Methodologic Guide for Evaluating Clinical Performance and Effect of Artificial Intelligence Technology for Medical Diagnosis and Prediction
The DOI matches its Crossref record; 49 of the 49 references it cites were found in a registry or an index.
Abstract
The use of artificial intelligence in medicine is currently an issue of great interest, especially with regard to the diagnostic or predictive analysis of medical images. Adoption of an artificial intelligence tool in clinical practice requires careful confirmation of its clinical utility. Herein, the authors explain key methodology points involved in a clinical evaluation of artificial intelligence technology for use in medicine, especially high-dimensional or overparameterized diagnostic or predictive models in which artificial deep neural networks are used, mainly from the standpoints of clinical epidemiology and biostatistics. First, statistical methods for assessing the discrimination and calibration performances of a diagnostic or predictive model are summarized. Next, the effects of disease manifestation spectrum and disease prevalence on the performance results are explained, followed by a discussion of the difference between evaluating the performance with use of internal and external datasets, the importance of using an adequate external dataset obtained from a well-defined clinical cohort to avoid overestimating the clinical performance as a result of overfitting in high-dimensional or overparameterized classification model and spectrum bias, and the essentials for achieving a more robust clinical evaluation. Finally, the authors review the role of clinical trials and observational outcome studies for ultimate clinical verification of diagnostic or predictive artificial intelligence tools through patient outcomes, beyond performance metrics, and how to design such studies. © RSNA, 2018
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“This common scenario means that estimations of AI performance based on internal test data may overestimate its real-world performance on external data [73–75].”
From Fairness of artificial intelligence in healthcare: review and recommendations (2024) · cites this paper as [74]
In the citing paper
“Similar to internal validation of the AIPM, external AIPM model validation can be based on discrimination (area under the receiver operating characteristic curve, sensitivity, specificity, positive and negative predictive values), calibration (calibration plot)5,6,13,17,49,56,78, and Decision Curve Analysis5,6,17,49,68,72.”
From Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review (2022) · cites this paper as [56]
In the citing paper
“To ensure the generalizability of the AIPM to the intended healthcare setting, developers are advised to extensively validate the model for representative data from that setting6–8,10,13–15,24,27,56,64,66,68,72,77,79,87,88 (see phase 1, Representativeness).”
From Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review (2022) · cites this paper as [56]
In the citing paper
“The literature recommends to assess generalizability on external data from a different time period, place, or healthcare setting3,7,8,10,16,17,27,56,68,72,79.”
From Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review (2022) · cites this paper as [56]
In the citing paper
“Although prospective validation is rare, it is preferred by the literature5,14,56, as it provides a better idea of the AIPM’s true applicability to medical practice and allows the healthcare professionals to identify and review errors in real time19,72.”
From Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review (2022) · cites this paper as [56]
4 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
The Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970
Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362
QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies
Whiting, P. F., Rutjes, A. W. S., Westwood, M. E., Mallett, S., Deeks, J. J., Reitsma, J. B., Leeflang, M. M. G., Sterne, J. A. C., Bossuyt, P. M. M., & the QUADAS-2 Group* (2011) · Annals of Internal Medicine · doi:10.7326/0003-4819-155-8-201110180-00009 · Cited by 14,199
(2016) · Cited by 11,679
Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., Venugopalan, S., Widner, K., Madams, T., Cuadros, J., et al. (2016) · JAMA · doi:10.1001/jama.2016.17216 · Cited by 7,697
Collins, G. S., Reitsma, J. B., Altman, D. G., & Moons, K. G. M. (2015) · BMJ · doi:10.1136/bmj.g7594 · Cited by 4,388
Ehteshami Bejnordi, B., Veta, M., Johannes van Diest, P., van Ginneken, B., Karssemeijer, N., Litjens, G., van der Laak, J. A. W. M., and the CAMELYON16 Consortium, Hermsen, M., Manson, Q. F., et al. (2017) · JAMA · doi:10.1001/jama.2017.14585 · Cited by 3,293
Lakhani, P., & Sundaram, B. (2017) · Radiology · doi:10.1148/radiol.2017162326 · Cited by 1,775
STARD 2015: An Updated List of Essential Items for Reporting Diagnostic Accuracy Studies
Bossuyt, P. M., Reitsma, J. B., Bruns, D. E., Gatsonis, C. A., Glasziou, P. P., Irwig, L., Lijmer, J. G., Moher, D., Rennie, D., de Vet, H. C. W., et al. (2015) · Radiology · doi:10.1148/radiol.2015151516 · Cited by 1,337
Deep Learning in Medical Imaging: General Overview
Lee, J.-G., Jun, S., Cho, Y.-W., Lee, H., Kim, G. B., Seo, J. B., & Kim, N. (2017) · Korean Journal of Radiology · doi:10.3348/kjr.2017.18.4.570 · Cited by 1,276
Research works printed but not linked: 3
- Steyerberg EW, 2010, Clinical prediction models: a practical approach to development, validation, and updating, 83
- Steyerberg EW, 2010, Clinical prediction models: a practical approach to development, validation, and updating, 299
- Newman TB, 2013, Designing clinical research, 117
Cited by
Items 601–700 of 1,000
Artificial Intelligence Techniques Introduced Into Evolutionary Games and Simulation Studies
Li, X., Zhang, L., & Wang, P. (2025) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2024.3515085 · Cited by 5
Wu, X., & Yao, W. (2026) · Journal of Surgical Oncology · doi:10.1002/jso.70167 · Cited by 5
Ardila, C. M., Pineda‐Vélez, E., Vivares‐Builes, A. M., & Díaz-Laclaustra, A. I. (2026) · Medical Sciences · doi:10.3390/medsci14020183 · Cited by 5
“Imaging-based radiomics and deep learning frequently show promising apparent discrimination, yet generalizability across scanners, institutions, and acquisition protocols remains an unresolved challenge [27,28].”
Liu, N., Han, G., Gu, Q., Zhang, Y., & Chen, M. M. (2026) · Cell Death and Disease · doi:10.1038/s41419-026-08769-z · Cited by 5
Shen, S., Qi, W., Liu, X., Zeng, J., Li, S., Peng, G., Li, P., Wang, J., Lü, X., & Cao, S. (2026) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2026.103474 · Cited by 5
Artificial Intelligence and Machine Learning in Integrated Diagnostic
Milan, L. (2023) · Springer eBooks · doi:10.1007/978-3-031-35213-3_2 · Cited by 5
Kusztos, V. E., & Simonetto, D. A. (2025) · Journal of Clinical and Experimental Hepatology · doi:10.1016/j.jceh.2025.102579 · Cited by 5
Khare, V., Agrawal, A., Gupta, P. K., & Saxena, S. N. (2019) · International Journal of Scientific and Research Publications · doi:10.29322/ijsrp.9.12.2019.p9669 · Cited by 5
“AIc anbeusedevenin the remotest areas where expert microscopists are not available.[3] The use of artificial intelligence in medicine is currently of great interest.”
BackgroundDevelopment of breast phantoms using a 3D printer and glandular dose evaluation
Lee, D., Jo, Y., & Yang, S. W. (2021) · Journal of Applied Clinical Medical Physics · doi:10.1002/acm2.13408 · Cited by 5
A Primer into the Current State of Artificial Intelligence in Gastroenterology
Moldoveanu, A. C., & Fierbinteanu-Braticevici, C. G. (2022) · Journal of Gastrointestinal and Liver Diseases · doi:10.15403/jgld-4180 · Cited by 5
Machine learning technologies in CT-based diagnostics and classification of intracranial hemorrhages
Сморчкова, А. К., Khoruzhaya, A. N., Kremneva, E. I., & Petryaikin, A. V. (2023) · Burdenko s Journal of Neurosurgery · doi:10.17116/neiro20238702185 · Cited by 5
Hong, W., Hwang, E. J., Park, C. M., & Goo, J. M. (2023) · Korean Journal of Radiology · doi:10.3348/kjr.2023.0255 · Cited by 5
“The ultimate goal of using AI-CAD is to improve the quality of patient management and patient outcomes [13,14].”
BackgroundArtificial intelligence and neural networks in urology.
Shchamkhalova, K. K., Moscow, R., Merinov, D. S., Артемов, А. В., & Gurbanov, S. S. (2023) · Experimental and Сlinical Urology · doi:10.29188/2222-8543-2023-16-2-32-37 · Cited by 5
Сергеевна, М. А., Ussov, W. Y., Shelkovnikova, T. A., Витальевна, М. О., Игоревна, Р. Н., Евгеньевна, С. А., & Zavadovsky, K. V. (2023) · Сибирский журнал клинической и экспериментальной медицины · doi:10.29001/2073-8552-2023-39-3-13-22 · Cited by 5
Considerations in the assessment of machine learning algorithm performance for medical imaging
Gossmann, A., Sahiner, B., Samala, R. K., Wen, S., Cha, K. H., & Petrick, N. (2024) · Elsevier eBooks · doi:10.1016/b978-0-32-385124-4.00029-5 · Cited by 5
How Well Do AI-Enabled Decision Support Systems Perform in Clinical Settings?
Susanto, A. P., Lyell, D., Widyantoro, B., Berkovsky, S., & Magrabi, F. (2024) · Studies in health technology and informatics · doi:10.3233/shti230971 · Cited by 5
Performance Analysis of Transfer Learning Framework for the Detection of Polyps in Colorectal Cancer
Chaudhari, Y., Jani, A., Sanghvi, H. A., Pandya, A. S., Gupta, V., & Baxi, D. (2024) · International Journal of Intelligent Systems and Applications in Engineering · Cited by 5
CT colonography interpretation: how to maximize polyp detection and minimize overcalling
Park, S. H., & Kim, D. H. (2018) · Abdominal Radiology · doi:10.1007/s00261-018-1455-x · Cited by 5
Self-citationHistogram-derived modified thresholds for coronary artery calcium scoring with lower tube voltage
Kim, S., Lee, C. J., Han, K., Lee, K. H., Lee, H., & Park, S. (2021) · Scientific Reports · doi:10.1038/s41598-021-96695-9 · Cited by 5
Self-citationMonitoring Methodology for an AI Tool for Breast Cancer Screening Deployed in Clinical Centers
Aguilar, C., Pacilè, S., Weber, N., & Fillard, P. (2023) · Life · doi:10.3390/life13020440 · Cited by 5
“These data have not been used for algorithm development to ascertain its generalizability [8,13,14].”
BackgroundMethodIntroducing Computer Vision into Healthcare Workflows
Mosquera, C., Lara, M. A. R., Díaz, F. N., Binder, F., & Benítez, S. (2023) · Health informatics · doi:10.1007/978-3-031-17666-1_4 · Cited by 5
GAN based ROI conditioned synthesis of medical image for data augmentation
Kim, Y., Lee, J. H., Kim, C., Jin, K. N., & Park, C. M. (2023) · SPIE Medical Imaging: Image Processing · doi:10.1117/12.2654458 · Cited by 5
“However, there exists regularizations in many countries in data sharing,(5) so medical Artificial Intelligence (AI) always suffers from less generalizability and difficulty in validation.(6)”
BackgroundTélémédecine, santé connectée, éthique numérique : enjeux de la médecine au XXIème siècle
Simon, P. (2018) · Presses de l'Université Toulouse Capitole eBooks · doi:10.4000/books.putc.4326 · Cited by 5
Marcén, A. G. (2020) · Mirai Estudios Japoneses · doi:10.5209/mira.67233 · Cited by 5
Toward Real-World Computational Nephropathology
Calumby, R. T., Duarte, A. A., Ângelo, M. F., Santos, E., Sarder, P., dos‐Santos, W. L. C., & de Oliveira, L. R. (2023) · Clinical Journal of the American Society of Nephrology · doi:10.2215/cjn.0000000000000168 · Cited by 5
Artificial Intelligence using TOPSIS Method
Kumbum, P. K., Adari, V. K., Chunduru, V. K., Gonepally, S., & Amuda, K. K. (2020) · Journal of Computer Science Applications and Information Technology · doi:10.15226/2474-9257/5/1/00147 · Cited by 5
Deep learning based screening model for hip diseases on plain radiographs
Park, J.-W., Ryu, S. M., Kim, H. S., Lee, Y., & Yoo, J. J. (2025) · PLoS ONE · doi:10.1371/journal.pone.0318022 · Cited by 4
“This may be due to the broader range of target diseases potentially leading to lower performance in a clinical setting, which could hinder its clinical utility [46].”
More, P., Saini, B. S., Sharma, R. K., & More, S. S. (2025) · Computer Methods in Biomechanics & Biomedical Engineering · doi:10.1080/10255842.2025.2495249 · Cited by 4
“While artificial intelligence (AI) shows promise in medicine, particularly in diagnosing and processing medical images, careful validation of its clinical value is essential before it can be implemented in practice (Park and Han 2018).”
Liang, W., Yang, C., Qin, L.-H., Lan, M.-N., & Liao, P. (2025) · Academic Radiology · doi:10.1016/j.acra.2025.07.008 · Cited by 4
The (In)Effectiveness of Psychological Targeting: A Meta‐Analytic Review
Perla, R., Maran, T. K., Bagci, B., Kraus, S., Kanbach, D. K., & Bouncken, R. B. (2025) · Psychology and Marketing · doi:10.1002/mar.70073 · Cited by 4
“Even for simple models, minimalistic guidelines recommend an observation ‐ to ‐ feature ratio of at least 10 – 20 to avoid issues stemming from the curse of dimensionality (Balki et al. 2019; Park and Han 2018).”
Feng, J.-W., Zhu, Y.-L., Zhang, L., Yang, Y., Qin, A., Liu, S., & Jiang, Y. (2025) · Insights into Imaging · doi:10.1186/s13244-025-02145-9 · Cited by 4
Juan, C.-E., Muzakky, H., Chang, C.-C., Chou, P.-L., Li, Y.-H., Lee, T.-Y., Juan, C.-H., Tsai, M.-T., Chen, C.-W., & Juan, C.-J. (2026) · Scientific Reports · doi:10.1038/s41598-025-34596-x · Cited by 4
Das, A., Arora, D., Deswal, G., Grewal, A. S., & Bansal, S. (2026) · Journal of the National Medical Association · doi:10.1016/j.jnma.2026.02.007 · Cited by 5
The role of artificial intelligence in virtual emergency care: a systematic review
Shankar, R., Wang, L. C., Ho, S. H., Yee, I., Fong, L. M., Gollamudi, S. P. K., Wong, T. C., & Wong, S. X. L. (2026) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2026.106411 · Cited by 4
Artificial intelligence (AI) imaging models optimization: From pre-processing to validation
Chierici, A. P., Guo, J., Goffart, S., Bakhouche, A., Delingette, H., Lareyre, F., & Raffort, J. (2026) · European Journal of Radiology Artificial Intelligence · doi:10.1016/j.ejrai.2026.100102 · Cited by 5
Artificial Intelligence-Based Prognostic Models for Postoperative Outcomes in Vitreoretinal Surgery
Al-Ani, A., Connors, L., Mikhail, D., Alkhawaja, M., Yang, L., Ambikkumar, A., Punja, K. G., Costello, F., Gooi, P., & Munro, M. (2026) · Ophthalmology Retina · doi:10.1016/j.oret.2026.04.022 · Cited by 4
Sunwoo, L., Ryu, W.-S., Buch, K. A., Conklin, J., Mehan, W. A., Desalvo, M. N., Loken, E. K., Rincon, S., Rocha, T., Succi, M. D., et al. (2026) · Journal of NeuroInterventional Surgery · doi:10.1136/jnis-2026-025339 · Cited by 4
“26 The reader study gave two complementary BHRs: a case level BHR of 2.89 (approximately three additional correct diagnoses per one new error) and a reliance level BHR of 9.25 isolating AI causal effects.”
InfluentialFlanders, A. E., Peng, Y., Prevedello, L. M. S., Ball, R. L., Colak, E., Menon, P. G., Shih, G., Lin, H., & Lakhani, P. C. (2026) · npj Health Systems · doi:10.1038/s44401-026-00100-4 · Cited by 4
“Usingall29,766cases,wecomparedAI result performance against four alternate ground truth de fi nitions (Top-3 Ensemble,Full-9Ensemble,GPT4o,andConsensus)usingMCC.”
Translational gaps in immuno-AI: From algorithmic accuracy to clinical trust
Oisakede, E. O., Daniel, R. I. A., Olawuyi, O. F., Alabi, J. O., Analikwu, C. C., & Olawade, D. B. (2026) · Human Immunology · doi:10.1016/j.humimm.2026.111774 · Cited by 4
A five-phase evaluation framework for diagnostic and predictive medical artificial intelligence
Ye, Z., Chen, Y., Huang, X., Chen, M., Wang, W., Zhu, H., Han, K., Wang, J., Lu, Q., Zhao, Y., et al. (2026) · npj Digital Medicine · doi:10.1038/s41746-026-03155-7 · Cited by 4
Self-citationPrimary Screening System for Sarcopenia in Elderly People Based on Artificial Intelligence
de Colima, U., Díaz, S. A., Bricio-Barrios, E. E., de Colima, I. T., Trujillo, X., de Colima, U., González-Farias, J. R., de Colima, U., Bricio‐Barrios, J. A., de Colima, U., et al. (2023) · Revista Mexicana de Ingeniería Biomédica · doi:10.17488/rmib.44.4.4 · Cited by 4
Investigation of distributed learning for automated lesion detection in head MR images
Yamada, A., Hanaoka, S., Takenaga, T., Miki, S., Yoshikawa, T., & Nomura, Y. (2024) · Radiological Physics and Technology · doi:10.1007/s12194-024-00827-5 · Cited by 4
“Recently, several guides have suggested using data gathered from multiple institutions to develop medical image processing based on artificial intelligence [7, 8].”
BackgroundPancreatic Cancer Classification Based on Deep Learning
Gomathi, P. (2025) · Journal of Information Systems Engineering & Management · doi:10.52783/jisem.v10i3.6223 · Cited by 4
“Park [5], It centers on practical uses of AI in radiology of the chest and abdomen, particularly imaging of the pancreas.”
Martín‐Noguerol, T., Díaz-Angulo, C., Luna, A., Segovia, F., Gómez-Río, M., & Górriz, J. M. (2025) · European Journal of Radiology · doi:10.1016/j.ejrad.2025.112255 · Cited by 4
Reasoning with AI: Six Essential Factors for Augmenting Human Expertise in the Workplace
Koon, S. (2025) · Progress in IS · doi:10.1007/978-3-031-83512-4_6 · Cited by 4
Canales-Fiscal, M. R., Tamez‐Peña, J. G., & Mudduluru, S. (2023) · SPIE Medical Imaging: Computer-Aided Diagnosis · doi:10.1117/12.2654025 · Cited by 4
“This is especially true in the clinical setting and is well outlined by Park and Han[20].”
BackgroundShin, H. J., Kim, M. H., Son, N., Han, K., Kim, E., Kim, Y. C., Park, Y. S., Lee, E. H., & Kyong, T. (2023) · Diagnostics · doi:10.3390/diagnostics13122090 · Cited by 4
“Additionally, we strived to present the most objective and accurate analysis in conjunction with two statistical experts for the research methodology and analytical aspect, while following various methodological proofs and advices [35,36].”
MethodSelf-citationNew psychological education: Leveraging the power of ChatGPT and artificial intelligence
Lin, Y. (2024) · Applied and Computational Engineering · doi:10.54254/2755-2721/36/20230450 · Cited by 4
Rofik, R., Artiyani, F., & Pertiwi, D. A. A. (2024) · Journal of Information System Exploration and Research · doi:10.52465/joiser.v2i2.249 · Cited by 4
“Disease diagnosis is a complicated process of identifying the type of disease in the field of medicine [6], [7].”
BackgroundGonzález-Pérez, P. P., & Sánchez-Gutiérrez, M. E. (2022) · Intelligent Data Analysis · doi:10.3233/ida-215826 · Cited by 4
Lekadir, K. (2024) · European Heart Journal · doi:10.1093/eurheartj/ehad775 · Cited by 4
Current and Future Trends in Life Sciences Training: Questionnaire Study
Magagna, W., Wang, N., & Peck, K. L. (2020) · JMIR Medical Education · doi:10.2196/15877 · Cited by 4
“medical imaging [5,6] and automating medical diagnosis and prediction [7,8].”
BackgroundClinician Cognition and Artificial Intelligence in Medicine
Chang, A. C. (2020) · Elsevier eBooks · doi:10.1016/b978-0-12-823337-5.00007-x · Cited by 4
Developing an Effective e-Learning Platform
Alomran, N. Y. A., Alameer, A. O. M., Alherz, M. S. K., Tayfour, M. F., Alshabanah, M., Alrajhi, D., & Alsmadi, M. K. (2020) · International Journal of Scientific Research in Science and Technology · doi:10.32628/ijsrst207336 · Cited by 4
Jianying, Z., Zhi-jun, W., Bo, Z., Yongqi, Y., & Liu, Y. (2021) · IEEJ Transactions on Electrical and Electronic Engineering · doi:10.1002/tee.23322 · Cited by 4
Identification of COVID-19 with CT scans using radiomics and DL-based features
Dalal, S., Singh, J. P., Tiwari, A. K., & Kumar, A. (2024) · Network Modeling Analysis in Health Informatics and Bioinformatics · doi:10.1007/s13721-024-00448-3 · Cited by 4
“…acknowledge these limitations, we are committed to addressing them through subsequent validation studies, including cohort, clinical outcome, and cost-effectiveness analyses, to ensure the robustness and applicability of our COVID-19 detection algorithm in real-world scenarios (Park and Han 2018).”
Classification of Breast Cancer Diagnosis Systems Using Artificial Intelligence Techniques: Survey
abokaff, L. (2022) · SN Computer Science · doi:10.1007/s42979-022-01275-x · Cited by 4
“so that, Most authors explain key methodology points involved in a clinical evaluation of artificial intelligence technology for use in diagnostic or predictive models in which artificial deep neural networks are used, mainly from the standpoints of clinical epidemiology and biostatistics so it helps the expert in the…”
BackgroundKline, T. L., Kitamura, F., Pan, I., Korchi, A. M., Tenenholtz, N., Moy, L. P., Gichoya, J. W., Santos, I. M. A., Blumer, S. L., Hwang, M. Y., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2202.01863 · Cited by 4
Adopting Artificial Intelligence in Veterinary Diagnostics: A Scoping Review of Key ChallengesPreprint
Farhoodimoghadam, M., Brandt, C., Keller, S. M., Reagan, K. L., Zwingenberger, A. L., & Brown, C. T. (2025) · MetArXiv (OSF Preprints) · doi:10.31222/osf.io/gy9pz_v3 · Cited by 4
Cindrakasih, R., Jahara, J., Soegiarto, I., Ma’sum, H., & Asmuri, A. (2024) · International Journal of Educational Narratives · doi:10.70177/ijen.v2i2.822 · Cited by 3
“Lecturer participation in community service activities and service to institutions is also an integral part of performance evaluation (Park & Han, 2018).”
BackgroundSocially beneficial metaverse: Framework, technologies, applications, and challenges
Xu, X., Zhou, X., Bilal, M., Zeadally, S., Crowcroft, J., Qi, L., & Xue, S. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111198 · Cited by 3
Clinical Validation in AI for Healthcare: An Experiential Learning
Nabhani‐Gebara, S., Zacharias, L., Martí‐Bonmatí, L., Galiana-Bordera, A., Colantonio, S., Chouvarda, I., & Elkhoury, G. (2025) · Springer eBooks · doi:10.1007/978-3-031-89963-8_12 · Cited by 3
Wang, Y., Zhao, J. L., Ba, Y., Mancenido, M. V., Chiou, E. K., & Maciejewski, R. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2564272 · Cited by 3
“…various applications to enhance automation, especially in high-stakes and time-sensitive cases where the cost of system errors could result in catastrophic consequences, like security checks (Liang et al., 2019), autonomous driving (Rao & Frtunikj, 2018), and medical diagnosis (Park & Han, 2018).”
Jia, L., Du, G., Fan, Z., Li, X., Liu, H., Zhang, J., Li, D., Yan, L., Jiu, J., Li, R., et al. (2025) · Knee Surgery Sports Traumatology Arthroscopy · doi:10.1002/ksa.70191 · Cited by 3
Immunofixation electrophoresis image interpretation using transfer learning method
Öztaş, B., & Kösesoy, İ. (2025) · Clinica Chimica Acta · doi:10.1016/j.cca.2025.120726 · Cited by 3
Heimer, M. M., Dexl, J., Ta, J., Ebner, R., Herr, F. L., Orasanin, L., Jeblick, K., Adams, L. C., Sundar, L. K. S., Tufman, A., et al. (2025) · European Journal of Nuclear Medicine and Molecular Imaging · doi:10.1007/s00259-025-07677-2 · Cited by 3
Evaluation of large language models in assigning PI-RADS v2.1 categories for prostate MRI reports
Dölek, B. A., & Beşler, M. S. (2026) · BMC Urology · doi:10.1186/s12894-025-02038-5 · Cited by 3
“Applications include summarizing key findings [22, 23],, answering image-related questions [24], converting free text into structured reports [25, 26] and offering differential diagnoses [27, 28].”
AI for screening in healthcare: promise and challenges
Saito, K., Walston, S. L., Takita, H., Mitsuyama, Y., Arita, Y., & Ueda, D. (2026) · Abdominal Radiology · doi:10.1007/s00261-025-05370-4 · Cited by 3
“The rarity of the target condition demands that AI screening tools be extraordinarily well-calibrated to achieve extremely high specificity without sacrificing sen - sitivity [37 ].”
Duwe, G., Moench, K., Kauth, V., Angeloni, M., Eckhoff, J., Görtz, M., Hoefert, S., Kocar, T. D., Kollitsch, L., Mehralivand, S., et al. (2026) · Die Urologie · doi:10.1007/s00120-026-02778-8 · Cited by 3
Fuzzing the brain: automated stress testing for the safety of ML-driven neurostimulation
Downing, M., Peng, M., Granley, J., Beyeler, M., & Bultan, T. (2026) · Journal of Neural Engineering · doi:10.1088/1741-2552/ae4927 · Cited by 3
“Because they would prescribe electrical stimuli in real time, their outputs must adhere to established limits on charge density, instantaneous current, and active electrode count (Park and Han 2018).”
Artificial intelligence robots for mental health applications: a scoping review
Dong, P., Zhang, S., Zheng, X., Yuan, W., Wu, L., & Chen, Y. (2026) · Psychiatry Research · doi:10.1016/j.psychres.2026.117059 · Cited by 3
Sharma, V., Chawla, G. K., Kukreti, S., Ahuja, K., & Singh, S. (2026) · Exploration of Medicine · doi:10.37349/emed.2026.1001383 · Cited by 3
Alidina, Z., Banani, I., Abiha, U. E., Sultan, U., & Pawlik, T. M. (2026) · Cancers · doi:10.3390/cancers18060937 · Cited by 2
“However, deep learning approaches, especially convolutional neural networks (CNNs), often demonstrated higher specificity, suggesting potential advantages to reduce false positives in various clinical settings [41,44,45].”
HEGAZY, N. Y., & Sawah, M. S. (2026) · Scientific Reports · doi:10.1038/s41598-026-42492-1 · Cited by 3
Nguyen, H. T. T., Le, V. Q., Dinh‐Xuan, A. T., & Nguyen, L. N. (2026) · Diagnostics · doi:10.3390/diagnostics16081127 · Cited by 3
“These include spectrum bias arising from case–control study designs, use of vendor-curated datasets, differences in imaging acquisition protocols, and potential dataset shift between training and real-world deployment environments [15–17].”
Zhao, Y., Zhang, Y., Zhang, J., Chen, C., Li, P., Li, J., & Fu, Q. (2026) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2026.1734208 · Cited by 3
“Consequently, it is challenging for clinical practitioners and technology developers to derive clear, comparable conclusions about the efficacy of different models (8).”
Perlmutter, J. W., & Joseph, M. (2025) · Education and human development · doi:10.5772/intechopen.1014025 · Cited by 3
Survey of the Knowledge of Korean Radiology Residents on Medical Artificial Intelligence
Lee, H., Park, S. H., Kim, C., Kim, S., & Cha, J. (2020) · Journal of the Korean Society of Radiology · doi:10.3348/jksr.2019.0179 · Cited by 3
Self-citationDeep Learning Approach to Classify Brain Tumors from Magnetic Resonance Imaging Images
Mohammed, A. A. A. (2024) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2024.0150587 · Cited by 3
“It was also used to fine-tune hyperparameters, and select the best-fit model [17].”
MethodLumbar Radicular Pain in the Eyes of Artificial Intelligence: Can You ‘Imagine’ What I ‘Feel’?
Temel, M. H., Erden, Y., & Bağcıer, F. (2024) · World Neurosurgery · doi:10.1016/j.wneu.2024.09.075 · Cited by 3
Explainable AI for automated respiratory misalignment detection in PET/CT imaging
Salimi, Y., Mansouri, Z., Amini, M., Mainta, I., & Zaidi, H. (2024) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ad8857 · Cited by 3
“Heterogenous, vast, and inclusive curated datasets with high-quality images and labels are essential for developing generalizable and robust models suitable for commercialization and clinical exploitation (Park and Han 2018).”
Integrated Photonic Processor Implementing Digital Image Convolution
Wang, C., Wu, W., Wang, Z., Zhang, Z., Xiong, W. H., & Deng, L. (2025) · Electronics · doi:10.3390/electronics14040709 · Cited by 3
Abdelmahdy, N. E. E., Suliman, E. T. A. A., Mohmed, F. M. O., Elamin, N. S. A., Yousif, B. A. H., & Ahmmed, N. A. M. (2025) · Cureus · doi:10.7759/cureus.83543 · Cited by 3
“None of the included studies tested their models on independent, geographically diverse cohorts, a cornerstone of robust AI validation [24].”
Bralić, N., Bandić, R., Vuković, M., Matijaca, D., Valsami, R., Zoumpoulakis, P., Schnitzer, K., Levula, M., Roine, R., Viitala, A., et al. (2026) · Frontiers in Medical Technology · doi:10.3389/fmedt.2026.1857401 · Cited by 3
Fine-Grained Bandwidth Estimation for Smart Grid Communication Network
Luo, J., Liao, J., Zhang, C., Wang, Z., Zhang, Y., Xu, J., & Huang, Z. (2021) · Intelligent Automation & Soft Computing · doi:10.32604/iasc.2022.022812 · Cited by 3
“In recent years, deep learning models based on artificial neural networks have achieved outstanding performances for many difficult tasks like computer vision [29–32], medical diagnosis [33], translation [34], path planning [35] and semantic understanding [36–39].”
BackgroundLu, Y., & Lü, B. (2021) · Artificial Intelligence in Gastrointestinal Endoscopy · doi:10.37126/aige.v2.i3.50 · Cited by 3
An Intelligent Model for Improved Breast Cancer Prognosis
Iloghalu, C. O., F, E. U., John-Otumu, A. M., Nwokonkwo, O. C., Oshoiribhor, E. O., Onyeakazi, J. C., Aliga, A. P., Okolie, S. A., Nwokorie, E. C., & Nnadi, L. C. (2023) · International Journal of Electronics and Communication Engineering · doi:10.14445/23488549/ijece-v10i8p104 · Cited by 3
Artificial Intelligence in Small Bowel Endoscopy: Current Perspectives and Future Directions
Meher, D., Gogoi, M., Bharali, P., Anirvan, P., & Singh, S. P. (2020) · Journal of Digestive Endoscopy · doi:10.1055/s-0040-1717824 · Cited by 3
[18F]FDG-PET/CT Texture Analysis in “Hot” Thyroid Nodules: Results of the validation Cohort
Sollini, M. (2019) · Biomedical Journal of Scientific & Technical Research · doi:10.26717/bjstr.2019.18.003110 · Cited by 3
Walczak, S. (2019) · IGI Global eBooks · doi:10.4018/978-1-7998-1204-3.ch021 · Cited by 3
Stachel, A. G. (2020) · CUNY Academic Works (City University of New York) · doi:10.5281/zenodo.3839988 · Cited by 3
Liew, C. J. Y., Quah, J., Goh, H. L., & Venkataraman, N. (2020) · medRxiv · doi:10.1101/2020.05.25.20113084 · Cited by 3
“Three separate patient sample sets, training, validation and test sets were created (18,19).”
BackgroundWong, L. M., Ai, Q. Y. H., Mo, F. K. F., Poon, D. M. C., & King, A. D. (2020) · medRxiv · doi:10.1101/2020.07.09.20148817 · Cited by 3
“Of the 201 cases, 6 were randomly sampled as the training-validation set, which refers to a small set of data unseen during training to monitor whether over-fitting occurred as described in [27], and the remaining 195 cases were analyzed with 3-fold cross-validation.”
MethodBenjamin, M., Engelhard, G., Aisen, A. M., Aradi, Y., & Benjamin, E. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.13781 · Cited by 3
“For algorithms to be generalizable for deployment in diverse settings, performance should be verified using appropriate external data, beyond the data sets on which they are initially developed [16, 17].”
BackgroundZhao, C.-Y., Luo, J., & Kong, J.-L. (2026) · International Journal of Surgery · doi:10.1097/js9.0000000000004865 · Cited by 3
Medical Image Perception Research in the Emerging Age of Artificial Intelligence
Jacobson, F. L. (2019) · Radiology · doi:10.1148/radiol.2019194020 · Cited by 2
Shih, Y.-C., Ko, C., Wang, S.-Y., Chang, C.-Y., Lin, S.-S., Huang, C.-W., Cheng, M., Chen, C., & Wu, Y. (2025) · European Journal of Nuclear Medicine and Molecular Imaging · doi:10.1007/s00259-025-07243-w · Cited by 2
“To ensure the generalizability of a model for clinical application, the patient population in the training dataset should closely reflect the population that the model will serve [ 23, 24 ].”
Privacy-Centric Seizure Detection Using Surface Normals, Pose and Segmentation Masks
Ponnambalam, K. G., Ilyas, T., Sivathamboo, S., Ge, Z., Kwan, P., Kuhlmann, L., & Mehta, D. S. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4972-6_25 · Cited by 2
Diagnostic performance of artificial intelligence in detecting bladder carcinoma
Yuan, S., Yang, K., Wu, H., Peng, L., Li, R., Deng, D., & Liu, X. (2025) · World Journal of Urology · doi:10.1007/s00345-025-06144-9 · Cited by 2
“External validation performance differences can be attributed to variations in imaging protocols, patient demographics, and tumor characteristics between datasets, reflecting real-world heterogeneity [46, 47 ].”
Li, Z., Li, H., Tian, B., Liu, H., Jiang, Y., Yang, P., Fan, G., & Liu, H. (2026) · Journal of Autoimmunity · doi:10.1016/j.jaut.2026.103560 · Cited by 2
Metadata
- Authors
- Park, S. H., & Han, K.
- Affiliations
- Yonsei University (KR)
- Venue
- Radiology
- Published
- 2018-03
- Volume
- 286
- Issue
- 3
- Pages
- 800-809
- ISSN
- 0033-8419 (ISSN-L)
- 1527-1315
- OpenAlex
- W2783687327
- Cited by
- 894
- References
- 49
- Citations by year
- 2026: 123 · 2025: 98 · 2024: 96 · 2023: 135 · 2022: 111 · 2021: 121 · 2020: 103 · 2019: 80 · 2018: 25
- FWCI
- 1.84
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Radiology (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Ministry of Trade, Industry and Energy
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
- Keywords
- artificial intelligence in healthcare, deep neural network, medical image diagnosis, prediction model, discrimination and calibration, overfitting, spectrum bias, external validation, disease prevalence, outcomes research, high-dimensional models
- MeSH terms
- Artificial Intelligence, Data Interpretation, Statistical, Diagnostic Imaging, Humans, Image Interpretation, Computer-Assisted, Terminology as Topic, Predictive Value of Tests, Technology Assessment, Biomedical, Neural Networks, Computer
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.