Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies / (Record no. 576)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 05992naa a22006137i 4500 |
| 001 - CONTROL NUMBER | |
| control field | UMUN-OA-20261005-AI-019 |
| 003 - CONTROL NUMBER IDENTIFIER | |
| control field | local |
| 005 - DATE AND TIME OF LATEST TRANSACTION | |
| control field | 20261005174824.0 |
| 006 - FIXED-LENGTH DATA ELEMENTS--ADDITIONAL MATERIAL CHARACTERISTICS | |
| fixed length control field | m o d |
| 007 - PHYSICAL DESCRIPTION FIXED FIELD--GENERAL INFORMATION | |
| fixed length control field | cr|||||||||||| |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION | |
| fixed length control field | 261005s2020 xx o u000 0 eng d |
| 024 7# - OTHER STANDARD IDENTIFIER | |
| Standard number or code | 10.1136/bmj.m689 |
| Source of number or code | doi |
| 035 ## - SYSTEM CONTROL NUMBER | |
| System control number | (local)OpenAlex:W3013681994 |
| 040 ## - CATALOGING SOURCE | |
| Original cataloging agency | local |
| Language of cataloging | eng |
| Transcribing agency | local |
| 041 0# - LANGUAGE CODE | |
| Language code of text/sound track or separate title | eng |
| 100 0# - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Myura Nagendran |
| Relator term | author. |
| 245 10 - TITLE STATEMENT | |
| Title | Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies / |
| Statement of responsibility, etc. | Myura Nagendran; Yang Chen; Christopher A Lovejoy [and others]. |
| 264 #1 - PRODUCTION, PUBLICATION, DISTRIBUTION, MANUFACTURE, AND COPYRIGHT NOTICE | |
| Place of production, publication, distribution, manufacture | [Place of publication not identified] : |
| Name of producer, publisher, distributor, manufacturer | [publisher not identified], |
| Date of production, publication, distribution, manufacture, or copyright notice | 2020. |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | 1 online resource (1 article). |
| 336 ## - CONTENT TYPE | |
| Content type term | text |
| Content type code | txt |
| Source | rdacontent |
| 337 ## - MEDIA TYPE | |
| Media type term | computer |
| Media type code | c |
| Source | rdamedia |
| 338 ## - CARRIER TYPE | |
| Carrier type term | online resource |
| Carrier type code | cr |
| Source | rdacarrier |
| 500 ## - GENERAL NOTE | |
| General note | Publication type: Review article. |
| 500 ## - GENERAL NOTE | |
| General note | Linked open-access copy: published version. |
| 506 0# - RESTRICTIONS ON ACCESS NOTE | |
| Terms governing access | Open access; no subscription required for the linked open-access version. |
| Standardized terminology for access restriction | Unrestricted online access |
| Source of term | star |
| 520 3# - SUMMARY, ETC. | |
| Summary, etc. | OBJECTIVE: To systematically examine the design, reporting standards, risk of bias, and claims of studies comparing the performance of diagnostic deep learning algorithms for medical imaging with that of expert clinicians. DESIGN: Systematic review. DATA SOURCES: Medline, Embase, Cochrane Central Register of Controlled Trials, and the World Health Organization trial registry from 2010 to June 2019. ELIGIBILITY CRITERIA FOR SELECTING STUDIES: Randomised trial registrations and non-randomised studies comparing the performance of a deep learning algorithm in medical imaging with a contemporary group of one or more expert clinicians. Medical imaging has seen a growing interest in deep learning research. The main distinguishing feature of convolutional neural networks (CNNs) in deep learning is that when CNNs are fed with raw data, they develop their own representations needed for pattern recognition. The algorithm learns for itself the features of an image that are important for classification rather than being told by humans which features to use. The selected studies aimed to use medical imaging for predicting absolute risk of existing disease or classification into diagnostic groups (eg, disease or non-disease). For example, raw chest radiographs tagged with a label such as pneumothorax or no pneumothorax and the CNN learning which pixel patterns suggest pneumothorax. REVIEW METHODS: Adherence to reporting standards was assessed by using CONSORT (consolidated standards of reporting trials) for randomised studies and TRIPOD (transparent reporting of a multivariable prediction model for individual prognosis or diagnosis) for non-randomised studies. Risk of bias was assessed by using the Cochrane risk of bias tool for randomised studies and PROBAST (prediction model risk of bias assessment tool) for non-randomised studies. RESULTS: Only 10 records were found for deep learning randomised clinical trials, two of which have been published (with low risk of bias, except for lack of blinding, and high adherence to reporting standards) and eight are ongoing. Of 81 non-randomised clinical trials identified, only nine were prospective and just six were tested in a real world clinical setting. The median number of experts in the comparator group was only four (interquartile range 2-9). Full access to all datasets and code was severely limited (unavailable in 95% and 93% of studies, respectively). The overall risk of bias was high in 58 of 81 studies and adherence to reporting standards was suboptimal (<50% adherence for 12 of 29 TRIPOD items). 61 of 81 studies stated in their abstract that performance of artificial intelligence was at least comparable to (or better than) that of clinicians. Only 31 of 81 studies (38%) stated that further prospective studies or trials were required. CONCLUSIONS: Few prospective deep learning studies and randomised trials exist in medical imaging. Most non-randomised trials are not prospective, are at high risk of bias, and deviate from existing reporting standards. Data and code availability are lacking in most studies, and human comparator groups are often small. Future studies should diminish risk of bias, enhance real world clinical relevance, improve reporting and transparency, and appropriately temper conclusions. STUDY REGISTRATION: PROSPERO CRD42019123605. |
| 540 ## - TERMS GOVERNING USE AND REPRODUCTION NOTE | |
| Terms governing use and reproduction | Creative Commons Attribution-NonCommercial (licence family recorded by the source; version not supplied in metadata). |
| Uniform Resource Identifier | <a href="https://openalex.org/W3013681994">https://openalex.org/W3013681994</a> |
| 546 ## - LANGUAGE NOTE | |
| Language note | In English. |
| 588 0# - SOURCE OF DESCRIPTION NOTE | |
| Source of description note | Description generated from OpenAlex bibliographic metadata retrieved on 5 October 2026; full text linked from the source. |
| 590 ## - LOCAL NOTE (RLIN) | |
| Local note | Course allocation: B. Sc. Artificial Intelligence. |
| 650 #4 - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | deep learning |
| 650 #4 - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | convolutional neural networks |
| 650 #4 - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | diagnostic imaging |
| 650 #4 - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | diagnostic accuracy |
| 650 #4 - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | reporting guidelines |
| 650 #4 - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | risk of bias |
| 653 ## - INDEX TERM--UNCONTROLLED | |
| Uncontrolled term | B. Sc. Artificial Intelligence |
| 653 ## - INDEX TERM--UNCONTROLLED | |
| Uncontrolled term | UMUN open access collection |
| 653 ## - INDEX TERM--UNCONTROLLED | |
| Uncontrolled term | deep learning |
| 655 #4 - INDEX TERM--GENRE/FORM | |
| Genre/form data or focus term | Review articles. |
| 700 0# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Yang Chen |
| Relator term | author. |
| 700 0# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Christopher A Lovejoy |
| Relator term | author. |
| 700 0# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Anthony C Gordon |
| Relator term | author. |
| 700 0# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Matthieu Komorowski |
| Relator term | author. |
| 700 0# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Hugh Harvey |
| Relator term | author. |
| 700 0# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Eric J Topol |
| Relator term | author. |
| 700 0# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | John P A Ioannidis |
| Relator term | author. |
| 700 0# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Gary S Collins |
| Relator term | author. |
| 700 0# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Mahiben Maruthappu |
| Relator term | author. |
| 773 0# - HOST ITEM ENTRY | |
| Title | BMJ |
| Related parts | Vol. 368, (2020), pages/article m689 |
| International Standard Serial Number | 1756-1833 |
| 856 40 - ELECTRONIC LOCATION AND ACCESS | |
| Uniform Resource Identifier | <a href="https://www.bmj.com/content/bmj/368/bmj.m689.full.pdf">https://www.bmj.com/content/bmj/368/bmj.m689.full.pdf</a> |
| Link text | Read open-access publication |
| Public note | Open access. |
| Access status | 0 |
| Electronic format type | application/pdf |
| 884 ## - DESCRIPTION CONVERSION INFORMATION | |
| Conversion process | Course selection and automated MARC21 enrichment from OpenAlex metadata. |
| Conversion date | 20261005 |
| Identifier of source metadata | https://openalex.org/W3013681994 |
| Conversion agency | local |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Suppress in OPAC | No |
No items available.