No abstract

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.

The prevalence of gestational diabetes mellitus (GDM) is increasing in Iran. Collection of patients’ data is commonly conducted through using medical records. However, for providing a structured reporting based on the information needs, a minimum data set is a fast, inexpensive, and suitable method. For exchanging high-quality data between different healthcare centers and health monitoring organization, the data are required to be uniformly collected and registered. The present study aims at designing an MDS for creating the registry of GDM. The present study is an applied one, conducted in two stages, with a qualitative Delphi method in 2018. In the first stage of the study, it was attempted to extract the data elements of mothers with GDM, through reviewing the related studies and collecting these patients’ data from the medical records. Then, based on the results of the first stage, a questionnaire including demographic, clinical, and pharmaceutical data was distributed among 20 individuals including gynecologists, pharmacists, nurses, and midwives. The validity of the questionnaire was examined by a team of experts and its reliability was examined by using Cronbach’s alpha. Data analysis was conducted using descriptive statistics (frequency, percentage, and mean) and excel. An MDS of gestational diabetes mellitus was developed. This MDS divided into three categories: administrative, clinical, and pharmaceutical with 4, 18, and 2 sections and 35, 199, and 12 data elements, respectively. Determining the minimum data sets of GDM will be an effective step toward integrating and improving data management of patients with GDM. Moreover, it will be possible to store and retrieve the data related to these patients.

INTRODUCTION: Providing information exchange and collaboration between isolated information systems (ISs) is essential in the health-care environments. In this context, we aimed to develop a communication protocol to facilitate better interoperability among electrophysiology study (EPS)-related ISs in order to allow exchange unified reporting in EPS ablation. MATERIALS AND METHODS: This study was an applied-descriptive research that was conducted in 2019. To determine the information content of agreed cardiac EPS Minimum Data Set (MDS) in Iran, the medical record of patients undergoing EPS ablation procedure in the Tehran Heart Center (THC) hospital was reviewed by a checklist. Then, an information model based on Health Level Seven, Clinical Document Architecture (HL7 CDA) standard framework for structural interoperability has been developed. In this framework, using NPEX online browser and MindMaple software, a set of terminology mapping rules was used for consistent transfer of data between various ISs. RESULTS: The information content of each data field was introduced into the heading and body sections of HL7 CDA document using Systematized Nomenclature of Medicine – Clinical Terminology names and codes. Then, the ontology alignment was designed in the form of thesaurus mapping routes. CONCLUSION: The sensitive, complex, and multidimensional nature of cardiovascular conditions requires special attention to the interoperability of ISs. Designing customized communication protocols plays an important role in improving the interoperability, and they are compatible with the needs of future Iranian health information exchange.

No abstract