Computer methods and programs in biomedicine update最新文献

Background and Objective

The collection of patient-generated health data (PGHD) is important for understanding a patient's daily status for efficient treatment. Mobile applications are effective for continuously collecting patient data, and it is desirable to promptly integrate such data into electronic medical records. However, most hospital information systems have limited connections with external mobile applications. Therefore, in this study, we developed a simple system that can collect data from patients with inflammatory bowel disease (IBD) and transfer the data to electronic medical records without a direct connection to a hospital information system.

Methods

We developed patient-facing mobile applications and physician-facing user-defined form templates for the hospital information system. The PGHD were transferred via QR codes using a two-way linkage. The persistence rates were measured and analyzed to clarify the factors affecting the continuous usage of the application.

Results

A mobile application connected to a hospital information system was implemented and used in on-site operations. Among patients with IBD using this application, 84.6%–91.7% continued to use it over six months and 72.2%–84.5% continued for over one year. Particularly, patients who used the application during the first two visits tended to be significantly frequent users.

Conclusions

We developed a mobile application connected to a hospital information system using a QR code, which is a simple way to continuously collect data from patients and enables physicians to use the data efficiently for patient-centered medical care.

In recent decades, both economic development and technological advances in medicine have contributed to an increase in health demand and costs, mainly derived from the growing implementation of innovative health services. In this context, it is necessary to note that welfare economics involves the rationalization of limited economic resources. Likewise, the concern about the increase in health spending that is occurring in developed countries has meant that hospitals have flexible management accounting that helps to maximize the efficiency of internal management and obtain the maximum performance of the allocated financial resources. This will have a favourable impact on indicators such as minimal infant mortality, increased life expectancy at birth, or the rate and effectiveness of transplants. Hence, organizations choose to improve their management systems to carry out a more efficient health care education, in such a way that these try to optimize the available resources to offer a quality product or service with the minimum possible costs. Bibliometric techniques have been applied to a sample of 2003 articles to establish the relationships between the main dynamic agents of this research topic, in addition to identifying the main current and future lines of research. Providing a benchmark for future research on management control for health care education, this study reveals the emerging intellectual structure of this interdisciplinary field.

Disturbances in balance control lead to movement impairment and severe discomfort, dizziness, vertigo and may also lead to serious accidents. It is important to monitor the level of balance in order to determine the risk of a fall and to evaluate progress during treatment. Some solutions exist, but they are generally restricted to indoor environments. We propose and evaluate a system, based on accelerometers and support vector machines, that indicates the user’s postural balance variation which can be used in indoor and outdoor environments. For the training phase of the system, we used the accelerometer signals acquired from a single subject under monitored conditions of balance and intentional imbalance, and used the scores provided by the SWAY®software for establishing the reference target values. Based on these targets, we trained a support vector machine to classify the signal into $n$ levels of balance and later evaluated the performance using cross validation by random resampling. We also developed a support vector machine approach for estimating the center of pressure, by using as reference targets the results from a force platform. For validation, we performed experiments with a subject who was performing determined movements. Later other experiments were executed, so the different centers of pressure could be computed by our system and compared to the results from the force platform. We also performed tests with a dummy and a John Doe doll, in order to observe the system’s behavior in the presence of a sudden drop or a lack of balance. The results show that the system can classify the acquired signals into two to seven levels of balance, with significant accuracy, and was also able to infer the centroid of each center of pressure region with an error lower than 0.9 cm. The tests performed with the dolls show that the system is able to distinguish between the conditions of a sudden drop and of a recovery of balance after losing one’s balance. The results suggest that the system can be used to detect variations in balance and, therefore, to indicate the risk of a fall even in outdoor environments.

Background and Objective

Fast and correct classification of bacterial samples are important for accurate diagnostics and treatment. Manual microscopic interpretation of Gram stain samples is both time consuming and operator dependent. The aim of this study was to investigate the potential for developing an automated algorithm for the classification of microscopic Gram stain images.

Methods

We developed and tested two algorithms (using image processing an Casual Probabilistic Network (CPN) and a Random Forest (RF) classification) for the automated classification of Gram stain images. A dataset of 660 images including 33 microbial species (32 bacteria and one fungus) was split into training, validation, and test sets. The algorithms were evaluated based on their ability to correctly classify samples and general characteristics such as aggregation and morphology.

Results

The CPN correctly classified 633/792 images to achieve an overall accuracy of 80% compared to the RF which correctly classified 782/792 images to achieve an overall accuracy of 99% (p < 0.001). The CPN performed well when distinguishing between GN and GP, with an accuracy of 95% (731/768). The RF also performed well in distinguishing between GN and GP, achieving an accuracy of 99% (767/768) (p < 0.001).

Conclusions

The findings from this study show promising results regarding the potential for an automated algorithm for the classification of microscopic Gram stain images.

In recent years, COVID-19 has impacted millions of individuals worldwide, resulting in numerous fatalities across several countries. While RT-PCR technology remains the most reliable method for detecting COVID-19, this approach is expensive and time-consuming. As a result, researchers have explored various machine learning and deep learning-based approaches to rapidly identify COVID-19 cases using X-ray images. Machine learning based models can reduce costs and have shorter processing times. However, preserving patient confidentiality poses challenges within such third-party-controlled systems, potentially failing to safeguard patients from potential disgrace and discomfort. Nonetheless, blockchain technology offers the potential to securely store sensitive medical data anonymously, without requiring third-party intervention. Consequently, the combination of deep learning and blockchain might offer a viable solution to mitigate the spread of COVID-19 while ensuring patient privacy protection. In this paper, we propose a hybrid model of blockchain and deep learning model for automatically detecting COVID-19 using chest X-rays (CXR). The deep learning model includes a stacking ensemble of three modified pre-trained Deep Learning (DL) models: VGG16, Xception, and DenseNet169. The model obtained an accuracy of 99.10% and 98.60% for binary and multi-class respectively. Further, to ensure COVID-19 patients’ privacy and security, the Ethereum blockchain has been adopted to store information related to COVID-19 cases. In addition, a smart contract on the blockchain has been designed for handling X-ray images in the Interplanetary File System (IPFS).

Purpose

The contents of nursing notes play an important role in predicting patient fall risk. Based on data collected from fall risk assessment tools, we aimed to identify and define fall risk factors to support natural language processing, data mining of nursing notes, and automated fall prediction.

Methods

The PRISMA-ScR guidelines were used to summarize entities associated with the fall risk factors described in fall risk assessment tools. Fall risk factors (concepts) and their related words (entities) were extracted from the tools. In order to clarify the meaning of unclear fall risk factors and classify fall risk factor entities, we searched the websites of the World Health Organization and the governments of Victoria, Australia, and New South Wales (up to 20 December 2021). A nurse and a safety expert reviewed and assessed the extracted concepts and entities for clarity and relevance. Then, the NLPfallRisk tool was developed to extract entities associated with fall risk factors.

Results

We identified 20 validated fall risk assessment tools appropriate for hospitals and healthcare facilities. Using these tools, we extracted 19 especially significant risk factors as the most significant and identified 151 entities related to them.

Conclusion

We found that fall assessment tools considered a history of falls more frequently than any other risk factor. However, as fall risk tends to be multifaceted, risk assessments must take many factors into account.

Background and Objective

Hypertension is critical risk factor of fatal cardiovascular diseases and multiple organ damage. Early detection of hypertension even at pre-hypertension stage is helpful in preventing the forthcoming complications. Electrocardiogram (ECG) has been attempted to observe the changes in electrical activities of the hearts of hypertensive patients. To automate the ECG assessment in the detection of hypertension, an interpretable hybrid model is proposed in this paper.

Methods

The proposed hybrid framework consists of one dimensional - Convolutional Neural Network architecture with four blocks of convolutional layers, maxpooling followed by dropout layers fused with Support Vector Machine classifier in the final layer. The implemented hybrid model is made explainable and interpretable using Local Interpretable Model-agnostic Explanations (LIME) method. The developed hybrid model is trained and tested for patient-wise classification of ECGs using online Physionet datasets and hospital data.

Results

The proposed method achieved highest accuracy of 81.81% in patient-wise ECG classification of online datasets, and highest accuracy of 93.33% in patient-wise ECG classification of hospital datasets as normotensive and hypertensive. The visualization of results showed only one normotensive patient's ECG is misclassified (predicted) as hypertensive, with identification of patient number, among the 15 patients (8 normotensive and 7 hypertensive) ECGs tested. In addition, the LIME results demonstrated an explanation to the predictions of hybrid model by highlighting the features and location of ECG waveform responsible for it, thus making the decision of hybrid model more interpretable.

Conclusion

Furthermore, our developed system is implemented as an assisting automated software tool called, HANDI (Hypertensive And Normotensive patient Detection with Interpretability) for real-time validation in clinics for early capture of hypertensive and proper monitoring of the patients.

Background:

In December 2020, the COVID-19 disease was confirmed in 1,665,775 patients and caused 45,784 deaths in Spain. At that time, health decision support systems were identified as crucial against the pandemic.

Methods:

This study applies Deep Learning techniques for mortality prediction of COVID-19 patients. Two datasets with clinical information were used. They included 2,307 and 3,870 COVID-19 infected patients admitted to two Spanish hospitals. Firstly, we built a sequence of temporal events gathering all the clinical information for each patient, comparing different data representation methods. Next, we used the sequences to train a Recurrent Neural Network (RNN) model with an attention mechanism exploring interpretability. We conducted an extensive hyperparameter search and cross-validation. Finally, we ensembled the resulting RNNs to enhance sensitivity.

Results:

We assessed the performance of our models by averaging the performance across all the days in the sequences. Additionally, we evaluated day-by-day predictions starting from both the hospital admission day and the outcome day. We compared our models with two strong baselines, Support Vector Classifier and Random Forest, and in all cases our models were superior. Furthermore, we implemented an ensemble model that substantially increased the system’s sensitivity while producing more stable predictions.

Conclusions:

We have shown the feasibility of our approach to predicting the clinical outcome of patients. The result is an RNN-based model that can support decision-making in healthcare systems aiming at interpretability. The system is robust enough to deal with real-world data and can overcome the problems derived from the sparsity and heterogeneity of data.