algorithm made a precise real-time extubation outcome prediction for patients at different time points.

Analysis of agricultural exports based on deep learning and text mining.

Agricultural exports are an important source of economic profit for many countries. Accurate predictions of a country's agricultural exports month on month are key to understanding a country's domestic use and export figures and facilitate advance planning of export, import, and domestic use figures and the resulting necessary adjustments of production and marketing. This study proposes a novel method for predicting the rise and fall of agricultural exports, called agricultural exports time series-long short-term memory (AETS-LSTM). The method applies Jieba word segmentation and Word2Vec to train word vectors and uses TF-IDF and word cloud to learn news-related keywords and finally obtain keyword vectors. This research explores whether the purchasing managers' index (PMI) of each industry can effectively use the AETS-LSTM model to predict the rise and fall of agricultural exports. Research results show that the inclusion of keyword vectors in the PMI values of the finance and insurance industries has a relative impact on the prediction of the rise and fall of agricultural exports, which can improve the prediction accuracy for the rise and fall of agricultural exports by 82.61%. The proposed method achieves improved prediction ability for the chemical/biological/medical, transportation equipment, wholesale, finance and insurance, food and textiles, basic materials, education/professional, science/technical, information/communications/broadcasting, transportation and storage, retail, and electrical and machinery equipment categories, while its performance for the electrical and optical categories shows improved prediction by combining keyword vectors, and its accuracy for the accommodation and food service, and construction and real estate industries remained unchanged. Therefore, the proposed method offers improved prediction capacity for agricultural exports month on month, allowing agribusiness operators and policy makers to evaluate and adjust domestic and foreign production and sales.