Has the Volume-Based Drug Purchasing Approach Achieved Equilibrium among Various Stakeholders? Evidence from China

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.

Changing Characteristics of Pharmaceutical Prices in China Under Centralized Procurement Policy: A Multi-Intervention Interrupted Time Series

Objective: National centralized drug procurement organized by the Chinese government currently represents the largest group purchasing organization worldwide, to establish a reasonable price formation mechanism. This study aimed to evaluate the effects of centralized procurement policy on drug price and price ratio in China.

Method: Monthly drug procurement data of public medical institutions were extracted from the national procurement database, including 11 pilot cities and 36 months from January 2018 to December 2020. Centralized procured INNs (International Nonproprietary Names) (n = 25) and their alternative INNs (n = 96) were selected as study samples. Centralized procured INNs were divided into bid-winning and non-winning products according to the bidding results. Drug price, price distribution, and price ratio were measured. Multi-intervention interrupted time series analysis was performed to estimate the policy impacts in two centralized procurement periods.

Results: The price of centralized procured INNs showed an immediate drop of 44.57% (β = -0.59, p < 0.001) at the policy implementation, among which bid-winning drugs decreased by 61.71% (β = -0.96, p < 0.001). No significant change in the price level or trends was found for non-winning products and alternative drugs in the first-year procurement period (all p-values > 0.05). During the second-year procurement period, alternative drugs in four therapeutic categories detected significant increases in the price level (all p-values < 0.05). The overall coefficient of variation of price distribution exhibited upward trends after policy implementation. Among the most centralized procured INNs, the price ratio between certificated generics (generics that have passed the consistency evaluation) and original drugs declined significantly after policy intervention (p < 0.05), whereas the price ratio between uncertificated and certificated generics increased significantly (p < 0.05).

Conclusion: Chinese government-organized group purchasing resulted in prominent price reduction of bid-winning drugs. The policy observed a short-term “spillover” effect of synergistic price reduction, while the effect wore off after 1-year procurement period. The extremely dispersed price distribution, as well as unreasonable price ratios, requires further effective price regulation means.