Evaluating the Performance of Artificial Intelligence in Generating Differential Diagnoses for Infectious Diseases Cases: A Comparative Study of Large Language Models DOI Creative Commons
Agnibho Mondal, Rucha Karad, Boudhayan Bhattacharjee

et al.

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: June 30, 2024

Abstract Background Artificial Intelligence (AI) has potential to transform healthcare including the field of infectious diseases diagnostics. This study assesses capability three large language models (LLMs), GPT 4, Llama 3, and Gemini 1.5 generate differential diagnoses, comparing their outputs against those medical experts evaluate AI’s in augmenting clinical decision-making. Methods evaluates diagnosis capabilities LLMs, 1.5, using 50 simulated disease cases. The cases were diverse, complex, reflective common scenarios, detailed histories, symptoms, lab results, imaging findings. Each model received standardized case information produced which then compared reference lists created by experts. analysis utilized Jaccard index Kendall’s Tau assess similarity order accuracy, summarizing findings with mean, standard deviation, combined p-values. Results mean numbers diagnoses generated 6.22, 5.06, 10.02 respectively was significantly different (p < 0.001) from Jac-card 0.3, 0.21, 0.24 while 0.4, 0.7, 0.33 respectively. p-value 1, 0.979 indicating no significant association between LLMs Conclusion Although like exhibit varying effectiveness, none align expert-level diagnostic emphasizing need for further development refinement. highlight importance rigorous validation, ethical considerations, seamless integration into workflows ensure AI tools enhance delivery patient outcomes effectively.

Language: Английский

Machine learning in infectious diseases: potential applications and limitations DOI Creative Commons
Ahmad Z. Al Meslamani,

Isidro Sobrino,

José de la Fuente

et al.

Annals of Medicine, Journal Year: 2024, Volume and Issue: 56(1)

Published: June 10, 2024

Infectious diseases are a major threat for human and animal health worldwide. Artificial Intelligence (AI) combined algorithms including Machine Learning Big Data analytics have emerged as potential solution to analyse diverse datasets face challenges posed by infectious diseases. In this commentary we explore the applications limitations of ML management disease. It explores in key areas such outbreak prediction, pathogen identification, drug discovery, personalized medicine. We propose solutions mitigate these hurdles identify biomolecules effective treatment prevention addition use diseases, based on catastrophic evolution events identification biomolecular targets reduce risks vaccinomics discovery characterization vaccine protective antigens using intelligent techniques. These considerations set foundation developing strategies managing future.

Language: Английский

Citations

13
Advantages and limitations of large language models for antibiotic prescribing and antimicrobial stewardship DOI Creative Commons
Daniele Roberto Giacobbe, Cristina Marelli,

Byomkesh Manna

et al.

npj Antimicrobials and Resistance, Journal Year: 2025, Volume and Issue: 3(1)

Published: Feb. 27, 2025

Antibiotic prescribing requires balancing optimal treatment for patients with reducing antimicrobial resistance. There is a lack of standardization in research on using large language models (LLMs) supporting antibiotic prescribing, necessitating more efforts to identify biases and misinformation their outputs. Educating future medical professionals these aspects crucial ensuring the proper use LLMs providing deeper understanding strengths limitations.

Language: Английский

Citations

1
Prediction model of pressure injury occurrence in diabetic patients during ICU hospitalization——XGBoost machine learning model can be interpreted based on SHAP DOI
Jie Xu, Tie Chen,

Xixi Fang

et al.

Intensive and Critical Care Nursing, Journal Year: 2024, Volume and Issue: 83, P. 103715 - 103715

Published: May 2, 2024

Language: Английский

Citations

8
Machine learning algorithms for the evaluation of risk by tick-borne pathogens in Europe DOI Creative Commons
Agustín Estrada‐Peña, José de la Fuente

Annals of Medicine, Journal Year: 2024, Volume and Issue: 56(1)

Published: Sept. 30, 2024

Tick-borne pathogens pose a major threat to human health worldwide. Understanding the epidemiology of tick-borne diseases reduce their impact on requires models covering large geographic areas and considering both abiotic traits that affect tick presence, as well vertebrates used hosts, vegetation, land use. Herein, we integrated public information available for Europe regarding variables may habitat suitability ticks hosts tested five machine learning algorithms (MLA) predicting distribution four prominent species across Europe.

Language: Английский

Citations

4
Reverse vaccinology: A strategy also used for identifying potential vaccine antigens in poultry DOI Creative Commons

Noémie Gloanec,

Muriel Guyard‐Nicodème, Marianne Chemaly

et al.

Vaccine, Journal Year: 2025, Volume and Issue: 48, P. 126756 - 126756

Published: Jan. 23, 2025

Language: Английский

Citations

0
The Future of Virology Diagnostics Using Wearable Devices Driven by Artificial Intelligence DOI
Malik Sallam, Maad M. Mijwil, Mostafa Abotaleb

et al.

Advances in computational intelligence and robotics book series, Journal Year: 2025, Volume and Issue: unknown, P. 473 - 504

Published: Jan. 10, 2025

The utilization of the wearable devices (WDs) that are enhanced by artificial intelligence (AI) can have a notable potential in healthcare. This chapter aimed to provide an overview applications AI-driven WDs enhancing early detection and management virus infections. First, we presented examples highlight capabilities very monitoring infections such as COVID-19. In addition, provided on utility machine learning algorithms analyze large data for signs We also overviewed enable real-time surveillance effective outbreak management. showed how this be achieved via collection analysis diverse WDs' across various populations. Finally, discussed challenges ethical issues comes with virology diagnostics, including concerns about privacy security well issue equitable access.

Language: Английский

Citations

0
Fusion of quantum computing and explainable AI: A comprehensive survey on transformative healthcare solutions DOI
Shashank Sheshar Singh, Sumit Kumar, Rohit Ahuja

et al.

Information Fusion, Journal Year: 2025, Volume and Issue: unknown, P. 103217 - 103217

Published: April 1, 2025

Language: Английский

Citations

0
Prediction of candidemia with machine learning techniques: state of the art DOI
Daniele Roberto Giacobbe, Cristina Marelli, Sara Mora

et al.

Future Microbiology, Journal Year: 2024, Volume and Issue: 19(10), P. 931 - 940

Published: May 20, 2024

In this narrative review, we discuss studies assessing the use of machine learning (ML) models for early diagnosis candidemia, focusing on employed and related implications. There are currently few evaluating ML techniques candidemia as a prediction task based clinical laboratory features. The tools holds promise to provide highly accurate real-time support clinicians relevant therapeutic decisions at bedside patients with suspected candidemia. However, further research is needed in terms sample size, data quality, recognition biases interpretation model outputs by better understand if how these could be safely adopted daily practice.

Language: Английский

Citations

1
ARTIFICIAL INTELLIGENCE IN CLINICAL APPLICATIONS FOR INFECTIOUS DISEASES: DIAGNOSIS, TREATMENT AND IMMUNIZATION DOI Creative Commons
Selda Aslan

Gaziantep Islam Science and Technology University, Journal Year: 2024, Volume and Issue: unknown

Published: June 13, 2024

Despite scientific and technological advances in recent years, infectious diseases continue to pose a significant threat public health. These can cause serious health problems as they have the potential spread rapidly. In addition, occur form of epidemics affect populations. The difficulty rapid accurate diagnosis increasing antimicrobial resistance create difficulties treatment diseases. Artificial intelligence technology has developed useful applications many areas such development methods, anti-infective drug vaccine discovery, prevention resistance. particular, AI-assisted clinical decision support systems help predict disease outbreaks, diseases, optimise options monitor epidemiological trends by analysing large datasets. It also provide more faster results diagnostic images identifying Advances this field need be supported multidisciplinary studies strong ethical framework. review, we outline approaches application use artificial highlight progress intelligence, discuss how it used. We benefits AI way, effective intervention strategies control protect

Language: Английский

Citations

1
Catastrophic selection: the other side of the coin DOI Creative Commons
José de la Fuente

Annals of Medicine, Journal Year: 2024, Volume and Issue: 56(1)

Published: Aug. 14, 2024

Recently, a machine learning molecular de-extinction paleoproteomic approach was used to recover inactivated antimicrobial peptides overcome the challenges posed by antibiotic-resistant pathogens. The authors showed possibility of identifying lost molecules with antibacterial capacity, but other side coin associated catastrophic selection should be considered for development new pharmaceuticals.

Language: Английский

Citations

1