Healthcare Informatics Research最新文献

Objectives: This study compared feature selection by machine learning or expert recommendation in the performance of classification models for in-hospital mortality among patients with acute coronary syndrome (ACS) who underwent percutaneous coronary intervention (PCI).

Methods: A dataset of 1,123 patients with ACS who underwent PCI was analyzed. After assigning 80% of instances to the training set through random splitting, we performed feature scaling and resampling with the synthetic minority over-sampling technique and Tomek link method. We compared two feature selection.

Methods: recursive feature elimination with cross-validation (RFECV) and selection by interventional cardiologists. We used five simple models: support vector machine (SVM), random forest, decision tree, logistic regression, and artificial neural network. The performance metrics were accuracy, recall, and the false-negative rate, measured with 10-fold cross-validation in the training set and validated in the test set.

Results: Patients' mean age was 66.22 ± 12.88 years, and 33.63% had ST-elevation ACS. Fifteen of 34 features were selected as important with the RFECV method, while the experts chose 11 features. All models with feature selection by RFECV had higher accuracy than the models with expert-chosen features. In the training set, the random forest model had the highest accuracy (0.96 ± 0.01) and recall (0.97 ± 0.02). After validation in the test set, the SVM model displayed the highest accuracy (0.81) and a recall of 0.61.

Conclusions: Models with feature selection by RFECV had higher accuracy than those with feature selection by experts in identifying patients with ACS at high risk for in-hospital mortality.

Objectives: The purpose of this study was to identify any difference in user experience between tablet- and augmented reality (AR) glasses-based tele-exercise programs in elderly women.

Methods: Participants in the AR group (n = 14) connected Nreal glasses with smartphones to display a pre-recorded exercise program, while each member of the tablet group (n = 13) participated in the same exercise program using an all-in-one personal computer. The program included sitting or standing on a chair, bare-handed calisthenics, and muscle strengthening using an elastic band. The exercise movements were presented first for the upper and then the lower extremities, and the total exercise time was 40 minutes (5 minutes of warm-up exercises, 30 minutes of main exercises, and 5 minutes of cool-down exercises). To evaluate the user experience, a questionnaire consisting of a 7-point Likert scale was used as a measurement tool. In addition, the Wilcoxon rank-sum test was used to assess differences between the two groups.

Results: Of the six user experience scales, attractiveness (p = 0.114), stimulation (p = 0.534), and novelty (p = 0.916) did not differ significantly between the groups. However, efficiency (p = 0.006), perspicuity (p = 0.008), and dependability (p = 0.049) did vary significantly between groups.

Conclusions: When developing an AR glasses-based exercise program for the elderly, the efficiency, clarity, and stability of the program must be considered to meet the participants' needs.

Objectives: Electrocardiography (ECG)-based diagnosis by experts cannot maintain uniform quality because individual differences may occur. Previous public databases can be used for clinical studies, but there is no common standard that would allow databases to be combined. For this reason, it is difficult to conduct research that derives results by combining databases. Recent commercial ECG machines offer diagnoses similar to those of a physician. Therefore, the purpose of this study was to construct a standardized ECG database using computerized diagnoses.

Methods: The constructed database was standardized using Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT) and Observational Medical Outcomes Partnership-common data model (OMOP-CDM), and data were then categorized into 10 groups based on the Minnesota classification. In addition, to extract high-quality waveforms, poor-quality ECGs were removed, and database bias was minimized by extracting at least 2,000 cases for each group. To check database quality, the difference in baseline displacement according to whether poor ECGs were removed was analyzed, and the usefulness of the database was verified with seven classification models using waveforms.

Results: The standardized KURIAS-ECG database consists of high-quality ECGs from 13,862 patients, with about 20,000 data points, making it possible to obtain more than 2,000 for each Minnesota classification. An artificial intelligence classification model using the data extracted through SNOMED-CT showed an average accuracy of 88.03%.

Conclusions: The KURIAS-ECG database contains standardized ECG data extracted from various machines. The proposed protocol should promote cardiovascular disease research using big data and artificial intelligence.

Objectives: The optic disc is part of the retinal fundus image structure, which influences the extraction of glaucoma features. This study proposes a method that automatically segments the optic disc area in retinal fundus images using deep learning based on a convolutional neural network (CNN).

Methods: This study used private and public datasets containing retinal fundus images. The private dataset consisted of 350 images, while the public dataset was the Retinal Fundus Glaucoma Challenge (REFUGE). The proposed method was based on a CNN with a single-shot multibox detector (MobileNetV2) to form images of the region-of-interest (ROI) using the original image resized into 640 × 640 input data. A pre-processing sequence was then implemented, including augmentation, resizing, and normalization. Furthermore, a U-Net model was applied for optic disc segmentation with 128 × 128 input data.

Results: The proposed method was appropriately applied to the datasets used, as shown by the values of the F1-score, dice score, and intersection over union of 0.9880, 0.9852, and 0.9763 for the private dataset, respectively, and 0.9854, 0.9838 and 0.9712 for the REFUGE dataset.

Conclusions: The optic disc area produced by the proposed method was similar to that identified by an ophthalmologist. Therefore, this method can be considered for implementing automatic segmentation of the optic disc area.

Objectives: This study assessed the current state of pharmacy management information systems in Indonesia and systematically determined the improvements needed from the stakeholders' perspective.

Methods: This descriptive study used focus group discussions and observations in 13 institutions, and 17 respondents were selected by purposive sampling. The PIECES (performance, information, economy, control, efficiency, service) framework was used to help identify needs. The research was conducted from September 2021 to November 2021 at primary health centers and health offices in Yogyakarta, Indonesia and involved pharmacists and information systems staff.

Esults: There was no standardized information system in place to support drug management and no format or rules for drug labeling (performance). Pharmacists were not able to provide non-prescription services outside the pharmacy warehouse (information). A new system needs to be developed, and budget availability needs to be determined (economy). System security decreases when users share accounts (control), and the existing systems have not been integrated as needed (efficiency). It is first necessary to plan and support regulations for system development (service). The authors formulated a recommended drug labeling format and a proposed system integration plan.

Conclusions: The development of an information system to support drug management is eagerly awaited by pharmacists in Indonesia to assist in their work. Further research on the development and implementation of an information system is needed to improve the quality of drug management at primary health centers.

Objectives: The rate of coronavirus disease 2019 (COVID-19) booster vaccination in Indonesia remains relatively low, representing 15.33% of the overall vaccination target as of April 2022. The implementation of a reminder and recall system has been shown to be effective in increasing vaccination rates. In prior research, reminders and recalls were sent through traditional media, such as mail, and had not yet been integrated into modern media, such as smartphone applications and (in particular) contact tracing applications. Therefore, the present study was conducted to design a reminder and recall system for the PeduliLindungi contact tracing application.

Methods: We used the design science research (DSR) methodology with three iterations. The first iteration produced a low-fidelity prototype (or wireframe), and the next yielded a high-fidelity (clickable) prototype.

Results: The final prototype included three main features: a reminder and recall mechanism, online registration for COVID-19 booster vaccination, and educational articles. The evaluation consisted of interviews in the first iteration, interviews and the System Usability Scale (SUS) questionnaire in the second, and the Post-Study System Usability Questionnaire (PSSUQ) in the third. The SUS value obtained in the second iteration was 71.6, indicating good (acceptable) results, while in the third iteration, the system usefulness, information quality, interface quality, and overall PSSUQ values were 2.456, 2.473, 2.230, and 2.397, respectively, indicating good quality of the resulting design.

Conclusions: This research contributes to two areas: implementation of a reminder and recall system in the PeduliLindungi contact tracing application and enhancement of contact tracing applications using DSR methodology.

Objectives: Healthcare-related information sharing via social media is on the rise following the coronavirus disease 2019 (COVID-19) pandemic. Dental practices primarily use social media to search, share, and communicate health-related information. Considering the increasing trend of using social media, the primary aim of the present study was to identify the use of social media by dentists and laypeople to post and view dentistry-related content in Bahrain.

Methods: This questionnaire-based cross-sectional study included adult participants and dentists. A pretested validated questionnaire was administered. The chi-square test for association was used to assess the association between categorical outcomes. A p-value of ≤ 0.05 was considered statistically significant.

Results: In total, 249 adult participants and 53 dentists were included. A substantial majority (83.5%) of the participants reported that they always used social media to view dentistry-related content, and 69.8% of the dentists felt that patients who use social media have better oral health awareness. A longer duration of social media usage showed significant associations with particularly viewing dentistry-related content (p = 0.008) and contacting dentists directly through social media for consultation (p = 0.055).

Conclusions: An extremely high percentage of the younger population in Bahrain is using various social media to discuss dentistry. This engagement should be wisely managed to promote dentistry-related information sharing, which can lead to increased awareness related to overall dental health. There is a definite need to enforce certain standard operating procedures in every country that will prevent the misuse of this technological advancement.

Objectives: Orthognathic surgery is used to treat moderate to severe occlusal discrepancies. Examinations and measurements for preoperative screening are essential procedures. A careful analysis is needed to decide whether cases require orthognathic surgery. This study developed screening software using a multi-layer perceptron to determine whether orthognathic surgery is required.

Methods: In total, 538 digital lateral cephalometric radiographs were retrospectively collected from a hospital data system. The input data consisted of seven cephalometric variables. All cephalograms were analyzed by the Detectron2 detection and segmentation algorithms. A keypoint region-based convolutional neural network (R-CNN) was used for object detection, and an artificial neural network (ANN) was used for classification. This novel neural network decision support system was created and validated using Keras software. The output data are shown as a number from 0 to 1, with cases requiring orthognathic surgery being indicated by a number approaching 1.

Results: The screening software demonstrated a diagnostic agreement of 96.3% with specialists regarding the requirement for orthognathic surgery. A confusion matrix showed that only 2 out of 54 cases were misdiagnosed (accuracy = 0.963, sensitivity = 1, precision = 0.93, F-value = 0.963, area under the curve = 0.96).

Conclusions: Orthognathic surgery screening with a keypoint R-CNN for object detection and an ANN for classification showed 96.3% diagnostic agreement in this study.