Pre-anaesthetic evaluation of the patient with end-stage lung disease

Machine learning approach for predicting post-intubation hemodynamic instability (PIHI) index values: towards enhanced perioperative anesthesia quality and safety

BACKGROUND

Adequate preoperative evaluation of the post-intubation hemodynamic instability (PIHI) is crucial for accurate risk assessment and efficient anesthesia management. However, the incorporation of this evaluation within a predictive framework have been insufficiently addressed and executed. This study aims to developed a machine learning approach for preoperatively and precisely predicting the PIHI index values.

METHODS

In this retrospective study, the valid features were collected from 23,305 adult surgical patients at Peking Union Medical College Hospital between 2012 and 2020. Three hemodynamic response sequences including systolic pressure, diastolic pressure and heart rate, were utilized to design the post-intubation hemodynamic instability (PIHI) index by computing the integrated coefficient of variation (ICV) values. Different types of machine learning models were constructed to predict the ICV values, leveraging preoperative patient information and initiatory drug infusion. The models were trained and cross-validated based on balanced data using the SMOTETomek technique, and their performance was evaluated according to the mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE) and R-squared index (R2).

RESULTS

The ICV values were proved to be consistent with the anesthetists' ratings with Spearman correlation coefficient of 0.877 (P < 0.001), affirming its capability to effectively capture the PIHI variations. The extra tree regression model outperformed the other models in predicting the ICV values with the smallest MAE (0.0512, 95% CI: 0.0511-0.0513), RMSE (0.0792, 95% CI: 0.0790-0.0794), and MAPE (0.2086, 95% CI: 0.2077-0.2095) and the largest R2 (0.9047, 95% CI: 0.9043-0.9052). It was found that the features of age and preoperative hemodynamic status were the most important features for accurately predicting the ICV values.

CONCLUSIONS

Our results demonstrate the potential of the machine learning approach in predicting PIHI index values, thereby preoperatively informing anesthetists the possible anesthetic risk and enabling the implementation of individualized and precise anesthesia interventions.

Effects of intraoperative fluid therapy on intensive care process, morbidity, and mortality after lung transplantation

Background

This study aims to evaluate the effect of intraoperative fluid therapy on intensive care process and first 90-day morbidity and mortality in patients undergoing lung transplantation.

Methods

Between March 2013 and December 2020, a total of 77 patients (64 males, 13 females; mean age: 47.6±13.0 years; range, 19 to 67 years) who underwent lung transplantation were retrospectively analyzed. The patients were divided into two groups according to the amount of fluid given intraoperatively: Group 1 (<15 mL/kg^-1/h^-1) and Group 2 (>15 mL/kg^-1/h^-1). Demographic, clinical, intra- and postoperative data of the patients were recorded.

Results

Less than 15 mL/kg-1/h-1 f luid w as a dministered t o 75.3% (n=58) of the patients (Group 1) and 24.7% (n=19) were administered more than 15 mL/kg-1/h-1 (Group 2). In t erms of native disease, the rate of diagnosis of chronic obstructive pulmonary disease and idiopathic pulmonary fibrosis was higher in Group 1, and the rate of other diagnoses was higher in Group 2 (p<0.01). The ratio of women in Group 2 was higher (p<0.05), while the body mass index values were significantly lower in this group (p<0.01). The erythrocyte, fresh frozen plasma, platelet, crystalloid and total fluid given in Group 2 were significantly higher (p<0.001). Inotropic/vasopressor agent use rates and extracorporeal membrane oxygenation requirement were significantly higher in Group 2 (p<0.01). Primary graft dysfunction, gastrointestinal complications, and mortality rates were also significantly higher in Group 2 (p<0.05).

Conclusion

The increased intraoperative fluid volume in lung transplantation is associated with primary graft dysfunction, gastrointestinal complications, and mortality rates.