RESUMO
While a growing number of machine learning (ML) systems have been deployed in clinical settings with the promise of improving patient care, many have struggled to gain adoption and realize this promise. Based on a qualitative analysis of coded interviews with clinicians who use an ML-based system for sepsis, we found that, rather than viewing the system as a surrogate for their clinical judgment, clinicians perceived themselves as partnering with the technology. Our findings suggest that, even without a deep understanding of machine learning, clinicians can build trust with an ML system through experience, expert endorsement and validation, and systems designed to accommodate clinicians' autonomy and support them across their entire workflow.
RESUMO
BACKGROUND: New software (SuperSTAT(R) algorithm) with enhancements aimed at shorter determination times was developed for a non-invasive blood pressure (NIBP) device and a clinical evaluation was conducted to verify accuracy. OBJECTIVE: To determine the accuracy of the new algorithm according to ANSI/AAMI SP10-1992 and SP10A-1996 American National Standard for Electronic or Automated Sphygmomanometers. METHODS: The blood pressure values obtained from the test device were compared to the intra-arterial blood pressure reference standard (IBP). RESULTS: The NIBP and IBP comparisons for systolic, diastolic, and mean arterial pressure met the 1992 ANSI/AAMI accuracy standards by being within a mean difference of +/- 5 mmHg and standard deviation of < or = 8 mmHg. CONCLUSION: Non-invasive blood pressure determinations taken with the new algorithm, developed to provide greater patient comfort due to faster determinations, were accurate when compared to neonatal IBP.
