原创技术

Feeding intolerance (FI) is common in critically ill patients fed with enteral nutrition. Although there is increasing evidence showing the association between FI and mortality, no reliable quantitative assessment was available in clinical practice.

Thus, CAPCTG&CCCNTG conducted a post hoc analysis based on data collected in a previous cross-sectional study and proposed a FI scoring system based on gastrointestinal symptoms which is independently associated with 28-day mortality in critically ill patients with acceptable predictive accuracy.

In recent years, physical function assessment has become an important outcome measure in medical research. Six-minute walking distance test is commonly used to assess functional exercise capacity, overall physical performance, and mobility. However, implementing a six-minute walking test requires involvement of medical professionals, and the results could provide limited information to reflect physical function. There is a lack of an objective, convenient and reliable tool for large-scale research and clinical practice.

By cooperating with Department of Computer Science and Technology, Nanjing University, CAPCTG&CCCNTG have proposed a novel system to remotely and continuously perform gait monitoring called “GaitTracker.” The GaitTracker is able to accurately perform 3D skeletal tracking of lower limbs for gait analysis, providing data like gait symmetry and swing/stance time. It is of potential to be used as a standard measurement of physical function, thereby being widely used for both academic and practical purposes.

Organ dysfunction (OD) assessment is essential in intensive care units. However, current OD assessment scores merely describe the number and the severity of each OD, without evaluating the duration of organ injury.

Thus, CAPCTG&CCCNTG developed and validated a machine learning model based on the Sequential Organ Failure Assessment (SOFA) score for the prediction of mortality in critically ill patients. Data from MIMIC-III were mixed for model development. The MIMIC-IV and Nanjing Jinling Hospital Surgical ICU database were used as external test set. The time-incorporated T-SOFA model could significantly improve the prediction performance of the original SOFA score and is of potential for identifying high-risk patients in future clinical application.