Importance of Patient History in Artificial Intelligence-Assisted Medical Diagnosis : Comparison Study
© Fumitoshi Fukuzawa, Yasutaka Yanagita, Daiki Yokokawa, Shun Uchida, Shiho Yamashita, Yu Li, Kiyoshi Shikino, Tomoko Tsukamoto, Kazutaka Noda, Takanori Uehara, Masatomi Ikusaka. Originally published in JMIR Medical Education (https://mededu.jmir.org)..
Background: Medical history contributes approximately 80% to a diagnosis, although physical examinations and laboratory investigations increase a physician's confidence in the medical diagnosis. The concept of artificial intelligence (AI) was first proposed more than 70 years ago. Recently, its role in various fields of medicine has grown remarkably. However, no studies have evaluated the importance of patient history in AI-assisted medical diagnosis.
Objective: This study explored the contribution of patient history to AI-assisted medical diagnoses and assessed the accuracy of ChatGPT in reaching a clinical diagnosis based on the medical history provided.
Methods: Using clinical vignettes of 30 cases identified in The BMJ, we evaluated the accuracy of diagnoses generated by ChatGPT. We compared the diagnoses made by ChatGPT based solely on medical history with the correct diagnoses. We also compared the diagnoses made by ChatGPT after incorporating additional physical examination findings and laboratory data alongside history with the correct diagnoses.
Results: ChatGPT accurately diagnosed 76.6% (23/30) of the cases with only the medical history, consistent with previous research targeting physicians. We also found that this rate was 93.3% (28/30) when additional information was included.
Conclusions: Although adding additional information improves diagnostic accuracy, patient history remains a significant factor in AI-assisted medical diagnosis. Thus, when using AI in medical diagnosis, it is crucial to include pertinent and correct patient histories for an accurate diagnosis. Our findings emphasize the continued significance of patient history in clinical diagnoses in this age and highlight the need for its integration into AI-assisted medical diagnosis systems.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:10 |
---|---|
Enthalten in: |
JMIR medical education - 10(2024) vom: 08. Apr., Seite e52674 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Fukuzawa, Fumitoshi [VerfasserIn] |
---|
Links: |
---|
Anmerkungen: |
Date Completed 12.04.2024 Date Revised 25.04.2024 published: Electronic Citation Status MEDLINE |
---|
doi: |
10.2196/52674 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM370916344 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM370916344 | ||
003 | DE-627 | ||
005 | 20240425233907.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240411s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.2196/52674 |2 doi | |
028 | 5 | 2 | |a pubmed24n1386.xml |
035 | |a (DE-627)NLM370916344 | ||
035 | |a (NLM)38602313 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Fukuzawa, Fumitoshi |e verfasserin |4 aut | |
245 | 1 | 0 | |a Importance of Patient History in Artificial Intelligence-Assisted Medical Diagnosis |b Comparison Study |
264 | 1 | |c 2024 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 12.04.2024 | ||
500 | |a Date Revised 25.04.2024 | ||
500 | |a published: Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a © Fumitoshi Fukuzawa, Yasutaka Yanagita, Daiki Yokokawa, Shun Uchida, Shiho Yamashita, Yu Li, Kiyoshi Shikino, Tomoko Tsukamoto, Kazutaka Noda, Takanori Uehara, Masatomi Ikusaka. Originally published in JMIR Medical Education (https://mededu.jmir.org). | ||
520 | |a Background: Medical history contributes approximately 80% to a diagnosis, although physical examinations and laboratory investigations increase a physician's confidence in the medical diagnosis. The concept of artificial intelligence (AI) was first proposed more than 70 years ago. Recently, its role in various fields of medicine has grown remarkably. However, no studies have evaluated the importance of patient history in AI-assisted medical diagnosis | ||
520 | |a Objective: This study explored the contribution of patient history to AI-assisted medical diagnoses and assessed the accuracy of ChatGPT in reaching a clinical diagnosis based on the medical history provided | ||
520 | |a Methods: Using clinical vignettes of 30 cases identified in The BMJ, we evaluated the accuracy of diagnoses generated by ChatGPT. We compared the diagnoses made by ChatGPT based solely on medical history with the correct diagnoses. We also compared the diagnoses made by ChatGPT after incorporating additional physical examination findings and laboratory data alongside history with the correct diagnoses | ||
520 | |a Results: ChatGPT accurately diagnosed 76.6% (23/30) of the cases with only the medical history, consistent with previous research targeting physicians. We also found that this rate was 93.3% (28/30) when additional information was included | ||
520 | |a Conclusions: Although adding additional information improves diagnostic accuracy, patient history remains a significant factor in AI-assisted medical diagnosis. Thus, when using AI in medical diagnosis, it is crucial to include pertinent and correct patient histories for an accurate diagnosis. Our findings emphasize the continued significance of patient history in clinical diagnoses in this age and highlight the need for its integration into AI-assisted medical diagnosis systems | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a AI | |
650 | 4 | |a AI diagnosis | |
650 | 4 | |a AI in medicine | |
650 | 4 | |a ChatGPT | |
650 | 4 | |a United States | |
650 | 4 | |a accuracy | |
650 | 4 | |a adolescent | |
650 | 4 | |a adolescents | |
650 | 4 | |a artificial intelligence | |
650 | 4 | |a child | |
650 | 4 | |a children | |
650 | 4 | |a diagnostic accuracy | |
650 | 4 | |a digital health | |
650 | 4 | |a elder | |
650 | 4 | |a elderly | |
650 | 4 | |a female | |
650 | 4 | |a investigative | |
650 | 4 | |a laboratory investigation | |
650 | 4 | |a laboratory investigations | |
650 | 4 | |a mHealth | |
650 | 4 | |a male | |
650 | 4 | |a medical diagnosis | |
650 | 4 | |a medical history | |
650 | 4 | |a mobile health | |
650 | 4 | |a older adult | |
650 | 4 | |a older adults | |
650 | 4 | |a older people | |
650 | 4 | |a older person | |
650 | 4 | |a patient history | |
650 | 4 | |a physical examination | |
650 | 4 | |a physical examinations | |
650 | 4 | |a public health | |
650 | 4 | |a teen | |
650 | 4 | |a teenager | |
650 | 4 | |a teenagers | |
650 | 4 | |a teens | |
650 | 4 | |a treatment | |
650 | 4 | |a youth | |
700 | 1 | |a Yanagita, Yasutaka |e verfasserin |4 aut | |
700 | 1 | |a Yokokawa, Daiki |e verfasserin |4 aut | |
700 | 1 | |a Uchida, Shun |e verfasserin |4 aut | |
700 | 1 | |a Yamashita, Shiho |e verfasserin |4 aut | |
700 | 1 | |a Li, Yu |e verfasserin |4 aut | |
700 | 1 | |a Shikino, Kiyoshi |e verfasserin |4 aut | |
700 | 1 | |a Tsukamoto, Tomoko |e verfasserin |4 aut | |
700 | 1 | |a Noda, Kazutaka |e verfasserin |4 aut | |
700 | 1 | |a Uehara, Takanori |e verfasserin |4 aut | |
700 | 1 | |a Ikusaka, Masatomi |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t JMIR medical education |d 2015 |g 10(2024) vom: 08. Apr., Seite e52674 |w (DE-627)NLM265223024 |x 2369-3762 |7 nnns |
773 | 1 | 8 | |g volume:10 |g year:2024 |g day:08 |g month:04 |g pages:e52674 |
856 | 4 | 0 | |u http://dx.doi.org/10.2196/52674 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 10 |j 2024 |b 08 |c 04 |h e52674 |