Aims We aim (i) to redesign sepsis's clinical pathway and fit the organizational requirements of a novel machine-learning algorithm incorporating a novel biomarker test and (ii) to assess adoption drivers of the new combined technology. Background There is an urgent need to achieve sepsis' early detection and diagnostic excellence. Methods A qualitative study based on semi-structured interviews conducted at the target site and across other Italian hospitals. A content analysis was undertaken, emergent themes were selected and categorized, and interviews were conducted until saturation was reached. Results Sixteen nurses (10 at the target site and six across other hospitals) and nine non-nursing professionals (seven at the target site and two across other hospitals) were interviewed. An organizational redesign was identified as the primary adoption driver. Even though nurses perceived workload increase related to the machine-learning component, technology acceptability was relatively high, as the standardization of tasks was perceived as crucial to improving professional satisfaction. Conclusions A novel business-oriented solution based on machine learning requires interprofessional integration, new professional roles, infrastructure improvement, and data integration to be effectively implemented. Implications for Nursing Management Lessons learned from this study suggest the need to involve nurses in the early stages of the design of new machine-learning technologies and the importance of training nurses on sepsis management through the support of disruptive technological innovation.

Adoption of novel biomarker test parameters with machine learning-based algorithms for the early detection of sepsis in hospital practice

De Benedictis, Anna;
2022-01-01

Abstract

Aims We aim (i) to redesign sepsis's clinical pathway and fit the organizational requirements of a novel machine-learning algorithm incorporating a novel biomarker test and (ii) to assess adoption drivers of the new combined technology. Background There is an urgent need to achieve sepsis' early detection and diagnostic excellence. Methods A qualitative study based on semi-structured interviews conducted at the target site and across other Italian hospitals. A content analysis was undertaken, emergent themes were selected and categorized, and interviews were conducted until saturation was reached. Results Sixteen nurses (10 at the target site and six across other hospitals) and nine non-nursing professionals (seven at the target site and two across other hospitals) were interviewed. An organizational redesign was identified as the primary adoption driver. Even though nurses perceived workload increase related to the machine-learning component, technology acceptability was relatively high, as the standardization of tasks was perceived as crucial to improving professional satisfaction. Conclusions A novel business-oriented solution based on machine learning requires interprofessional integration, new professional roles, infrastructure improvement, and data integration to be effectively implemented. Implications for Nursing Management Lessons learned from this study suggest the need to involve nurses in the early stages of the design of new machine-learning technologies and the importance of training nurses on sepsis management through the support of disruptive technological innovation.
2022
artificial intelligence; biomarker; machine learning; nursing and hospital practice; sepsis
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12610/71083
Citazioni
  • ???jsp.display-item.citation.pmc??? 1
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 3
social impact