Main bottlenecks and solutions of artificial intelligence decision system in burn field

doi:10.3877/cma.j.issn.1673-9450.2019.06.002

Abstract

Abstract:

Artificial intelligence decision-making faces 3 bottlenecks before it goes into burn treatment: big data, deep learning and medical ethics. How to maintain data stabiliy in long-term acquisition and select scientific methods for analysis and judgement. Which kinds of material should be studied and analyzed by deeping learning. How to overcome the long-term difference between artificial intelligence machine and doctor training. Under the situation of rapid development of big data and artificial intelligence, the ethical shortcomings are increasingly reflected. The main way to solve the 3 problems is: the initiative to build a data model platform together with data scientists should be taken, and the basic circuit diagram of data adoption should be developed. Meanwhile, it is urgent for the national committee of burns to formulate the ethical rules of big data and artificial intelligence.

Key words: Burns, Artificial intelligence, Data interpretation, statistical, Problem solving

Qin Zhang. Main bottlenecks and solutions of artificial intelligence decision system in burn field[J]. Chinese Journal of Injury Repair and Wound Healing(Electronic Edition), 2019, 14(06): 406-409.

/ / Recommend

Add to citation manager EndNote|Ris|BibTeX

URL: https://zhssyxfzz.cma-cmc.com.cn/EN/10.3877/cma.j.issn.1673-9450.2019.06.002

https://zhssyxfzz.cma-cmc.com.cn/EN/Y2019/V14/I06/406

References 15

[1]	李海航，包振兴，刘晓彬，等. 人工智能在烧伤领域的应用研究进展[J]. 中华烧伤杂志，2018, 34 (4): 246-248.
[2]	Celi LA, Hinske LC, Alterovitz G, et al. An artificial intelligence tool to predict fluid requirement in the intensive care unit: a proof-of-concept study[J]. Crit Care, 2008, 12 (6): R151.
[3]	Golas SB, Shibahara T, Agboola S, et al. A machine learning model to predict the risk of 30-day readmissions in patients with heart failure: a retrospective analysis of electronic medical records data[J]. BMC Med Inform Decis Mak, 2018, 18(1): 44.
[4]	Yoshioka A. Use of randomisation in the Medical Research Council's clinical trial of streptomycin in pulmonary tuberculosis in the 1940s[J]. BMJ, 1998, 317(7167): 1220-1223.
[5]	Jones DS, Podolsky SH. The history and fate of the gold standard[J]. Lancet, 2015, 385(9977): 1502-1503.
[6]	Feinstein AR, Horwitz RI. Double standards, scientific methods, and epidemiologic research[J]．N Engl J Med, 1982, 307(26): 1611-1617.
[7]	Howard R, Lovestone S, Levy R. Ernest Saunders: diagnostic dilemma[J]. BMJ, 1992, 304(6841): 1568-1569.
[8]	Bhagat S, Kapatkar V, Katare S, et al. Potential Risks and Mitigation Strategies During the Conduct of a Clinical Trial: An Industry Perspective[J]. Rev Recent Clin Trials, 2018, 13(1): 52-60.
[9]	Celi LA, Lokhandwala S, Montgomery R, et al. Datathons and Software to Promote Reproducible Research[J]. J Med Internet Res, 2016, 18(8): e230.
[10]	张政波，薛万国，曹德森，等. 急救大数据与Datathon活动[J]. 中华危重病急救医学，2018, 30(6): 603-605.
[11]	Adama M, Ng EYK, Tan JH, et al. Computer aided diagnosis of diabetic foot using infrared thermograhpy: A review[J]. Comput Biol Med, 2017, 91: 326-336.
[12]	Shortliffe EH, Sepúlveda MJ. Clinical Decision Support in the Era of Artificial Intelligence[J]. JAMA, 2018, 320(21): 2199-2200.
[13]	Salerno J, Knoppers BM, Lee LM, et al. Ethics, big data and computing in epidemiology and public health[J]. Ann Epidemiol, 2017, 27(5): 297-301.
[14]	Gordijn B, Have HT. Technology and dementia[J]. Med Health Care Philos, 2016, 19(3): 339-340
[15]	Van den Hoven J, Lokhorst GJ, Van de Poel I. Engineering and the problem of moral overload[J]. Sci Eng Ethics, 2012, 18(1): 143-155.

Please choose a citation manager

Content to export