Search

Background: Early outcome prediction of hospitalized patients is critical because the intensivists are constantly striving to improve patientschr('39') survival by taking effective medical decisions about ill patients in Intensive Care Units (ICUs). Despite rapid progress in medical treatments and intensive care technology, the analysis of outcomes, including mortality prediction, has been a challenge in ICUs. Hence, this study aims to predict the mortality of patients admitted to ICUs using data mining techniques. Methods: In this study, among the cases of patients who were admitted to ICUs of the Rasoul Akram and Firoozgar hospitals of Tehran City, Iran, from December 2017 to March 2018, the first 24 hours of the ICUs admission data of 874 cases were gathered. A new model based on the standard methodology CRISP was developed. In the modeling section, two well-known data mining techniques called artificial neural network (ANN), K nearest neighbor (KNN) and decision tree (DT) were used. WEKA 3.9.2 open-source software was implemented for data analysis. Finally, according to the accuracy, sensitivity, specificity criteria and AUC-ROC Curve, the superior model was introduced. Results: Based on the WEKA results, 19 variables had the most impact on the mortality prediction of patients admitted to ICUs including Glasgow Coma Scale (GCS), mechanical ventilation, surgical service at ICUs admission, gender, temperature, serum creatinine, diabetes, Blood urea nitrogen (BUN), age, addiction, International Normalized Ratio (INR), PH, Partial Thromboplastin Time (PTT), albumin, hemoglobin, glucose, pulse rate, hematocrit (HCT), PO2. Based on the created models, some rules have been extracted which can be used as a pattern to predict the probability of mortality. Although the AUC of the three models was acceptable (KNN 81.5%, ANN 77.5% and DT 74.3%), but the accuracy of decision tree J48 (74.2%) was higher. Conclusion: The study indicated that in the KNN model, the rules derived from it can be effective in mortality prediction in patients admitted to ICUs.

Background: Various prediction models have been developed aiming to estimate risk-adjusted mortality, morbidity and length of intensive care unit stay following cardiac surgeries. The European system for cardiac operative risk evaluation II (EuroSCORE II) is a prediction model which maps 18 predictors to a 30-day post-operative risk of death. The objective of this study was to evaluate the performance of the EuroSCORE II risk-analysis predictions among patients who underwent heart surgeries. Methods: A prospective cross-sectional study was conducted to collect required variables for all consecutive patients underwent heart surgeries in Emam Reza hospital, Mashhad, Iran, from March 2014 to March 2015. Once the patient was hospitalized a cardiologist or a general physician evaluated pre- peri- and post-operative state to fill out the pre-designed structural paper form. Comparing the observed and expected mortality, the sensitivity, specificity, area under the receiver operating characteristic curve (AUC) and finally the discrimination power of the model for our patients were calculated and reported. The model value was calculated using the online tool. Results: A total of 1337 patients (60% males) were included, the observed mortality rate was 3.2%. Although the overall performance was acceptable, the model showed poor discriminatory power (AUC=0.667, CI 95%: 0.648-0.685) and accuracy with sensitivity=61.88% and specificity=66.23%. Conclusion: Our single-center study, based on consecutive patients who underwent cardiac surgery showed that EuroSCORE II demonstrated a moderate statistical overall performance with poor discrimination and calibration measures remain as concerning issues regarding 30-day post-operative mortality prediction after adult cardiac surgery. Poor performance measures for this system show the need for reformulating this risk stratification tool aiming to improve post cardiac surgery outcome predictions in Iran.

Background: There is no need to explain the importance of collection, recording and analyzing the information of disease in any health organization. In this regard, systematic design of standard data sets can be helpful to record uniform and consistent information. It can create interoperability between health care systems. The main purpose of this study was design the core dataset to record colorectal cancer information in Iran. Methods: For the design of the colorectal cancer core data set, a combination of literature review and expert consensus were used. In the first phase, the draft of the data set was designed based on colorectal cancer literature review and comparative studies. Then, in the second phase, this data set was evaluated by experts from different discipline such as medical informatics, oncology and surgery. Their comments and opinion were taken. In the third phase refined data set, was evaluated again by experts and eventually data set was proposed. Results: In first phase, based on the literature review, a draft set of 85 data elements was designed. In the second phase this data set was evaluated by experts and supplementary information was offered by professionals in subgroups especially in treatment part. In this phase the number of elements totally were arrived to 93 numbers. In the third phase, evaluation was conducted by experts and finally this dataset was designed in five main parts including: demographic information, diagnostic information, treatment information, clinical status assessment information, and clinical trial information. Conclusion: In this study the comprehensive core data set of colorectal cancer was designed. This dataset in the field of collecting colorectal cancer information can be useful through facilitating exchange of health information. Designing such data set for similar disease can help providers to collect standard data from patients and can accelerate retrieval from storage systems.