人工智能支持罕见病诊疗的研究进展

弓孟春; 焦塬石; 马武仁; 刘鹏; 金晔; 胡继发; 牛灵; 史文钊; 张抒扬

doi:10.12376/j.issn.2097-0501.2022.02.003

人工智能支持罕见病诊疗的研究进展

doi: 10.12376/j.issn.2097-0501.2022.02.003

1.
南方医科大学卫生与健康管理研究所, 广州 510515
2.
神州医疗科技股份有限公司，北京 100080
3.
中国医学科学院北京协和医院，北京 100730
4.
武汉市中心医院，武汉 430014
5.
新疆维吾尔自治区人民医院，乌鲁木齐 830011

基金项目:

国家重点研发计划 2020YFC2006400

详细信息

通信作者:
张抒扬, E-mail: shuyangzhang103@163.com

中图分类号: R319;R4
计量
- 文章访问数: 341
- HTML全文浏览量: 172
- PDF下载量: 91
- 被引次数: 0
出版历程
- 收稿日期: 2021-12-13
- 录用日期: 2022-02-09
- 网络出版日期: 2022-06-02

Artificial Intelligence Supports Research Progress in the Diagnosis and Treatment of Rare Diseases

1.
School of Health Management, Southern Medical University, Guangzhou 510515, China
2.
Chinese Academy of Medical Sciences, Digital China Health Technologies Corporation, Beijing 100080, China
3.
Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing 100730, China
4.
The Central Hospital of Wuhan, Wuhan 430014, China
5.
The People's Hospital of Xinjiang Uygur Autonomous Region, Urumqi 830011, China

Funding:

National Key Research and Development Program of China 2020YFC2006400

More Information

Corresponding author: ZHANG Shuyang, E-mail: shuyangzhang103@163.com

摘要

摘要: 在已描述的7000多种罕见疾病中仅有5%找到了治疗方法。大数据时代，随着生物医学数据的不断增加，迫切需要高效快速的数据收集、分析和识别方法。以机器学习为着重点的人工智能应用为罕见病开辟了一条全新的途径，并广泛应用于诊断与治疗。人工智能已经向人们充分展示了其学习和分析来自不同来源的数据并做出可靠预测的能力。目前已有数量可观的人工智能技术应用于罕见疾病的案例，本文旨在总结罕见病中人工智能应用的研究进展。另外，还系统地总结了人工智能应用程序的局限性，并展望了人工智能在罕见病应用领域中的发展。
- 人工智能 /
- 机器学习 /
- 罕见病 /
- 诊断 /
- 治疗 /
- 药物重定位 /
- 药物开发
Abstract: It is noteworthy that only 5% of more than 7000 described rare diseases are treated. In the era of big data, there is ever-increasing data for understanding biomedicine. The need for efficient and rapid data collection, analyses and characterization methods is pressing. Rare diseases can particularly benefit from artificial intelligence (AI) application. AI, with an emphasis on machine learning, creates a path for such efforts and is being applied to diagnosis and treatment. AI has demonstrated its potential to learn and analyze data from different sources with results in prediction。Presently, there are AI-driven technologies applied for rare diseases and this review aims to summarize these advances. Moreover, this review scrutinizes the limitation and identifies the pitfalls of AI applications in the diagnosis and treatment of rare diseases.
- artificial intelligence /
- machine learning /
- rare disease /
- diagnosis /
- treatment /
- drug repositioning /
- drug development
注释:

作者贡献：张抒扬选定研究方向、提出研究选题并负责文章终审工作。弓孟春在研究中为文章设定内容框架并起草主要部分; 焦塬石、马武仁在文章撰写阶段负责调研和整理文献、内容起草及修订; 刘鹏、金晔、胡继发、牛灵、史文钊为文章内容提出了修订建议。

利益冲突：所有作者均声明不存在利益冲突。

HTML全文

参考文献(76)

[1]	Arno PS, Bonuck K, Davis M. Rare diseases, drug development, and AIDS: the impact of the Orphan Drug Act[J]. Milbank Q, 1995, 73: 231-252. doi: 10.2307/3350258
[2]	Franco P. Orphan drugs: the regulatory environment[J]. Drug Discov Today, 2013, 18: 163-172. doi: 10.1016/j.drudis.2012.08.009
[3]	Nguengang Wakap S, Lambert DM, Olry A, et al. Estimat-ing cumulative point prevalence of rare diseases: analysis of the Orphanet database[J]. Eur J Hum Genet, 2020, 28: 165-173. doi: 10.1038/s41431-019-0508-0
[4]	Li X, Lu Z, Zhang J, et al. The urgent need to empower rare disease organizations in China: an interview-based study[J]. Orphanet J Rare Dis, 2020, 15: 282. doi: 10.1186/s13023-020-01568-5
[5]	Wang JB, Guo JJ, Yang L, et al. Rare diseases and legislation in China[J]. Lancet, 2010, 375: 708-709. doi: 10.1016/S0140-6736(10)60240-1
[6]	Rare Diesease Impact Report: Insights from patients and the medical community Shire2013[J/OL]. https://globalgenes.org/wpcontent/uploads/2013/04/ShireReport-1.pdf.
[7]	Yan X, He S, Dong D. Determining how far an adult rare disease patient needs to travel for a definitive diagnosis: A cross-sectional examination of the 2018 national rare disease survey in China[J]. Int J Environ Res Public Health, 2020, 17: 1757. doi: 10.3390/ijerph17051757
[8]	Schaefer J, Lehne M, Schepers J, et al. The use of machine learning in rare diseases: a scoping review[J]. Orphanet J Rare Dis, 2020, 15: 145. doi: 10.1186/s13023-020-01424-6
[9]	Gong S, Wang Y, Pan X, et al. The availability and affordability of orphan drugs for rare diseases in China[J]. Orphanet J Rare Dis, 2016, 11: 20. doi: 10.1186/s13023-016-0392-4
[10]	Ramesh AN, Kambhampati C, Monson JR, et al. Artificial intelligence in medicine[J]. Ann R Coll Surg Engl, 2004, 86: 334-338.
[11]	Barbour AB, Frush JM, Gatta LA, et al. Artificial intelligence in health care: insights from an educational forum[J]. J Med Educ Curric Dev, 2019, 6: 2382120519889348.
[12]	Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level classification of skin cancer with deep neural networks[J]. Nature, 2017, 542: 115-118. doi: 10.1038/nature21056
[13]	Gulshan V, Peng L, Coram M, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs[J]. JAMA, 2016, 316: 2402-2410. doi: 10.1001/jama.2016.17216
[14]	Yu KH, Beam AL, Kohane IS. Artificial intelligence in healthcare[J]. Nat Biomed Eng, 2018, 2: 719-731. doi: 10.1038/s41551-018-0305-z
[15]	Hosny A, Parmar C, Quackenbush J, et al. Artificial intelligence in radiology[J]. Nat Rev Cancer, 2018, 18: 500-510. doi: 10.1038/s41568-018-0016-5
[16]	Jha S, Topol EJ. Adapting to artificial intelligence: radiologists and pathologists as information specialists[J]. JAMA, 2016, 316: 2353-2354. doi: 10.1001/jama.2016.17438
[17]	Yu KH, Levine DA, Zhang H, et al. Predicting ovarian cancer patients' clinical response to platinum-based chemotherapy by their tumor proteomic signatures[J]. J Proteome Res, 2016, 15: 2455-2465. doi: 10.1021/acs.jproteome.5b01129
[18]	Yu KH, Fitzpatrick MR, Pappas L, et al. Omics analysis system for precision oncology (OASISPRO): a web-based omics analysis tool for clinical phenotype prediction[J]. Bioinformatics, 2018, 34: 319-320. doi: 10.1093/bioinformatics/btx572
[19]	Hayden EC. The automated lab[J]. Nature, 2014, 516: 131-132. doi: 10.1038/516131a
[20]	Lasker JN, Sogolow ED, Sharim RR. The role of an online community for people with a rare disease: content analysis of messages posted on a primary biliary cirrhosis mailinglist[J]. J Med Internet Res, 2005, 7: e10. doi: 10.2196/jmir.7.1.e10
[21]	Rajkomar A, Dean J, Kohane I. Machine learning in medicine[J]. N Engl J Med, 2019, 380: 1347-1358. doi: 10.1056/NEJMra1814259
[22]	Alirezaie N, Kernohan KD, Hartley T, et al. ClinPred: prediction tool to identify disease-relevant nonsynonymous single-nucleotide variants[J]. Am J Hum Genet, 2018, 103: 474-483. doi: 10.1016/j.ajhg.2018.08.005
[23]	Papadimitriou S, Gazzo A, Versbraegen N, et al. Predicting disease-causing variant combinations[J]. Proc Natl Acad Sci USA, 2019, 116: 11878-11887. doi: 10.1073/pnas.1815601116
[24]	Bosio M, Drechsel O, Rahman R, et al. eDiVA-classifica-tion and prioritization of pathogenic variants for clinical diagnostics[J]. Hum Mutat, 2019, 40: 865-878. doi: 10.1002/humu.23772
[25]	Boudellioua I, Kulmanov M, Schofield PN, et al. Deep-PVP: phenotype-based prioritization of causative variants using deep learning[J]. BMC Bioinformatics, 2019, 20: 65. doi: 10.1186/s12859-019-2633-8
[26]	Rao A, Vg S, Joseph T, et al. Phenotype-driven gene prioritization for rare diseases using graph convolution on heterogeneous networks[J]. BMC Med Genomics, 2018, 11: 57. doi: 10.1186/s12920-018-0372-8
[27]	Smpokou P, Lanpher BC, Rosenbaum KN. Important considerations in the initial clinical evaluation of the dysmorphic neonate[J]. Adv Neonatal Care, 2015, 15: 248-252. doi: 10.1097/ANC.0000000000000216
[28]	Gurovich Y, Hanani Y, Bar O, et al. Identifying facial phenotypes of genetic disorders using deep learning[J]. Nat Med, 2019, 25: 60-64. doi: 10.1038/s41591-018-0279-0
[29]	Brasil S, Pascoal C, Francisco R, et al. Artificial intelli-gence (AI) in rare diseases: is the future brighter?[J]. Genes (Basel), 2019, 10: 978. doi: 10.3390/genes10120978
[30]	Xu K, Yang Z, Kang P, et al. Document-level attention-based BiLSTM-CRF incorporating disease dictionary for disease named entity recognition[J]. Comput Biol Med, 2019, 108: 122-132. doi: 10.1016/j.compbiomed.2019.04.002
[31]	Bhasuran B, Murugesan G, Abdulkadhar S, et al. Stacked ensemble combined with fuzzy matching for biomedical named entity recognition of diseases[J]. J Biomed Inform, 2016, 64: 1-9. doi: 10.1016/j.jbi.2016.09.009
[32]	Kaminsky EB, Kaul V, Paschall J, et al. An evidence-based approach to establish the functional and clinical significance of copy number variants in intellectual and developmental disabilities[J]. Genet Med, 2011, 13: 777-784. doi: 10.1097/GIM.0b013e31822c79f9
[33]	Yang X, Song Z, Wu C, et al. Constructing a database for the relations between CNV and human genetic diseases via systematic text mining[J]. BMC Bioinformatics, 2018, 19(Suppl 19): 528.
[34]	Shen F, Liu S, Wang Y, et al. Utilization of electronic medical records and biomedical literature to support the diagnosis of rare diseases using data fusion and collaborative filtering approaches[J]. JMIR Med Inform, 2018, 6: e11301. doi: 10.2196/11301
[35]	Kaufmann P, Pariser AR, Austin C. From scientific discovery to treatments for rare diseases-the view from the national center for advancing translational sciences - office of rare diseases research[J]. Orphanet J Rare Dis, 2018, 13: 196. doi: 10.1186/s13023-018-0936-x
[36]	Keiser MJ, Setola V, Irwin JJ, et al. Predicting new molecular targets for known drugs[J]. Nature, 2009, 462: 175-181. doi: 10.1038/nature08506
[37]	Lee YS, Krishnan A, Oughtred R, et al. A computational framework for genome-wide characterization of the human disease landscape[J]. Cell Syst, 2019, 8: 152-162. doi: 10.1016/j.cels.2018.12.010
[38]	Geva A, Gronsbell JL, Cai T, et al. A computable phenotype improves cohort ascertainment in a pediatric pulmonary hypertension registry[J]. J Pediatr, 2017, 188: 224-231. doi: 10.1016/j.jpeds.2017.05.037
[39]	Blasco H, Patin F, Descat A, et al. A pharmaco-metabolomics approach in a clinical trial of ALS: Identification of predictive markers of progression[J]. PLoS One, 2018, 13: e0198116. doi: 10.1371/journal.pone.0198116
[40]	Lagrue E, Madji Hounoum B, Rullier C, et al. Cerebro-spinal fluid metabolomics in west syndrome: Central role of the serine metabolic pathway[J]. J Transl Sci, 2018, 4: e101.
[41]	Carlier A, Vasilevich A, Marechal M, et al. In silico clinical trials for pediatric orphan diseases[J]. Sci Rep, 2018, 8: 2465. doi: 10.1038/s41598-018-20737-y
[42]	Combi C, Pozzani G, Pozzi G. Telemedicine for developing countries. A survey and some design issues[J]. Appl Clin Inform, 2016, 7: 1025-1050. doi: 10.4338/ACI-2016-06-R-0089
[43]	Ekeland AG, Bowes A, Flottorp S. Effectiveness of telemedicine: a systematic review of reviews[J]. Int J Med Inform, 2010, 79: 736-771. doi: 10.1016/j.ijmedinf.2010.08.006
[44]	Greis C, Maul LV, Hsu C, et al. Artificial intelligence to support telemedicine in Africa[J]. Hautarzt, 2020, 71: 686-990. doi: 10.1007/s00105-020-04664-6
[45]	Lucey CR, Johnston SC. The transformational effects of COVID-19 on medical education[J]. JAMA, 2020, 324: 1033-1034. doi: 10.1001/jama.2020.14136
[46]	Sinha S, Kern LM, Gingras LF, et al. Implementation of video visits during COVID-19: lessons learned from a primary care practice in New York City[J]. Front Public Health, 2020, 8: 514. doi: 10.3389/fpubh.2020.00514
[47]	Chen LK, Yuan RP, Ji XJ, et al. Modular composite building in urgent emergency engineering projects: a case study of accelerated design and construction of Wuhan Thunder God Mountain/Leishenshan hospital to COVID-19 pandemic[J]. Autom Constr, 2021, 124: 103555. doi: 10.1016/j.autcon.2021.103555
[48]	Shaw J, Rudzicz F, Jamieson T, et al. Artificial intelligence and the implementation challenge[J]. J Med Internet Res, 2019, 21: e13659. doi: 10.2196/13659
[49]	Samek W, Wiegand T, Müller KR. Explainable artificial intelligence: understanding, visualizing and interpreting deep learning models[J]. arXiv preprint arXiv: 170808296, 2017.
[50]	Greenhalgh T, Howick J, Maskrey N. Evidence based medicine: a movement in crisis? [J]. BMJ, 2014, 348: 3725. doi: 10.1136/bmj.g3725
[51]	Ford RA, Price W, Nicholson I. Privacy and accountability in black-box medicine[J]. Mich Telecomm Tech L Rev, 2016, 23: 1.
[52]	Benjamens S, Dhunnoo P, Meskó B. The state of artificial intelligence-based FDA-approved medical devices and algorithms: an online database[J]. NPJ Digit Med, 2020, 3: 118. doi: 10.1038/s41746-020-00324-0
[53]	Molnar C, Casalicchio G, Bischl B. Interpretable machine learning-a brief history, state-of-the-art and challenges[J]. arXiv preprint arXiv: 09337, 2010.
[54]	Gostin LO, Halabi SF, Wilson K. Health data and privacy in the digital era[J]. JAMA, 2018, 320: 233-234. doi: 10.1001/jama.2018.8374
[55]	Grundy Q, Held FP, Bero LA. Tracing the potential flow of consumer data: A network analysis of prominent health and fitness apps[J]. J Med Internet Res, 2017, 19: e233. doi: 10.2196/jmir.7347
[56]	Culnane C, Rubinstein BI, Teague V. Health data in an open world[J]. arXiv preprint arXiv: 171205627, 2017.
[57]	Gong M, Wang S, Wang L, et al. Evaluation of privacy risks of patients' data in China: Case study[J]. JMIR Med Inform, 2020, 8: e13046. doi: 10.2196/13046
[58]	Festag S, Spreckelsen C. Privacy-preserving deep learning for the detection of protected health information in real-world data: comparative evaluation[J]. JMIR Form Res, 2020, 4: e14064. doi: 10.2196/14064
[59]	Zhang W, Wang Q, Li M. Privacy-preserving collaborative training for medical image analysis based on multi-blockchain[J]. Comb Chem High Throughput Screen, 2021, 24: 933-946. doi: 10.2174/1386207323666201022110616
[60]	Sun M, Tang F, Yi J, et al. Identify susceptible locations in medical records via adversarial attacks on deep predictive models[J]. arXiv preprint arXiv: 1802.04822.
[61]	Finlayson SG, Bowers JD, Ito J, et al. Adversarial attacks on medical machine learning[J]. Science, 2019, 363: 1287-1289. doi: 10.1126/science.aaw4399
[62]	Gianfrancesco MA, Tamang S, Yazdany J, et al. Potential biases in machine learning algorithms using electronic health record data[J]. JAMA Intern Med, 2018, 178: 1544-1547. doi: 10.1001/jamainternmed.2018.3763
[63]	Mittelstadt BD, Allo P, Taddeo M, et al. The ethics of algorithms: mapping the debate[J]. Big Data Society, 2016, 3: 2053951716679679.
[64]	Abrams C. Google's effort to prevent blindness shows AI challenges[J]. The Wall Street J, 2019, 1: 26.
[65]	Straw I, Callison-Burch C. Artificial Intelligence in mental health and the biases of language based models[J]. PLoS One, 2020, 15: e0240376. doi: 10.1371/journal.pone.0240376
[66]	Schwendicke F, Samek W, Krois J. Artificial intelligence in dentistry: chances and challenges[J]. J Dent Res, 2020, 99: 769-774. doi: 10.1177/0022034520915714
[67]	Khullar DAI. Could worsen health disparities[N]. New York Times, 2019-1-31.
[68]	Hripcsak G, Duke JD, Shah NH, et al. Observational health data sciences and informatics (OHDSI): opportunities for observational researchers[J]. Stud Health Technol Inform, 2015, 216: 574-578.
[69]	Xiao C, Choi E, Sun J. Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review[J]. J Am Med Inform Assoc, 2018, 25: 1419-1428. doi: 10.1093/jamia/ocy068
[70]	Kingma DP, Welling M. Auto-encoding variational bayes[J]. arXiv preprint arXiv: 13126114, 2013.
[71]	Nelson GS. Bias in artificial intelligence[J]. N C Med J, 2019, 80: 220-222.
[72]	Jaganathan K, Kyriazopoulou Panagiotopoulou S, McRae JF, et al. Predicting splicing from primary sequence with deep learning[J]. Cell, 2019, 176: 535-548. doi: 10.1016/j.cell.2018.12.015
[73]	Wang F, Preininger A. AI in health: state of the art, challenges, and future directions[J]. Yearb Med Inform, 2019, 28: 16-26. doi: 10.1055/s-0039-1677908
[74]	Austin CP, Cutillo CM, Lau LPL, et al. Future of rare diseases research 2017—2027: an IRDiRC perspective[J]. Clin Transl Sci, 2018, 11: 21-27. doi: 10.1111/cts.12500
[75]	Han J, Cui Y, Zhou X. Rare diseases research in China: opportunities, challenges, and solutions[J]. Intractable Rare Dis Res, 2012, 1: 10-12.
[76]	Austin CP, Dawkins HJS. Medical research: next decade's goals for rare diseases[J]. Nature, 2017, 548: 158.