Cost-Effectiveness of Proton Pump Inhibitor Co-Therapy in Patients Taking Aspirin for Secondary Prevention of Ischemic Stroke

A machine learning model for visualization and dynamic clinical prediction of stroke recurrence in acute ischemic stroke patients: A real-world retrospective study

Background and purpose

Recurrent stroke accounts for 25–30% of all preventable strokes, and this study was conducted to establish a machine learning-based clinical predictive rice idol for predicting stroke recurrence within 1 year in patients with acute ischemic stroke (AIS).

Methods

A total of 645 AIS patients at The Second Affiliated Hospital of Xuzhou Medical University were screened, included and followed up for 1 year for comprehensive clinical data. Univariate and multivariate logistic regression (LR) were used to screen the risk factors of stroke recurrence. The data set was randomly divided into training set and test set according to the ratio of 7:3, and the following six prediction models were established by machine algorithm: random forest (RF), Naive Bayes model (NBC), decision tree (DT), extreme gradient boosting (XGB), gradient boosting machine (GBM) and LR. The model with the strongest prediction performance was selected by 10-fold cross-validation and receiver operating characteristic (ROC) curves, and the models were investigated for interpretability by SHAP. Finally, the models were constructed to be visualized using a web calculator.

Results

Logistic regression analysis showed that right hemisphere, homocysteine (HCY), C-reactive protein (CRP), and stroke severity (SS) were independent risk factors for the development of stroke recurrence in AIS patients. In 10-fold cross-validation, area under curve (AUC) ranked from 0.777 to 0.959. In ROC curve analysis, AUC ranged from 0.887 to 0.946. RF model has the best ability to predict stroke recurrence, and HCY has the largest contribution to the model. A web-based calculator https://mlmedicine-re-stroke2-re-stroke2-baylee.streamlitapp.com/ has been developed accordingly.

Conclusion

This study identified four independent risk factors affecting recurrence within 1 year in stroke patients, and the constructed RF-based prediction model had good performance.

The budget impact of using enteric-coated aspirin 325 mg + immediate-release omeprazole 40 mg to prevent recurrent cardiovascular events

OBJECTIVE

Aspirin (acetylsalicylic acid; ASA) is commonly used for secondary prevention of cardiovascular (CV) events, but may be associated with gastrointestinal (GI) adverse events, which can reduce adherence. Use of ASA co-therapy with proton pump inhibitors in patients at risk may be suboptimal. PA32540 (Yosprala™) is a coordinated-delivery tablet combining EC-ASA 325 mg and immediate-release omeprazole 40 mg. The objective of this flexible budget impact model was to project the financial consequences of introducing PA32540 325 mg/40 mg to prevent recurrent CV events, while reducing ASA-associated GI events in US adults.

METHODS

A Markov Model was employed to estimate health state transitions associated with ASA 75-325 mg, ASA 75-325 mg + generic delayed-release omeprazole 40 mg, PA32540, or clopidogrel 75 mg to prevent recurrent CV events. Health states included ulcers, GI bleeding, CV events, and death. Model inputs included demographics, treatment dosages, treatment costs, adverse GI and CV events, and premature death. Data from peer-reviewed literature and censuses enabled appropriate allocation of CV and GI disease prevalence and mortality. The PA32540 non-adherence rate was conservatively set at 20%. PA32540 market share was set to 50%.

RESULTS

The model projected annual savings of $81.0 million to $190.9 million within 1-5 years after PA32540 introduction to the plan, which included 134,558 members at risk for recurrent CV events. These values translate into savings of $602 (year 5) to $1,419 (year 1) per patient per year, and $81 (year 5) to $191 (year 1) per member per year. These values were robust to variations in parameters under a deterministic sensitivity analysis.

CONCLUSION

PA32540 use to prevent recurrent CV events was associated with cost reductions in each year examined with the model. From a health plan perspective, PA32540 is likely to have a net overall effect, resulting in significant cost savings.