Physician Confidence in Artificial Intelligence: An Online Mobile Survey

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

Background

It is expected that artificial intelligence (AI) will be used extensively in the medical field in the future.

Objective

The purpose of this study is to investigate the awareness of AI among Korean doctors and to assess physicians’ attitudes toward the medical application of AI.

Methods

We conducted an online survey composed of 11 closed-ended questions using Google Forms. The survey consisted of questions regarding the recognition of and attitudes toward AI, the development direction of AI in medicine, and the possible risks of using AI in the medical field.

Results

A total of 669 participants completed the survey. Only 40 (5.9%) answered that they had good familiarity with AI. However, most participants considered AI useful in the medical field (558/669, 83.4% agreement). The advantage of using AI was seen as the ability to analyze vast amounts of high-quality, clinically relevant data in real time. Respondents agreed that the area of medicine in which AI would be most useful is disease diagnosis (558/669, 83.4% agreement). One possible problem cited by the participants was that AI would not be able to assist in unexpected situations owing to inadequate information (196/669, 29.3%). Less than half of the participants(294/669, 43.9%) agreed that AI is diagnostically superior to human doctors. Only 237 (35.4%) answered that they agreed that AI could replace them in their jobs.

Conclusions

This study suggests that Korean doctors and medical students have favorable attitudes toward AI in the medical field. The majority of physicians surveyed believed that AI will not replace their roles in the future.

Related collections

Most cited references 31

Record: found
Abstract: found
Article: found

Is Open Access

Predicting non-small cell lung cancer prognosis by fully automated microscopic pathology image features

Kun-Hsing Yu, Ce Zhang, Gerald Berry … (2016)

Lung cancer is the most prevalent cancer worldwide, and histopathological assessment is indispensable for its diagnosis. However, human evaluation of pathology slides cannot accurately predict patients' prognoses. In this study, we obtain 2,186 haematoxylin and eosin stained histopathology whole-slide images of lung adenocarcinoma and squamous cell carcinoma patients from The Cancer Genome Atlas (TCGA), and 294 additional images from Stanford Tissue Microarray (TMA) Database. We extract 9,879 quantitative image features and use regularized machine-learning methods to select the top features and to distinguish shorter-term survivors from longer-term survivors with stage I adenocarcinoma (P<0.003) or squamous cell carcinoma (P=0.023) in the TCGA data set. We validate the survival prediction framework with the TMA cohort (P<0.036 for both tumour types). Our results suggest that automatically derived image features can predict the prognosis of lung cancer patients and thereby contribute to precision oncology. Our methods are extensible to histopathology images of other organs.

0 comments Cited 348 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: not found
Article: not found

Adapting to Artificial Intelligence

Saurabh Jha, Eric Topol (2016)

0 comments Cited 161 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Somatic Mutations Drive Distinct Imaging Phenotypes in Lung Cancer

Hugo Aerts, Emmanuel Rios Velazquez, Chintan Parmar … (2017)

Tumors are characterized by somatic mutations that drive biological processes ultimately reflected in tumor phenotype. With regard to radiographic phenotypes, generally unconnected through present understanding to the presence of specific mutations, artificial intelligence (AI) methods can automatically quantify phenotypic characters by using predefined, engineered algorithms or automatic deep-learning methods, a process also known as radiomics. Here we demonstrate how imaging phenotypes can be connected to somatic mutations through an integrated analysis of independent datasets of 763 lung adenocarcinoma patients with somatic mutation testing and engineered computed tomography (CT) image analytics. We developed radiomic signatures capable of distinguishing between tumor genotypes in a discovery cohort (n=353) and verified them in an independent validation cohort (n=352). All radiomic signatures significantly outperformed conventional radiographic predictors (tumor volume and maximum diameter). We found a radiomic signature related to radiographic heterogeneity that successfuilly discriminated between EGFR+ and EGFR- cases (AUC=0.69). Combining this signature with a clinical model of EGFR status (AUC=0.70) significantly improved prediction accuracy (AUC=0.75). The highest performing signature was capable of distinguishing between EGFR+ and KRAS+ tumors (AUC=0.80) and, when combined with a clinical model (AUC=0.81), substantially improved its performance (AUC=0.86). A KRAS+/KRAS- radiomic signature also showed significant albeit lower performance (AUC=0.63) and did not improve accuracy of a clinical predictor of KRAS status. Our results argue that somatic mutations drive distinct radiographic phenotypes that can be predicted by radiomics. This work has implications for the use of imaging-based biomarkers in the clinic, as applied non-invasively, repeatedly and at low cost.

0 comments Cited 153 times – based on 0 reviews      Review now

Bookmark

All references

Author and article information

Contributors

Soon Hyo Kwon:

Division of NephrologyDepartment of Internal MedicineSoonchunhyang University HospitalDaesagwanro 59 YoungsanguSeoul, 04401Republic of Korea82 01034413147ksoonhyo@schmc.ac.kr

ORCID: http://orcid.org/0000-0002-4114-4196

Journal

Journal ID (nlm-ta): J Med Internet Res

Journal ID (iso-abbrev): J. Med. Internet Res

Journal ID (publisher-id): JMIR

Title: Journal of Medical Internet Research

Publisher: JMIR Publications (Toronto, Canada )

ISSN (Print): 1439-4456

ISSN (Electronic): 1438-8871

Publication date Collection: March 2019

Publication date (Electronic): 25 March 2019

Volume: 21

Issue: 3

Electronic Location Identifier: e12422

Affiliations

[1 ] Division of Nephrology Department of Internal Medicine Soonchunhyang University Hospital Seoul Republic of Korea

[2 ] Department of Urology Soonchunhyang University Hospital Seoul Republic of Korea

[3 ] Department of Orthopedic Surgery Soonchunhyang University Seoul Hospital Seoul Republic of Korea

[4 ] Department of Internal Medicine New York Medical College New York Health Hospital New York, NY United States

Author notes

Corresponding Author: Soon Hyo Kwon ksoonhyo@ 123456schmc.ac.kr

Author information

Songhee Oh http://orcid.org/0000-0001-7432-0953

Jae Heon Kim http://orcid.org/0000-0002-4490-3610

Sung-Woo Choi http://orcid.org/0000-0001-6263-6037

Hee Jeong Lee http://orcid.org/0000-0002-3950-1641

Jungrak Hong http://orcid.org/0000-0002-9952-8117

Soon Hyo Kwon http://orcid.org/0000-0002-4114-4196

Article

Publisher ID: v21i3e12422

DOI: 10.2196/12422

PMC ID: 6452288

PubMed ID: 30907742

SO-VID: af721e57-842f-48d8-966b-a40916232ecb

License:

This is an open-access article distributed under the terms of the Creative Commons Attribution License ( https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in the Journal of Medical Internet Research, is properly cited. The complete bibliographic information, a link to the original publication on http://www.jmir.org/.as well as this copyright and license information must be included.

History

Date received : 15 October 2018

Date revision requested : 3 December 2018

Date revision received : 9 January 2019

Date accepted : 17 January 2019

Comments

Comment on this article

scite_

Cited by 87

See all cited by

Most referenced authors 582

See all reference authors

- Version 1

Submit your digital health research with an established publisher
- celebrating 25 years of open access