Back

A Comparative Study: Diagnostic Performance of ChatGPT 3.5, Google Bard, Microsoft Bing, and Radiologists in Thoracic Radiology Cases

2024-01-20 radiology and imaging Title + abstract only
View on medRxiv
Show abstract

PurposeTo investigate and compare the diagnostic performance of ChatGPT 3.5, Google Bard, Microsoft Bing, and two board-certified radiologists in thoracic radiology cases published by The Society of Thoracic Radiology. Materials and MethodsWe collected 124 "Case of the Month" from the Society of Thoracic Radiology website between March 2012 and December 2023. Medical history and imaging findings were input into ChatGPT 3.5, Google Bard, and Microsoft Bing for diagnosis and differential diagnosi...

Predicted journal destinations

1
Scientific Reports
701 training papers
Top 4% 18.2%
2
PLOS ONE
1737 training papers
Top 37% 18.2%
3
Diagnostics
36 training papers
#1 6.1%
4
PLOS Digital Health
88 training papers
Top 6% 4.0%
5
Journal of Clinical Medicine
77 training papers
Top 5% 3.2%
6
Heliyon
57 training papers
Top 0.3% 3.1%
7
Computers in Biology and Medicine
39 training papers
Top 3% 2.0%
8
Cureus
64 training papers
Top 6% 2.0%
9
BMJ Open
553 training papers
Top 48% 2.0%
10
npj Digital Medicine
85 training papers
Top 10% 2.0%
11
Frontiers in Oncology
34 training papers
Top 5% 1.6%
12
Cancers
57 training papers
Top 6% 1.6%
13
Scientific Data
30 training papers
Top 1% 1.6%
14
PeerJ
46 training papers
Top 3% 1.4%
15
Nature Medicine
88 training papers
Top 7% 1.4%
16
NeuroImage
36 training papers
Top 5% 1.2%
17
eLife
262 training papers
Top 38% 1.2%
18
Medicine
29 training papers
Top 3% 1.2%
19
BMC Cancer
21 training papers
Top 5% 1.0%
20
Human Brain Mapping
53 training papers
Top 8% 1.0%
21
Imaging Neuroscience
18 training papers
Top 2% 1.0%
22
NeuroImage: Clinical
77 training papers
Top 12% 0.7%
23
Frontiers in Medicine
99 training papers
Top 23% 0.7%
24
Journal of Medical Internet Research
81 training papers
Top 20% 0.7%
25
Brain and Behavior
19 training papers
Top 2% 0.7%
26
Nature Communications
483 training papers
Top 59% 0.7%