New age approaches to predictive healthcare using in silico drug design and internet of things (IoT)

Abstract

The new era of analytics has revolutionized human life by improving varied areas including healthcare. The conventional drug discovery process is complicated, time-consuming and costly, and some of the main factors that make it amenable to failure include lack of effectiveness, adverse reactions, poor pharmacokinetics and marketable reasons. Traditional medicine (TM), used conventionally, is subjected to rigorous research for its efficacy and safety, which increases both the time and cost of the process. With rapidly changing economic scenario, the need for utilizing novel approaches for evidence-based clinical drug development that overcomes these facets of TM has increased leading to the increased usage of predictive modelling. The whole process of predictive analytics finds its roots with drug design and development. Some latest approaches in predictive healthcare for predicting clinical outcomes are done by modelling to optimize the dosage of drugs and also to evaluate potential adverse mechanism. Big data analytics, data mining and text mining are the latest technologies being used in predictive analytics. These technologies have helped in the prediction, treatment and effective diagnosis of diseases which has brought a lot of significant changes such as in the service quality which is being provided and most importantly cost reduction. This chapter involves various steps being followed for the development of a drug in the USA. Development of drug from identifying the protein to its clinical testing and post-market trials has many phases and involves approval of certain applications. This chapter is an attempt to encompass Internet of Things (IoT) and in silico approaches to address various healthcare components including predictive analytics. In silico modelling tools can be used for prediction of dosage and pathway-related adverse effects in humans as well as machine learning can be used in the prediction of the chemical toxicity during drug design. In silico design methods can reduce the average cost to develop a drug considerably, and it can minimize therapeutic risks efficiently. Next-generation sequencing (NGS) along with clinical trial simulation concepts helps in facilitating key decisions in drug delivery management and regulatory approval. Use of IoT-enabled devices to remotely monitor patient’s health helps in reducing the length of hospital stay and prevents readmissions. This analysis is achieved by the use of cloud-centric architecture, wherein the physical activities of users are monitored in primary health centres. If these results obtained exceed the overall threshold value, then an alert is sent to the healthcare personnel thereby preventing any severe complications that might occur. Thus it has a major impact on reducing healthcare costs significantly and improving treatment outcomes. Some IoT applications are in devices for the remote patient monitoring (RPM) like the glucose metres for the patients having diabetes. Blood pressure can be monitored by automated blood pressure cuffs. However, IoT comes with certain limitations like it demands faster processing of the generated data, large data volume, variation and velocity and the requirement for accuracy, quality of service (QoS), security and user expectations, and operational costs arise as a result of large utilization of sensors, mobility and geographic distribution. Cloud computing services are widely in use to mitigate these negatives, using IoT-enabled healthcare solutions.