Improving management of febrile neutropenia in oncology patients: the role of artificial intelligence and machine learning

ABSTRACT

Introduction

Artificial intelligence (AI) and machine learning (ML) have the potential to revolutionize the management of febrile neutropenia (FN) and drive progress toward personalized medicine.

Areas covered

In this review, we detail how the collection of a large number of high-quality data can be used to conduct precise mathematical studies with ML and AI. We explain the foundations of these techniques, covering the fundamentals of supervised and unsupervised learning, as well as the most important challenges, e.g. data quality, ‘black box’ model interpretation and overfitting. To conclude, we provide detailed examples of how AI and ML have been used to enhance predictions of chemotherapy-induced FN, detection of bloodstream infections (BSIs) and multidrug-resistant (MDR) bacteria, and anticipation of severe complications and mortality.

Expert opinion

There is promising potential of implementing accurate AI and ML models whilst managing FN. However, their integration as viable clinical tools poses challenges, including technical and implementation barriers. Improving global accessibility, fostering interdisciplinary collaboration, and addressing ethical and security considerations are essential. By overcoming these challenges, we could transform personalized care for patients with FN.

KEYWORDS:

• Febrile neutropenia
• artificial intelligence
• machine learning
• supervised learning
• personalized medicine
• clinical decision-making
• bloodstream infections
• multidrug-resistant bacteria

Acknowledgments

We would like to thank Anthony Armenta for providing medical language editing assistance for the manuscript at hand. Authors also would like to thank for OP post-doctoral fellow financial support: la Ligue Nationale contre le Cancer (convention number: AAPMRC 2022/OP) and la Direction de l’Assistance Publique – Hôpitaux de Paris (APHP).

Article highlights

• AI in healthcare: AI and ML can improve the management of FN in patients. Their adoption will depend on a better understanding of how they work.

• Data quality in AI: Managing large volumes of high-quality data and interdisciplinary work are key to the success of predictive studies in AI. Tools like SQL, Python, and R are crucial.

• AI in clinical practice: The integration of AI faces challenges such as the perception of ‘black boxes,’ the need for more transparency in algorithms, and the risk of overfitting.

• ML and assistance for neutropenic patients: ML models outperform traditional methods in predicting complications in patients with FN. At the same time, they can minimize subjectivity in clinical decisions, overcoming the limitations of current clinical scales.

• Challenges and obstacles: Despite the potential of AI and ML to revolutionize the management of FN, there are barriers to overcome, including the availability and management of high-quality data; the integration of real-time data collection and processing; and the complete collaboration amongst technical and clinical teams.

Declaration of interest

CG-V has received honoraria for talks on behalf of Gilead Science, MSD, Pfizer, Janssen, Novartis, Basilea, GSK, Shionogi, AbbVie, and Advanz Pharma, as well as grant support from Gilead Science, Pfizer, GSK, MSD, and Pharmamar. AS has received honoraria for talks on behalf of Merck Sharp and Dohme, Pfizer, Novartis, Angelini, Menarini, and Gilead Science as well as grant support from Pfizer, and Gilead Science. JM has received honoraria for talks on behalf of Merck Sharp and Dohme, Pfizer, Novartis and Angelini. OP has received honoraria for talks on behalf of BMS and Qiagen, and expertise for Sanofi.

Reviewer disclosure

Peer reviewers on this manuscript have no relevant financial or other relationships to disclose.

Correction Statement

This article has been corrected with minor changes. These changes do not impact the academic content of the article.

Additional information

Funding

This study was co-funded by the European Regional Development Fund (EDRD). CG-V [FIS PI21/01640] have received research grants from the Ministerio de Sanidad y Consumo, Instituto de Salud Carlos III. This work was co-funded by a research grant [SGR 01324 Q5856414G] from the AGAUR (Agencia de Gestión de Ayudas Universitarias y de Investigación) of Catalunya.