钱懿轶
云南省阜外心血管病医院 药剂科
Background:With the rapid development of artificial intelligence, prediction of warfarin dose via machine learning has received more and more attention. Since the dose prediction involve both linear and nonlinear problems, traditional machine learning algorithms are ineffective to solve such problems at one time.Objective:Based on the characteristics of clinical data of Chinese warfarin patients, an improved stacking ensemble learning can achieve higher prediction accuracy.Methods:Information of 641 patients from southern China who had reached a steady state on warfarin was collected, including demographic information, medical history, genotype, and co-medication status. The dataset was randomly divided into a training set (90%) and a test set (10%). The predictive capability is evaluated on a new test set generated by stacking ensemble learning. Additional factors associated with warfarin dose were discovered by feature selection methods.Results:A newly proposed heuristic-stacking ensemble learning performs better than traditional-stacking ensemble learning in key metrics such as accuracy of ideal dose (73.44%, 71.88%), mean absolute errors (0.11 mg/day, 0.13 mg/day), root mean square errors (0.18 mg/day, 0.20 mg/day) and R2 (0.87, 0.82).Conclusions:The developed heuristic-stacking ensemble learning can satisfactorily predict warfarin dose with high accuracy. A relationship between hypertension, a history of severe preoperative embolism, and warfarin dose is found, which provides a useful reference for the warfarin dose administration in the future.
Frontiers in cardiovascular medicine 2023
BACKGROUND:Non-vitamin K antagonist oral anticoagulants (NOACs) are alternative to vitamin K antagonists (VKAs) for stroke prevention in patients with atrial fibrillation (AF). Along with their widespread clinical use in China, the off-label use of NOACs is commonly seen in real-world practice, which could result in adverse drug events and poor clinical outcomes. However, guideline adherence and label adherence for NOAC prescriptions have not been well evaluated in a real-world setting in China.METHODS:Between January 2021 and June 2021, a total of 1,750 outpatients or inpatients with AF will be consecutively enrolled at 26 canters in China. Data on patient demographics, clinical characteristics, treatment strategies, and prescribing information related to anticoagulation therapy for patients with AF will be collected. Clinical pharmacists will evaluate the rationality of the anticoagulation regimens and NOAC prescriptions based on the guideline recommendations and drug labels that are approved by the National Medical Products Administration. The primary outcomes will be the prevalence of irrational anticoagulation strategies and the inappropriate NOAC prescriptions, as well as potential risk factors associated with inappropriate prescriptions in patients with AF.DISCUSSION:This study will be the first national, multicenter, prospective study performed by pharmacists to explore real-world data on the appropriateness of NOAC prescription in Chinese patients with AF.TRIAL REGISTRATION:The Chi-NOACs-AF trial (Trial number: ChiCTR2000035908).
Annals of translational medicine 2021
BACKGROUND:The incidence of atrial fibrillation (AF) is increasing, and effective anticoagulation therapy can prevent adverse events. Selecting the appropriate OAC based on patient characteristics has become a challenge. Interventions are going to be a potential area of focus.OBJECTIVES:To explore the discrepancies between clinician prescriptions and recommended guidelines of oral anticoagulants (OACs) for patients with atrial fibrillation (AF), and to provide direction for improving anticoagulation strategies for treating patients with AF.MATERIALS AND METHODS:Data were collected from the electronic medical record system of Fuwai Yunnan Cardiovascular Hospital between July 2019 and January 2020. The suitability of prescribed OACs for patients with AF was assessed according to the Rules for Avoiding Prescription Inappropriateness, the prescribed medicine label, and any relevant antithrombotic guidelines for treating patients with AF.RESULTS:A total of 460 patients met the inclusion criteria. Of these, 53.7% received an appropriate prescription and 46.3% received an inappropriate prescription. Of the patients who received inappropriate prescriptions, 15.4% were prescribed without the presenting appropriate indicators, 1.3% were prescribed inappropriate drug selection, and 29.6% were prescribed inappropriate drug doses. For patients prescribed without providing appropriate indicators, 2.2% had no indication for medication and 13.3% had an indication for medication, but not a specific OAC. For patients with inappropriate drug selection, 1, 5 patients were on rivaroxaban, dabigatran respectively. The distribution of NOAC doses was as follows: dabigatran standard dose (45.2%), the low dose (54.8%). Rivaroxaban standard dose (58.9%), low dose (36.8%), high dose (4.3%). A total of 44 patients (9.6%) experienced bleeding events, 12 patients (2.6%) experienced embolic events, and 7 patients experienced other adverse events after dosing.CONCLUSIONS:In clinical practice, it is common for patients with AF to receive inappropriate prescriptions of OACs. Therefore there is a need to enhance anticoagulation management in patients with AF to improve the appropriate use of OACs.
PloS one 2021
