Profiling Patients by Intensity of Nursing Care: An Operative Approach Using Machine Learning

Abstract

Physical function is a patient-oriented indicator and can be considered a proxy for the assignment of healthcare personnel. The study aims to create an algorithm that classifies patients into homogeneous groups according to physical function. A two-step machine-learning algorithm was applied to administrative data recorded between 2015 and 2018 at the University Hospital of Padova. A clustering-large-applications (CLARA) algorithm was used to partition patients into homogeneous groups. Then, machine learning technique (MLT) classifiers were used to categorize the doubtful records. Based on the results of the CLARA algorithm, records were divided into three groups according to the Barthel index: <45, >65, ≥45 and ≤65. The support vector machine was the MLT showing the best performance among doubtful records, reaching an accuracy of 66%. The two-step algorithm, since it splits patients into low and high resource consumption, could be a useful tool for organizing healthcare personnel allocation according to the patients’ assistance needs.

Comparison between the General Assessment of Hospitalised Patient Tool and the Barthel Index: A Retrospective Study

“…There are several methods to profile patient characteristics—for example, those that incorporate medication regimen complexity, cognition, physical and mental health, hospitalisation, and physical function [ 10 , 11 ]. Others use algorithms that classify patients into homogeneous groups according to physical function and costs calculated by reimbursement systems [ 1 ]. None of the reported methods are per se wrong.…”

“…Developments in human resource planning in healthcare facilities have led to studies on the estimation of nursing staff through the creation of patient categorisation systems. Classification systems were created primarily to assess the level of dependence on professional care in hospital wards and to profile patients according to the intensity of nursing care they receive [ 1 ]. Much of the current literature agrees that the prospective use of standardised tools for assessing care may represent valid support to improve the organisational appropriateness of healthcare organisations [ 2 ].…”

Research Trends in Artificial Intelligence-Associated Nursing Activities Based on a Review of Academic Studies Published From 2001 to 2020

“…Tawfik et al 44 established a nurse staffing prediction model and evaluated deviation from predicted nurse staffing as a contributor to patient outcomes. In the aspect of nursing assessment, with the development of nursing techniques, the data of patients could be collected through Internet of Things and sensors 21 ; for example, Ocagli et al 45 integrated various AI algorithms to evaluate and classify patients' physical conditions and to provide adequate nursing assistance. In addition, among the nursing activities, few AINA studies could be found to examine quality improvement in the dimension of prevention and control or continuing education in the dimension of nursing education.…”

Advancing Health Equity Through Artificial Intelligence: An Educational Framework for Preparing Nurses in Clinical Practice and Research

“…This technology can process large volumes of patient data to predict health outcomes and personalize treatment plans (Shruti & Trivedi, 2023). In nursing, ML is used to identify practice location factors (Bounsanga et al, 2022), predict pressure injuries (Song et al, 2021), categorize patients by care intensity (Ocagli et al, 2020), and enhance patient monitoring (Ng et al, 2022). The combination of ML and clinical expertise is set to transform health care through data-driven approaches that support human decisionmaking (Alowais et al, 2023).…”

“…The ethical integration of AI into health care demands a comprehensive approach that addresses privacy, consent, and transparency. Transparency in AI development and communication with patients about how their data will be utilized is vital for building trust, facilitating informed consent, and ensuring that AI supports health equity and universal access to health-care services without discrimination (Schwartz et al, 2022).…”