Democratizing Artificial Intelligence Imaging Analysis With Automated Machine Learning: Tutorial
Deep learning–based clinical imaging analysis underlies diagnostic artificial intelligence (AI) models, which can match or even exceed the performance of clinical experts, having the potential to revolutionize clinical practice. A wide variety of automated machine learning (autoML) platfo...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2023-10-01
|
| Series: | Journal of Medical Internet Research |
| Online Access: | https://www.jmir.org/2023/1/e49949 |
| _version_ | 1797660935825915904 |
|---|---|
| author | Arun James Thirunavukarasu Kabilan Elangovan Laura Gutierrez Yong Li Iris Tan Pearse A Keane Edward Korot Daniel Shu Wei Ting |
| author_facet | Arun James Thirunavukarasu Kabilan Elangovan Laura Gutierrez Yong Li Iris Tan Pearse A Keane Edward Korot Daniel Shu Wei Ting |
| author_sort | Arun James Thirunavukarasu |
| collection | DOAJ |
| description |
Deep learning–based clinical imaging analysis underlies diagnostic artificial intelligence (AI) models, which can match or even exceed the performance of clinical experts, having the potential to revolutionize clinical practice. A wide variety of automated machine learning (autoML) platforms lower the technical barrier to entry to deep learning, extending AI capabilities to clinicians with limited technical expertise, and even autonomous foundation models such as multimodal large language models. Here, we provide a technical overview of autoML with descriptions of how autoML may be applied in education, research, and clinical practice. Each stage of the process of conducting an autoML project is outlined, with an emphasis on ethical and technical best practices. Specifically, data acquisition, data partitioning, model training, model validation, analysis, and model deployment are considered. The strengths and limitations of available code-free, code-minimal, and code-intensive autoML platforms are considered. AutoML has great potential to democratize AI in medicine, improving AI literacy by enabling “hands-on” education. AutoML may serve as a useful adjunct in research by facilitating rapid testing and benchmarking before significant computational resources are committed. AutoML may also be applied in clinical contexts, provided regulatory requirements are met. The abstraction by autoML of arduous aspects of AI engineering promotes prioritization of data set curation, supporting the transition from conventional model-driven approaches to data-centric development. To fulfill its potential, clinicians must be educated on how to apply these technologies ethically, rigorously, and effectively; this tutorial represents a comprehensive summary of relevant considerations. |
| first_indexed | 2024-03-11T18:38:05Z |
| format | Article |
| id | doaj.art-a86cc8ad4ae342269b109b5653ec07e3 |
| institution | Directory Open Access Journal |
| issn | 1438-8871 |
| language | English |
| last_indexed | 2024-03-11T18:38:05Z |
| publishDate | 2023-10-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | Journal of Medical Internet Research |
| spelling | doaj.art-a86cc8ad4ae342269b109b5653ec07e32023-10-12T15:01:30ZengJMIR PublicationsJournal of Medical Internet Research1438-88712023-10-0125e4994910.2196/49949Democratizing Artificial Intelligence Imaging Analysis With Automated Machine Learning: TutorialArun James Thirunavukarasuhttps://orcid.org/0000-0001-8968-4768Kabilan Elangovanhttps://orcid.org/0000-0002-7711-7368Laura Gutierrezhttps://orcid.org/0000-0001-7416-2350Yong Lihttps://orcid.org/0000-0002-8949-8612Iris Tanhttps://orcid.org/0009-0005-5049-3725Pearse A Keanehttps://orcid.org/0000-0002-9239-745XEdward Korothttps://orcid.org/0000-0002-5687-1564Daniel Shu Wei Tinghttps://orcid.org/0000-0003-2264-7174 Deep learning–based clinical imaging analysis underlies diagnostic artificial intelligence (AI) models, which can match or even exceed the performance of clinical experts, having the potential to revolutionize clinical practice. A wide variety of automated machine learning (autoML) platforms lower the technical barrier to entry to deep learning, extending AI capabilities to clinicians with limited technical expertise, and even autonomous foundation models such as multimodal large language models. Here, we provide a technical overview of autoML with descriptions of how autoML may be applied in education, research, and clinical practice. Each stage of the process of conducting an autoML project is outlined, with an emphasis on ethical and technical best practices. Specifically, data acquisition, data partitioning, model training, model validation, analysis, and model deployment are considered. The strengths and limitations of available code-free, code-minimal, and code-intensive autoML platforms are considered. AutoML has great potential to democratize AI in medicine, improving AI literacy by enabling “hands-on” education. AutoML may serve as a useful adjunct in research by facilitating rapid testing and benchmarking before significant computational resources are committed. AutoML may also be applied in clinical contexts, provided regulatory requirements are met. The abstraction by autoML of arduous aspects of AI engineering promotes prioritization of data set curation, supporting the transition from conventional model-driven approaches to data-centric development. To fulfill its potential, clinicians must be educated on how to apply these technologies ethically, rigorously, and effectively; this tutorial represents a comprehensive summary of relevant considerations.https://www.jmir.org/2023/1/e49949 |
| spellingShingle | Arun James Thirunavukarasu Kabilan Elangovan Laura Gutierrez Yong Li Iris Tan Pearse A Keane Edward Korot Daniel Shu Wei Ting Democratizing Artificial Intelligence Imaging Analysis With Automated Machine Learning: Tutorial Journal of Medical Internet Research |
| title | Democratizing Artificial Intelligence Imaging Analysis With Automated Machine Learning: Tutorial |
| title_full | Democratizing Artificial Intelligence Imaging Analysis With Automated Machine Learning: Tutorial |
| title_fullStr | Democratizing Artificial Intelligence Imaging Analysis With Automated Machine Learning: Tutorial |
| title_full_unstemmed | Democratizing Artificial Intelligence Imaging Analysis With Automated Machine Learning: Tutorial |
| title_short | Democratizing Artificial Intelligence Imaging Analysis With Automated Machine Learning: Tutorial |
| title_sort | democratizing artificial intelligence imaging analysis with automated machine learning tutorial |
| url | https://www.jmir.org/2023/1/e49949 |
| work_keys_str_mv | AT arunjamesthirunavukarasu democratizingartificialintelligenceimaginganalysiswithautomatedmachinelearningtutorial AT kabilanelangovan democratizingartificialintelligenceimaginganalysiswithautomatedmachinelearningtutorial AT lauragutierrez democratizingartificialintelligenceimaginganalysiswithautomatedmachinelearningtutorial AT yongli democratizingartificialintelligenceimaginganalysiswithautomatedmachinelearningtutorial AT iristan democratizingartificialintelligenceimaginganalysiswithautomatedmachinelearningtutorial AT pearseakeane democratizingartificialintelligenceimaginganalysiswithautomatedmachinelearningtutorial AT edwardkorot democratizingartificialintelligenceimaginganalysiswithautomatedmachinelearningtutorial AT danielshuweiting democratizingartificialintelligenceimaginganalysiswithautomatedmachinelearningtutorial |