By Michelle Petersen
The novel coronavirus outbreak, named COVID19, has decimated the world and its markets, with the second wave of the pandemic expected imminently, and the virus already experiencing antigenic drift at an alarming rate. This global epidemic has led to the implementation of social distancing and lockdowns, establishing a strong environmentally-friendly, more health-conscious social movement. The global pandemic has also led to even more urgency to convert multi-site clinical studies into virtual or decentralized trials, where participants conduct the evaluation in the comfort of their own home staying in remote contact with clinical staff. Presently the majority of clinical studies are based in the center of busy cities causing problems involving accessibility for many participants living more than two hours from a trial site or who are too ill to travel. This level of physicality also compromises social distancing measures and creates serious issues in terms of patient diversity. Therefore, virtual trials capable of achieving high patient retention rates and accurate results, whilst providing maximum benefits for its participants are highly desired.
Artificial Intelligence or AI is the practice of building computational systems capable of intelligent reasoning. AI is viewed by many as a magic bullet for the inception and optimization of completely decentralized trials as well as patient diversity, recruitment, and adherence. However, this technology is often convoluted by unstandardized definitions and the slew of software currently available on the market. The first step is to 'unclutter' the terminology, people can often get bogged down by types, techniques, and methods under the umbrella of AI. So let's start by uncomplicating things, there are only a minute amount of AI architectures, even less when counting those applicable for healthcare. If you're currently overpowered by massive lists of 'AI', the chances are you're viewing a table of software or apps all utilizing the same small number of AI mathematical models available, possibly using them in conjunction with each other.
For health the main types of AI used are:
These systems are then mixed and matched depending on the task such as:
AI has the potential to disrupt every stage of the clinical trial process, from matching eligible patients to studies to monitoring adherence and data collection. Patient recruitment is a highly selective process, even where participants have volunteered to partake in trials, with the prerequisite that all candidates must be verified using intensive analysis of electronic records gained from medical facilities. NLP and ML methods are currently earmarked to improve processes such as electronic phenotyping, a patient recruitment method focused on reducing heterogeneity in clinical trials through the analysis of Electronic Health Records (EHR). It is thought AI could make electronic phenotyping so sensitive by gathering and dissecting relevant health data in EHR, they could mirror the results of a genetic test in the future. I won't start reeling off stats for patient recruitment and adherence as we all know the figures are dire and currently costing hundreds of millions of dollars, so let's jump straight into the available and hypothesized solutions, as well as the causes. Public awareness of clinical trials and what they entail is incredibly low, affecting patient recruitment greatly, therefore fielding patient's EHR is often posited as the usual solution. This would ensure patient suitability by using NLP & ML to scan EHR for key phrases, different disease stages, and diagnostics, whilst providing individualized patient selection as well as meticulous quality checks for participant retention and adherence. However, this method is fraught with hurdles involving data protection and undefined information making up EHR.
IBM estimate medical data doubled every seventy-three days in the run-up to 2020, with Accenture predicting a three hundred percent rise in health data between 2017-2020, thus the long-feared big tsunami has arrived, overpowering clinical staff, leaving crucial medical information washed up, missed and inaccessible in its wake. Luckily AI never fatigues, possessing the same standardized mood to go through masses of data, extracting salient patient details with ease, however, this is only when structured data is used and there is express permission to do so. Structured data is information stored and displayed in a consistent manner using organized databases and spreadsheets with labeled fields such as weight, disease type, or dates. Unfortunately, it is currently approximated a staggering eighty percent of all existing medical information is recorded as typed or written text, photos, radiological images, pathology slides, video, audio, streaming device data, PDF files, faxes, PowerPoint slides, and emails. This is known as unstructured data, highly valuable, yet unlabelled, difficult to store, search, and interpret. This unspecified material is usually converted into labeled structured data using DL, NLP, and CV, a time-consuming process that may lead to the clinical trial missing enrollment deadlines, a massive issue for the pharmaceutical industry. Therefore, another solution is needed here such as ensuring clinical trials give patients the most benefit and best experience possible, it is only in this way optimal results will occur. Let's discuss how to make this happen.
There is no doubt the future of gathering health data lies with wearables and mobile apps containing inbuilt personal data permission forms such as those found in Apple Health. However, the sensitivity of current mobile health devices limits the amount and precision of data collected, a problem for active clinical trials where medically approved diagnostics are a prerequisite to provide continuous data. Continuous data is where multiple data values and different types of measurements are taken continuously over a set range, in this case, clinical trial longevity. In theory, this is a wearable that doesn't switch off over many years monitoring multiple health data fields, hypothetically they should provide a range as opposed to a set point in time as the data is unceasing. This continuous data is expected to precede the dawn of Continuous Learning (CL), an expanded version of TL using NN or DL, where the machine is progressively learning across infinite data fields and measurements, constantly updating and analyzing, endowed with the ability to pick up any discrepancies in milliseconds. CL is expected to produce incredibly sensitive and raw precision- data for participants, furnishing them with individualized whole-system information, as well as raising quality-control for adherence and endpoint results until wearables reach the correct level of exactitude. Logic would dictate the ranges produced by this hypothetical CL will also lead to far larger, structured, datasets. Currently, various methodologies are being employed across multiple industries to increase the amount of structured data in their electronic record systems. Simplistic in their ingenuity these techniques are cost-efficient, easy to implement, and quick to carry out. One such technique involves expanding the number of automated services for patient or customer communications. Examples include chatbots, invoicing and even telephone calls where the recipient is unaware an AI-bot has just phoned them or answered their call. Increasing automated customer services and its resulting records leads to centrally available data, gathered, labeled, and stored by AI as opposed to unlabelled, dark processed data produced by humans. Another proven shortcut to structured records is the conversion of e-mail attachments of any type into Portable Document Format (PDF) files upon receipt. The resultant library of formatted PDF files can be reproduced in the same way, regardless of the conversion software used. Traditionally PDF files are viewed as unstructured data, however, as they can be decomposed into standard components outlining database relationships and structure, they are often viewed as semi-structured data. An even bigger improvement would be the immediate conversion of e-mail contents and attachments using PDF/A. PDF/A is an ISO-standardized PDF system used in the long-term archiving of electronic documents prohibiting features unsuitable for lengthy storage, such as encryption or linking fonts across documents. Automated input management systems are now capable of recognizing all common formats of e-mail attachments and converting them into PDF/A. This standardized central archive allows the extraction of the desired data from documents using the appropriate AI mechanics.
Specifically, pattern recognition, part of both computer vision and NLP, can be used to extract the data from these standardized documents. Pattern recognition incorporates ML, NN OR DL, and employs many biometric attributes such as image recognition, handwriting recognition, facial recognition, as well as diagnosis and medical imaging extraction. In this way, it can Identify and label patterns or objects from different angles, even when they are partially hidden. This ML also possesses the capability to recognize and classify a person's handwriting, making it easier to decipher and label. As you can see the unsung hero that is biometrics is used in many different areas of clinical trials and electronic records, the next section will talk a bit more about this versatile 'jack of all trades'.
Patient adherence is perhaps the most accurate indicator of participant fallout in clinical trials. Therefore, systems monitoring participation and/or adherence to treatments being evaluated are a vital part of the study, albeit one of the hardest to monitor, a statement dropout and trial failure rates will attest to. Easy-to-swallow pill trackers are currently being investigated in regards to patient adherence, as are hard-to-fool nanopore wearables utilizing nanoscale precision for various analytes. It is hoped the sensitivity of data collection and adherence will improve through the use of synthetic biology to build DNA computers that live in the body, able to monitor the whole host system, sense disease, and release drugs on command. These programmed synthetic DNA complexes are primed for AI incorporation due to their vast capacity for storage, encoding data very concisely onto their base-pair sequence strands, as opposed to using binary language like their electrical counterparts. As DNA computers are made of synthetic biological matter there is no survival rate with scientists predicting these biocomputers could, in theory, store encoded information for millions of years outside of the human body. These exobiologics have already been successfully programmed to store data, perform basic mathematical sums, and even carry out tasks with Caltech designing a DNA computer whose hardware was successfully reconfigured to run different software. The six-bit DNA computer-executed reprogrammable algorithms ranging from copying and sorting processes, generating random walks, and executing cellular automata. A team from MIT has also programmed human and bacterial cells with the ability to keep a record of complex molecular events over a long length of time. Their DNA biocomputer, dubbed DOMINO, is a human-CRISPR cellular chimera extending the utility of molecular recording beyond DNA write-only applications. Their astrobiologic successfully carried out long-term recording and monitoring of in vivo molecular events, which could one day evolve into AI-based sensors capable of detecting, and possibly even treating, diseased cells, as well as incorporating patient adherence facilities. However, these programmable molecules are a long way off whereas readily available AI biometrics can easily be utilized to check dosage adherence where present-day urine samples or wearables may be easily tampered with. Biometrics allows a person to be identified based on a unique set of biological data specific to them and is thought of as a natural part of everyday life with many companies and personal products now employing these verification systems. Biometrics is not based on AI, however, DL, ML, or TL is usually integrated into this technology to train, analyze, and decode systems, making them much smarter and a lot quicker.
The main types of biometrics are based on:
Biometrics, in turn, can be mixed and matched with AI such as:
Concerning clinical trials, fingerprint-based identification facilities could be made available for patients to sign into their records and results, as well as dosage verification systems. Most importantly this ensures only the patient can sign into their trial results outside of the main site, giving them peace of mind over their data. As people now use fingerprint biometrics multiple times a day to sign into their smartphone they should be fully accustomed to this added security, and may even feel uncomfortable with their data being left vulnerable without added protective measures. Like a fingerprint, an iris scan also provides unique biometric data that is very difficult to duplicate and remains the same over a lifetime. The scan can sometimes be difficult for children or the infirm, however, AI can encode the scan data into a barcode format to add extra security to portable carded-entry systems. This commonplace technology already exists as a biometric voter verification system requiring the insertion of a unique barcode card and a fingerprint to vote. Friendly virtual avatars could also work well for patient adherence, innocuously interacting without judgment whilst evaluating patient behavioral attributes and patterns. The U.S. Department of Homeland Security has funded research for Discern Science International's deception detection tool named 'AVATAR'. This features a virtual border guard that asks travelers questions to detect any suspicious behavior consistently without fatiguing, with AVATAR's basic interview and decision-making facility taking seconds. AVATAR has been tested since 2011 by border services in airports across the U.S., Canada, and the European Union in separate trials of different durations resulting in a deception detection rate of 80-85%, far outperforming human agents. AVATAR combines advanced statistics, ML, sensors, and biometrics to flag untruthful individuals or those who pose a potential risk. It does so by filming a person’s responses whilst analyzing information including their facial expressions, tone of voice, and verbal responses, to flag deception signals. Homeland Security state AVATAR can easily be adapted, allowing different interview content to be scientifically designed and tested for contrasting situations, and plan to commercialize the technology in multiple industries. Initial markets for the AVATAR system will be at airports, municipal buildings, large stations, and sports stadiums, with plans to expand. As their system is based on a kiosk it can be transported and installed in any location, perhaps a local hospital or doctor's office or rented office of your choice, it is unclear whether this AI is transferable to personal computers. This aside the person's use of biometric science could also denote a greater dedication to the trial; patients may also react more positively to an interactive avatar as opposed to a real person watching them via a video system to check their adherence every day, which could be construed as quite Orwellian. Overall it is clear these biometric systems are quietly working themselves into all of our lives both at work and at home.
Despite the many promising software solutions available there is no way to avoid the most crucial aspects of evolving AI here, namely, the simulation of tests or trials using open repositories containing ML datasets and/or non-identifying labeled patient data. This is a method used by other industries for many years with pharmaceutical companies quietly consulting and partnering with virtual reality producers known to have mastered AI simulation, even allowing ML to run their companies in some cases. Simulation and open repositories are the only way forward in improving clinical investigations whilst raising the level of AI integration in ever decentralized trial systems, needing no approval from patients to use their data when doing so. There is a multitude of free simulation datasets easily accessible online such as the one found at OpenML, where ML files can be downloaded and uploaded. There are also countless opensource labeled medical databases such as this useful list built on Github by Dr. Andrew Beam, Assistant Professor, Harvard School of Public Health, as well as an open-access medical image library with a small number of ML datasets included, curated by Stephen R. Aylward, Ph.D. Of Kitware. These simulations guarantee you can still design, train, evolve and integrate AI into clinical trials that are so patient-centric the participants you do have permission to treat won't leave early and will readily adhere to treatment, all the while avoiding data protection restrictions through the use of these open datasets. This is the first step in the solution, the good old-fashioned practice of consumer reviews and word-of-mouth to spread the news about great clinical trials participants find highly constructive, easy-to-follow, and wholly interesting whilst gaining unparalleled whole-body results to take with them. Remember I mentioned a computerized induction into clinical trials for participants by way of online gamification, where the patients get to act out their trial virtually in my earlier posts? Well, the information from this individualized induction could not only be upgraded via immersive technologies such as Virtual Reality (VR), the results could also be plugged back into your AI simulations to help predict levels of patient adherence and endpoint results.
Immersive technologies or Extended Reality (XR) is a software emulating either the physical world or a simulated world via a headset feeding sensory information into the eyes whilst adding haptics and/or auditory feedback to immerse the user in an alternate reality. XR can be incorporated into AI, however, it is not based on artificial intelligence.
The main types of XR are:
XR, in turn, can be mixed and matched with AI such as:
XR has also been established as a positive distraction technique with AR and VR content used to provide stress relief. This is achieved by applying ML, as well as biometric-based facial, emotion, and voice recognition software to create an immersive game experience, adapting to the patient’s response and emotional state, to ease stress and anxiety. This could prove to be a game-changer for patient enhancement and retention in clinical trials. The most obvious application for XR is holographic telepresence between participants and their clinical team making the interaction more personalized, immersing both parties into the meeting. This premise has been upgraded by Silver Chain and Saab Australia, the manufacturers of a simple lightweight headset employing Enhanced Medical Mixed Reality technology to ‘holoport’ clinicians into patients’ homes. Their MR-based science allows the patient to view full holograms of their clinical team at a separate location without the need for bulky holographic studios and projectors. The XR system also provides holographic diagnostics in real-time which can be viewed by both the patient and clinical team simultaneously, allowing the participant to receive virtual medical consults on command. This Microsoft HoloLens-based facility is now being used as a foundation to build Australia's first virtual hospital, although Johns Hopkins Neurosurgeons may beat them to the finish line after performing the world's first AR surgery. The surgeons used the Augmedics xvision Spine System, consisting of a headset with a see-through eye display projecting images of the patient’s internal anatomy, such as bones and connecting blood vessels. In effect, the AR guidance system allows surgeons to visualize the 3D spinal anatomy of a patient during surgery as if they had x-ray vision, permitting them to accurately navigate instruments and implants while looking directly at the patient, as opposed to a remote screen. Thus, full-body avatars providing whole-body diagnostics in real-time for participants in the comfort of their own home is set to become a reality. It is hoped this XR will give rise to self-service tools and diagnostics capable of virtual interaction, utilizing same-day pickup drones, XR-based instructions, and virtual practice-runs, with this technology proven to enhance learning and knowledge uptake. This experience should be boosted even further through the use of AR and MR to completely immerse individuals into their personalized version of the trial, gifted with the power to securely check their medical status at any time using state-of-the-art science.
There is also much work being performed in the burgeoning field of Brain-Computer Interfaces (BCI), an invasive implant in the brain paired with NN or DL to amalgamate the native central nervous system with machines. BCIs are primarily used to integrate prosthetics into the nervous system transforming them into neuroprosthetics, allowing the patient to control artificial limbs or implants using thought alone. These machine-neural interfaces have also been used to restore the sense of touch to paralyzed human limbs and to help those patients without the capacity for speech to communicate. This field has been slowly moving towards non-invasive BCI using electroencephalograms (EEG) to reach circuits deep within the brain to control a robotic arm, opening many doors for trials investigating neurological disorders. These neuroscientific slanted investigations are paramount to clinical trial development as it is anticipated they will be the very first individualized trials due to past problems preventing a one-size-fits-all experience, rule-based diagnostics and treatment path caused by uncharacteristic behaviors and emotions exhibited by patients.
It is predicted non-invasive BCI with the capacity to record activity in the deep recesses of the brain will enable a more automated classification of patients with mental disorders through the identification of individual components and characteristics associated with their disease severity. These BCIs could also be incorporated into XR systems to stimulate regions contained within the brain involved in 3D and 4D devices, heightening immersion. Most recently non-invasive electronic smart glasses incorporating a BCI have been designed by Korea University. The e-glasses integrate AI to monitor a person's brain waves, postures, and movement. The portable BCI can also function as sunglasses allowing users to control XR applications with eye motions, possessing multiple points of crossover regarding systems currently being utilized in clinical trials. This exciting discipline doesn't stop there, with direct information exchange between brains achieved non-invasively via Brain-to-Brain interfaces (BBIs). BBIs in humans are computer interfaces combining neuroimaging and neurostimulation to extract and share information between brains, allowing direct brain-to-brain communication. Specifically, BBIs extract the salient content from the neural signals of a ‘Sender’ brain, digitizes it and delivers it to a ‘Receiver’ brain. Existing human BBIs rely on non-invasive technologies, typically EEG, to record neural activity, and transcranial magnetic stimulation to deliver information to the brain.
Great inroads are being made in this sphere, for instance, The University of Washington has engineered a BBI enabling three people to work together to solve a problem using only their minds. Their BrainNet BBI enabled multi-person collaborative problem-solving for three people to play a Tetris-like game. In clinical trials, this BBI could potentially enable cooperative problem solving by humans using a social network of connected brains in different locations, perhaps used in conjunction with XR. The science also exists to train AI and gain opinions from just the brainwaves of participants. Here the University of Helsinki engineered a BCI capable of evaluating opinions and drawing conclusions based on the brain activity of groups of people alone. The team states their technique, dubbed ‘brainsourcing’, can be used to label images or recommend preferred content by analyzing neural signals which can later be plugged into ML recognition software to train AI. Taken altogether brainsourcing proffers another great option for structuring data, monitoring patient adherence, and designing AI-based clinical trials. Through the incorporation of the above-mentioned technologies and mathematical frameworks, those who participate in clinical trials can expect a more holistic and immersive experience, providing opportunities for continuous learning whilst receiving quality individualized care with exclusive results that cannot be gained from any other medical facility. Personalized interactive medical reports, virtual health data, and status visualizations capable of being uploaded or downloaded should greatly add to the patient-experience. The introduction to high-end approved technology, some of which may not be readily available on the open market, will also ensure your participants gain the utmost benefit from trials, raising adherence. To conclude, it is these symbiotic changes involving patient-centricity and improved clinical trial design that will also afford the medical team with the most accurate results possible in larger datasets. This, in turn, should furnish the patient with the opportunity to carry forward an empowering and eye-opening experience, gifting greater ownership over their health and data.
Michelle Petersen is the founder of Healthinnovations, having worked in the health and science industry for over 21 years, including medical and scientific posts within the NHS and Oxford University. She has held positions in the field, working in private, non-profit, and academic laboratories where she taught Oxford undergraduates the spectrum of biological sciences integrating physics for over four years.
Healthinnovations is a publication that has reported on, influenced, and researched current and future innovations in health for the past decade. The success of this brand has resulted in Michelle Petersen currently being featured and indexed by numerous prestigious brands and publishers worldwide. You can follow her on Twitter at @OriginateHealth.
