HEALTHCARE
This section throws detailed light on the rising mountains amount of complex data and parallelly provides a glimpse of how those issues can be resolved by the quantum machine learning algorithms.
With rapid digitization of data, healthcare sector presently has got shifted from pen and paperwork to modern form of data, from traditional one for all to precision/personalized medicine, where the patient data is stored in electronic medical record (EMR), health electronic record (HER), personal health record (PHR), electronic health record (EHR), health information organization (HIO), personal sanitary electronic registry (RESP), etc., which resulted in generation of large amounts of data, driven by record keeping, healthcare management, regulatory requirements, and patient care [65]. The goal to improve the quality of healthcare delivery and reducing the costs made it mandatory requirement to visualize these massive quantities of data (known as big data), which hold the promise of supporting a wide range of medical and healthcare functions, including among others clinical decision support, disease surveillance, and population health management [66]. Analytics is the biggest opportunity nowadays. The U.S. healthcare system alone touched the landmark in reaching the mark of 150 exabytes in 2011 and with such a growing pace is expected to reach the zettabyte’s (1021 gigabytes) scale soon and not long far the yottabyte (1024 gigabytes) [67]. The California-based health network, Kaiser Permanente, which has more than 9 million members, is believed to have between 26.5 and 44 petabytes of potentially rich data from EHRs, including images and annotations [68].
ImageCLEF medical image dataset contained around 66,000 images between 2005 and 2007 while just in the year 2013 around 300,000 images were stored every day. ProteomicsDB covers 92% (18,097 of 19,629) of known human genes that are annotated in the Swiss-Prot database. ProteomicsDB has a data volume of 5.17 ТВ. and clinical decision support systems (physician’s written notes and prescriptions, medical imaging, laboratory, pharmacy, insurance, and other administrative data); patient data in electronic patient records (EPRs); machine-generated/sensordata, such as from monitoring vital signs; social media posts, including Twitter feeds (so-called tweets), blogs, status updates on Facebook and other platforms, web pages; and less patient-specific information, including emergency care data, news feeds, and articles in medical journals. Figure 13.3 gives a glimpse of the multidimensional view and multiple data formats in healthcare sector nowadays ranging from biomedical image data, biomedical sensor data, social media, gene sequencing, drug-related data, lab test, etc.
If healthcare analytics existed in the middle ages, avoiding the black plague may have saved millions of lives. Human errors cause the death of between 44,000 to 98,000 American patients annually [69]. In 2008, the total healthcare spending in the US was 15.2% of its GDP and is expected to reach as much as 19.5% by 2017 [70]. The goal nowadays is to shift from traditional healthcare to data-driven healthcare organization (DDHO), so as to provide the treatment to people with high accuracy and with minimal cost [73,74].
FIGURE 13.3 Diverse formats of healthcare data.
