International Defense Security & Technology Your trusted Source for News, Research and Analysis
Related Articles
Artificial Intelligence technologies aim to develop computers, or robots that match or exceed the abilities of human intelligence in tasks such as learning and adaptation, reasoning and planning, decision making and autonomy; creativity; extracting knowledge and making predictions from data.
Within AI is a large subfield called machine learning or ML. Machine Learning enables computers with capability to learn from data, so that new program need not be written. Machine learning Algorithms extract information from the training data to discover patterns which are then used to make predictions on new data.
Artificial intelligence expands the availability and quality of data leading to improved policy decisions for the benefit of society. Precision medicine can extend life and enhance quality of life. Smart vehicles may save thousands of lives every year worldwide and increase mobility for the elderly and those with disabilities. Personalized and precise educational content can improve the learning.
Artificial intelligence (AI) is revolutionizing healthcare or the way physicians treat patients and deliver care. AI can be used in healthcare systems to improve workflow and enhance patient care. AI can help healthcare providers identify potential risks and complications earlier, recommend treatments more accurately, and automate administrative tasks.
An AI system can assist physicians by providing up-to-date medical information from journals, textbooks, and clinical practices to inform proper patient care.
Doctors are already using A.I. to spot potentially lethal lesions on mammograms. Scientists are also developing A.I. systems that can diagnose common childhood conditions, predict whether a person will develop Alzheimer’s disease and monitor people with conditions like multiple sclerosis and Parkinson’s disease.
All these diseases are leading causes of death; therefore, early diagnoses are crucial to prevent the deterioration of patients’ health status. Furthermore, early diagnoses can be potentially achieved through improving the analysis procedures on imaging, genetic, EP or EMR, which is the strength of the AI system. This category of AI devices includes machine learning (ML) techniques that analyse structured data such as imaging, genetic and EP data. In the medical applications, the ML procedures attempt to cluster patients’ traits, or infer the probability of the disease outcomes.
In 2020, digital acceleration went into overdrive as the global pandemic pushed us faster, and further, into the Data Age. In response to the COVID-19 pandemic, the White House and a coalition of leading research groups have prepared the COVID-19 Open Research Dataset (CORD-19). CORD-19 is a resource of over 200,000 scholarly articles, including over 100,000 with full text, about COVID-19, SARS-CoV-2, and related coronaviruses. This freely available dataset is provided to the global research community to apply recent advances in natural language processing and other AI techniques to generate new insights in support of the ongoing fight against this infectious disease.
The market for artificial intelligence in healthcare has witnessed major increase in demand due to the coronavirus pandemic. Its usage minimizes the risk of transmission as it limits human interaction and shields frontline workers. Pharmaceutical companies are among the primary companies adopting AI for development of vaccines and to study different strains of the virus.
AI has been used to develop sophisticated computer models that can help identify potential drug targets and generate more effective treatments. This technology is also being put to use in the development of clinical trials and patient management systems.
In addition, AI can help hospitals reduce costs by automating certain processes. For example, hospitals can use AI to automate billing and data entry. This will save hospitals a lot of time and money. By automating processes and providing insights into patient history, AI will significantly improve the quality of care delivered to patients. Additionally, by reducing costs and improving efficiency, AI will play an important role in making healthcare more affordable for everyone involved.
Chatbots can help healthcare providers better serve their customers by automating customer service tasks. For example, a chatbot could be used to handle inquiries about health insurance or hospital admissions. According to a study by Greenwich Associates, customer service chatbots could render up to $1 billion in savings for healthcare providers over the next five years. Additionally, chatbots can help providers improve customer satisfaction ratings. In fact, a study by the Convergence Consulting Group found that 73% of customers would be more likely to recommend a provider if they had positive interactions with a chatbot.
Health care sector is also prime target for cyber attacks with breaches of privacy and security.
AI Applications in healthcare
Medical diagnosis.
AI applications significantly improve the speed and accuracy of the diagnosis. AI tools help to analyze survey data more quickly and accurately, allowing doctors to be more accurate with diagnoses and to see more patients. Today, AI-based image recognition diagnostic devices are already used to diagnose dermatological and optical deviations, diabetes and other diseases which cause appearance changes.
Today’s health care companies have substantial amounts of information at their disposal, from claims and clinical data to consumer information. Imagine the possibilities if we were to apply this data to how we diagnose and treat patients.
AI system can help to reduce diagnostic and therapeutic errors that are inevitable in human clinical practice. Somashekhar et al demonstrated that the IBM Watson for oncology would be a reliable AI system for assisting the diagnosis of cancer through a double-blinded validation study. Esteva et al analyzed clinical images to identify skin cancer subtypes. Bouton et al developed an AI system to restore the control of movement in patients with quadriplegia. Dilsizian and Siegel discussed the potential application of the AI system to diagnose heart disease through cardiac image. Arterys recently received clearance from the US Food and Drug Administration (FDA) to market its Arterys Cardio DL application, which uses AI to provide automated, editable ventricle segmentations based on conventional cardiac MRI images.
Partner of the London Medical Imaging & AI Centre for Value Based Healthcare (Ai4VBH), AINOSTICS, has been awarded Breakthrough Device Designation by the US Food and Drug Administration (FDA) to its product, BR[AI]N™, developed by funding received as part of the collaboration with the AI Centre. The product automates the analysis of medical images such as CT, MRI and PET scans, providing users with the capability to identify subtle, early signs of neurological conditions such as dementia which are often invisible to the naked eye. Currently, these scans are visually inspected by clinicians, a process which is subjective, time-consuming and not reproducible. Consequently, it is not possible to know whether someone has dementia when they are first assessed. Doctors refer to this uncertain situation as ‘mild cognitive impairment’ (MCI).
The number of people living with dementia worldwide is estimated at over 50 million, reaching 82 million in 2030 and is the UK’s leading cause of death, yet it is estimated that only 66 percent of sufferers have received a diagnosis. Even in those who receive a diagnosis, due to the absence of an accurate early diagnostic test, the average time from symptom onset to diagnosis is 3 years.
Optum® is using artificial intelligence (AI) to uncover those possibilities in a pilot with WestMed Medical Group that leverages machine learning to better predict patients with atrial fibrillation. A heart rhythm condition, atrial fibrillation is difficult to detect, particularly in its mildest forms.
In an interview with Business Insider, Steve Griffiths, senior vice president and chief operating officer of Optum Enterprise Analytics, explained how leveraging AI can help develop applications that are useful in diagnosing, and treating, patients. “Analytics isn’t the end, it’s the beginning.” says Griffiths. “It’s what you do with it to drive care improvement, quality improvement.”
UK researchers have created a new Artificial Intelligence (AI) tool that can detect Covid-19.
The software analyses chest CT scans and uses deep learning algorithms to accurately diagnose the disease. With an accuracy rate of 97.86 per cent, it’s currently the most successful Covid-19 diagnostic tool in the world, said the team of University of Leicester.
Currently, the diagnosis of Covid is based on nucleic acid testing, or PCR tests as they are commonly known. These tests can produce false negatives and results can also be affected by hysteresis – when the physical effects of an illness lag behind their cause. AI, therefore, offers an opportunity to rapidly screen and effectively monitor Covid cases on a large scale, reducing the burden on doctors.
“Research focuses on the automatic diagnosis of Covid-19 based on random graph neural networks. The results showed that our method can find the suspicious regions in the chest images automatically and make accurate predictions based on the representations,” said Yudong Zhang, Professor of Knowledge Discovery and Machine Learning at the varsity.
Altoida’s Alzheimer’s-predicting smartphone app
Altoida’s technology uses artificial intelligence to analyze cognitive test results to determine whether a case of mild cognitive impairment will escalate into Alzheimer’s within a year.
It comprises a slate of neurological tests for users aged 55 and up and AI software to analyze the results of those tests. The assessment portion of the system takes 10 minutes to complete and can be accessed on a user’s own smartphone or tablet. It focuses on measuring 11 specific areas of the brain research has suggested are linked to the onset of Alzheimer’s.
The augmented reality tests are designed to feel like video games. In one, users are asked to hide three virtual items around the room they’re in, then relocate them at random. Another tasks users with learning the tools and actions needed to simulate a fire evacuation, and the third main activity has them simultaneously locate virtual tools in their environment while a dynamic sound plays intermittently.
Once the tests are complete, Altoida’s AI assesses the results to score the user’s risk of developing Alzheimer’s within the next year. It produces a full cognitive report based on hand and gait movements and errors, eye tracking and pupil dilation, voice parameters and more.
Diagnosing the condition that early, before symptoms have even begun to appear, could help physicians begin to treat at-risk patients right away, potentially delaying the onset or lessening the severity of the neurodegenerative disease. Travis Bond, CEO of Altoida, believed that a “completely digital solution for predictive Alzheimer’s disease diagnosis” will help meet a swath of urgent needs: more accurate, non-invasive, and cost-effective diagnosis of an increasingly prevalent disease.
The FDA expresses early confidence in Altoida’s investigational tech gadget, designed to predict whether someone will develop Alzheimer’s in the next year. Studies so far show it is 94 percent accurate.
Artificial Intelligence Could Use EKG Data To Measure Patient’s Overall Health Status
In the near future, doctors may be able to apply artificial intelligence to electrocardiogram data in order to measure overall health status, according to new research published in Circulation: Arrhythmia and Electrophysiology, a journal of the American Heart Association. But the potential for AI in health care goes beyond improving patient outcomes — it could bring down the cost of health care.
An electrocardiogram, also known as an EKG or ECG, is a test used to measure the electrical activity of the heart. While it’s known that a patient’s sex and age could affect an EKG, researchers hypothesized that artificial intelligence could determine a patient’s gender and estimate their ‘physiologic age’ — a measure of overall body function and health status distinct from chronological age.
Using EKG data of almost 500,000 patients, a type of artificial intelligence known as a convolutional neural network was trained to find similarities among the input and output data. Once trained, the neural network was tested for accuracy on the data of an additional 275,000 patients by predicting the output when only given input data.
The neural network estimated a patient’s chronological age as higher after experiencing adverse health situations such as heart attack, low ejection fraction and coronary artery disease, and lower age if they experienced few or no adverse events.
“While physicians already consider whether a patient ‘appears [their] stated age’ as part of their baseline physical examination, the ability to more objectively and consistently assess this may impact healthcare on multiple levels,” said study author Suraj Kapa, M.D., assistant professor of medicine and director for Augmented and Virtual Reality Innovation at Mayo Clinic in Rochester, Minnesota.
Being able to more accurately assess overall health status may help doctors determine which patients they should examine further to determine if there are asymptomatic or currently silent diseases that could benefit from early diagnosis and intervention. For people at large, an AI-enhanced electrocardiogram could better show there may be something going on such as a new health issue or comorbid condition that they were otherwise unaware of,” continued Kapa.
Researchers discovered that the artificial intelligence was able to accurately determine a patient’s gender 90% of the time and could determine the chronological age group of a patient with 72% accuracy.
“This evidence — that we might be gleaning some sort of ‘physiologic age’ — was certainly both surprising and exciting for its potential role in future outcomes research, and may foster a new area of science where we seek to better understand the biologic underpinnings of such a finding,” Kapa said.
While the study was able to draw from a large sample size, all individuals in the study were patients, and EKGs were administered for another clinical indication. Future studies with an overtly healthy population are needed to revalidate the neural network’s determination. Additionally, gender in the study was self-identified by patients and may not represent the sex of all individuals in the study.
Genomic-Based AI Technology
GE Healthcare and SOPHiA GENETICS have signed a letter of intent to collaborate on developing genomic-based artificial intelligence technology to advance cancer care. The goal of the technology is to better target and match a patient’s treatment based on her specific genomic profile and cancer type.
By using GE Healthcare’s extensive medical imaging capabilities and the SOPHiA DDM analytic genomic insight platform, the new artificial intelligence system will work to serve both the clinical and biopharma markets. As cases of cancer continue to rise, there is an increasing demand for data-driven medicine. GE Healthcare will use its Edison platform to integrate data from several different resources, including the EHR, radiology information systems (RIS), imaging, and other medical device data.
“The integration of genomics-based artificial intelligence into oncology workflow solutions would be a major breakthrough for integrated cancer medicine and for future clinical research, which increasingly depend on the ability to select those patients most likely to respond to new therapies,” Jan Makela, President & CEO, Imaging at GE Healthcare said in a press release.
GE Healthcare said it brings to the table a deep understanding of clinical workflows, learning AI algorithms for image reconstruction and segmentation, analytics, and standardization. Meanwhile, SOPHiA GENETICS is an institution in data-driven medicine. SOPHiA GENETICS’ cloud-based analytic platform software uses AI and machine learning to develop actionable insights for clinicians and researchers from complicated datasets. Working together, these companies hope to break down the data silos across instruments and sites that often delay or prevent patients from receiving the best treatment for their condition.
Medical product development.
The process of research and development of new drugs is very slow and expensive. Pharmacists need to take into account hundreds of variables starting from financial appropriateness and finishing with legal and ethical issues. Today, AI is used to safely explore chemical and biological interactions in the drug discovery process based on early-stage clinical data. Among the most prominent examples here are IBM Watson and GNS Healthcare AI system used in the search of cancer treatment.
Workflow optimization.
AI helps to automate such repetitive tasks as routine paperwork, scheduling, and time-sheet entry. These are the task which medical staff often consider to be the most tiresome and frustrating because of their monotony. By augmenting human performance, A.I. has the potential to markedly improve productivity, efficiency, work flow, accuracy and speed, both for doctors and for patients. giving more charge and control to consumers through algorithmic support of their data.
AI has the potential to improve patient care by automating tasks and providing recommendations. For example, a system could automatically generate a list of medications for a patient based on their medical history and current medication prescriptions. AI could also help physicians make more informed decisions about patients’ care. For example, an AI-powered system could suggest preventive measures or treatments based on an analysis of a patient’s medical history.
– The second category includes natural language processing (NLP) methods that extract information from unstructured data such as clinical notes/medical journals to supplement and enrich structured medical data. The NLP procedures target at turning texts to machine-readable structured data, which can then be analysed by ML techniques.
Natural language processing (NLP)
AI can use sophisticated algorithms to ‘learn’ features from a large volume of healthcare data, and then use the obtained insights to assist clinical practice. It can also be equipped with learning and self-correcting abilities to improve its accuracy based on feedback. Moreover, an AI system extracts useful information from a large patient population to assist making real-time inferences for health risk alert and health outcome prediction.
The increasing availability of healthcare data and rapid development of big data analytic methods has made possible the recent successful applications of AI in healthcare. Guided by relevant clinical questions, powerful AI techniques can unlock clinically relevant information hidden in the massive amount of data, which in turn can assist clinical decision making.
But while AI exhibits great promise, many of its practical health care applications are at an early stage. However, one area of AI — natural language processing (NLP) — is having a transformative impact today, and the case for using NLP to improve the revenue cycle is strong.
Clinical documentation provides the fuel by which health care organizations drive much of their operations. Patient interactions with providers are often brief, and when they leave a provider’s care, the only lasting evidence of the patient encounter resides in the medical record documentation. NLP can automatically review electronic patient records for relevant data to help ensure that clinical documentation is complete, so that the NLP-assigned codes are accurate.
NLP technology, combined with clinical models and rules engines, can capture and “understand” the context and meaning implicit in medical records, and thoroughly review millions of clinical documents every day. The ability of artificial intelligence to fully understand both the structured and unstructured data in medical records is critical to effective documentation review. Most of the information in the record is unstructured, meaning recorded as free-form narrative about the patient’s care. Clinically intelligent NLP unlocks the unstructured content to provide the structured data elements, including the diagnoses, procedures, findings, labs and drugs, and outcomes that comprise complete and accurate clinical documentation. Data from unstructured sources complement the structured data to create a more complete picture of a patient’s health. At the same time, the ability to handle a variety of different formats and narrative structures places as few constraints as possible on those providing the source documentation.
The right NLP technology can automate complex, time-consuming processes to dramatically increase efficiency and accuracy in critical areas. For example, intelligent automation can power comprehensive clinical documentation improvement and coding — and do it earlier in the revenue cycle —supporting accuracy, efficiency and revenue integrity. Clinically intelligent natural language processing will have far-reaching organizational impact.
Internet of Medical Things (IoMT)
AI will also be used to enhance the Internet of Medical Things (IoMT). Developing Internet of Medical Things (IoMT) strategies that match sophisticated sensors with AI-backed analytics will be key for developing the smart hospitals – and smart homes – of the future. “Sensors, artificial intelligence, big data analytics, and blockchain are vital technologies for IoMT as they provide multiple benefits to patients and facilities alike,” Varun Babu, Senior Research Analyst, TechVision, told tech writer Jennifer Bresnick, in a review of the Frost & Sullivan report.
Several breakthrough technologies have taken place in 2019, with the World Economic Forum (WEF) identifying the prominent role IoMT has played in the healthcare industry. It gives an example of a pill with a tiny sensor, that transmits information to a patch on the patients arm when taken, with the resulting information then relayed to a mobile phone which is monitored by a doctor to ensure medication is taken at the correct frequency and time.
Similarly, the MIT Technology Review has identified several groundbreaking technologies such as a revolutionary blood test to predict premature births; a swallowable probe making it easier to screen for gut disease; personalised cancer vaccines which can reprogram the body to attack cancerous cells; EKG-enabled smartwatches; and voice assistants in clinics.
Future Potential
In the future it will enable Brain Science, as Dr. Daniel Barron points out in his new book, “Reading Our Minds: The Rise of Big Data Psychiatry,” our generation faces the supreme challenges of applying such technologies to the brain and to the disciplines of behavior and mental health. The last great challenges of 21st-century medicine lie in the workings of the mind and the brain. Moreover, such challenges are testing the social and psychological fabric of societies, as we witnessed during the COVID-19 pandemic.
In Future AI is predicted to aid in personalized nutrition by determining the best diet for every individual. There are emerging data to support this possibility, such as avoiding glucose spikes after eating, which are highly individualized, much more common than anticipated, and related to the specific foods we take in and our gut microbiomes.
Artificial Intelligence in Healthcare Market
The AI in the healthcare market is expected to grow from USD 3.39 Billion in 2019 to USD 61.59 Billion by 2027, at a CAGR of 43.6%. The huge availability of big data, growing number of cross-industry partnerships and collaborations is fueling the growth of the Artificial Intelligence market. In addition, demand to reduce the imbalance between the healthcare workforce and patients is further supplementing the growth of the AI in the healthcare market.
Hospitals and physician providers will be the major investors in machine learning and artificial intelligence solutions and services, the report predicts. The healthcare sector is developing rapidly and using artificial intelligence to increase productivity and reducing the burden on healthcare workers.
“A few major factors responsible for the high share of the hospitals and providers segment include a large number of applications of AI solutions across provider settings; ability of AI systems to improve care delivery, patient experience, and bring down costs; and growing adoption of electronic health records by healthcare organizations,” noted the summary of the report.
“Moreover, AI-based tools, such as voice recognition software and clinical decision support systems, help streamline workflow processes in hospitals, lower cost, improve care delivery, and enhance patient experience.” Natural language processing (NLP) tools will play an important role in bringing these improvements to providers. NLP can translate speech into text, extract concrete data elements from unstructured input, and power chatbots that offer customer service or even basic triage for low-level complaints.
AI is used in healthcare sector for analysis of complex diagnostic and medical data. These services will be valuable to consumers seeking more convenient, on-demand access to care as well as among providers looking to reduce their keyboard time and simplify interactions with their electronic health records (EHRs).
Using artificial intelligence to create more intuitive, user-friendly workflows is a top goal for EHR developers moving into 2019, especially as provider burnout continues to rise and dissatisfaction with existing products hits a fever pitch. Combining machine learning with medical-grade or consumer-facing devices may exponentially increase the impact of both technologies, noted a report from Frost & Sullivan in 2018.
Artificial Intelligence in planning and scheduling methods can offer substantial support to the management of hospitals and patient care, thereby improving administrative workflow assistance. AI-enabled bots is an AI application that patients can interact with through a chat window on a website or through a telephone. Applications such as scheduling appointments; checking insurance coverage parameters; instantly accessing information about drug interactions and side effects; collecting the latest information about patient medications, care team, and recent procedures; designing special diet plans for patients with dietary restrictions; and engaging with discharged patients to follow up on treatment plans and adherence are supported by these bots. These applications are expected to lead the growth of in-patient care and hospital management systems.
Increasing need for hardware platforms with high computing power to run various AI software is the key factor accelerating the growth for hardware devices in the AI in healthcare market. Demand for high-computing processors to run AI algorithms continues to surge its growth in the hardware segment. The processor segment consists of MPUs, GPUs, FPGAs, and ASICs. In processors, GPUs are expected to foresee strong growth owing to high parallel computing capabilities, and the same is expected to continue in the coming years.
The development of more sophisticated hard and soft sensors has accelerated the growth of context-aware processing. Increased processing power, innovative sensing capabilities, and improved connectivity have resulted in the growth of context-aware processing systems. A few core healthcare applications include lifestyle management and monitoring, in-patient care and hospital management, and virtual assistant.
North America, being a developed and technologically advanced region, is likely to be one of the key contributors to the overall AI in healthcare market growth during the forecast period. Moreover, high spending of GDP in healthcare, especially in the US and Canada, is likely to supplement the growth of next-gen technologies such as AI in the region. APAC is likely to closely pursuit the growth of North America and is expected to register the second-fastest growth rate. Improving IT infrastructure, demand for affordable healthcare, and favorable government norms are expected to boost the growth of healthcare AI in the region.
AI in the healthcare Industry
AliveCor, with their Mayo Clinic collaboration, was able to develop deep learning algorithms to determine a person’s blood potassium levels via a smartwatch ECG signal. For tech titans, Google AI and its DeepMind division has done some impressive work that includes accurately triaging urgent eye conditions, predicting outcomes in the hospital setting, and an important prospective study of pathology slides in cancer, says Topol.
A few companies in the AI in healthcare market are NVIDIA (US), Intel (US), IBM (US), Google (US), Microsoft (US), AWS (US), General Vision (US), GE Healthcare (US), Siemens Healthineers (Germany), Medtronic (US). The market has active participation of start-ups. A few emerging start-ups in the market are CloudMedx (US), Imagia Cybernetics (Canada), Precision Health AI (US), and Cloud Pharmaceuticals (US).
IBM is among the leading companies in the AI in healthcare market. The company’s Watson is widely used by end users for cognitive computing and data-driven applications. IBM follows organic as well as inorganic growth strategies to improve its position in AI in healthcare and other emerging AI markets. The company has invested ~USD 6 billion to make 15 acquisitions in cognitive, cloud, and security businesses. Also, partnerships/collaborations with AI solution providers/consumers remain the important aspects of the company’s strategy to enhance its footprint in the AI market. The company continues to strengthen its position through strategic organic investments and acquisitions in higher value areas, broadening its industry expertise and integrating AI into more of what the company offers. Moreover, the company focuses on developing core AI products, especially for enterprises and large businesses-e.g., the launch of Power Systems Servers to deliver AI services for enterprises in December 2017.
References and Resources also include:
https://www.webuters.com/robotics-and-artificial-intelligence-is-transforming-healthcare-industries
