International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395 -0056
Volume: 04 Issue: 04 | Apr -2017
p-ISSN: 2395-0072
www.irjet.net
An Analytical Survey on Adverse Drug Reactions Using Data Mining Soniya.G1, L. Thomas Robinson2, D. Brintha Sweetly3 1M.Phil
Research Scholar, Nanjil Catholic College of Arts and Science Kaliyakkavilai, Tamilnadu,India Professor, Nanjil Catholic College of Arts and Science Kaliyakkavilai, Tamilnadu,India ---------------------------------------------------------------------***--------------------------------------------------------------------2,3Assistant
Abstract - Adverse drug reactions denote a major health
problem all over the world. It describes any injury caused by taking a drug or overdose of drug or due to combination of two or more drugs. Detection of adverse drug reactions is compulsory because they affect large number of people and can help in raising early warning against adverse effects of drugs and help medical experts in making treatment effective and timely. In today’s digital era a huge amount of data correlated to adverse effects of drugs is being collected at hospitals, drug retail stores and by drug producers. This data can be used for finding out the secreted relationships between drugs and their adverse reactions. In the current scenario, our world is being completely deployed by many drugs. Few of them are alcohol, marijuana, cocaine, steroids and tobacco. Due to the maximum addiction to those drugs, many problems are getting worse in our society, and alcohol is the most acutely destructive of other drugs. This research deals about the society problems due to the use of alcohol. Key Words: treatment.
Addiction, drug, health, medical,
exposure to alcohol, the brain adapts to the changes alcohol makes and becomes dependent on it. For people with alcoholism, drinking becomes the primary medium through which they can deal with people, work, and life. Alcohol dominates their thinking, emotions, and actions. The severity of this disease is influenced by factors such as genetics, psychology, culture, and response to physical pain. Data mining is a powerful new technology to discover information within the large amount of the data. Data mining software is one of a number of analytical tools for analyzing data. Knowledge discovery in databases often called data mining, extracting information and patterns from data in large database, and it is one of the technologies used to find the interesting knowledge from the vast data produced by the health care system and used to analysis the patterns in large sets of data.
2. SURVEY ON ADVERSE DRUG REACTION 2.1 Refining Adverse Drug Reactions using Association Rule Mining for Electronic Healthcare Data
1.INTRODUCTION
Objective
Drugs are suggested to patients for curing diseases and improving their health. But sometimes drugs may lead to negative side effects which can degenerate patient’s health. A drug allergy is the abnormal reaction of your immune system to a medication. However, a drug allergy is more likely with certain medications. The most common signs and symptoms of drug allergy are hives, rash or fever. A drug allergy may cause serious reactions, including anaphylaxis, a life-threatening condition that affects multiple body systems. A drug is any substance (other than food that provides nutritional support) that, when inhaled, injected, smoked, consumed, absorbed via a patch on the skin, or dissolved under the tongue, causes a physiological change in the body. Drugs may be legal (e.g. alcohol, caffeine and tobacco) or illegal (e.g. cannabis, ecstasy, cocaine and heroin) depends on the law of the country and states. Drug repositioning represents the application of known drugs for new indications and plays an important role in healthcare research and industry. With its increasing value in drug development, multiple approaches have been applied in its exercise, basically classified as drug-based and disease based approaches. In the brain, alcohol interacts with centers responsible for pleasure and other desirable sensations. After prolonged
Side effects of prescribed medications are a common occurrence. Electronic healthcare databases present the opportunity to identify new side effects efficiently but currently the methods are limited due to confounding (i.e. when an association between two variables is identified due to them both being associated to a third variable). In this paper we propose a proof of concept method that learns common associations and uses this knowledge to automatically refine side effect signals (i.e. exposureoutcome associations) by removing instances of the exposure-outcome associations that are caused by confounding. This leaves the signal instances that are most likely to correspond to true side effect occurrences. We then calculate a novel measure termed the confounding-adjusted risk value, a more accurate absolute risk value of a patient experiencing the outcome within 60 days of the exposure. Tentative results suggest that the method works. For the four signals (i.e. exposureoutcome associations) investigated we are able to correctly filter the majority of exposure-outcome instances that were unlikely to correspond to true side effects. The method is likely to improve when tuning the association rule mining parameters for specific health outcomes. This paper shows that it may be possible to
© 2017, IRJET
|
Impact Factor value: 5.181
|
ISO 9001:2008 Certified Journal
|
Page 1540