Skip to main content
NCBI home page
Chronic Diseases and Translational Medicine logoLink to Chronic Diseases and Translational Medicine
letter
. 2019 Jan 9;5(1):64–68. doi: 10.1016/j.cdtm.2018.11.004

Artificial intelligence—Developments in medicine in the last two years

Rezida Maratovna Galimova 1,2,3,4,5, Igor Vyacheslavovich Buzaev 1,2,3,4,5,∗, Kireev Ayvar Ramilevich 1,2,3,4,5, Lev Khadyevich Yuldybaev 1,2,3,4,5, Aigul Fazirovna Shaykhulova 1,2,3,4,5
PMCID: PMC6449768  PMID: 30993265

Dear Editor,

Artificial intelligence (AI) is the theory and development of computer systems that are able to perform tasks that normally require human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages. There are some knowledge and thinking tasks that humans cannot perform as perfectly as they wish to or should be able to. These tasks are closely related to security and responsibility. A multitude of cognitive distortions have been well explored1 and present opportunities to use AI for powerful assistance in thinking tasks. The core of the Industrial Revolution 4.0 is the adoption of AI methods. This revolution has affected all aspects of human activities and medicine is one example.

AI systems can usually include formal algorithms for subtasks that can be solved using logic, for example, a decision tree. The task solution process moves from logic point to logic point similar to a train on a railway. These algorithms are fast and have the ability to explain. One of the most common is well described in the publication of Fei Jiang et al.2 in 2017, which divides AI features into language processing and machine learning tasks. In conjunction with his colleagues, he published different algorithms in the Pubmed database and found that the most frequently used are support vector machines, neural networks, logistic regression, discriminant analysis, random forest, linear regression, naïve bayes, nearest neighbor, decision tree, and hidden Markov.

The goal of this study was to show qualitative change to AI development that has occurred over the last two years by examining the trends in Pubmed publications, including dynamics interest in AI topic, dynamics of non-English language publications, and implementations of AI in modern practice. The literature for this research included books related to the topic, included Goodfellow's Deep Learning3 and a Deep Learning in R.4 We also used Google patent search, specialized journal “Artificial intelligence” articles, and the Pubmed database.

All abstracts with keyword “artificial intelligence” have been downloaded to txt files from the Pubmed database https://www.ncbi.nlm.nih.gov/pubmed/. Microsoft Access Visual Basic program was used to import these abstracts into the database. We then performed machine analysis of the dataset. The dataset includes names of all authors, all Mesh tags, year, language, and all words from the title and abstract. This information was extracted to tables, which were linked to the table of abstracts using a unique key. All non-informative words were marked as non-informative, and then the remaining keywords were grouped with generalizing words. We classified the present applications of AI in medicine by generalizing topics. We then made structured query language (SQL) queries to make frequency tables. Using this research, we classified the AI technologies.

A total of 78,420 abstracts were extracted, including 30,835 journal articles, 37,332 research supports, 5558 reviews, 304 randomized controlled trials, 247 multicenter studies, and 4137 other publication types. We observed that the exponential growth of interest in AI solutions slowed down in middle of 2010. This followed the typical phenomenon of “S”-like development of innovation curves. It illustrates effectiveness of old technology and predicts the stagnation or a new stage of development.5

English was the most often used language in publication, followed by Chinese and then German. Non-English publications decreased over the last five years, especially Chinese publications.

Fig. 1 shows that around 2010, interest to AI in oncology accelerated. The main reason was the development of medical visualization AI. It was mostly targeted to recognize tumors on images and the genome (Fig. 2).

Fig. 1.

Fig. 1

Open in a new tab

Interest in artificial intelligence in different medicine fields.

Fig. 2.

Fig. 2

Open in a new tab

Most frequent tasks performed with artificial intelligence.

From this dataset, 809,451 Mesh tags were extracted from the abstracts of 77,964 articles that had Mesh tags in the abstracts. Mesh tags were grouped and added to the united table of grouped keywords. Then the typical applications were classified (Table 1). Poole D6 marked out AI agent subclasses that could be a coupling of a computational engine with physical actuators and sensors, called a robot. Examples include autonomous delivery robots or cleaning robots. It could also be the coupling of an advice-giving computer, an expert system, with a human who provides the perceptual information and who carries out the task, for example, a diagnostic assistant. An agent could also be a program that acts in a purely computational environment, an infobot. An “infobot” could search for information on a computer system for naïve users such as company managers.

Table 1.

Application of artificial intelligence in clinical medicine.

Classification Description
Management and optimization Co-occurrence graphs7
Medical treatment process clustering
Detecting inconsistencies in clinical guidelines8
Marketing (e.g. trust for medical center investigation9)
Data mining
Registration
Planning
Signal analysis, encoding, decoding Tactile sense10
Kinesthetic sense11
Taste sense12
Image analysis (e.g. auto-contouring,13 segmentation of corneal endothelium,14 histopathological image cancer identification15)
Sound analysis (e.g. lung sound classification)
Smell analysis (e.g. the predictions for ethanol and ethylene concentrations,16 electronic nose,17 breath analysis18, 19)
Detection, identification Epidemiology (e.g. identifying thalassemia carriers20)
Prediction, prognosis, modeling, simulation, mapping Risk modeling (e.g. drug reaction assessment, cancer risk21)
Disease modeling (e.g. connections of brain regions in children with autism22)
Classification, clustering, segmentation
Monitoring and control Telemedicine23
Text analysis and language processing Speech intentions from online conversation24
Medical text semantics25
Statistics from death certificates26
Automatic classification of radiological reports27
Classification of multilingual biomedical documents28
Relation classification in medical records23
Natural language processing tasks (e.g. summarization, text classification, relation extraction)
Devices and gadgets Internet of Health Things (IoHT)29
Smart home and early anomaly detection in elderly30
Portable devices and mobile applications
Decision support and expert systems Retinopathy by arteriovenous ratio31
Coronary bypass surgery vs coronary stenting32
Diagnostics Diagnostic labeling33
Diagnosis by pattern recognition34
Fatigue by eye tracking35 >
Correlations between diseases
Early anomaly detection in behavior30
Early indicators of Parkinson's disease progression36
Treatment Therapy (e.g. automatic anesthesia37)
Surgery (e.g. robotic, remebot, a navigation and orientation robot used for neurosurgery38)
Rehabilitation (e.g. prosthesis)
Automatization of tasks above
Open in a new tab

In particular, deep learning has achieved breakthroughs in historically difficult areas of machine learning, such as near-human-level image classification, near-human-level speech recognition, digital assistants such as Google Now and Amazon Alexa, near-human-level autonomous driving, improved search results on the Web, ability to answer natural language questions, and superhuman Go playing.4

The first is the instruments and tools for AI development. AI tools are not currently considered bizarre instruments of future, but available fast algorithms, such are Tensor Flow (https://tensorflow.rstudio.com/) or Keras. Both were released in 2015 and are open source and free. In 2017, Apple introduced CoreML in its Xcode platform with Core ML developer, which can integrate trained machine learning models into the application.39 Apple has also already developed the framework for Vision, which analyzes images, and Natural Language for natural language processing.

On April 11, 2018, IDx-DR became the first device authorized for marketing that provided a screening decision without the need for a clinician to also interpret the image or results, which made it usable by health care providers who might not normally be involved in eye care.40 On February 13, 2018, the Food and Drug Administration (FDA) permitted marketing of clinical decision support software for alerting providers of a potential stroke in patients.41 OsteoDetect software, a computer-aided detection and diagnostic software, uses an AI algorithm to analyze two-dimensional X-ray images for signs of distal radius fracture, a common type of wrist fracture. The software marks the location of the fracture in the image to aid the provider in detection and diagnosis. It was approved by FDA on May 24, 2018.42

Interest in the AI topic in the Pubmed library indexed publications is increasing according to the law of innovation development. The number of non-English publications increased until 2018, with English publications being the most common, followed by Chinese, German, and French. After 2018, the number of non-English publications decreased in favor of English publications.

Examples of AI implementation in modern practice are now available to more people than just mathematics professionals. Tools for machine learning are widely available to more mainstream scientists. For example, a scientist can download the R statistic language that is an open source and free from the Comprehensive R Archive Network (CRAN) project site and connect the TensorFlow and Keras libraries, which are free to download as well. There are good books explaining how to start,4 which can easily be found. There are a lot of local registries in any regional hospital that are available and can be used for machine learning decision support.32

FDA-approved tools have become available. This is another change that applies not only to the scientists but also to clinical practitioners as well. They were approved mainly for medical image analysis and demonstrated comparable accuracy to human specialists.

The most fantastic possible use of AI in medicine would be the transfer of a mind from an ill and mortal human body to the upgradable, connectable, and easy-to-fix machine body by scanning parameters of neurons and synapses and then replicating them in the AI machine. There are relationships between carbon, which makes up a portion of the human body, and silicon, which could be used for this application. They are in one column and must have similar characteristics in the Mendeleev periodic table. So next period “silicon life” may be an upgrade to a new life cyborg-form type.

Edited by Jing-Ling Bao

Footnotes

Peer review under responsibility of Chinese Medical Association.

References

  • 1.Tversky A., Kahneman D. Judgement under uncertainty: heuristics and biases. Sciences. 1974;185:1124–1131. doi: 10.1126/science.185.4157.1124. [DOI] [PubMed] [Google Scholar]
  • 2.Jiang F., Jiang Y., Zhi H. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neuro. 2017;2:230–243. doi: 10.1136/svn-2017-000101. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 3.Goodfellow I., Bengio Y., Courville A. Massachusetts Institute of Technology; 2016. Deep Learning; p. 12. [Google Scholar]
  • 4.Chollet F., Allaire J.J., editors. Deep Learning with R. Manning Publications; 2017. p. 4. [Google Scholar]
  • 5.Selivanov S.G., Guzairov M.B., Kutin A.A. 3rd ed. M: Machinostroyeniye; 2013. Innovatics. The University Textbook; pp. 110–113. [Google Scholar]
  • 6.Poole D., Mackworth A., Goebel R. Oxford University Press; New York: 1998. Computational Intelligence: A Logical Approach; p. 1. [Google Scholar]
  • 7.Duque A., Stevenson M., Martinez-Romo J., Araujo L. Co-occurrence graphs for word sense disambiguation in the biomedical domain. Artif Intell Med. 2018;87:9–19. doi: 10.1016/j.artmed.2018.03.002. [DOI] [PubMed] [Google Scholar]
  • 8.Tsopra R., Lamy J.B., Sedki K. Using preference learning for detecting inconsistencies in clinical practice guidelines: methods and application to antibiotherapy. Artif Intell Med. 2018;89:24–33. doi: 10.1016/j.artmed.2018.04.013. [DOI] [PubMed] [Google Scholar]
  • 9.Yazdanparast R., Zadeh S.A., Dadras D., Azadeh A. An intelligent algorithm for identification of optimum mix of demographic features for trust in medical centers in Iran. Artif Intell Med. 2018;88:25–36. doi: 10.1016/j.artmed.2018.04.006. [DOI] [PubMed] [Google Scholar]
  • 10.De Rossi D., Domenici C., Chiarelli P. Sensors and Sensory Systems for Advanced Robots. Springer; 1988. Analogs of biological tissues for mechanoelectrical transduction: tactile sensors and muscle-like actuators; pp. 201–218. [Google Scholar]
  • 11.Giorgino T., Quaglini S., Lorassi F., De Rossi D. Wearable and Implantable Body Sensor Networks. IEEE; 2006. Experiments in the detection of upper limb posture through kinestetic strain sensors. BSN 2006. International Workshop on. 2006. [Google Scholar]
  • 12.Riul A.R., Malmegrim R.R., Fonseca F.J., Mattoso L.H. Nano-assembled films for taste sensor application. Artif Organs. 2003;27(5):469–472. doi: 10.1046/j.1525-1594.2003.07243.x. [DOI] [PubMed] [Google Scholar]
  • 13.Liang F., Qian P., Su K.H. Abdominal, multi-organ, auto-contouring method for online adaptive magnetic resonance guided radiotherapy: an intelligent, multi-level fusion approach. Artif Intell Med. 2018;90:34–41. doi: 10.1016/j.artmed.2018.07.001. [DOI] [PubMed] [Google Scholar]
  • 14.Piórkowski A. A statistical Dominance algorithm for edge detection and segmentation of medical images. In: Piętka E., Badura P., Kawa J., Wieclawek W., editors. vol. 471. Springer; Cham: 2016. pp. 3–14. (Information Technologies in Medicine. ITiB 2016. Advances in Intelligent Systems and Computing). [Google Scholar]
  • 15.Gandomkar Z., Brennan P.C., Mello-Thoms C. MuDeRN: Multi-category classification of breast histopathological image using deep residual networks. Artif Intell Med. 2018;88:14–24. doi: 10.1016/j.artmed.2018.04.005. [DOI] [PubMed] [Google Scholar]
  • 16.Jonsson A., Winquist F., Schnürer J., Sundgren H., Lundström I. Electronic nose for microbial quality classification of grains. Int J Food Microbiol. 1997;35(2):187–193. doi: 10.1016/s0168-1605(96)01218-4. [DOI] [PubMed] [Google Scholar]
  • 17.Gardner J.W., Vincent T.A. Electronic noses for well-being: breath analysis and energy expenditure. Sensors (Basel) 2016 Jun 23;16(7) doi: 10.3390/s16070947. pii: E947. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 18.Di Francesco F., Fuoco R., Trivella M.G., Ceccarinib A. Breath analysis: trends in techniques and clinical applications. Microchem J. 2005;79(1):405–410. [Google Scholar]
  • 19.Kopylov P.Y., Syrkin A.L., Chomakhidze P.S. Proton transfer reaction mass spectrometry of exhaled breath in diagnostics of heart failure. Kardiologiia. 2016;56:37–41. doi: 10.18565/cardio.2016.5.37-41. [DOI] [PubMed] [Google Scholar]
  • 20.AlAgha A.S., Faris H., Hammo B.H., AI-Zoubi A.M. Identifying β-thalassemia carriers using a data mining approach: the case of the Gaza Strip, Palestine. Artif Intell Med. 2018;88:70–83. doi: 10.1016/j.artmed.2018.04.009. [DOI] [PubMed] [Google Scholar]
  • 21.Richter A.N., Khoshgoftaar T.M. A review of statistical and machine learning methods for modeling cancer risk using structured clinical data. Artif Intell Med. 2018;90:1–14. doi: 10.1016/j.artmed.2018.06.002. [DOI] [PubMed] [Google Scholar]
  • 22.Askari E., Setarehdan S.K., Sheikhani A., Mohammadi M.R., Teshnehlab M. Modeling the connections of brain regions in children with autism using cellular neural networks and electroencephalography analysis. Artif Intell Med. 2018;89:40–50. doi: 10.1016/j.artmed.2018.05.003. [DOI] [PubMed] [Google Scholar]
  • 23.He B., Guan Y., Dai R. Classifying medical relations in clinical text via convolutional neural networks. Artif Intell Med. 2018 May 16;17:30552–30553. doi: 10.1016/j.artmed.2018.05.001. pii: S0933-3657, [Epub ahead of print] [DOI] [PubMed] [Google Scholar]
  • 24.Epure E.V., Compagno D., Salinesi C., Deneckere R., Bajec M., Žitnik S. Process models of interrelated speech intentions from online health-related conversations. Artif Intell Med. 2018 Jul 17;17:30604–30608. doi: 10.1016/j.artmed.2018.06.007. pii: S0933-3657, [Epub ahead of print] [DOI] [PubMed] [Google Scholar]
  • 25.Denecke K., van Harmelen F. Recent advances in extracting and processing rich semantics from medical texts. Artif Intell Med. 2018 Aug 3;18:30441–X. doi: 10.1016/j.artmed.2018.07.004. pii: S0933-3657, [Epub ahead of print] [DOI] [PubMed] [Google Scholar]
  • 26.Koopman B., Zuccon G., Nguyen A., Bergheim A., Grayson N. Extracting cancer mortality statistics from death certificates: a hybrid machine learning and rule-based approach for common and rare cancers. Artif Intell Med. 2018;89:1–9. doi: 10.1016/j.artmed.2018.04.011. [DOI] [PubMed] [Google Scholar]
  • 27.Gerevini A.E., Lavelli A., Maffi A. Automatic classification of radiological reports for clinical care. Artif Intell Med. 2018 Jun 7;17:30591–30592. doi: 10.1016/j.artmed.2018.05.006. pii: S0933-3657, [Epub ahead of print] [DOI] [PubMed] [Google Scholar]
  • 28.Antonio Mouriño García M., Pérez Rodríguez R., Anido Rifón L. Leveraging Wikipedia knowledge to classify multilingual biomedical documents. Artif Intell Med. 2018;88:37–57. doi: 10.1016/j.artmed.2018.04.007. [DOI] [PubMed] [Google Scholar]
  • 29.da Costa C.A., Pasluosta C.F., Eskofier B., da Silva D.B., da Rosa Righi R. Internet of Health Things: toward intelligent vital signs monitoring in hospital wards. Artif Intell Med. 2018;89:61–69. doi: 10.1016/j.artmed.2018.05.005. [DOI] [PubMed] [Google Scholar]
  • 30.Hela S., Amel B., Badran R. Early anomaly detection in smart home: A causal association rule-based approach. Artificial Intelligence in Medicine. 2018;91:57–71. doi: 10.1016/j.artmed.2018.06.001. [DOI] [PubMed] [Google Scholar]
  • 31.Akbar S., Akram M.U., Sharif M., Tariq A., Khan S.A. Decision support system for detection of hypertensive retinopathy using arteriovenous ratio. Artif Intell Med. 2018;90:15–24. doi: 10.1016/j.artmed.2018.06.004. [DOI] [PubMed] [Google Scholar]
  • 32.Buzaev I.V., Plechev V.V., Nikolaeva I.E., Galimova R.M. Artificial intelligence: neural network model as the multidisciplinary team member in clinical decision support to avoid medical mistakes. Chronic Dis Transl Med. 2016;2:166–172. doi: 10.1016/j.cdtm.2016.09.007. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 33.Guo J., Yuan X., Zheng X., Xu P., Xiao Y., Liu B. Diagnosis labeling with disease-specific characteristics mining. Artif Intell Med. 2018;90:25–33. doi: 10.1016/j.artmed.2018.06.006. [DOI] [PubMed] [Google Scholar]
  • 34.Luo M., Zhao R. A distance measure between intuitionistic fuzzy sets and its application in medical diagnosis. Artif Intell Med. 2018;89:34–39. doi: 10.1016/j.artmed.2018.05.002. [DOI] [PubMed] [Google Scholar]
  • 35.Yamada Y., Kobayashi M. Detecting mental fatigue from eye-tracking data gathered while watching video: evaluation in younger and older adults. Artif Intell Med. 2018 Jul 16;17:30614–30620. doi: 10.1016/j.artmed.2018.06.005. pii: S0933-3657, [Epub ahead of print] [DOI] [PubMed] [Google Scholar]
  • 36.Valmarska A., Miljkovic D., Konitsiotis S., Gatsios D., Lavrač N., Robnik-Šikonja M. Symptoms and medications change patterns for Parkinson's disease patients stratification. Artif Intell Med. 2018 May 23;17:30587–30590. doi: 10.1016/j.artmed.2018.04.010. pii: S0933-3657, [Epub ahead of print] [DOI] [PubMed] [Google Scholar]
  • 37.Mendez J.A., Leon A., Marrero A. Improving the anesthetic process by a fuzzy rule based medical decision system. Artif Intell Med. 2018;84:159–170. doi: 10.1016/j.artmed.2017.12.005. [DOI] [PubMed] [Google Scholar]
  • 38.AI is here – are you ready? ChinAfrica. 2018;10:24. http://www.chinafrica.cn/Homepage/201808/t20180808_800137708.html. [2018-08-09] [Google Scholar]
  • 39.Core ML. Available from: https://developer.apple.com/documentation/coreml. [2018-12-05].
  • 40.FDA Permits Marketing of Artificial Intelligence-based Device to Detect Certain Diabetes-related Eye Problems. April 11, 2018. https://www.fda.gov/NewsEvents/Newsroom/PressAnnouncements/ucm604357.htm. [2018-09-01] Available from: [Google Scholar]
  • 41.FDA permits marketing of clinical decision support software for alerting providers of a potential stroke in patients. February 13, 2018. https://www.fda.gov/NewsEvents/Newsroom/PressAnnouncements/ucm596575.htm. [2018-09-01] Available from: [Google Scholar]
  • 42.FDA Permits Marketing of Artificial Intelligence Algorithm for Aiding Providers in Detecting Wrist Fractures. May 24, 2018. https://www.fda.gov/NewsEvents/Newsroom/PressAnnouncements/ucm608833.htm. [2018-09-01] Available from: [Google Scholar]

Articles from Chronic Diseases and Translational Medicine are provided here courtesy of Chinese Medical Association

RESOURCES