Search

BackgroundThe inappropriate use of prescription medication has recently garnered worldwide attention, but most national policies do not effectively provide for early detection or timely intervention. ObjectiveThis study aimed to develop and assess the validity of a model that can detect the inappropriate use of prescription medication. This effort combines a multiview and topic matching method. The study also assessed the validity of this approach. MethodsA multiview extension of the latent Dirichlet allocation algorithm for topic modeling was chosen to generate diagnosis-medication topics, with data obtained from the Chinese Monitoring Network for Rational Use of Drugs (CMNRUD) database. Topic mapping allowed for calculating the degree to which diagnoses and medications were similarly distributed and, by setting a threshold, for identifying prescription misuse. The Beijing Regional Prescription Review Database (BRPRD) database was used as the gold standard to assess the model’s validity. We also conducted a sensitivity analysis using random samples of validated prescriptions and evaluated the model’s performance. ResultsA total of 44 million prescriptions were used to generate topics using the diagnoses and medications from the CMNRUD database. A random sample (15,000 prescriptions) from the BRPRD was used for validation, and it was found that the model had a sensitivity of 81.8%, specificity of 47.4%, positive-predictive value of 14.5%, and negative-predictive value of 96.0%. The model showed superior stability under different sampling proportions. ConclusionsA method that combines multiview topic modeling and topic matching can detect the inappropriate use of prescription medication. This model, which has mediocre specificity and moderate sensitivity, can be used as a primary screening tool and will likely complement and improve the process of manually reviewing prescriptions.

Abnormal prescriptions refer to abnormal prescriptions prescribed by doctors for patients. Abnormalities in medical prescription, such as drug abuse and incorrect medicine, will affect the efficiency of treatment and even result in serious consequence. Because of some subjective or objective reasons, there exist more or less abnormal prescriptions. The detection of the abnormal prescriptions can improve the efficiency of the patient??s medical treat-ment and reduce the cost of the medical treatment. It is of great significance to drug abuse, polypharmacy and incorrect medicine. For this reason, this paper proposes an extended topic model based abnormal medical prescri-ption detection method, which can automatically detect the abnormal prescription from a large number of prescri-ption data. In addition, for each new prescription, this method can determine whether its diagnose and medicine match, and then determine whether it is normal or not. Compared with other abnormal detection algorithms, this method has a wider range of applications, not only can be used to detect abnormal prescriptions, but also can be used to detect the matching relations between other features. This method has been implemented and its validity has been verified in a real prescription dataset.