Skip to main content
Fig 7 | Journal of Translational Medicine

Fig 7

From: Construction and validation of prognostic models in critically Ill patients with sepsis-associated acute kidney injury: interpretable machine learning approach

Fig 7

Force plots visualized individual model prediction as result of feature contributions. The base value represented the averaged predicted results. Feature values were listed at the plot bottom with feature names. Each group of features was ranked from center to both ends by the extent of their impact. A: A patient died within 7-day of ICU admission. “SOFA = 16” means that the score of SOFA of the patient was 16 when he admitted to ICU. “meanbp_mean = 57.15” represented that the maximum of mean arterial pressure of the patient was 57.15 mmHg in the first 24 h during ICU stay. “urine output = 34.0” means that the urine output of the patient was 34.0 ml in the first 24 h during ICU stay. B: A patient died within 14-day of ICU admission C: A patient died within 28-day of ICU admission. “aki_stage_III = 1.0” represented that the AKI stage of the patient was 3 when he admitted to ICU. D: A patient surviving after 28-day of ICU admission

Back to article page