Drug Utilization for Pain Management during Perioperative Period of Total Knee Arthroplasty in China: A Retrospective Research Using Real-World Data

Development and validation of a machine learning model to improve precision prediction for irrational prescriptions in orthopedic perioperative patients

OBJECTIVE

Our objective was to develop a machine learning model capable of predicting irrational medical prescriptions precisely within orthopedic perioperative patients.

METHODS

A dataset comprising 3047 instances of suspected irrational medication prescriptions was collected from a sample of 1318 orthopedic perioperative patients from April 2019 to March 2022. Four machine learning models were employed to forecast irrational prescriptions, following which, the performance of each model was meticulously assessed. Subsequently, a thorough variable importance analysis was conducted on the model that performed the best predictive capabilities. Thereafter, the efficacy of integrating this optimal model into the existing audit prescription process was rigorously evaluated.

RESULTS

Of the models utilized in this study, the RF model yielded the highest AUC of 92%, whereas the NB model presented the lowest AUC of 68%. Also, the RF model boasted the most robust performance in terms of PPV, reaching 82.4%, and NPV, reaching 86.6%. The ANN and the XGBoost model were neck and neck, with the ANN slightly edging out with a higher PPV of 95.9%, while the XGBoost model boasted an impressive NPV of 98.2%. The RF model singled out the following five factors as the most influential in predicting irrational prescriptions: the type of drug, the type of surgery, the number of comorbidities, the date of surgery after hospitalization, as well as the associated hospital and drug costs.

CONCLUSION

The RF model showcased significantly high level of proficiency in predicting irrational prescriptions among orthopedic perioperative patients, outperforming other models by a considerable margin. It effectively enhanced the efficiency of pharmacist interventions, displaying outstanding performance in assisting pharmacists to intervene with irrational prescriptions.

Continuous Lumbar Plexus Block under the Guidance of the "Shamrock Method" Ultrasound: Analgesic Effects and Hemodynamic Effects after Total Knee Arthroplasty in Elderly Patients

Objective

To explore the effect of continuous lumbar plexus block guided by the “Shamrock method” on postoperative analgesia and hemodynamics in elderly patients after total knee arthroplasty (TKA).

Methods

From January 2020 to December 2020 in our hospital, 98 patients who underwent TKA were selected. Using the random number table method, the patients were divided into two groups: a continuous lumbar plexus block group (group L), with 49 patients, and a continuous femoral nerve block group (group F), with 49 patients. The onset time and maintenance time of motor and sensory nerve blocks in patients were recorded. A visual analogue scale (VAS) was applied to assess the pain severity at 6, 12, 24, and 48 h after the operation. The VAS score (FVAS) was applied to evaluate the pain severity of the patients during 24 and 48 h after the operation and knee joint functional exercise. The levels of hemodynamic indexes such as heart rate, mean arterial pressure, and oxyhemoglobin saturation and the levels of hemorheological indexes such as plasma viscosity, high and low whole blood shear viscosity, fibrinogen, and hematocrit were detected and compared between the two groups immediately after the operation and at 12 h and 48 h after the operation, respectively. The incidence of adverse reactions induced by anesthesia was counted.

Results

The onset time of motor and sensory nerve blocks in group L was lower than that in group F, and the maintenance time was higher than that in group F (P < 0.05). The VAS scores of 6, 12, 24, and 48 h after operation in group L were significantly lower than those in group F (P < 0.05). The FVAS scores of group L at 24 and 48 h after operation were significantly lower than those of group F (P < 0.05). The heart rates of the patients in the two groups were higher at 12 h and 48 h after operation than those immediately after operation (P < 0.05). The heart rates at 12 h and 48 h after operation in group L were lower than those in group F (P < 0.05). The plasma viscosity, high whole blood shear viscosity, and low whole blood shear viscosity in the group L at 12 h and 48 h after operation were lower than those in group F (P < 0.05). There was no significant difference in the incidence of local anesthetic poisoning, nausea, vomiting, urinary retention, pruritus, and other adverse reactions between the two groups (P > 0.05).

Conclusion

The “Shamrock method” ultrasound-guided continuous lumbar plexus block in elderly patients after TKA has good analgesic effect, stable hemodynamics, little influence on hemorheology, and good safety. It is of great value to enhance the surgical effect and promote postoperative rehabilitation.