The decision support system for pharmaceutical applications plays a major role in handling the critical situation of patients. The effective and efficient real time monitoring has to be provided and the accurate decision has to be made in advance by the decision making system continuously by acquiring the biosignals. Thus, in the current world, remote health monitoring has to be implemented effectively in order to avoid critical situation and fatal death. The main aim of the project is to develop a prototype which constitutes the multimodal biosignal acquisition system, thereby providing multi-label classification and clinical decision support system (CDSS). Several studies have been focused in the related areas which effectively provide the faster diagnosis for the critically ill patients. It is highly demandable for the critically ill patients to be treated in the right time with the proper and effective treatment which can be done efficiently using the CDSS and multi-label classification. The proposed system includes the biosignal acquisition like temperature, heart rate and ECG (electrocardiogram) using the sensors such as BMP180, pulse sensor and ECG electrodes with sensor module (AD8232) which are interfaced with Raspberry Pi. The acquired biosignals are further updated in cloud continuously. The updated database in the cloud is exported to Matlab® for performing multi-label classification through which the patient’s critical situation can be identified. Thus, whenever the patient is found to be in unstable state, an alert is sent to the physician by effective CDSS to take the necessary clinical interventions. Therefore, on developing the logical learning model using the multi-label classification, decision support system can be enhanced using the context-awareness methods to predict the future vital signs and thereby providing appropriate pharmaceutical drugs to the ill patients. © RJPT All right reserved.