Artificial intelligence in healthcare

X-ray of a hand, with automatic calculation of bone age by a computer software.

Artificial intelligence (AI) in healthcare is the use of algorithms and software to approximate human cognition in the analysis of complex medical data. Specifically, AI is the ability for computer algorithms to approximate conclusions without direct human input.

What distinguishes AI technology from traditional technologies in health care, is the ability to gain information, process it and give a well-defined output to the end-user. AI does this through machine learning algorithms, which can recognize patterns in behavior and create its own logic. In order to reduce the margin of error, AI algorithms need to be tested repeatedly. AI algorithms behave differently from humans in two ways: (1) algorithms are literal: if you set a goal, the algorithm can’t adjust itself and only understand what is has been told explicitly,  (2) and algorithms are black boxes; algorithms can predict extremely precise, but not the cause or the why. [1]

The primary aim of health-related AI applications is to analyze relationships between prevention or treatment techniques and patient outcomes.[2] AI programs have been developed and applied to practices such as diagnosis processes, treatment protocol development, drug development, personalized medicine,and patient monitoring and care. Medical institutions such as The Mayo Clinic, Memorial Sloan Kettering Cancer Center[3], Massachusetts General Hospital[4], and National Health Service,[5] have developed AI algorithms for their departments. Large technology companies such as IBM[6] and Google[5], and startups such as Welltok and Ayasdi,[7] have also developed AI algorithms for healthcare.

History

Research in the 1960s and 1970s produced the first problem-solving program, or expert system, known as Dendral.[8] While it was designed for applications in organic chemistry, it provided the basis for the subsequent system MYCIN,[9] considered one of the most significant early uses of artificial intelligence in medicine.[9][10] MYCIN and other systems such as INTERNIST-1 and CASNET did not achieve routine use by practitioners, however.[11]

The 1980s and 1990s brought the proliferation of the microcomputer and new levels of network connectivity. During this time there was recognition by researchers and developers that AI systems in healthcare must be designed to accommodate the absence of perfect data and build on the expertise of physician.[12] Approaches involving fuzzy set theory,[13] Bayesian networks,[14] and artificial neural networks,[15][16] have been applied to intelligent computing systems in healthcare.

Medical and technological advancements occurring over this half-century period that have simultaneously enabled the growth healthcare-related applications of AI include:

Current Research

Various specialties in medicine have shown an increase in research regarding AI. However the specialty that has gained the greatest attention is the field of Radiology.[24]

Radiology

Such an ability to interpret imaging results may allow clinicians to be aided to detect a change in an image that is minute in detail, or something that a clinician may have accidentally missed. Such a study that has incorporated AI in radiology is a study at Stanford which has results presenting that the algorithm that they created can detect Pneumonia better than radiologists[25]. The radiology conference Radiological Society of North America has implemented a large part of its schedule to the use of AI in imaging. The emergence of AI technology in the radiology discipline is perceived as a threat by some specialists, as the technology can perform certain tasks better than human specialists, changing the role radiologists have currently. [26][27]

Telehealth

The increase of Telemedicine, has shown the rise of possible AI application.[28] The ability to monitor patients using AI, may allow for the communication of information to physicians if possible disease activity may have occurred. The use of a device such that a person may wear, may allow for constant monitoring of a patient and also for the ability to notice changes that may be less distinguishable by humans.

Industry

The subsequent motive of large based health companies merging with other health companies, allow for greater health data accessibility.[29] Greater health data may allow for more implementation of AI algorithms.[30]

A large part of industry focus of implementation of AI in the healthcare sector is in the clinical decision support systems. [31] As the amount of data increases, AI decision support systems become more efficient. Numerous companies are exploring the possibilities of  the incorporation of big data in the health care industry [32].

The following are examples of large companies that have contributed to AI algorithms for use in healthcare.

IBM

IBM's Watson Oncology is in development at Memorial Sloan Kettering Cancer Center and Cleveland Clinic.[33] IBM is also working with CVS Health on AI applications in chronic disease treatment and with Johnson & Johnson on analysis of scientific papers to find new connections for drug development.[34]

Microsoft

Microsoft's Hanover project, in partnership with Oregon Health & Science University's Knight Cancer Institute, analyzes medical research to predict the most effective cancer drug treatment options for patients.[35] Other projects include medical image analysis of tumor progression and the development of programmable cells.[36]

Google

Google's DeepMind platform is being used by the UK National Health Service to detect certain health risks through data collected via a mobile app.[37] A second project with the NHS involves analysis of medical images collected from NHS patients to develop computer vision algorithms to detect cancerous tissues.[38]

Intel

Intel's venture capital arm Intel Capital recently invested in startup Lumiata which uses AI to identify at-risk patients and develop care options.[39]

Startups

IDx's first solution, IDx-DR founded by Michael Abramoff, is the first and only FDA authorized AI system for the autonomous detection of diabetic retinopathy. As an autonomous, AI-based system, IDx-DR is unique in that it makes an assessment without the need for a clinician to also interpret the image or results, making it usable by health care providers who may not normally be involved in eye care. IDx is a leading AI diagnostics company on a mission to transform the quality, accessibility, and affordability of healthcare world-wide.

Medvice provides real time medical advice to clients, who can access and store their Electronic Health Records (EHRs) over a decentralized blockchain[40]. Medvice uses machine learning aided decision making to help physicians predict medical red flags (i.e. medical emergencies which require clinical assistance) before serving them. Predictive Medical Technologies uses intensive care unit data to identify patients likely to suffer cardiac incidents.[33] Modernizing Medicine uses knowledge gathered from healthcare professionals as well as patient outcome data to recommend treatments.[41] "Compassionate AI Lab" uses grid cell, place cell and path integration with machine learning for the navigation of blind people.[42] Nimblr.ai uses an A.I. Chatbot to connect scheduling EHR systems and automate the confirmation and scheduling of patients.[43]

Other

Digital consultant apps like Babylon in the UK use AI to give medical consultation[44] based on personal medical history and common medical knowledge. Users report their symptoms into the app, which uses speech recognition to compare against a database of illnesses. Babylon then offers a recommended action, taking into account the user’s medical history.

Regulation

While research on the use of AI in healthcare aims to validate its efficacy in improving patient outcomes before its broader adoption, its use may nonetheless introduce several new types of risk to patients and healthcare providers, such as algorithmic bias, Do not resuscitate implications, and other machine morality issues. These challenges of the clinical use of AI has brought upon potential need for regulations.[45]

Currently no regulations exist specifically for the use of AI in healthcare. In May 2016, the White House announced its plan to host a series of workshops and formation of the National Science and Technology Council (NSTC) Subcommittee on Machine Learning and Artificial Intelligence.[46] In October 2016, the group published The National Artificial Intelligence Research and Development Strategic Plan, outlining its proposed priorities for Federally-funded AI research and development (within government and academia). The report notes a strategic R&D plan for the subfield of health information technology is in development stages.[47]

The only agency that has expressed concern is the FDA. Bakul Patel, the Associate Center Director for Digital Health of the FDA, is quoted saying in May 2017.

“We're trying to get people who have hands-on development experience with a product's full life cycle. We already have some scientists who know artificial intelligence and machine learning, but we want complementary people who can look forward and see how this technology will evolve.”[48]

Government investment

Investments from the US government in healthcare initiatives that will rely on AI[46] include its $1B proposed budget for the Cancer Moonshot[49] and $215M proposed investment in the Precision Medicine Initiative.[50]

See also

References

  1. ↑ "Algorithms Need Managers, Too". Harvard Business Review. 2016-01-01. Retrieved 2018-10-08.
  2. ↑ Coiera, E. (1997). Guide to medical informatics, the Internet and telemedicine. Chapman & Hall, Ltd..
  3. ↑ Power, B. (March 19, 2015). Artificial Intelligence Is Almost Ready for Business. Retrieved from https://hbr.org/2015/03/artificial-intelligence-is-almost-ready-for-business
  4. ↑ Bahl, Manisha (June 27, 2017). "High-Risk Breast Lesions: A Machine Learning Model to Predict Pathologic Upgrade and Reduce Unnecessary Surgical Excision". Radiology. 286 (3): 810–818. doi:10.1148/radiol.2017170549. PMID 29039725.
  5. 1 2 Bloch-Budzier, S. (November 22, 2016). NHS using Google technology to treat patients. Retrieved from https://www.bbc.com/news/health-38055509
  6. ↑ Lorenzetti, L. (April 5, 2016). Here's How IBM Watson Health is Transforming the Health Care Industry. Retrieved from http://fortune.com/ibm-watson-health-business-strategy/
  7. ↑ CB Insights Artificial Intelligence report. (June 28, 2016). Retrieved from https://www.cbinsights.com/reports/CB-Insights-Artificial-Intelligence-Webinar.pdf
  8. ↑ Lindsay, R. K., Buchanan, B. G., Feigenbaum, E. A., & Lederberg, J. (1993). DENDRAL: a case study of the first expert system for scientific hypothesis formation. Artificial intelligence, 61(2), 209-261.
  9. 1 2 Clancey, W. J., & Shortliffe, E. H. (1984). Readings in medical artificial intelligence: the first decade. Addison-Wesley Longman Publishing Co., Inc..
  10. ↑ Bruce, G., Buchanan, B. G., & Shortliffe, E. D. (1984). Rule-based expert systems: the MYCIN experiments of the Stanford Heuristic Programming Project.
  11. ↑ Duda, R. O., & Shortliffe, E. H. (1983). Expert systems research. Science, 220(4594), 261-268.
  12. ↑ Miller, R. A. (1994). Medical diagnostic decision support systems—past, present, and future. Journal of the American Medical Informatics Association, 1(1), 8-27.
  13. ↑ Adlassnig KP. A fuzzy logical model of' computer-assisted medical diagnosis. Methods Inf Med. 1980; 19:14
  14. ↑ Reggia, J. A., & Peng, Y. (1987). Modeling diagnostic reasoning: a summary of parsimonious covering theory. Computer methods and programs in biomedicine, 25(2), 125-134.
  15. ↑ Baxt, W. G. (1991). Use of an artificial neural network for the diagnosis of myocardial infarction. Annals of Internal Medicine, 115(11), 843-848.
  16. ↑ Maclin, P. S., Dempsey, J., Brooks, J., & Rand, J. (1991). Using neural networks to diagnose cancer. Journal of Medical Systems, 15(1), 11-19.
  17. ↑ Koomey, J., Berard, S., Sanchez, M., & Wong, H. (2011). Implications of historical trends in the electrical efficiency of computing. IEEE Annals of the History of Computing, 33(3), 46-54.
  18. ↑ Dinov, I. D. (2016). Volume and value of big healthcare data. Journal of medical statistics and informatics, 4.
  19. ↑ Barnes, B., & Dupré, J. (2009). Genomes and what to make of them. University of Chicago Press.
  20. ↑ Jha, A. K., DesRoches, C. M., Campbell, E. G., Donelan, K., Rao, S. R., Ferris, T. G., ... & Blumenthal, D. (2009). Use of electronic health records in US hospitals. New England Journal of Medicine, 360(16), 1628-1638.
  21. ↑ Banko, M., & Brill, E. (2001, July). Scaling to very very large corpora for natural language disambiguation. In Proceedings of the 39th annual meeting on association for computational linguistics (pp. 26-33). Association for Computational Linguistics.
  22. ↑ Dougherty, G. (2009). Digital image processing for medical applications. Cambridge University Press.
  23. ↑ "Artificial Intelligence and Machine Learning for Healthcare" Sigmoidal, December 21, 2017. https://sigmoidal.io/artificial-intelligence-and-machine-learning-for-healthcare/.
  24. ↑ "Artificial Intelligence in Radiology: The Game-Changer on Everyone's Mind". Radiology Business. Retrieved 2018-04-10.
  25. ↑ Rajpurkar, Pranav; Irvin, Jeremy; Zhu, Kaylie; Yang, Brandon; Mehta, Hershel; Duan, Tony; Ding, Daisy; Bagul, Aarti; Langlotz, Curtis (2017-11-14). "CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning". arXiv:1711.05225 [cs.CV].
  26. ↑ Chockley, Katie; Emanuel, Ezekiel (December 2016). "The End of Radiology? Three Threats to the Future Practice of Radiology". Journal of the American College of Radiology. 13 (12): 1415–1420. doi:10.1016/j.jacr.2016.07.010. ISSN 1546-1440.
  27. ↑ Jha, Saurabh; Topol, Eric J. (2016-12-13). "Adapting to Artificial Intelligence". JAMA. 316 (22): 2353. doi:10.1001/jama.2016.17438. ISSN 0098-7484.
  28. ↑ Pacis, Danica (February 2018). "Trends in telemedicine utilizing artificial intelligence". AIP Conference Proceedings. AIP Conference Proceedings. 1933: 040009. doi:10.1063/1.5023979.
  29. ↑ Monica, Paul R. La. "What merger mania means for health care". CNNMoney. Retrieved 2018-04-11.
  30. ↑ "Why You're the Reason For Those Health Care Mergers". Fortune. Retrieved 2018-04-10.
  31. ↑ Horvitz, Eric J.; Breese, John S.; Henrion, Max (July 1988). "Decision theory in expert systems and artificial intelligence". International Journal of Approximate Reasoning. 2 (3): 247–302. doi:10.1016/0888-613x(88)90120-x. ISSN 0888-613X.
  32. ↑ "What Doctor? Why AI and robotics will define New Health" (PDF). pwc global. June 2017. Retrieved 8 October 2018. line feed character in |title= at position 38 (help)
  33. 1 2 Cohn, Jonathan. "The Robot Will See You Now." The Atlantic, March 2013. https://www.theatlantic.com/magazine/archive/2013/03/the-robot-will-see-you-now/309216/.
  34. ↑ Spear, Andrew. "From Cancer to Consumer Tech: A Look Inside IBM's Watson Health Strategy." Fortune, April 5, 2016. http://fortune.com/ibm-watson-health-business-strategy/.
  35. ↑ Bass, Dina. "Microsoft Develops AI to Help Cancer Doctors Find the Right Treatments." Bloomberg, September 20, 2016. https://www.bloomberg.com/news/articles/2016-09-20/microsoft-develops-ai-to-help-cancer-doctors-find-the-right-treatments.
  36. ↑ Knapton, Sarah. "Microsoft Will 'Solve' Cancer within 10 Years by 'Reprogramming' Diseased Cells." The Telegraph, September 20, 2016. https://www.telegraph.co.uk/science/2016/09/20/microsoft-will-solve-cancer-within-10-years-by-reprogramming-dis/.
  37. ↑ Bloch-Budzier, Sarah. "NHS Using Google Technology to Treat Patients." BBC News, November 22, 2016. https://www.bbc.com/news/health-38055509.
  38. ↑ Lee, Chris Baraniuk, Dave. "Google DeepMind Targets NHS Head and Neck Cancer Treatment." BBC News, August 31, 2016. https://www.bbc.com/news/technology-37230806.
  39. ↑ Primack, Dan. "Intel Capital Cancels $1 Billion Portfolio Sale." Fortune, May 26, 2016. http://fortune.com/2016/05/26/intel-capital-cancels-1-billion-portfolio-sale/.
  40. ↑ Medvice Official Website
  41. ↑ Hernandez, Daniela. "Artificial Intelligence Is Now Telling Doctors How to Treat You." WIRED, June 2, 2014. https://www.wired.com/2014/06/ai-healthcare/.
  42. ↑ Ray, Amit. "Artificial Intelligence for Assisting Navigation of Blind People". Inner Light Publishers. Retrieved 18 May 2018.
  43. ↑ Proffitt, Cas (Mar 8, 2017). "Top 10 Artificially Intelligent Personal Assistants". Disruptor Daily.
  44. ↑ Parkin, Simon (9 March 2016). "The Artificially Intelligent Doctor Will Hear You Now". MIT Technology Review. Retrieved 14 April 2018.
  45. ↑ "Artificial Intelligence in Health Care: Applications and Legal Issues". Petrie-Flom Center. Retrieved 2018-04-11.
  46. 1 2 Felten, Ed. "Preparing for the Future of Artificial Intelligence." Whitehouse.gov, May 3, 2016. https://www.whitehouse.gov/blog/2016/05/03/preparing-future-artificial-intelligence.
  47. ↑ "The National Artificial Intelligence Research and Development Strategic Plan." Office of Science and Technology Policy, October 16, 2016. https://www.nitrd.gov/PUBS/national_ai_rd_strategic_plan.pdf.
  48. ↑ "FDA Assembles Team to Oversee AI Revolution in Health". IEEE Spectrum: Technology, Engineering, and Science News. Retrieved 2018-04-04.
  49. ↑ Office of the Press Secretary. "At Cancer Moonshot Summit, Vice President Biden Announces New Actions to Accelerate Progress Toward Ending Cancer As We Know It." Whitehouse.gov, June 28, 2016. https://www.whitehouse.gov/the-press-office/2016/06/28/fact-sheet-cancer-moonshot-summit-vice-president-biden-announces-new.
  50. ↑ Office of the Press Secretary. "President Obama's Precision Medicine Initiative." Whitehouse.gov, January 30, 2015. https://www.whitehouse.gov/the-press-office/2015/01/30/fact-sheet-president-obama-s-precision-medicine-initiative.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.