An Early Prediction and Diagnosis of Sepsis in Intensive Care Units: an Unsupervi̇sed Machine Learning Model

Abstract

Sepsis infection, which is one of the most important causes of death in intensive care units, is seen as a severe global health crisis. If an early diagnosis of sepsis infection cannot be made, and treatment is not started rapidly, septic shock may result in multiple organ failure and death is almost inevitable. Therefore, it is vital to establish an early diagnosis and start the treatment at once. This study aims to accomplish a new model of unsupervised machine learning using lactate and Ph laboratory test values, which are considered to be important parameters to diagnose sepsis infection. The data used in the study have been obtained from MIMIC-III international clinical database. Unsupervised machine learning has been performed via the Fuzzy-C algorithm along with validity indexes like Xie Beni on patients' data diagnosed sepsis and non-sepsis. The machine-generated ten labels at the end of the training session considering-designed validity indexes. The labelled cluster representatives have been reduced to two dimensions by Principal Component Analysis method in order to monitor the learning in a two-dimensional space. The study contributes to the literature by conducting unsupervised learning through two parameters (Lactate and Ph) and leading to multi-parameter studies. In addition, the study reports that there are five types of sepsis patterns in terms of Lactate and PH laboratory tests.

Characterization of Mortality Prediction: An Ensemble Learning Analysis Using the Mimic-Iii Dataset

“…Support Vector Machine (SVM), Logistic Regression (LR), and XGBoost classification algorithms were employed in the study by Ergul Aydn & Kamişli Ozturk, [8] one of the comparable studies in this field, to assess whether the patients' stays in critical care were longer than 3 days. The study found that, similarly to earlier prediction articles, the XGBoost classifier outperformed Support Vector Machine (SVM) and Logistic Regression (LR) [9,10,11,12]. Poucke's study was to compare the predictive performance of Decision Tree, Naïve Bayes, Logistic and Regression methods, and ensemble learning methods (Random Forest, Boosting, and Bagging) when assessing the predictive power of laboratory tests for hospital mortality in patients admitted to the intensive care unit.…”

“…For specialists doing various studies on intensive care research, from the creation of clinical decision support algorithms to a better comprehension of retrospective clinical investigations, the MIMIC-II and MIMIC-III databases are crucial sources of data. Despite advances in disease identification and treatment, the rate of mechanical ventilation, sepsis infection and mortality in intensive care units have been growing recently [12,29,32,33]. Globally, deaths in intensive care units are seen as a severe health concern.…”

A Machine Learning Approach to Predict Creatine Kinase Test Results

“…Prediction models based on machine learning have been successfully applied in the diagnosis and detection of many diseases in the field of health for the last few years [17]. These models have some advantages, such as rapid processing and generating results with minimum human intervention.…”