Objective

farmaec

FARMAKOEKONOMIKA. Modern Pharmacoeconomics and Pharmacoepidemiology

ФАРМАКОЭКОНОМИКА. Современная фармакоэкономика и фармакоэпидемиология

2070-49092070-4933

IRBIS LLC

10.17749/2070-4909/farmakoekonomika.2025.287

farmaec-1128

Research Article

REVIEW ARTICLES

ОБЗОРНЫЕ ПУБЛИКАЦИИ

The effectiveness of using artificial intelligence in clinical medicine

Эффективность применения искусственного интеллекта в клинической медицине

https://orcid.org/0000-0002-0459-0488

Корабельников

Д. И.

Korabelnikov

D. I.

Корабельников Даниил Иванович, к.м.н., доцент

2-я Брестская ул., д. 5, Москва 123056

Daniil I. Korabelnikov, PhD, Assoc. Prof.

5 2nd Brestskaya Str., Moscow 123056

dkorabelnikov@mail.ru

https://orcid.org/0000-0001-7930-6018

Ламоткин

А. И.

Lamotkin

A. I.

Ламоткин Андрей Игоревич

2-я Брестская ул., д. 5, Москва 123056;

ул. Добролюбова, д. 11, Москва 127254

Andrey I. Lamotkin

5 2nd Brestskaya Str., Moscow 123056;

11 Dobrolyubov Str., Moscow 127254

Автономная некоммерческая организация дополнительного профессионального образования «Московский медико-социальный институт им. Ф.П. Гааза»РоссияMoscow Haass Medical and Social InstituteRussian Federation

Автономная некоммерческая организация дополнительного профессионального образования «Московский медико-социальный институт им. Ф.П. Гааза»; Федеральное государственное бюджетное учреждение «Центральный научно-исследовательский институт организации и информатизации здравоохранения» Министерства здравоохранения Российской ФедерацииРоссияMoscow Haass Medical and Social Institute; Central Research Institute of Organization and Informatization of HealthcareRussian Federation

2025

02052025

181114124

2025

Корабельников Д.И., Ламоткин А.И.

Korabelnikov D.I., Lamotkin A.I.

This work is licensed under a Creative Commons Attribution 4.0 License.

https://www.pharmacoeconomics.ru/jour/article/view/1128

Objective

Objective: To examine the effectiveness of using artificial intelligence (AI) in clinical medicine (in terms of accuracy, sensitivity, and specificity).

Material and methods

Material and methods. The study involved a search and analysis of scientific publications examining various types of AI training and training approaches, as well as areas of AI application in clinical practice, which were submitted to PubMed/MEDLINE, Scopus, Web of Science, Embase, eLibrary, and CyberLeninka databases in 2009–2023. A sequential analysis of randomly sampled articles yielded 30 publications on the use of AI in endocrinology (4 articles), dermatovenerology (3), cardiology (1), radiology (1), gastroenterology (1), neurology (5), hematology (5), nephrology (4), orthopedics and rheumatology (4), oncology (2).

Results

Results. AI demonstrated sufficient effectiveness: accuracy ranged from 49% to 99%, sensitivity from 42% to 100%, and specificity from 48% to 100% in such areas as cardiology, endocrinology, gastroenterology, dermatovenereology, and radiology. In some cases, AI was more effective than clinical diagnostics by medical specialists, e.g. in detecting melanoma and diagnosing atrial fibrillation.

Conclusion

Conclusion. AI shows high diagnostic efficiency, increases accuracy and speeds up diagnostic search, which makes it promising to expand the use of AI in clinical medicine.

Цель

Цель: исследовать эффективность применения искусственного интеллекта (ИИ) в клинической медицине (на основе показателей точности, чувствительности и специфичности).

Материал и методы

Материал и методы. Проведены поиск и анализ научных публикаций, представленных в базах данных PubMed/MEDLINE, Scopus, Web of Science, Embase, eLibrary и КиберЛенинка с 2009 по 2023 гг. и включающих различные виды и подходы к обучению ИИ, а так же различные сферы его применения в клинической практике. Методом последовательного анализа статей, попавших в случайную выборку, было отобрано 30 публикаций, посвященных применению ИИ в эндокринологии (4 статьи), дерматовенерологии (3), кар диологии (1), рентгенологии (1), гастроэнтерологии (1), неврологии (5), гематологии (5), нефрологии (4), ортопедии и ревматоло гии (4), онкологии (2).

Результаты

Результаты. ИИ продемонстрировал достаточную эффективность: точность варьировалась от 49% до 99%, чувствительность – от 42% до 100%, а специфичность – от 48% до 100% в таких областях, как кардиология, эндокринология, гастроэнтерология, дерма товенерология и рентгенология. В некоторых случаях ИИ превосходил по эффективности клиническую диагностику врачей-специа листов, например при выявлении меланомы и в диагностике фибрилляции предсердий.

Заключение

Заключение. ИИ показывает высокую эффективность в диагностике, повышает точность и ускоряет проведение диагностического поиска, что делает перспективным его более широкое применение в клинической медицине.

искусственный интеллектнейронные сетиздравоохранениемедицинаклиническая практикаиагностикалечение

artificial intelligenceneural networkshealthcaremedicineclinical practicediagnosticstreatment

Авторы заявляют об отсутствии финансовой поддержки

The authors declare no funding

References1

Kusters R., Misevic D., Berry H., et al. Interdisciplinary research in artificial intelligence: challenges and opportunities. Front Big Data. 2020; 3: 577974. https://doi.org/10.3389/fdata.2020.577974.

Куракова Н. Г., Цветкова Л. А., Черченко О.В. Технологии искус ственного интеллекта в медицине и здравоохранении: позиции России на глобальном патентном и публикационном ландшафте. Врач и информационные технологии. 2020; 2: 81–100. https://doi.org/10.37690/1811-0193-2020-2-81-100.

Kurakova N.G., Tsvetkova L.A., Cherchenko O.V. Artificial intelligence technologies in medicineand healthcare: Russia's position on the global patent and publication landscape. Medical Doctor and IT. 2020; 2: 81 100 (in Russ.). https://doi.org/10.37690/1811-0193-2020-2-81-100.

Jimma B.L. Artificial intelligence in healthcare: a bibliometric analysis. Telemat Inform Rep. 2023; 9 (Suppl. 1): 100041. https://doi.org/10.1016/j.teler.2023.100041.

Guo Y., Hao Z., Zhao S., et al. Artificial intelligence in health care: bibliometric analysis. J Med Internet Res. 2020; 22 (7): e18228. https://doi.org/10.2196/18228.

Ламоткин А.И., Корабельников Д.И., Ламоткин И.А. и др. Искус ственный интеллект в здравоохранении и медицине: история клю чевых событий, его значимость для врачей, уровень развития в разных странах. ФАРМАКОЭКОНОМИКА. Современная фармакоэкономика и фармакоэпидемиология. 2024; 17 (2): 243–50. https://doi.org/10.17749/2070-4909/farmakoekonomika.2024.254.

Lamotkin A.I., Korabelnikov D.I., Lamotkin I.A., et al. Artificial intelligence in healthcare and medicine: the history of key events, its significance for doctors, the level of development in different countries. FARMAKOEKONOMIKA. Sovremennaya farmakoekonomika i farmako epidemiologiya / FARMAKOEKONOMIKA. Modern Pharmacoeconomics and Pharmacoepidemiology. 2024; 17 (2): 243–50. https://doi.org/10.17749/2070-4909/farmakoekonomika.2024.254.

Hicks S.A., Strümke I., Thambawita V., et al. On evaluation metrics for medical applications of artificial intelligence. Sci Rep. 2022; 12 (1): 5979. https://doi.org/10.1038/s41598-022-09954-8.

Соловьев А.А. Взвешенная погрешность – новая метрика для оценки качества валидации ответов в задаче вопросно-ответного поиска. Вестник МГТУ им. Н.Э. Баумана. Серия «Приборостроение». 2013; 1: 58–64.

Solovyev A.A. Weighted error – new metrics for estimating quality of answer validation in the problem of question-answering retrieval. Herald of the Bauman Moscow State Technical University. Series “Instrument Building”. 2013; 1: 58–64 (in Russ.).

van Stralen K.J., Stel V.S., Reitsma J.B., et al. Diagnostic methods I: sensitivity, specificity, and other measures of accuracy. Kidney Int. 2009; 75 (12): 1257–63. https://doi.org/10.1038/ki.2009.92.

Shreffler J., Huecker M.R. Diagnostic testing accuracy: sensitivity, specificity, predictive values and likelihood ratios. In: StatPearls. Treasure Island (FL): StatPearls Publishing; 2024.

Çorbacıoğlu Ş.K., Aksel G. Receiver operating characteristic curve analysis in diagnostic accuracy studies: a guide to interpreting the area under the curve value. Turk J Emerg Med. 2023; 23 (4): 195–8. https://doi.org/10.4103/tjem.tjem_182_23.

Zhou J., Gandomi A., Chen F., Holzinger A. Evaluating the quality of machine learning explanations: a survey on methods and metrics. Electronics. 2021; 10 (5): 593. https://doi.org/10.3390/electronics10050593.

Attia Z.I., Noseworthy P.A., Lopez-Jimenez F., et al. An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction. Lancet. 2019; 394 (10201): 861–7. https://doi.org/10.1016/S0140-6736(19)31721-0.

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. JAMA. 2016; 316 (22): 2402–10. https://doi.org/10.1001/jama.2016.17216.

Sudharsan B., Peeples M., Shomali M. Hypoglycemia prediction using machine learning models for patients with type 2 diabetes. J Diabetes Sci Technol. 2015; 9 (1): 86–90. https://doi.org/10.1177/1932296814554260.

Pei X., Yao X., Yang Y., et al. Efficacy of artificial intelligence-based screening for diabetic retinopathy in type 2 diabetes mellitus patients. Diabetes Res Clin Pract. 2022; 184: 109190. https://doi.org/10.1016/j.diabres.2022.109190.

Marling C.R., Struble N.W., Bunescu R.C., et al. A consensus perceived glycemic variability metric. J Diabetes Sci Technol. 2013; 7 (4): 871–9. https://doi.org/10.1177/193229681300700409.

Nam J.G., Park S., Hwang E.J., et al. Development and validation of deep learning-based automatic detection algorithm for malignant pulmonary nodules on chest radiographs. Radiology. 2019; 290 (1): 218–28. https://doi.org/10.1148/radiol.2018180237.

Misawa M., Kudo S.E., Mori Y., et al. Artificial intelligence-assisted polyp detection for colonoscopy: initial experience. Gastroenterology. 2018; 154 (8): 2027–9.e3. https://doi.org/10.1053/j.gastro.2018.04.003.

Brinker T.J, Hekler A., Enk A.H., et al. A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task. Eur J Cancer. 2019; 111: 148–54. https://doi.org/10.1016/j.ejca.2019.02.005.

Esteva A., Kuprel B., Novoa R.A., et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017; 542 (7639): 115–8. https://doi.org/10.1038/nature21056.

Han S.S., Park G.H., Lim W., et al. Deep neural networks show an equivalent and often superior performance to dermatologists in onychomycosis diagnosis: automatic construction of onychomycosis datasets by region-based convolutional deep neural network. PLoS One. 2018; 13 (1): e0191493. https://doi.org/10.1371/journal.pone.0191493.

Abedi V., Avula V., Chaudhary D., et al. Prediction of long-term stroke recurrence using machine learning models. J Clin Med. 2021; 10 (6): 1286. https://doi.org/10.3390/jcm10061286.

Daoud H., Bayoumi M.A. Efficient epileptic seizure prediction based on deep learning. IEEE Transact Biomed Circuits Syst. 2019; 13 (5): 804–13. https://doi.org/10.1109/TBCAS.2019.2929053.

Qiu S., Joshi P.S., Miller M.I., et al. Development and validation of an interpretable deep learning framework for Alzheimer’s disease classification. Brain. 2020; 143 (6): 1920–33. https://doi.org/10.1093/brain/awaa137.

Rava R.A., Seymour S.E., Snyder K.V., et al. Automated collateral flow assessment in patients with acute ischemic stroke using computed tomography with artificial intelligence algorithms. World Neurosurg. 2021; 155: e748–60. https://doi.org/10.1016/j.wneu.2021.08.136.

Shinde R., Gupta D., Bansal S., et al. Predictive modeling for stroke outcomes: a comparison of machine learning algorithms. NeuroImage. 2021; 227: 117726. https://doi.org/10.1016/j.neuroimage.2020.117726.

Boldú L., Merino A., Acevedo A., et al. A deep learning model (ALNet) for the diagnosis of acute leukaemia lineage using peripheral blood cell images. Comput Methods Programs Biomed. 2021; 202: 105999. https://doi.org/10.1016/j.cmpb.2021.105999.

El Hussein S., Chen P., Medeiros L.J., et al. Artificial intelligence assisted mapping of proliferation centers allows the distinction of accelerated phase from large cell transformation in chronic lymphocytic leukemia. Mod Pathol. 2022; 35 (8): 1121–5. https://doi.org/10.1038/s41379-022-01015-9.

AlAgha A.S., Faris H., Hammo B.H., Al-Zoubi A.M. Identifying β-thalassemia carriers using a data mining approach: the case of the Gaza Strip, Palestine. Artif Intel Med. 2018; 88: 70–83. https://doi.org/10.1016/j.artmed.2018.04.009.

Didi I., Simoncini D., Vergez F., et al. Artificial intelligence-based predictive models for acute myeloid leukemia. Blood. 2021; 138 (Suppl. 1): 3389. https://doi.org/10.1182/blood-2021-145122.

Memmolo P., Aprea G., Bianco V., et al. Differential diagnosis of hereditary anemias from a fraction of blood drop by digital holography and hierarchical machine learning. Biosens Bioelectron. 2022; 201: 113945. https://doi.org/10.1016/j.bios.2021.113945.

Tomašev N., Glorot X., Rae J.W., et al. A clinically applicable approach to continuous prediction of future acute kidney injury. Nature. 2019; 572 (7767): 116–9. https://doi.org/10.1038/s41586-019-1390-1.

Mohamadlou H., Lynn-Palevsky A., Barton C., et al. Prediction of acute kidney injury with a machine learning algorithm using electronic health record data. Can J Kidney Health Dis. 2018; 5: 2054358118776326. https://doi.org/10.1177/2054358118776326.

Adhikari L., Ozrazgat-Baslanti T., Ruppert M., et al. Improved predictive models for acute kidney injury with IDEA: Intraoperative Data Embedded Analytics. PLoS One. 2019; 14 (4): e0214904. https://doi.org/10.1371/journal.pone.0214904.

Kuo C.C., Chang C.M., Liu K.T., et al. Automation of the kidney function prediction and classification through ultrasound-based kidney imaging using deep learning. NPJ Digit Med. 2019; 2: 29. https://doi.org/10.1038/s41746-019-0104-2.

Couteaux V., Si-Mohamed S., Nempont O., et al. Automatic knee meniscus tear detection and orientation classification with Mask-RCNN. Diagn Interv Imaging. 2019; 100 (4): 235–42. https://doi.org/10.1016/j.diii.2019.03.002.

Rouzrokh P., Ramazanian T., Wyles C.C., et al. Deep learning artificial intelligence model for assessment of hip dislocation risk following primary total hip arthroplasty from postoperative radiographs. J Arthroplasty. 2021; 6 (6): 2197–203.e3. https://doi.org/10.1016/j.arth.2021.02.028.

Patrick M.T., Stuart P.E., Raja K. et al. Genetic signature to provide robust risk assessment of psoriatic arthritis development in psoriasis patients. Nat Commun. 2018; 9 (1): 4178. https://doi.org/10.1038/s41467-018-06672-6.

Long N.P., Park S., Anh N.H., et al. Efficacy of integrating a novel 16-gene biomarker panel and intelligence classifiers for differential diagnosis of rheumatoid arthritis and osteoarthritis. J Clin Med. 2019; 8 (1): 50. https://doi.org/10.3390/jcm8010050.

Lu J., Liu R., Zhang Y., et al. Development and application of a detection platform for colorectal cancer tumor sprouting pathological characteristics based on artificial intelligence. Intel Med. 2022; 2 (2): 82–7. https://doi.org/10.1016/j.imed.2021.08.003.

Pantanowitz L., Quiroga-Garza G.M., Bien L., et al. An artificial intelligence algorithm for prostate cancer diagnosis in whole slide images of core needle biopsies: a blinded clinical validation and deployment study. Lancet Digit Health. 2020; 2 (8): e407-e416. https://doi.org/10.1016/S2589-7500(20)30159-X.

The authors declare that there are no conflicts of interest present.