Artificial Intelligence (IA) Advanced Triage Tool for G&O Emergencies

Overview

Triage represents the first opportunity to classify patients who come to an Emergency Department (ED) and to be able to identify, prioritize high-risk patients and efficiently allocate the limited resources that are available. Therefore, the purpose of triage in the ED is to prioritize patients, detecting those that are urgent (that cannot wait to be attended). Urgency is defined as that clinical situation with the capacity to generate deterioration or danger to the health or life of the patient, depending on the time elapsed between its appearance and the establishment of an effective treatment, which determines a healthcare episode with significant intervention needs in a short period of time. There are currently six triage systems or models systematically structured into 5 levels. Although simple in concept, the practice of triage is challenging due to time pressure, the limitations of available information, the various medical conditions of the patients, and a great reliance on intuition on the part of the professionals who perform it. which conditions a great variability in it. On the other hand, almost half of adult ED visits nationwide are classified as level 3 in a 5-level structured triage system, which makes level 3 a heterogeneous group with patients with diverse pathologies, in which triage is not capable of accurately differentiating them, and this inability poses safety risks for the most severely ill patients ("under-triage") and may influence the accuracy and efficiency in resource allocation when patients with low acuity are overrated. Therefore, it seems necessary to develop new triage procedures that allow us to improve their accuracy and reduce inter-individual variability. TIAGO is a prospective, single-center, observational, comparative study to determine the validity of the Mediktor ® Triage and its effectiveness with respect to the current triage system and the "gold standard" (physician's diagnosis).

Prospective interventional, comparative study to determine the validity of the Mediktor ® Triage and its effectiveness with respect to "Model Andorra of Triage" (MAT) system and the "gold standard" (doctor's diagnosis). Obtaining informed consent. Participation in the study will be offered to all those patients who attend the Emergency Department of Gynecology and Obstetrics of the Hospital de la Santa Creu i Sant Pau during the study period and who meet the inclusion criteria. An information sheet on the study will also be provided to each patient. Sequential triage Once the patient's consent has been obtained, the patient will be assessed sequentially in the same triage space. Initially, a nurse from the Gynecology and Obstetrics Service will classify the patient in the triage box using the MAT system according to the usual practice. Then, another professional from the center, trained in the use of the Mediktor Hospital ® tool, and who has not been present in the conventional sorting, will perform the advanced triage in the same space, both professionals being blind to the result of each of the tools. In the event that the first triage performed with MAT gave the investigators an emergency level 1, the triage with the Mediktor tool would not be performed, since in this case the immediate care of the patient would be prioritized. Attention in the Emergency Service Once the sequential triage is completed, the patient will return to the Gynecology and Obstetrics Emergency Room. The patient's care will be performed according to usual clinical practice, following the triage assessment performed with the MAT system. Data recovery and entry in Data Recovery Form (DRF) All data of the study variables will be retrieved from the emergency report issued in the area of Gynecology and Obstetrics Emergencies and will be entered in an electronic DRF for further analysis and processing. Evaluation of Effectiveness Main evaluation variables Level of triage assigned by MAT, Level of triage assigned by Mediktor Hospital Secondary evaluation variables * Affiliation variables (administrative): Date of birth, sex, residence, financing, date and time of arrival in the emergency room or administrative record, form of arrival in the emergency room (own foot, ambulance, etc.…), reason for the urgency ( common illness, traffic accident, school…). * Triage variables: Triage date and time, triage duration time, coded clinical reason for consultation, readmission within 72 hours, readmission reason, triage level, number of reevaluations, triage level of each reevaluation. * Care variables: date and time of the emergency room visit, request for additional test, type of additional test, analytical parameters requested (if applicable), diagnosis according to International Classification of Diseases (ICD) (primary and secondary), most important procedures performed, patient admission \> 24h), date and time of admission, urgent surgery, time of stay in the emergency room (LOS) which is the time that the patient remains in the emergency room from the time of admission to the hospital until the patient is discharged or hospitalized. Number of patients admitted to the hospital and number of patients discharged. Number of emergency consultations / revisits in the first 72 hours after discharge. * Variables of discharge: circumstance of discharge or reason for emergency discharge (home discharge, hospital admission, transfer to another center, voluntary discharge, escape, exit…), identification of the transfer center, date and time of discharge, date and time of administrative discharge, departure transport, cause of success, time spent in emergencies, registration canceled