Construction and validation of a clinical prediction model for sepsis using peripheral perfusion index to predict in-hospital and 28-day mortality risk

Abstract

Sepsis is a clinical syndrome caused by infection, leading to organ dysfunction due to a dysregulated host response. In recent years, its high mortality rate has made it a significant cause of death and disability worldwide. The pathophysiological process of sepsis is related to the body's dysregulated response to infection, with microcirculatory changes serving as early warning signals that guide clinical treatment. The Peripheral Perfusion Index (PI), as an indicator of peripheral microcirculation, can effectively evaluate patient prognosis. This study aims to develop two new prediction models using PI and other common clinical indicators to assess the mortality risk of sepsis patients during hospitalization and within 28 days post-ICU admission. This retrospective study analyzed data from sepsis patients treated in the Intensive Care Unit of Peking Union Medical College Hospital between December 2019 and June 2023, ultimately including 645 patients. LASSO regression and logistic regression analyses were used to select predictive factors from 35 clinical indicators, and two clinical prediction models were constructed to predict in-hospital mortality and 28-day mortality. The models' performance was then evaluated using ROC curve, calibration curve, and decision curve analyses. The two prediction models performed excellently in distinguishing patient mortality risk. The AUC for the in-hospital mortality prediction model was 0.82 in the training set and 0.73 in the validation set; for the 28-day mortality prediction model, the AUC was 0.79 in the training set and 0.73 in the validation set. The calibration curves closely aligned with the ideal line, indicating consistency between predicted and actual outcomes. Decision curve analysis also demonstrated high net benefits for the clinical utility of both models. The study shows that these two prediction models not only perform excellently statistically but also hold high practical value in clinical applications. The models can help physicians accurately assess the mortality risk of sepsis patients, providing a scientific basis for personalized treatment.

Keywords: 28-day mortality; Clinical prediction model; In-hospital mortality; LASSO regression; Peripheral perfusion index (PI); Sepsis.

Fig. 1

The heatmap illustrates the significance analysis of sample feature variables. It shows the correlations between multiple clinical and laboratory variables, where the colors indicate the direction and strength of the correlations. Blue represents positive correlations, red indicates negative correlations, and the deeper the color, the stronger the correlation. The significance levels of the correlation coefficients are represented by asterisks: * indicates p < 0.05, ** indicates p < 0.01, and *** indicates p < 0.001. The upper left portion of the diagonal displays the correlation coefficients and their significance levels between the variables.

Fig. 2

Variable selection in LASSO binary logistic regression model. For predicting in-hospital mortality, a coefficient profile plot was generated for the log(lambda) sequence (a). Nine variables with non-zero coefficients were selected using the optimal lambda. The optimal parameter (lambda) in the LASSO model was validated, and a plot of the partial likelihood deviance (binomial deviance) against log(lambda) was created, with a dashed vertical line drawn according to the standard error criterion (b). Similarly, for predicting mortality within 28 days after ICU admission, a coefficient profile plot was generated (c), followed by drawing a dashed vertical line (d).

Fig. 3

Development of nomogram prediction models for mortality risk. (a) Development of the nomogram prediction model for in-hospital mortality risk. (b) Development of the nomogram prediction model for 28-day mortality risk post-ICU admission.