Can Chatbot Artificial Intelligence Replace Infectious Diseases Physicians in the Management of Bloodstream Infections? A Prospective Cohort Study
© The Author(s) 2023. Published by Oxford University Press on behalf of Infectious Diseases Society of America. All rights reserved. For permissions, please e-mail: journals.permissionsoup.com..
BACKGROUND: The development of chatbot artificial intelligence (AI) has raised major questions about their use in healthcare. We assessed the quality and safety of the management suggested by Chat Generative Pre-training Transformer 4 (ChatGPT-4) in real-life practice for patients with positive blood cultures.
METHODS: Over a 4-week period in a tertiary care hospital, data from consecutive infectious diseases (ID) consultations for a first positive blood culture were prospectively provided to ChatGPT-4. Data were requested to propose a comprehensive management plan (suspected/confirmed diagnosis, workup, antibiotic therapy, source control, follow-up). We compared the management plan suggested by ChatGPT-4 with the plan suggested by ID consultants based on literature and guidelines. Comparisons were performed by 2 ID physicians not involved in patient management.
RESULTS: Forty-four cases with a first episode of positive blood culture were included. ChatGPT-4 provided detailed and well-written responses in all cases. AI's diagnoses were identical to those of the consultant in 26 (59%) cases. Suggested diagnostic workups were satisfactory (ie, no missing important diagnostic tests) in 35 (80%) cases; empirical antimicrobial therapies were adequate in 28 (64%) cases and harmful in 1 (2%). Source control plans were inadequate in 4 (9%) cases. Definitive antibiotic therapies were optimal in 16 (36%) patients and harmful in 2 (5%). Overall, management plans were considered optimal in only 1 patient, as satisfactory in 17 (39%), and as harmful in 7 (16%).
CONCLUSIONS: The use of ChatGPT-4 without consultant input remains hazardous when seeking expert medical advice in 2023, especially for severe IDs.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:78 |
|---|---|
| Enthalten in: |
Clinical infectious diseases : an official publication of the Infectious Diseases Society of America - 78(2024), 4 vom: 10. Apr., Seite 825-832 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Maillard, Alexis [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Artificial intelligence |
|---|
| Anmerkungen: |
Date Completed 12.04.2024 Date Revised 12.04.2024 published: Print Citation Status MEDLINE |
|---|
| doi: |
10.1093/cid/ciad632 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM363164618 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM363164618 | ||
| 003 | DE-627 | ||
| 005 | 20240412232527.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1093/cid/ciad632 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1373.xml |
| 035 | |a (DE-627)NLM363164618 | ||
| 035 | |a (NLM)37823416 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Maillard, Alexis |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Can Chatbot Artificial Intelligence Replace Infectious Diseases Physicians in the Management of Bloodstream Infections? A Prospective Cohort 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 12.04.2024 | ||
| 500 | |a published: Print | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a © The Author(s) 2023. Published by Oxford University Press on behalf of Infectious Diseases Society of America. All rights reserved. For permissions, please e-mail: journals.permissionsoup.com. | ||
| 520 | |a BACKGROUND: The development of chatbot artificial intelligence (AI) has raised major questions about their use in healthcare. We assessed the quality and safety of the management suggested by Chat Generative Pre-training Transformer 4 (ChatGPT-4) in real-life practice for patients with positive blood cultures | ||
| 520 | |a METHODS: Over a 4-week period in a tertiary care hospital, data from consecutive infectious diseases (ID) consultations for a first positive blood culture were prospectively provided to ChatGPT-4. Data were requested to propose a comprehensive management plan (suspected/confirmed diagnosis, workup, antibiotic therapy, source control, follow-up). We compared the management plan suggested by ChatGPT-4 with the plan suggested by ID consultants based on literature and guidelines. Comparisons were performed by 2 ID physicians not involved in patient management | ||
| 520 | |a RESULTS: Forty-four cases with a first episode of positive blood culture were included. ChatGPT-4 provided detailed and well-written responses in all cases. AI's diagnoses were identical to those of the consultant in 26 (59%) cases. Suggested diagnostic workups were satisfactory (ie, no missing important diagnostic tests) in 35 (80%) cases; empirical antimicrobial therapies were adequate in 28 (64%) cases and harmful in 1 (2%). Source control plans were inadequate in 4 (9%) cases. Definitive antibiotic therapies were optimal in 16 (36%) patients and harmful in 2 (5%). Overall, management plans were considered optimal in only 1 patient, as satisfactory in 17 (39%), and as harmful in 7 (16%) | ||
| 520 | |a CONCLUSIONS: The use of ChatGPT-4 without consultant input remains hazardous when seeking expert medical advice in 2023, especially for severe IDs | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a ChatGPT | |
| 650 | 4 | |a artificial intelligence | |
| 650 | 4 | |a bacteremia | |
| 650 | 4 | |a evaluation | |
| 650 | 4 | |a infectious diseases | |
| 700 | 1 | |a Micheli, Giulia |e verfasserin |4 aut | |
| 700 | 1 | |a Lefevre, Leila |e verfasserin |4 aut | |
| 700 | 1 | |a Guyonnet, Cécile |e verfasserin |4 aut | |
| 700 | 1 | |a Poyart, Claire |e verfasserin |4 aut | |
| 700 | 1 | |a Canouï, Etienne |e verfasserin |4 aut | |
| 700 | 1 | |a Belan, Martin |e verfasserin |4 aut | |
| 700 | 1 | |a Charlier, Caroline |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Clinical infectious diseases : an official publication of the Infectious Diseases Society of America |d 1992 |g 78(2024), 4 vom: 10. Apr., Seite 825-832 |w (DE-627)NLM012603007 |x 1537-6591 |7 nnns |
| 773 | 1 | 8 | |g volume:78 |g year:2024 |g number:4 |g day:10 |g month:04 |g pages:825-832 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1093/cid/ciad632 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 78 |j 2024 |e 4 |b 10 |c 04 |h 825-832 | ||