Patients experienced out-of-pocket increases as high as 12% for their healthcare costs last year, according to a new analysis by TransUnion Healthcare.
Technology experts have promised artificial intelligence (AI) and machine learning (ML) will revolutionize healthcare. Applications have the potential to streamline workflows and reduce human errors, speeding drug discovery, assisting surgery, and provisioning better billing and coding methods. But, in an industry that typically lags in digital maturity by as much as 10 years, according to a 2017 study, is AI in healthcare an empty promise or truly a forward-thinking and innovative reality?
Searching for ‘artificial intelligence (AI) in healthcare’ produces nearly 1B results. It seems every healthcare industry expert has an opinion on how to revolutionize patient treatments, from drug development to clinical decision support systems (DSS). The applications for ML/AI in healthcare are seemingly infinite—in this article, we’ll take a look at specific use cases and whether implementation is realistic for future practice.
AI For Drug Discovery – Fact
From discovery and research to final production, the full process for bringing a drug to market usually lasts 10-15 years and costs approximately $2.6B. While only 14 percent of all new drug candidates reach testing and gain FDA approval, medication developers and manufacturers are already investing heavily in AI as a way to discover new drug compounds quicker—with less miscalculations—leading to higher approval ratings. Growth in this area will continue to boom.
With such a lengthy and expensive process to bring a new drug to market, discovery must be streamlined to make the correct investments, as at present billions of data points are examined when judging a potential drug candidate. Drug development has historically been an iterative process using high-throughput screening (HTS) labs to physically test thousands of compounds a day, with an expected hit rate of one percent or less. ML /AI in healthcare offers the potential to add efficiency and scale. Machine learning technology is utilized to correlate vast amounts of data, uncover hidden relations, and generate new solutions. These systems are currently being used to search for new candidate compounds, speed complex computer simulations, and propose different routes of synthesis for new drugs.
ICD-11 Mapping and Coding Using AI – Fiction…Soon To Be Fact
ICD-11 is coming. The World Health Organization (WHO) announced in June 2018 the latest list of International Classification of Diseases (ICD-11) and presented the list to Member States in May 2019. The list, which contains four times the number of codes in ICD-10, will come into effect on January 1, 2022, including 10,000 proposals for revisions from ICD-10. This number is impossible for a human to correctly interpret and code.
When ICD-10 was implemented in October 2015, the number of codes rose from 13,000 (ICD-9-CM) to 68,000 (ICD-10-CM), according to the Centers for Medicare and Medicaid Services (CMS). While some healthcare facilities have become early adopters and have begun using some form of natural language processing (NLP) or ML, the majority of facilities still rely solely on human coders. This often leads to inaccuracies in interpreting provider notes, especially with unique codes and modifiers. For example, “pecked by a turkey” is ICD-10 code W61.43, while “pecked by a large chicken” is code W61.43, which may be easily confused by a human coder. Once the provider enters their note, ML /AI in healthcare is better able to determine the correct code and recommend it for reimbursement.
As the number of codes continues to increase with ICD-11, AI/ML is necessary to assist coders in transcribing provider notes and payers needing code validation.
Although ICD-11 will be offered in an electronic, user-friendly version, electronic health records (EHR) vendors will still invest significant development resources to ensure that end users can determine the correct codes. By implementing AI/ML, the system will be able to scan the provider’s notes, determine correct codes, and verify modifiers. Whether this use of AI in healthcare for coding and billing becomes widely adopted by all institutions remains to be seen, but for healthcare facilities looking for more accurate disease classification, the time to implement the solution is now.
Patient Engagement and Health Monitoring – Fact
A recent survey by Pega found that 52 percent of patients are comfortable with their doctors using AI to make healthcare decisions, and 29 percent are comfortable with payers doing so. The survey results show a substantial shift towards more personalized and data-driven patient care and engagement. As patients request more personalization in their care, payers and providers will comply. The push for AI in a patient-centric model will lead to improved care quality, showing a very positive trend for healthcare, in a typically change-resistant industry.
After diagnosing, creating a treatment plan is the next step to providing care. Despite the quality of treatment provided, the onus lies with the patient for compliancy. Medication non-adherence was estimated to cost the United States $528.4B in 2016 alone. AI/ML in Healthcare can identify potential non-compliant patients from several factors: history of non-compliance, limited support networks, adverse lifestyle choices, or limited interactions with their care team. With thousands of patients, with hundreds of protected health information (PHI) data points, and countless contributing factors, it can be impossible for providers and payers to address the ongoing needs of their clients. Using technology, clinicians can take steps to advise and monitor patients differently based on AI recommendations.
AI/ML can also assist in patient adherence. Gamification, payer incentives, and IoT health devices are highly successful tools to supplement motivation efforts. If the patient enjoys interacting with the technology, they will more closely adhere to the program. For example, a 2018 study by the Multidisciplinary Scientific Journal found a 17% improvement in blood glucose levels in children with diabetes when using gamification for tracking. When tracking data points such as blood glucose readings, or steps taken for a weight loss patient, ML /AL in healthcare is necessary to provide a personalized experience and provide immediate feedback and virtual rewards. This is excellent news for the healthcare community and the patient populations they serve.
Patient Diagnosis and Treatment Planning – Fiction
This point might not be so obvious. How can patient diagnosis and treatment planning by artificial intelligence be fiction, especially given the discussion surrounding patient engagement?
The idea of artificial intelligence or machines treating patients, without real human intervention, is unrealistic, and, frankly, unwanted. Even with the most sophisticated algorithms, billions of complex data points, and perfect programming, treatments will always be determined by experienced clinicians, caregivers, and a qualified hands-on team.
AI/ML still plays a critical role in patient prognosis. Clinical decision support and rules engines are successful due to the patient data collected within practice management (PMs) and health information systems (HIS). Repetitive tasks such as analyzing tests, X-rays, CT scans, and data entry are all prime targets for programmed intervention. Cardiology and radiology, for example, are two specialties where vast amounts of data need to be analyzed, creating a huge time burden on technologists. Cardiologists and radiologists can utilize ML/AI in healthcare to read test results and discover trends, but human interaction is necessary for determining treatments, engaging with the patient, and providing the care and support needed to maintain healthy humans.
Better Patient Care, Regardless of The Healthcare Industry – Fact
Data management, virtual assistants, facial recognition, surgical robotics – the list goes on for meaningful and realistic uses of AI/ML in healthcare. The growth of this technology is assured, though when and what applications are adopted, remains to be seen.
The AI in healthcare market is expected to grow from USD 2.1 billion in 2018 to USD 36.1B by 2025, at a CAGR of 50.2% during the forecast period, according to a survey by MarketsandMarkets.As the uses for AI/ML are as vast and varied as the industry itself, leaders need to keep a realistic eye on what is currently available, what’s coming, and what may never be. Value-led care is a primary goal for all healthcare—payers, providers, and life science professionals—and AI/ML is the enabling technology to create the patient-centric care model. Every healthcare company can appreciate the improved ROI that comes with greater efficiency and higher quality experience through digitization.