Dataset Information

Profile of the ORION (Osaka emergency information Research Intelligent Operation Network system) between 2015 and 2016 in Osaka, Japan: a population-based registry of emergency patients with both ambulance and in-hospital records.

ABSTRACT:

Aim

To describe the registry design of the Osaka Emergency Information Research Intelligent Operation Network system (ORION) and its profile of hospital information, patient and emergency medical service characteristics, and in-hospital outcomes among all patients transported to critical care centers and emergency hospitals in Osaka Prefecture, Japan.

Methods

The Osaka Prefecture Government has developed and introduced an information system for emergency patients (the ORION system) that uses a smartphone application (app) for hospital selection by on-scene emergency medical service personnel and has been accumulating all ambulance records. Since January 2015, medical institutions have obtained information on the diagnosis and outcome of patients transported to medical institutions, and the ORION system merged these data with ambulance records including smartphone app data.

Results

From January 2015 to December 2016, 753,301 eligible patients were registered. The mean age was 58.7 years, and 51.5% of patients were male. After hospital arrival, 39.7% were hospitalized, 58.2% were discharged from hospital, 1.1% changed hospital, and 1.0% died. The most common diagnoses were injury, poisoning, and certain other consequences of external causes. Among the hospitalized patients, 29.2% were continuously hospitalized, 59.0% discharged, 5.2% changed hospital, and 5.8% were dead at 21 days after hospitalization. The most common confirmed diagnosis was diseases of the circulatory system.

Conclusion

Using the ORION system developed and operated by Osaka Prefecture since January 2015, we described the epidemiological data of all emergency patients transported to emergency hospitals. Analysis using the ORION database in the future could lead to improvements in the emergency transport system and patient outcomes.

SUBMITTER: Okamoto J

PROVIDER: S-EPMC6328924 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Clinical handovers of patient care among healthcare professionals is vulnerable to the loss of important clinical information. A verbal report is typically provided by paramedics and documented by emergency department (ED) triage nurses. Paramedics subsequently complete a patient care report which is submitted electronically. This emergency medical system (EMS) patient care report often contains details of paramedic assessment and management that is not all captured in the nursing triage note. EMS patient care reports are often unavailable for review by emergency physicians and nurses. Two processes occur in the distribution of EMS patient care reports. The first is an external process to the ED that is influenced by the prehospital emergency medical system and results in the report being faxed to the ED. The second process is internal to the ED that requires clerical staff to distribute the fax report to accompany patient charts. A baseline audit measured the percentage of EMS patient care reports that were available to emergency physicians at the time of initial patient assessments and showed a wide variation in the availability of EMS reports. Also measured were the time intervals from patient transfer from EMS to ED stretcher until the EMS report was received by fax (external process measure) and the time from receiving the EMS fax report until distribution to patient chart (internal process measure). These baseline measures showed a wide variation in the time it takes to receive the EMS reports by fax and to distribute reports. Improvement strategies consisted of: 1. Educating ED clerical staff about the importance of EMS reports 2. Implementing a new process to minimize ED clerical staff handling of EMS reports for nonactive ED patients 3. Elimination of the automatic retrieval of old hospital charts and their distribution for ED patients 4. Introduction of an electronic dashboard for patients arriving by ambulance to facilitate more efficient distribution of EMS reports. Implementation of change strategies did not result in a significant improvement in the percentage of EMS reports available to emergency physicians at the time of initial patient assessment. However, tracking both external and internal processes that influence EMS report availability showed the internal process time from fax report receipt to distribution significantly improved. This improvement reflected the change strategies that were all directed at improving the internal process. EMS patient care reports are more efficiently processed and distributed in the ED due to change strategies implemented that targeted the ED's internal process of EMS report distribution. The external process responsible for transmitting EMS reports to the ED is the limiting factor that prevents consistent timely access of EMS reports by emergency physicians and will require dedicated improvement strategies.

Project description:BACKGROUND:Benefiting from big data, powerful computation and new algorithmic techniques, we have been witnessing the renaissance of deep learning, particularly the combination of natural language processing (NLP) and deep neural networks. The advent of electronic medical records (EMRs) has not only changed the format of medical records but also helped users to obtain information faster. However, there are many challenges regarding researching directly using Chinese EMRs, such as low quality, huge quantity, imbalance, semi-structure and non-structure, particularly the high density of the Chinese language compared with English. Therefore, effective word segmentation, word representation and model architecture are the core technologies in the literature on Chinese EMRs. RESULTS:In this paper, we propose a deep learning framework to study intelligent diagnosis using Chinese EMR data, which incorporates a convolutional neural network (CNN) into an EMR classification application. The novelty of this paper is reflected in the following: (1) We construct a pediatric medical dictionary based on Chinese EMRs. (2) Word2vec adopted in word embedding is used to achieve the semantic description of the content of Chinese EMRs. (3) A fine-tuning CNN model is constructed to feed the pediatric diagnosis with Chinese EMR data. Our results on real-world pediatric Chinese EMRs demonstrate that the average accuracy and F1-score of the CNN models are up to 81%, which indicates the effectiveness of the CNN model for the classification of EMRs. Particularly, a fine-tuning one-layer CNN performs best among all CNNs, recurrent neural network (RNN) (long short-term memory, gated recurrent unit) and CNN-RNN models, and the average accuracy and F1-score are both up to 83%. CONCLUSION:The CNN framework that includes word segmentation, word embedding and model training can serve as an intelligent auxiliary diagnosis tool for pediatricians. Particularly, a fine-tuning one-layer CNN performs well, which indicates that word order does not appear to have a useful effect on our Chinese EMRs.