Artificial intelligence and prescription of antibiotic therapy: present and future.

INTRODUCTION: In the past few years, the use of artificial intelligence in healthcare has grown exponentially. Prescription of antibiotics is not exempt from its rapid diffusion, and various machine learning (ML) techniques, from logistic regression to deep neural networks and large language models, have been explored in the literature to support decisions regarding antibiotic prescription. AREAS COVERED: In this narrative review, we discuss promises and challenges of the application of ML-based clinical decision support systems (ML-CDSSs) for antibiotic prescription. A search was conducted in PubMed up to April 2024. EXPERT OPINION: Prescribing antibiotics is a complex process involving various dynamic phases. In each of these phases, the support of ML-CDSSs has shown the potential, and also the actual ability in some studies, to favorably impacting relevant clinical outcomes. Nonetheless, before widely exploiting this massive potential, there are still crucial challenges ahead that are being intensively investigated, pertaining to the transparency of training data, the definition of the sufficient degree of prediction explanations when predictions are obtained through black box models, and the legal and ethical framework for decision responsibility whenever an antibiotic prescription is supported by ML-CDSSs.

Prediction of candidemia with machine learning techniques: state of the art.

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

Candida is a type of fungus that can cause fatal infections. To confirm the presence of the infection, doctors may search for the fungus in the blood. Here, we discuss if computer systems can help to identify infection more easily and more rapidly.

Explainable and Interpretable Machine Learning for Antimicrobial Stewardship: Opportunities and Challenges.

There is growing interest in exploiting the advances in artificial intelligence and machine learning (ML) for improving and monitoring antimicrobial prescriptions in line with antimicrobial stewardship principles. Against this background, the concepts of interpretability and explainability are becoming increasingly essential to understanding how ML algorithms could predict antimicrobial resistance or recommend specific therapeutic agents, to avoid unintended biases related to the "black box" nature of complex models. In this commentary, we review and discuss some relevant topics on the use of ML algorithms for antimicrobial stewardship interventions, highlighting opportunities and challenges, with particular attention paid to interpretability and explainability of employed models. As in other fields of medicine, the exponential growth of artificial intelligence and ML indicates the potential for improving the efficacy of antimicrobial stewardship interventions, at least in part by reducing time-consuming tasks for overwhelmed health care personnel. Improving our knowledge about how complex ML models work could help to achieve crucial advances in promoting the appropriate use of antimicrobials, as well as in preventing antimicrobial resistance selection and dissemination.

Experimental application of Business Process Management technology to manage clinical pathways: a pediatric kidney transplantation follow up case.

BACKGROUND: To test the application of Business Process Management technology to manage clinical pathways, using a pediatric kidney transplantation as case study, and to identify the benefits obtained from using this technology. METHODS: Using a Business Process Management platform, we implemented a specific application to manage the clinical pathway of pediatric patients, and monitored the activities of the coordinator in charge of the case management during a 6-month period (from June 2015 to November 2015) using two methodologies: the traditional procedure and the one under study. RESULTS: The application helped physicians and nurses to optimize the amount of time and resources devoted to management purposes. In particular, time reduction was close to 60%. In addition, the reduction of data duplication, the integrated event management and the efficient data collection improved the quality of the service. CONCLUSIONS: The use of Business Process Management technology, usually related to well-defined processes with high management costs, is an established procedure in multiple environments; its use in healthcare, however, is innovative. The use of already accepted clinical pathways is known to improve outcomes. The combination of these two techniques, well established in their respective areas of application, could represent a revolution in clinical pathway management. The study has demonstrated that the use of this technology in a clinical environment, using a proper architecture and identifying a well-defined process, leads to real benefits in terms of resources optimization and quality improvement.

Optimization and planning of operating theatre activities: an original definition of pathways and process modeling.

BACKGROUND: The Operating Room (OR) is a key resource of all major hospitals, but it also accounts for up 40% of resource costs. Improving cost effectiveness, while maintaining a quality of care, is a universal objective. These goals imply an optimization of planning and a scheduling of the activities involved. This is highly challenging due to the inherent variable and unpredictable nature of surgery. METHODS: A Business Process Modeling Notation (BPMN 2.0) was used for the representation of the "OR Process" (being defined as the sequence of all of the elementary steps between "patient ready for surgery" to "patient operated upon") as a general pathway ("path"). The path was then both further standardized as much as possible and, at the same time, keeping all of the key-elements that would allow one to address or define the other steps of planning, and the inherent and wide variability in terms of patient specificity. The path was used to schedule OR activity, room-by-room, and day-by-day, feeding the process from a "waiting list database" and using a mathematical optimization model with the objective of ending up in an optimized planning. RESULTS: The OR process was defined with special attention paid to flows, timing and resource involvement. Standardization involved a dynamics operation and defined an expected operating time for each operation. The optimization model has been implemented and tested on real clinical data. The comparison of the results reported with the real data, shows that by using the optimization model, allows for the scheduling of about 30% more patients than in actual practice, as well as to better exploit the OR efficiency, increasing the average operating room utilization rate up to 20%. CONCLUSIONS: The optimization of OR activity planning is essential in order to manage the hospital's waiting list. Optimal planning is facilitated by defining the operation as a standard pathway where all variables are taken into account. By allowing a precise scheduling, it feeds the process of planning and, further up-stream, the management of a waiting list in an interactive and bi-directional dynamic process.