پیش‌بینی مرگ‌و‌میر بیماران بستری در بخش‌های مراقبت ویژه:مقایسه سه تکنیک داده‌کاوی: یک گزارش کوتاه

زمینه و هدف: تحلیل پیامدها در بخش‌های مراقبت ویژه از چالش‌های مهم حوزه سلامت می‌باشد. از این‌رو هدف مطالعه حاضر پیش‌بینی مرگ‌و‌میر بیماران بخش‌های مراقبت ویژه (icus) با استفاده از چند تکنیک داده‌کاوی است.روش بررسی: در این مطالعه نرم‌افزار (weka software, version 3.9.2, university of waikato, new zealand) و داده‌های 874 بیمار icus از دی 1396 تا پایان اسفند 1397 برای توسعه مدل‌ها بکار گرفته شد. بر مبنای چند الگوریتم‌ منتخب داده‌کاوی، مدل‌های پیش‌بینی ایجاد و از شاخصهauc برای مقایسه عملکرد استفاده شد.یافته‌ها: بر مبنای 19 متغیر شناخته شده با اهمیت بیشتر از جمله نمره کمای گلاسکو، مدل‌های پیش‌بینی توسعه یافت. اگرچهauc مدل‌های knn، شبکه عصبی مصنوعی و درخت تصمیم (به‌ترتیب 81.5%، 77.5% و 74.3%) قابل قبول بود اما صحت الگوریتم درخت تصمیم 48j (74.2%) بالاتر گزارش شد.نتیجه‌گیری: نتایج این مطالعه بیانگر برتری مدل knn، نسبت به سایر مدل‌های پیش‌بینی مرگ‌ومیر بیماران icus بود.

Prediction of mortality in patients admitted to intensive care units, A comparison of three data mining techniques: a brief report.

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 wellknown data mining techniques called artificial neural network (ANN), K nearest neighbor (KNN) and decision tree (DT) were used. WEKA 3.9.2 opensource software was implemented for data analysis. Finally, according to the accuracy, sensitivity, specificity criteria and AUCROC 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.