Figure 6 | Scientific Reports

Figure 6

From: Machine learning algorithm to predict mortality in critically ill patients with sepsis-associated acute kidney injury

Figure 6The alternative text for this image may have been generated using AI.

LIME algorithm for explaining individual’s prediction results. Screenshot of the death prognosis for SA-AKI patients. (A) Utilizing the LIME method, show a death case. (B) Present a case of survival using the LIME method. The left portion of the picture depicts expected LIME findings. The center section lists, from highest to lowest, the eight variables that had the greatest impact on survival or death. The length of the bar for each feature reflects the weight of that feature in the prediction. A longer bar represents a characteristic that contributes more to survival or mortality. The right panel displays the crucial values of these eight factors at which they had the greatest influence on survival or death. SA-AKI Sepsis-associated acute kidney injury, SOFA Sequential organ failure assessment, SAPS II Simplified acute physiology score II, SpO2 Oxygen saturation, PTT Partial thromboplastin time, WBC White blood cell.

Back to article page