Trial of Converting Nursing Records into Simplified and Structured Information Utilizing ChatGPT-3.5.

In Japan, the excessive length of time required for nursing records has become a social problem. A shift to concise "bulleted" records is needed to apply speech recognition and to work with foreign caregivers. Therefore, using 96,000 descriptively described anonymized nursing records, we identified typical situations for each information source and attempted to convert them to "bulleted" records using ChatGPT-3.5(For return from the operating room, Status on return, Temperature control, Blood drainage, Stoma care, Monitoring, Respiration and Oxygen, Sensation and pain, etc.). The results showed that ChatGPT-3.5 has some usable functionality as a tool for extracting keywords in "bulleted" records. Furthermore, through the process of converting to a "bulleted" record, it became clear that the transition to a standardized nursing record utilizing the "Standard Terminology for Nursing Observation and Action (STerNOA)" would be facilitated.

Perceptions About Nursing Practice Based on the Internet of Things: A Survey of Nursing Managers.

The purpose of this study was to investigate the perceptions of nursing managers about adopting nursing practices based on the Internet of Things and to examine related ethical issues. Questionnaires were sent to 538 nursing managers in Japan, with 131 responses. Of these, 87% and 33% agreed that a system using radio frequency identifiers would be useful for locating patients and nurses, respectively, 58%-81% recognized the value for patient safety of various camera systems for nursing observation, such as cameras linked to biometric alarms, 73% agreed the usefulness of automatically prioritizing alarms, but only around 39% were in favor of using facial recognition to help nursing observation. Many nursing managers expressed concerns about privacy. Data storage for at least 6 months was supported by 53% for location data and 41% for ceiling camera videos. Thus, nursing practice based on the Internet of Things is widely accepted in Japan.

Terminology Gap in Continuous Care Between Acute and Long-Term Care Hospitals.

This study aimed to elucidate the gap in terminology between acute and long-term care (LTC) hospitals. Fifty-seven hospital documents were analyzed using text mining. Each document contained a mean 194.2 terms. Acute care hospital documents often contain pharmacological information. LTC hospital documents often contain information related to patients' lives. Documents from both settings used local, non-standardized language. Our results suggest that expanding the national standard of nursing terminologies has potential for enhancing continuity of care.

The Survey for Determining Knowledge-Related Problems in the Dissemination of ICD-11.

Changes in the 11th revision of the International Classification of Diseases (ICD-11) from ICD-10 may significantly impact coding quality. We conducted a field trial in 2017 to evaluate the line coding quality of 19 cases coded using the coding method of the World Health Organization. The cases with low agreement between the accuracy rates of ICD-10 and ICD-11 were cases that required the extension code. We should prepare effective educational content about how to use the extension code for proper coding in ICD-11.

Design of an Observation Support System to Improve Pain Management.

We were challenged to design an obeservation support system. To improve evidence-based observations, we anylysed nursing records from electronic medical records (EMR) and patient experiences (from blogs) regarding pain symptoms using text mining methods. As a result, it was found that the view point of pain differed between the patient and nurse. It is reccomended that an observation advice message should be inplemented into EMR to improve nurses' observations on pain management.

Development of Observation Support System Using Integrated Nursing Practice Data.

The purpose of this study was to develop a prototype nursing observation support system using integrated nursing practice data with nursing records, prescription data, and nurse call logs. These data show that the present observation system has improved. The system has the potential to provide improved observations of chest symptoms and pain management.

Clinical Decision Support Using Electronic Medical Records: For the Improvement of Diabetes Care and Proper Use of Insulin for Inpatients.

The aim of the study is to develop a scheme of a decision support system concerning insulin intervention for inpatients. Transaction data for 32,637 inpatients were collected from the EMR. As a result, antidiabetic agents were not taken by 38.9%-41.7% of patients with a Disease Complicated by DM. It is recommended that the EMR should provide a suggestion about insulin level for diseases with DM as a complicating factor.

Clinical documentation improvement for outpatients by implementing electronic medical records.

This observational study was conducted before and after implementing an electronic medical record (EMR) system to evaluate the change in outpatient workflow by implementation of EMR and the effectiveness of clinical documentation improvement (CDI). The number of hours for patient care increased by 89.2% (p < .05) and the hours for writing medical records after consulting decreased after implementation of EMR by 27.3% (p < .01). Implementation of EMR reduced nurses' workload to handle medical records by 78.8 (p < .05) but not changed for physicians. The necessary change in the information management process occurred after using the CDI indicator. We recommend that the "working hours of health professionals" and "handling hours for information resources" should be used widely as CDI indicators to improve workflow when implementing EMR.

Redesigned computerized prescribing system to reduce physicians' workload and improve patient safety.

The aim of our study was to redesign and evaluate the Computerized Prescribing System (PRS) to reduce physicians' workload and improve patient safety. The study was conducted in 2 prefectures in Japan. 186 physicians were surveyed with regard to prescription by physicians and medical office assistants. As a result, it was found that physicians demanded support from medical office assistants with regard to entry of prescription orders but for limited types of medicines. Based on our findings, we developed recommendations for a redesigned outline for PRS for the following 4 scenarios: (1) Continue prescription; (2) narcotic medicines; (3) chemotherapeutic medicines; and (4) medicines used in medical procedures. The outline was evaluated for effectiveness and safety and was confirmed to be a useful future prescription system.

Development of the incident reporting system using the nursing administrative database.

A role of incident reporting system has become more important for improving of the patient safety. However, the more various causes managers seek for, the longer time healthcare providers send to report near-miss/ medical errors. The purpose of our work was to try to develop "the incident reporting system" utilized the nursing administrative database. As a result, we found that the system would make us spend less time to report medical errors and easy to analyze of the nursing care structure. The system using the nursing administrative database is effective to improve the patient safety rationally.