Predicting Daily Nursing Load from Nurses’ Activity Logs and Patients’ Medical Records

Sozo Inoue, Tatsuya Isoda, Mako Shirouzu, Yasuhiko Sugiyama, Yasunobu Nohara, Naoki Nakashima,
ACM Int'l Conf. Pervasive and Ubiquitous Computing (Ubicomp) Poster
(Not Available)
(Not Available)
4 pages
Heidelberg, Germany
In this paper, we integrate nurse activity data, location data, and medical records to predict the nursing load of every day, assuming the application for task allocation for nurses. We collected nurse activity data, location data, medical payment data, and nursing needs data in cooperation with one floor of a hospital, which constitutes the orthopedic surgery department, for 40 days, 24 hours per day. With the collected data, we predicted the next day’s nursing time for a patient from the previous day’s patient status using RandomForest algorithm, and achieved 73.7% of accuracy.

Data Files

No records to display