From subconscious to conscious to artificial intelligence: A focus on electronic health records
Correspondence Address: Source of Support: None, Conflict of Interest: None DOI: 10.4103/0028-3886.241377
Source of Support: None, Conflict of Interest: None
Keywords: Digital healthcare, artificial Intelligence, electronic hospital records, data processing, cloud computing, telemedicine, wearable technologies, evidence based medicine
Every human action is data driven. Subconsciously, our brain processes enormous amount of data from afferent and efferent inputs, collaterals, feedback circuits and stored data of past experiences and prepares us for actions. This process starts in the mother's womb and continues through the milestones of development, all the while when innate encoded genetic data is processed by every cell of the body and blended with external inputs either subconsciously or consciously. We subconsciously process data continuously as we play the ball game in our childhood, hop and leap around a steeplechase or during a Kuchipudi or a ballet dance to keep balance and posture. As we grow, we consciously learn to analyze, organize and process more data in our pursuit to master skills and gain knowledge.
There has been a paradigm shift in human evolution, from the days of our predecessors, the ‘hunter- gatherers' to the current era of digital revolution, where the skills are more and more machine driven. The digital revolution had made available, within the last four to five decades, personal computers, internet, social networks, world wide web, global positioning system (GPS), and unfathomable data storage in the cloud and the smart phone. This digital initiative has provided a constant connectivity and collaboration; and, has also facilitated crowd-sourcing, consumer oriented customized platforms, and enormous data storage and cloud computing at high speeds are possible. Amazon's elastic cloud compute has a capacity of storing 200 billion bytes of digital data and has a speed that can process 200,000 requests per se cond.
Actions and interactions as well as interventions and their outcomes in our daily activities generate humongous amount of data. Navigating through this data deluge is difficult. The process of organizing, storing, integrating, and retrieving medical and patient information is traditionally managed through paper-based systems. This data management has transformed significantly since the digital revolution. Conversion of the data from the analog to the digital format has paved the way for the digital revolution and data management.
Some of the recent advances in the digital field like mobile networks, smart phones and apps, wearable devices, cloud computing, and internet of things have made several inroads into the digital healthcare. Electronic records, artificial intelligence (AI), telemedicine and telemonitoring, sensors and wearable devices have made real time monitoring and interventions possible.,,,
Governments and digital technology
Most advanced countries including Australia, Belgium, Canada, Denmark, the United Kingdom and the United States have made the use of electronic health records (EHR) mandatory over the last decade and have heavily invested in health information technologies, including electronic health records. The goal of these initiatives in health information technologies is to digitally transform the collection, display, transmission and storage of patient data. The adoption and meaningful use of data in the EHRs are key objectives of the Health Information Technology for Economic and Clinical Health (HITECH) Act of 2009 and the Federal Health Information Technology Strategic Plan. The Government of India, too, has been advocating digitalization in many fields and has made some beginnings in the digital healthcare as well. The following are some of the steps undertaken:
Let us consider some of the changes that the digital revolution is bringing about in health care.
Many forms of remote consultations and monitoring are being used. The concept of ‘Telemedicine in a Digital Village of Digital India' is contemplated through the Common Service Centers (CSCs) in India, with private entrepreneurs being empowered and encouraged to participate. The Ministry of Health and Family Welfare of India has initiated the use of information and communication technologies (ICT) for improving the efficiency and effectiveness of the public healthcare system and has been working on introducing more of ICT initiatives.
Clinical decision support systems (CDSS)
These are expert systems that link observations with knowledge, to influence choices by clinicians, for improved health care. They support the clinicians at the point of care. They have been a key element of the systems approach, to improving patient safety and the quality of care, and have been an essential requisite for the meaningful use of EHRs. These convert the abstract exercise of reading and appraising the literature into the pragmatic process of the structured usage of literature to benefit individual patients, while simultaneously expanding the clinician's knowledge base. iSyNCC  is an example that supports neuro-critical care. Closed loop AI systems  that control the ventilatory settings are also available. Different image-guided and computer-assisted “neuronavigation” systems have been developed to provide precise spatial information to neurosurgeons during surgery.
Wearable technologies  using sensors that monitor and communicate using internet and global positioning system (GPS) coordinates, connect the patient and the healthcare provider in real time, and have a great impact on health care. Self-monitoring of the fitness and well-being of subjects, more so during their domiciliary care, as well as providing clinical support on a remote basis, has become a reality. Sensors that monitor hand washing, activity tracking devices like the ‘fit-bit’, daily medication organizers like the ‘pill box’, glucose monitors and insulin pumps, smart watches, health patches as well as blood pressure, peripheral capillary oxygen saturation (SPO2) and other vital parameter monitoring devices and alert systems are already in use.
Internet of things and tele-healthcare
The ‘internet of things' (IoT) is a network of devices, embedded with electronics, software, and sensors that enable them to exchange and analyze data. They gather, share, and at times, intervene in real time at the point of care. Wireless sensors monitor and communicate information to mobile platforms that analyze, alert and initiate action that may be carried out by machines or human responses. They handle large data at great speeds with a great impact.
‘E call’ is an integrated alert system used in the European Union, that initiates a call from the site of accident, operates via a satellite station, informing the GPS coordinates to the rescue and intervention teams, the nearby health care center, the tertiary center as well as an ambulance team.
The artificial intelligence
The machine learning, as AI is otherwise called, is the latest trend in digital technology that provides intelligent automated diagnostic or management tools. Mobile technology, added to AI, is tending to substitute the specialist in providing digital healthcare in remote areas. The Food and Drug Administration (FDA) in the USA has recently approved the AI-powered software to detect diabetic retinopathy., AI has made significant inroads into the radiological assessment of patients. Michalski  stated that a computer's vision is one of the most advanced aspect of AI. Its algorithms surpass human ability in terms of distinguishing finer details of processing, and in characterizing features present in radiological imaging.
Electronic Health Records (EHR)
An electronic health record (EHR) is a digital version of a patient's paper chart. This definition has been stated on the official website of the Office of the National Coordinator for Health Information Technology (ONC). EHR is a real-time, patient-centered record that makes information available instantly and securely to authorized users. While an EHR contains the medical and treatment histories of patients, it goes beyond the standard clinical data collected by a provider and is inclusive of a broader view of a patient's care. EHRs can contain a patient's past and current medical history, diagnosis, medications, treatment plans, immunization dates, allergies, radiological images, and laboratory and test results.
It also provides access to evidence-based tools  that health providers can access, to make decisions about a patient's care; it also facilitates an enhanced decision support, as well as clinical alerts and reminders. It helps to make medical information safer, is more reliable for dispensing medications, and improves convenience for patients by sending e-prescriptions electronically to the pharmacy. Apart from providing point-of-care information, it also offers reminders that notify providers of important health interventions, as well as referral information and patient portals for follow-up care. The physicians choose their diagnosis and are immediately connected with the “knowledge page,” a collection of evidence-based library resources. Each resource is automatically populated with search results based on the chosen diagnosis and permits a positive response to the “knowledge page.”
Acceptance of EHRs
While the advanced technologies and digital devices are well received by the healthcare providers, the universal acceptance of the EHRs is far from target. The extra time that a doctor spends to fill these records is often at the expense of compromising his time with the patients. The administrative and other financial liabilities, and the automatic introduction of accountability by the usage of EHRs are resisted by doctors. Evaluating the direct clinical face time spent with the patients and clinical staff, the time spent in maintain the EHRs, and the desk work time spent while being involved in administrative and other tasks, Sinsky et al.,25 observed that physicians spend twice as much time wrestling with EHRs than they do in providing care to patients during the office day. For every hour spent with the patients, the doctors have ended up spending two hours in record-keeping. Lack of a clear standardization, the non-uniform governmental policies, the paucity of trained professionals in the field of medical informatics, and the non-acceptability of EHRs during the judicial process, further limit their acceptance by the health care professional. The amount of coordination and infrastructural needs that the application of EHRs demands, and the doubts raised regarding the confidentiality of information preserved in the EHRs, are its serious drawbacks. Peter Pronovost, the Senior Vice President for Clinical Strategy at the United Healthcare  observed that, “Medicine today invests heavily in information technology, yet the promised improvement in patient safety and productivity frankly has not been realized.” A report from the American EHR Partners and the American Medical Association (AMA), shows that compared to five years ago, more physicians report being dissatisfied or very dissatisfied with their EHR systems. The survey on the physicians' use of the EHR systems (2014) found that more than half of all respondents reported that their EHR system had a negative impact on costs, efficiency or productivity.,,,
Are we ready for these changes?
Is there an unspoken fear among caregivers that all this exercise is a devaluation of the human element? The average patient is not interested in getting a robot handle his annual exam; nor is the doctor thrilled to turn over his rounds to an algorithm. This is a delicate transition for everyone, and it is important that we do not mistake the technical changes performed during the maintenance of EHRs as a move for the marginalization of medical professionals. In the editorial in Lancet, ‘Is digital medicine different?', the editor referred to Jeremy Hunt, the erstwhile UK Secretary for Health and Social Care, who had acknowledged that while technology has been transforming many sectors, the health sector has remained comparatively unchanged. UK's track record for delivering on large digital projects is poor, perhaps most notably exemplified by the scrapping of care.data, an expensive single National Health scheme (NHS) database, over confidentiality concerns. UK's Royal College of General Practitioners (RCGP) has urged data safeguards and adequate resourcing and called for a rigorous and independent evaluation to ensure the safety and cost-effectiveness of EHR. “Continuing to argue for digital exceptionalism and failing to robustly evaluate digital health interventions, presents the greatest risk for patients and health systems,” the editorial stated. Are we comfortable with the idea of a machine looking over our shoulder in our practice?
An increasing use of the EHR, and at the same time, an increasing physician burnout has been seen in the recent years. This association between the introduction and the maintenance of EHRs is not a coincidence, and is in part, responsible for pushing clinicians to retire early, or to change to other careers. The system often forces them to spend more time pushing papers rather than in treating patients. With many countries taking up a ‘top-down' policy of insisting on digital healthcare, Robertson et al., stated in their publication that the international experience, including that of England, shows that neither the ‘top-down' nor the ‘bottom-up' approach is likely to achieve the goals. They do admit that the vision of a nationwide adoption of digital health records and of introducing a transformation based upon information technology is good; however, it needs to be an incremental and iterative process over many years and there is a need for flexibility and local adaptability. Moving to electronic healthcare infrastructure could help to reduce an epidemic of iatrogenic harms, but hasty implementation has led to suboptimal systems that may jeopardize the clinician-patient relationship.
Newer developments in EHRs
Newer developments to improve the functionality of EHR and delegation of data entry to support teams spares the time of a physician. Employing EHR scribes  cuts the physician documentation time in half. Speech-to-text technology helps the physicians in saving time. Voice recognition tools, which are primarily used to dictate reports and clinical notes into the EHR, have become the mainstay technology for providers in certain diagnostic disciplines, including radiology and pathology. Speech-to-text application is also rapidly growing popular among clinicians practicing in the inpatient setting and in primary care. These applications rely upon natural language processing (NLP), a type of machine learning, to turn sound into text. “Give them back their time to care,” said Bresnick. Scroll-down menus for data entry also save time. Cloud based EHRs,, when compared to on-premise based EHRs, have added AI systems that respond to questions and furnish data like drug dosage, interactions and reactions. These AI systems provide answers after reviewing evidence-based data on various diseases as a part of the EHR. In the case of cloud-based EHRs, all software and clinical data are stored, shared and updated in the cloud, providing medical practices with benefits that traditional EHR software systems cannot deliver. With a conventional software platform, information is siloed, and is usually limited to users that are in the same physical location as the software and servers.,,,,,
What is the role of health care providers?
How careful are we, the clinicians, the laboratory staff and other health care provider teams in data recording at the stage of its accruing? Do we record the deficiencies, errors, personal bias in ordering tests and their interpretation? Are the complications and untoward reactions reported and recorded? With advances in mobile technology, digital patient monitoring and tele-healthcare, there is need for constant upgrading and for providing provisions for real-time interoperability between the patient's data and EHR. We all know the value of data and the vigilance to be maintained at the point of care - where it is generated. The details, the quality, its reliability, and totality, including a report on the unexpected events, complications and interpretations need proper documentation.
Providers and organizations collect, track, store, and transmit personal health information. They must be able to distinguish between the chaff-and-the-grain while going through the abundant data, to determine what is meaningful, and try for the integration of data. Adequate care in documentation of data generated by patients, with self-monitoring and a constant evaluation of the care teams, taking the help of various mobile apps, with proper validation of the sources, and the incorporation of the data in a EHR system are essential. The data generated from the clinicians and their associates and laboratories forms the base data available for incorporation in EHRs. It is regrettably observed that there is much to be said regarding the carrying out of this responsibility by health care personnel. The comments of the former editor of New England Journal of Medicine  reflect the rather unfortunate situation. He feels sorry to state that it is no longer possible to believe much of clinical research, a conclusion he reached as an editor for over two decades, of this prestigious journal. Majority of the data goes unpublished, and the data that is actually published does not reflect the true status of the health care issues that it represents, thus reducing its validity. The problem does not seem to be with the analysis but where the data came from, what the impressions and interpretations drawn were, and what the relevance of this data was. Clinical documentation is an essential step in the acquiring of EHR. The successful capture of clinical data and its documentation helps in the accurate presentation of the clinical status in a coded data form. The coded data is, in turn, translated into quality reporting, physician report cards, public health data, and disease tracking and trending data. One should remember the old saying, “If an event is not documented, it did not occur.” The value-based care depends on the validity of knowledge base, the data and the database that goes into the EHR. How much care is exercised by the users of EHR at this stage?
Ethics and EHR
The breach of privacy, the compromise of cyber-security, the hacking and the misuse or exploitation of the data base are the risks that one is exposed to when the private data of an individual is on the cloud and accessible to an expert hacker willing to use it for the wrong purposes.,,, An easy access to records, making of succinct summaries, the presence of rational and reliable data, and ensuring of data privacy and security are the essential components of the work of a health care provider along with other duties of care. The risk to security increases with cloud based EHRs and greater interoperability. Security is a responsibility of the health provider as well as the vendor.
The advanced technologies and digital devices are well received by the health care providers but the universal acceptance of the EHRs seem to be goal that is still far away from being achieved. Adoption of digital health records and information technology based transformation seems to be good, but these processes need to be implemented on an incremental scale. The processes should be constantly undergoing evaluation and modifications over many years. There is also the need for flexibility and built-in protocols for encouraging local adaptability. The transition is a delicate issue for everyone, and it is important that we do not mistake the technical changes that will inevitably be encountered during the adoption of the EHR system as being methods that encourage the marginalization or substitution of medical professionals.
Identification of the deficits of the processes involved in acquiring EHRs and the causes for its nonacceptance; performing adequate research to overcome these deficiencies; the development of a support system; and delegation of the processes to the support teams to spare the vital time of a physician, are needed. The governments should realize that these measures cannot be thrust upon the health-care providers by a top-down policy. More medical and para-medical professionals need to gain knowledge of the advances prevalent in health informatics. Adequate training of the health-care providers, and the exercising of adequate care in valid clinical record-keeping are important measures for the EHRs to gain universal acceptance. Otherwise, a step in the right direction and a tool for meaningful use of abundant data goes awry and the investments and efforts would be unnecessarily wasted.
This paper forms a part of Dr. B. Dayananda Rao Oration delivered in the annual meet of Andhra Pradesh Neuro Scientists Association held at Kakinada on 10th June 2018.