SIAP: an intelligent algorithm for multiple prescription pattern recognition based on weighted similarity distances.

BACKGROUND: Clinical practices have demonstrated that disease treatment can be very complex. Patients with chronic diseases often suffer from more than one disease. Complex diseases are often treated with a variety of drugs, including both primary and auxiliary treatments. This complexity and multidimensionality increase the difficulty of extracting knowledge from clinical data. METHODS: In this study, we proposed a subgroup identification algorithm for complex prescriptions (SIAP). We applied the SIAP algorithm to identify the importance level of each drug in complex prescriptions. The algorithm quickly classified and determined valid prescription combinations for patients. The algorithm was validated through classification matching of classical prescriptions in traditional Chinese medicine. We collected 376 formulas and their compositions from a formulary to construct a database of standard prescriptions. We also collected 1438 herbal prescriptions from clinical data for automated prescription identification. The prescriptions were divided into training and test sets. Finally, the parameters of the two sub-algorithms of SIAP and SIAP-All, as well as those of the combination algorithm SIAP + All, were optimized on the training set. A comparison analysis was performed against the baseline intersection set rate (ISR) algorithm. The algorithm for this study was implemented with Python 3.6. RESULTS: The SIAP-All and SIAP + All algorithms outperformed the benchmark ISR algorithm in terms of accuracy, recall, and F1 value. The F1 values were 0.7568 for SIAP-All and 0.7799 for SIAP + All, showing improvements of 8.73% and 11.04% over the existing ISR algorithm, respectively. CONCLUSION: We developed an algorithm, SIAP, to automatically match sub-prescriptions of complex drugs with corresponding standard or classic prescriptions. The matching algorithm weights the drugs in the prescription according to their importance level. The results of this study can help to classify and analyse the drug compositions of complex prescriptions.

[Evaluation of diagnosing cervical vertigo with computerized static posturography].

OBJECTIVE: To provide a quantitative base for diagnosing cervical vertigo by establishing a biomechanics method. METHODS: From July 2004 to Nov 2005, the static posturography (SPG) of normal 86 health individuals and 75 patients with cervical vertigo were quantitatively measured and qualitative diagnosis respectively in closed and open eyes. There were 40 male and 46 female in health adults, ranging from 20 to 74 years old (mean 30 years). There were 16 male and 59 female in vertigo patients, ranging from 20 to 74 years old (mean 44.5 years). In contrast to current diagnosis method of patients with cervical vertigo, the clinical value was evaluated. RESULTS: Under the state of closed eyes, the sensitivity of SPG diagnosing cervical vertigo was 76%; the specificity was 93%; the Youden index was 69%; the coincidence was 85.1%; the positive predictive value was 90.5%; the negative predictive value was 93%; the positive and negative likelihood ratio were 10.893 and 0.258 respectively. Under the state of open eyes, the sensitivity was 49.3%; the specificity was 87.2%; the Youden index was 38.6%; the coincidence was 69.6%; the positive predictive value was 77.1%; the negative predictive value was 87.2%; the positive likelihood ratio was 3.857; the negative one was 0.581. Regardless of closed or open eyes, foreword-backward type shift orbit was the with cervical vertigo. CONCLUSION: The patients with cervical vertigo and normal individuals can be diagnosed objectively and quantitatively with SPG under the state of closed eyes, which can achieve the basic requirements of diagnosing cervical vertigo with validity, reliability and good clinical application. However, the rate of missed diagnosis with SPG under the state of open eyes is too high to meet the diagnostic needs.