Decision Support System for Drug-Drug Interaction Pertaining to COPD and its Comorbidities

Abstract

A Drug-Drug Interaction is an alteration in the impact of a drug when consolidated with another drug or group of drugs. Drug interactions are common and have caused increased hospital admission rates, treatment failures, avoidable medical complications, and even deaths. Studies have found multiple drug usage, and age-related comorbidities to be the reasons for the interactions and this demands a general study. Here in this paper, we discuss the Drug-Drug Interactions between Chronic Obstructive Pulmonary Disease (COPD) and its associated comorbidity diseases. We have designed a Drug Decision Support System which helps the Physicians to check the Drug-Drug interaction between Chronic Obstructive Pulmonary Disease and its associated comorbidity diseases. COPD is a fourth decade disease means after age 40 it may be diagnosed and is currently fourth largest killing disease. Study says one of the major cause for COPD is smoking (active/passive). As there is no cure for COPD yet. The patient's life can be improved by providing better treatment and management strategies. Once the patient is diagnosed with COPD the patient may also end up suffering with the comorbidity diseases associated with COPD like Asthma, Depression, Dementia, Diabetics, Heart Failure, Hypertension, Hypotension, Obesity, and Osteoporosis. The patient has no choice but taking the prescribed drugs for COPD and other comorbidity disease he is suffering from. Therefore the proposed work plays a vital role in avoiding the drug-drug interaction between COPD and its associated comorbidity diseases.

Exploration and Practice of Volunteer Service Model Based on Alleviating Emotional Disorders in Children with Leukemia

“…After the classification is completed, different aspects of the "REAL" service for the child need to be performed, and each service needs to be evaluated by SAS and SDS scores, and the best service method for the child is determined by quantitative comparison. When the amount of data is large enough, the system can predict the therapeutic effect of a certain aspect of "REAL" service for the child, and the difference between the predicted value and the real value can be evaluated by the root mean square error, so as to improve the reliability of the prediction and provide data support for the doctor's psychological treatment plan for the child [20]. The design flow of "REAL" service model customization system based on the recommendation algorithm is shown in Figure 1.…”