Machine Learning Methods for Identifying Critical Data Elements in Nursing Documentation

Abstract

Feature selection techniques show promise towards reducing PHN documentation burden by identifying the most critical data elements needed to predict risk status. Further studies to refine the process of feature selection can aid in informing public health nurses' focus on client-specific and targeted interventions in the delivery of care.

A Concept Analysis on the Use of Artificial Intelligence in Nursing

“…A more complex definition of AI is “multiple technologies that can augment human activities in the form of machine learning, to process and learn with raw data and deep learning, [sic] to stimulate decision-making using complex artificial neural networks” [ 25 ]. Definitions are currently scattered with only three articles formally defining AI [ 24 , 26 , 27 ], six not offering any formal definition [ 6 , 7 , 25 , 28 - 30 ], three defining only machine learning [ 4 , 14 , 31 ], three defining only neural networks [ 5 , 16 , 32 ], and one defining only decision trees [ 15 ]. Therefore, the definitions of AI used in the literature include machine learning, neural networks, and decision trees.…”

“…After an AI has been developed and tested, with appropriate ongoing evaluation plans in place, it still needs to demonstrate its ability to improve human processes. This would involve enhancing decision-making, such as identifying important aspects [ 14 , 31 ] and prioritization. Overall, by improving human processes, AIs are expected to reduce the time wasted and mental computations that are required of nurses [ 24 ].…”

“…In other words, a nurse-centric AI is a tool, and if there is no ongoing problem, then there is no need to create or use that tool. Examples of issues that would necessitate an AI could be the need to study nursing burnout [ 16 ], lack of patient actors for clinical education [ 6 ], and a general lack of time or resources [ 14 ]. In addition, AIs are developed to address and predict the occurrence of clinical issues, such as pressure ulcers [ 15 ], urinary tract infections [ 34 ], and sepsis [ 24 ].…”

“…For the organizational level, efficiency is key, and it can be accomplished through the identification of care priorities [ 14 ], optimization of staffing and patient bed allocation [ 30 ], and prediction of nurses’ job performance [ 5 ]. Several staffing issues can also be identified by the AI, including job stressors [ 16 ] and priorities described by nurses [ 33 ].…”

“…Relatedly, the lack of empirical evidence and authoritative voices created a space where definitions of AI are used interchangeably, namely AI, robots, machine learning, and neural networks [ 13 ]. In the few existing publications on the use of nurse-centric AI, some of them use extremely technical language [ 14 - 16 ], likely due to the dominance of the computer scientists within the research team. Thus, for AI to realize its full potential in nursing, a first step is to standardize and clarify the various terms and definitions.…”