Emergency department-based injury surveillance information system: a conceptual model.

BACKGROUND: Injury data play a pivotal role in monitoring public health issues and Injury Surveillance Information Systems (ISIS) are useful for continuous data collection and analysis purposes. Since emergency department (ED) is usually the first place of referral for the injured people, the aim of this study was to develop a conceptual model for an ED-based ISIS. METHODS: This study was completed in 2020 and the Delphi technique (three rounds) was used to determine the main components of an ED-based ISIS. The participants were selected using the purposive sampling method. A 5-point Likert scale questionnaire was used for data collection and data were analyzed using descriptive statistics. RESULTS: In the first, second, and third rounds of the Delphi study, 60, 44, and 28 experts participated, respectively. In the first and second rounds, most of the items including the personal data, clinical data, data sources, and system functions were found important. In the third round of the Delphi study, 13 items which did not reach a consensus in the previous rounds were questioned again and five items were removed from the final model. CONCLUSION: According to the findings, various data elements and functions could be considered for designing an ED-based ISIS and a number of data sources should be taken into count to be integrated with this system. Although the conceptual model presented in the present study can facilitate designing the actual system, the final system needs to be implemented and used in practice to determine how it can meet users' requirements.

Comparing machine learning algorithms to predict 5-year survival in patients with chronic myeloid leukemia.

INTRODUCTION: Chronic myeloid leukemia (CML) is a myeloproliferative disorder resulting from the translocation of chromosomes 19 and 22. CML includes 15-20% of all cases of leukemia. Although bone marrow transplant and, more recently, tyrosine kinase inhibitors (TKIs) as a first-line treatment have significantly prolonged survival in CML patients, accurate prediction using available patient-level factors can be challenging. We intended to predict 5-year survival among CML patients via eight machine learning (ML) algorithms and compare their performance. METHODS: The data of 837 CML patients were retrospectively extracted and randomly split into training and test segments (70:30 ratio). The outcome variable was 5-year survival with potential values of alive or deceased. The dataset for the full features and important features selected by minimal redundancy maximal relevance (mRMR) feature selection were fed into eight ML techniques, including eXtreme gradient boosting (XGBoost), multilayer perceptron (MLP), pattern recognition network, k-nearest neighborhood (KNN), probabilistic neural network, support vector machine (SVM) (kernel = linear), SVM (kernel = RBF), and J-48. The scikit-learn library in Python was used to implement the models. Finally, the performance of the developed models was measured using some evaluation criteria with 95% confidence intervals (CI). RESULTS: Spleen palpable, age, and unexplained hemorrhage were identified as the top three effective features affecting CML 5-year survival. The performance of ML models using the selected-features was superior to that of the full-features dataset. Among the eight ML algorithms, SVM (kernel = RBF) had the best performance in tenfold cross-validation with an accuracy of 85.7%, specificity of 85%, sensitivity of 86%, F-measure of 87%, kappa statistic of 86.1%, and area under the curve (AUC) of 85% for the selected-features. Using the full-features dataset yielded an accuracy of 69.7%, specificity of 69.1%, sensitivity of 71.3%, F-measure of 72%, kappa statistic of 75.2%, and AUC of 70.1%. CONCLUSIONS: Accurate prediction of the survival likelihood of CML patients can inform caregivers to promote patient prognostication and choose the best possible treatment path. While external validation is required, our developed models will offer customized treatment and may guide the prescription of personalized medicine for CML patients.

Injury surveillance information system: A review of the system requirements.

PURPOSE: An injury surveillance information system (ISIS) collects, analyzes, and distributes data on injuries to promote health care delivery. The present study aimed to review the data elements and functional requirements of this system. METHOD: This study was conducted in 2019. Studies related to injury surveillance system were searched from January 2000 to September 2019 via the databases of PubMed, Web of Knowledge, ScienceDirect, and Scopus. Articles related to the epidemiology of injury, population survey, and letters to the editor were excluded, while the review and research articles related to ISISs were included in the study. Initially 324 articles were identified, and finally 22 studies were selected for review. Having reviewed the articles, the data needed were extracted and the results were synthesized narratively. RESULTS: The results showed that most of the systems reviewed in this study used the minimum data set suggested by the World Health Organization injury surveillance guidelines along with supplementary data. The main functions considered for the system were injury track, data analysis, report, data linkage, electronic monitoring and data dissemination. CONCLUSION: ISISs can help to improve healthcare planning and injury prevention. Since different countries have various technical and organizational infrastructures, it is essential to identify system requirements in different settings.

Iranian healthcare professionals' perspectives about factors influencing the use of telemedicine in diabetes management.

AIM: To identify factors influencing the use of telemedicine in diabetes management from the perspectives of healthcare professionals. METHODS: This was a quantitative study that was conducted in 2016. The participants were 240 nurses and 55 physicians from three teaching hospitals as well as from one endocrinology and metabolism research center. No sampling method was used and the data were collected by using a five-point (1 to 5) Likert scale questionnaire, which had 37 questions. Descriptive and inferential statistics (Mann-Whitney U test) were used to analyze the data. RESULTS: The findings showed that both physicians (4.06 ± 0.69) and nurses (4.02 ± 0.61) tended to use telemedicine technology for managing diabetes. Overall, the lowest mean value for physicians (3.79 ± 0.82) was related to the compatibility of telemedicine with other clinical activities in diabetes management. For nurses, the lowest mean value pertained to the usefulness of telemedicine in diabetes management (3.99 ± 0.53) and their attitude toward using this technology (3.99 ±0.65). CONCLUSION: Although physicians and nurses agreed on using telemedicine technology in diabetes management, it is necessary to consider their concerns prior to the implementation and deployment of new technologies. This approach will help to improve the level of technology acceptance among the users.

Electronic health records: what are the most important barriers?

INTRODUCTION: The process of design and adoption of electronic health records may face a number of barriers. This study aimed to compare the importance of the main barriers from the experts' point of views in Iran. METHODS: This survey study was completed in 2011. The potential participants (62 experts) included faculty members who worked in departments of health information technology and individuals who worked in the Ministry of Health in Iran and were in charge of the development and adoption of electronic health records. No sampling method was used in this study. Data were collected using a Likert-scale questionnaire ranging from 1 to 5. The validity of the questionnaire was established using content and face validity methods, and the reliability was calculated using Cronbach's alpha coefficient. RESULTS: The response rate was 51.6 percent. The participants' perspectives showed that the most important barriers in the process of design and adoption of electronic health records were technical barriers (mean = 3.84). Financial and ethical-legal barriers, with the mean value of 3.80 were other important barriers, and individual and organizational barriers, with the mean values of 3.59 and 3.50 were found to be less important than other barriers from the experts' perspectives. CONCLUSION: Strategic planning for the creation and adoption of electronic health records in the country, creating a team of experts to assess the potential barriers and develop strategies to eliminate them, and allocating financial resources can help to overcome most important barriers to the adoption of electronic health records.