Establishing a Classification System for High Fall-Risk Among Inpatients Using Support Vector Machines

Abstract

We constructed a model using a support vector machine to determine whether an inpatient will suffer a fall on a given day, depending on patient status on the previous day. Using fall report data from our own facility and intensity-of-nursing-care-needs data accumulated through hospital information systems, a dataset comprising approximately 1.2 million patient-days was created. Approximately 50% of the dataset was used as training and testing data. A multistep grid search was conducted using the semicomprehensive combination of three parameters. A discriminant model for the testing data was created for each parameter to identify which parameter had the highest score by calculating the sensitivity and specificity. The score of the model with the highest score had a sensitivity of 64.9% and a specificity of 69.6%. By adopting a method that relies on daily data recorded in the electronic medical record system and accurately predicts unknown data, we were able to overcome issues described in previous studies while simultaneously constructing a discriminant model for patients' fall risk that does not burden nurses and patients with information gathering.

The role of artificial intelligence in enhancing clinical nursing care: A scoping review

“…Six broad AI use cases for improving nursing care were identified: nursing documentation ( n = 2) (Moen et al, 2019; Moen et al, 2020), formulating nursing diagnoses ( n = 8) (Adelson & Eckert, 2020; Aguña et al, 2018; Chen et al, 2018; Hidayat & Uliyah, 2018; Liao et al, 2014; Liao et al, 2015; McHeick et al, 2017; Thomas & Pratap, 2019), formulating nursing care plans ( n = 4) (An et al, 2019; Sparks & Okugami, 2016; Sullivan et al, 2019; Thomas & Pratap, 2019), patient monitoring (i.e., monitoring of intravenous transfusion, seizures, phlegm stagnation physiological data, sepsis risk and vital signs; n = 9) (Back et al, 2016; Barrera et al, 2020; Chang et al, 2019; Gao & Yu, 2020; Huang et al, 2020; Lin et al, 2018; Qiao & Wu, 2013; Sparks & Okugami, 2016; Stevens et al, 2012), patient care prediction (i.e., prediction of falls, mortality, pain levels, pressure injury, urinary tract infection and critical alarms; n = 15) (Bauer et al, 2017; Cho et al, 2013; Easton‐Garrett et al, 2020; Hu et al, 2020; Johnson et al, 2019; Joshi et al, 2019; Kim et al, 2010; Ladios‐Martin et al, 2020; Lee et al, 2020; Lindberg et al, 2020; Lodhi et al, 2015; Nakatani et al, 2020; Sullivan et al, 2019; Yokota et al, 2017; Zachariah et al, 2020) and wound management ( n = 2) (Abranches et al, 2019; Sellmer et al, 2013). The details of the studies are presented in Table 2.…”

“…This reduces the workload nurses have in monitoring vital signs, improving patient care (Tóth et al, 2020). In addition, machine learning can also predict certain medical problems (Bauer et al, 2017; Cho et al, 2013; Hu et al, 2020; Johnson et al, 2019; Joshi et al, 2019; Ladios‐Martin et al, 2020; Lee et al, 2020; Lindberg et al, 2020; Lodhi et al, 2015; Nakatani et al, 2020; Sullivan et al, 2019; Yokota et al, 2017; Zachariah et al, 2020). For example, based on past datasets, AI can predict risk factors to medical or nursing problems (e.g., fall occurrences and pressure ulcers), allowing quicker identification and diagnosis of comorbidities (e.g., pressure ulcers), and the corresponding priority levels.…”

Modulation Classification Using Compressed Sensing and Decision Tree–Support Vector Machine in Cognitive Radio System

“…Support vector machine (SVM) is based on the principle of structural risk minimization [28][29][30]. Its final solution can be transformed into a quadratic convex programming problem with linear constraints.…”

Digitalisierung und Patientensicherheit

“…Prüft man die in der Einleitung geweckten Erwartungen an den Einsatz von künstlicher Intelligenz (KI) zur Entscheidungsunterstützung und Verbesserung der Patientensicherheit, so war in der Literaturrecherche wenig dazu zu finden. Yokota et al (2017) Für die Krankenhäuser, die nach dem Gesetz über das Bundesamt für Sicherheit in der Informationstechnik als "kritische Infrastruktur" gelten, erarbeitet die Deutsche Krankenhausgesellschaft derzeit einen branchenspezifischen Sicherheitsstandard, der diese Krankenhäuser in die Lage versetzen soll, kritische Systeme, Prozesse und Komponenten zu identifizieren und angemessene technische Vor-kehrungen zur Vermeidung von Störungen der Verfügbarkeit, Integrität, Authentizität und Vertraulichkeit ihrer IT zu treffen (Holzbrecher-Morys 2018). Dieser Standard soll perspektivisch auch als Leitfaden zur Erhöhung der IT-Sicherheit in allen Krankenhäusern genutzt werden.…”