Institution-Specific Machine Learning Models for Prehospital Assessment to Predict Hospital Admission: Prediction Model Development Study

Abstract

Background Although multiple prediction models have been developed to predict hospital admission to emergency departments (EDs) to address overcrowding and patient safety, only a few studies have examined prediction models for prehospital use. Development of institution-specific prediction models is feasible in this age of data science, provided that predictor-related information is readily collectable. Objective We aimed to develop a hospital admission prediction model based on patient information that is commonly available during ambulance transport before hospitalization. Methods Patients transported by ambulance to our ED from April 2018 through March 2019 were enrolled. Candidate predictors were age, sex, chief complaint, vital signs, and patient medical history, all of which were recorded by emergency medical teams during ambulance transport. Patients were divided into two cohorts for derivation (3601/5145, 70.0%) and validation (1544/5145, 30.0%). For statistical models, logistic regression, logistic lasso, random forest, and gradient boosting machine were used. Prediction models were developed in the derivation cohort. Model performance was assessed by area under the receiver operating characteristic curve (AUROC) and association measures in the validation cohort. Results Of 5145 patients transported by ambulance, including deaths in the ED and hospital transfers, 2699 (52.5%) required hospital admission. Prediction performance was higher with the addition of predictive factors, attaining the best performance with an AUROC of 0.818 (95% CI 0.792-0.839) with a machine learning model and predictive factors of age, sex, chief complaint, and vital signs. Sensitivity and specificity of this model were 0.744 (95% CI 0.716-0.773) and 0.745 (95% CI 0.709-0.776), respectively. Conclusions For patients transferred to EDs, we developed a well-performing hospital admission prediction model based on routinely collected prehospital information including chief complaints.

Effects of evidence-based ICU care on long-term outcomes of patients with sepsis or septic shock (ILOSS): protocol for a multicentre prospective observational cohort study in Japan

“…Patient inclusion and exclusion at the time of ICU admission and data collection will be carried out using an electronic data capture (EDC) system created exclusively for this study by a data management and clinical research support company (TXP Medical, Tokyo Japan). 37 Using the EDC system, each ICU can manipulate only data from their own ICU and cannot access data registered from other participating ICUs. Furthermore, the system alerts research collaborators whose patient data is lacking with alarms on the EDC dashboard to limit the amount of missing data.…”

Development of machine learning model for predicting hospitalization in the prehospital setting

“…2 To address this concern, studies have developed models for predicting patient outcomes for successful risk stratification in the prehospital setting. [2][3][4][5][6] For example, a multicenter study of 4950 trauma patients developed a model to predict severe injury defined as an Injury Severity Score greater than 15, and the model had a high discrimination ability (C statistic of 0.823). 3 Another prognostic study using machine learning reported that a model using ≥1000 predictors has good discrimination ability.…”

“…1 Given increasing transportations over decades, early risk stratification of patients in the prehospital setting can improve patient outcomes and enhance efficient resource utilization in the context of integrated community health care. 2 To address this concern, studies have developed models for predicting patient outcomes for successful risk stratification in the prehospital setting. [2][3][4][5][6] For example, a multicenter study of 4950 trauma patients developed a model to predict severe injury defined as an Injury Severity Score greater than 15, and the model had a high discrimination ability (C statistic of 0.823).…”

Artificial intelligence decision points in an emergency department

“…With prehospital data, a machine-learning-based prediction of hospital admission was attempted in a previous study to inform prehospital providers of patient prognosis after ED care. 12 Natural language processing techniques were implemented in prehospital paramedic reports for diagnosis of stroke. 13 A previous study predicted early sepsis using prehospital data.…”

“…Dispatching could also be aided by AI-CDS; for example, when the conversation between callers and bystanders shows certain context or words for critical conditions, systems would suggest higher-level providers to be dispatched. With prehospital data, a machine-learning-based prediction of hospital admission was attempted in a previous study to inform prehospital providers of patient prognosis after ED care [ 12 ]. Natural language processing techniques were implemented in prehospital paramedic reports for diagnosis of stroke [ 13 ].…”