e-journal

Adverse Drug Effect Detection

---

Abstract—Largecollectionsofelectronicpatientrecordsprovide abundantbutunder-exploredinformationonthereal-worlduseof medicines. Although they are maintained for patient administration, they provide a broad range of clinical information for data analysis. One growing interest is drug safety signal detection from these longitudinal observational data. In this paper, we proposed two novel algorithms—a likelihood ratio model and a Bayesian network model—for adverse drug effect discovery. Although the performance of these two algorithms is comparable to the stateof-the-art algorithm, Bayesian confidence propagation neural network, the combination of three works better due to their diversity insolutions.Sincetheactualadversedrugeffectsonagivendataset cannotbeabsolutelydetermined,wemakeuseofthesimulatedobservational medical outcomes partnership (OMOP) dataset constructed with the predefined adverse drug effects to evaluate our methods.Experimentalresultsshowtheusefulnessoftheproposed pattern discovery method on the simulated OMOP dataset by improvingthestandardbaselinealgorithm—chi-square—by23.83%.

Index Terms—Adverse drug effect, Bayesian network, Bayesian confidence propagation neural network (BCPNN), correlation, likelihood ratio (LR).

---

Ketersediaan

Tidak ada salinan data

Informasi Detail

Judul Seri

-

No. Panggil

-

Penerbit

: IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS., 2013

Deskripsi Fisik

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, VOL. 17, NO. 2, MARCH 2013 p. 305-311

Bahasa

English

ISBN/ISSN

2168-2194

Klasifikasi

NONE

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

OBAT

Info Detail Spesifik

-

Pernyataan Tanggungjawab

Lian Duan ... [et al.]

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus masuk sebelum memberikan komentar