Optimizing prognostic factors of five-year survival in gastric cancer patients using feature selection techniques with machine learning algorithms: a comparative study.

BACKGROUND: Gastric cancer is the most common malignant tumor worldwide and a leading cause of cancer deaths. This neoplasm has a poor prognosis and heterogeneous outcomes. Survivability prediction may help select the best treatment plan based on an individual's prognosis. Numerous clinical and pathological features are generally used in predicting gastric cancer survival, and their influence on the survival of this cancer has not been fully elucidated. Moreover, the five-year survivability prognosis performances of feature selection methods with machine learning (ML) classifiers for gastric cancer have not been fully benchmarked. Therefore, we adopted several well-known feature selection methods and ML classifiers together to determine the best-paired feature selection-classifier for this purpose. METHODS: This was a retrospective study on a dataset of 974 patients diagnosed with gastric cancer in the Ayatollah Talleghani Hospital, Abadan, Iran. First, four feature selection algorithms, including Relief, Boruta, least absolute shrinkage and selection operator (LASSO), and minimum redundancy maximum relevance (mRMR) were used to select a set of relevant features that are very informative for five-year survival prediction in gastric cancer patients. Then, each feature set was fed to three classifiers: XG Boost (XGB), hist gradient boosting (HGB), and support vector machine (SVM) to develop predictive models. Finally, paired feature selection-classifier methods were evaluated to select the best-paired method using the area under the curve (AUC), accuracy, sensitivity, specificity, and f1-score metrics. RESULTS: The LASSO feature selection algorithm combined with the XG Boost classifier achieved an accuracy of 89.10%, a specificity of 87.15%, a sensitivity of 89.42%, an AUC of 89.37%, and an f1-score of 90.8%. Tumor stage, history of other cancers, lymphatic invasion, tumor site, type of treatment, body weight, histological type, and addiction were identified as the most significant factors affecting gastric cancer survival. CONCLUSIONS: This study proved the worth of the paired feature selection-classifier to identify the best path that could augment the five-year survival prediction in gastric cancer patients. Our results were better than those of previous studies, both in terms of the time required to form the models and the performance measurement criteria of the algorithms. These findings may be very promising and can, therefore, inform clinical decision-making and shed light on future studies.

Telemedicine technologies and applications in the era of COVID-19 pandemic: A systematic review.

INTRODUCTION: Telemedicine services saw substantial surges in their use during the COVID-19 pandemic due to the lockdowns and characteristics of the pandemic. Therefore, the authors aimed to systematically review the telemedicine services provided during the COVID-19 pandemic and their potential applications. METHODS: The authors searched PubMed, Scopus, and Cochrane databases on September 14, 2021. Then, the retrieved records underwent two-step title/abstract and full-text screening processes, and the eligible articles were included for qualitative synthesis. RESULTS: The review of studies demonstrated that the telephone is listed 38 times, making it the most common technology used in telemedicine. Video conferencing is also mentioned in 29 articles, as well as other technologies: Mobile-health (n = 15), Virtual reality (n = 7). According to the findings of the present study, Tele-follow-up (n = 24), Tele-consulting (n = 20), Virtual visits (20), and Tele-monitoring (n = 18) were the most widely used telemedicine applications. CONCLUSION: Telemedicine has been an effective approach to COVID-19 management. Telemedicine technology is going to play a key role in the future of health medicine, patient consultation, and many other extended applications of health care in remote rural locations.

Data quality assessment in emergency medical services: an objective approach.

BACKGROUND: In emergency medical services, high quality data are of great importance for patient care. Due to the unique nature of this type of services, the purpose of this study was to assess data quality in emergency medical services using an objective approach. METHODS: This was a retrospective quantitative study conducted in 2019. The research sample included the emergency medical records of patients who referred to three emergency departments by the pre-hospital emergency care services (n = 384). Initially a checklist was designed based on the data elements of the triage form, pre-hospital emergency care form, and emergency medical records. Then, data completeness, accuracy and timeliness were assessed. RESULTS: Data completeness in the triage form, pre-hospital emergency care form, and emergency medical records was 52.3%, 70% and 57.3%, respectively. Regarding data accuracy, most of the data elements were consistent. Measuring data timeliness showed that in some cases, paper-based ordering and computer-based data entry was not sequential. CONCLUSION: Data quality in emergency medical services was not satisfactory and there were some weaknesses in the documentation processes. The results of this study can inform the clinical and administrative staff to pay more attentions to these weaknesses and plan for data quality improvement.

Data Quality in Health Care: Main Concepts and Assessment Methodologies.

INTRODUCTION: In the health care environment, a huge volume of data is produced on a daily basis. However, the processes of collecting, storing, sharing, analyzing, and reporting health data usually face with numerous challenges that lead to producing incomplete, inaccurate, and untimely data. As a result, data quality issues have received more attention than before. OBJECTIVE: The purpose of this article is to provide an insight into the data quality definitions, dimensions, and assessment methodologies. METHODS: In this article, a scoping literature review approach was used to describe and summarize the main concepts related to data quality and data quality assessment methodologies. Search terms were selected to find the relevant articles published between January 1, 2012 and September 31, 2022. The retrieved articles were then reviewed and the results were reported narratively. RESULTS: In total, 23 papers were included in the study. According to the results, data quality dimensions were various and different methodologies were used to assess them. Most studies used quantitative methods to measure data quality dimensions either in paper-based or computer-based medical records. Only two studies investigated respondents' opinions about data quality. CONCLUSION: In health care, high-quality data not only are important for patient care, but also are vital for improving quality of health care services and better decision making. Therefore, using technical and nontechnical solutions as well as constant assessment and supervision is suggested to improve data quality.

Data Quality Assessment in Emergency Medical Services: What Are the Stakeholders' Perspectives?

Introduction: Emergency care is usually conducted within limited time and with limited resources. During emergency care processes, data quality issues should be taken into account. The aim of this study was to assess the quality of emergency care data from the perspectives of different data stakeholders. Method: This survey study was conducted in 2017. In this research, the viewpoints of three groups of data stakeholders, including data producers, data collectors, and data consumers, were collected regarding data quality in emergency care services. Data were collected by using a standard information quality assessment questionnaire. Results: The mean values for each dimension of data quality were as follows: sound data (6.23), dependable data (6.28), useful data (6.30), and usable data (6.35), with 0 being the lowest possible score and 10 being the highest. The role gap analysis suggested a clear gap between data producers and data customers at the university level. Conclusion: Overall, data quality in emergency medical services was not at a high level. Although data quality was improving, the levels of data completeness, compatibility, and usability were low. To improve the usability of emergency medical service data, more attention should be paid to the dimensions of accuracy, completeness, and consistency of data sources.

A Review of Data Quality Assessment in Emergency Medical Services.

INTRODUCTION: Data quality is an important issue in emergency medicine. The unique characteristics of emergency care services, such as high turn-over and the speed of work may increase the possibility of making errors in the related settings. Therefore, regular data quality assessment is necessary to avoid the consequences of low quality data. This study aimed to identify the main dimensions of data quality which had been assessed, the assessment approaches, and generally, the status of data quality in the emergency medical services. METHODS: The review was conducted in 2016. Related articles were identified by searching databases, including Scopus, Science Direct, PubMed and Web of Science. All of the review and research papers related to data quality assessment in the emergency care services and published between 2000 and 2015 (n=34) were included in the study. RESULTS: The findings showed that the five dimensions of data quality; namely, data completeness, accuracy, consistency, accessibility, and timeliness had been investigated in the field of emergency medical services. Regarding the assessment methods, quantitative research methods were used more than the qualitative or the mixed methods. Overall, the results of these studies showed that data completeness and data accuracy requires more attention to be improved. CONCLUSION: In the future studies, choosing a clear and a consistent definition of data quality is required. Moreover, the use of qualitative research methods or the mixed methods is suggested, as data users' perspectives can provide a broader picture of the reasons for poor quality data.

Household related predictors of burn injuries in an Iranian population: a case-control study.

BACKGROUND: To prevent burn injuries it is vital to have sound information on predictors of its occurrence in different settings. Ardabil Province is the coldest province of Iran with high burden of burn injuries. The aim of this study was to determine the household related predictors of unintentional burns in Ardabil Province located at North-West of Iran. METHODS: The study was conducted through a hospital based case-control design. 239 burn victims as well as 246 hospital-based controls were enrolled. Both bivariate and multivariate analysis methods were used. RESULTS: Males comprised 55.2% of all the study subjects. Mean age of the participants was 21.8 years (95% CI: 19.17-24.4). The economic ability of the households was associated with risk of burn injuries. Multivariate conditional logistic regression results showed the following variables to be independent factors associated with burn injuries. Using non-conventional pipe-less air heaters instead of conventional piped kerosene- or gas-burning heaters (Odds ratio: 1.98, 95% CI: 1.1-3.6). Common use of picnic gas-stove for cooking at home (odds ratio = 1.6, 95%CI: 1-2.4). Using electric samovars instead of other types of samovars (Odds ratio = 0.3, 95% CI: 0.1-1). Using samovars lacking the national standard authorization mark (Odds ratio = 2.2, 95% CI: 1.4-3.6). CONCLUSION: Using some types of specific heating or cooking appliances, and unsafe use of conventional appliances were major risk predictors of burn injuries in this population.

Epidemiology of minor and moderate burns in rural Ardabil, Iran.

Epidemiology of minor burns is not well defined worldwide. The aim of this study was to examine epidemiological features of minor and moderate burn events that could be beneficial for prevention purposes. The study was conducted in Ardabil province in north-west Iran in 2005-2006. A total of 1700 minor and moderate burns were studied using a pretested questionnaire. Using the SAS 9.1 statistical program analyses were made. Females comprised the majority of cases (n=1000, 58.8%) and children, aged six and younger, made up 36.4% of burn victims. The majority of burns were caused by hot water and tea with the primary containers being kettles in 37.8%, cups or glasses in 24.2%, pots in 13.6% and samovars in 7.9%. Samovars, gas stoves, valors and picnic gas stoves were the primary heating devices involved in burns. In 56% of the cases, overturning of liquid containers was the primary injury mechanism of scalds. 43% had a second-degree burn with a mean total body surface area of 1.3%. This study provides possible beneficial information for burn prevention in the Ardabil area and other similar settings.