Dataset Information

Construction and evaluation of two computational models for predicting the incidence of influenza in Nagasaki Prefecture, Japan.

ABSTRACT: It remains challenging to forecast local, seasonal outbreaks of influenza. The goal of this study was to construct a computational model for predicting influenza incidence. We built two computational models including an Autoregressive Distributed Lag (ARDL) model and a hybrid model integrating ARDL with a Generalized Regression Neural Network (GRNN), to assess meteorological factors associated with temporal trends in influenza incidence. The modelling and forecasting performance of these two models were compared using observations collected between 2006 and 2015 in Nagasaki Prefecture, Japan. In both the training and forecasting stages, the hybrid model showed lower error rates, including a lower residual mean square error (RMSE) and mean absolute error (MAE) than the ARDL model. The lag of log-incidence, weekly average barometric pressure, and weekly average of air temperature were 4, 1, and 3, respectively in the ARDL model. The ARDL-GRNN hybrid model can serve as a tool to better understand the characteristics of influenza epidemic, and facilitate their prevention and control.

SUBMITTER: He F

PROVIDER: S-EPMC5543162 | biostudies-literature | 2017 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Construction and evaluation of two computational models for predicting the incidence of influenza in Nagasaki Prefecture, Japan.

He Fei F Hu Zhi-Jian ZJ Zhang Wen-Chang WC Cai Lin L Cai Guo-Xi GX Aoyagi Kiyoshi K

Scientific reports 20170803 1

It remains challenging to forecast local, seasonal outbreaks of influenza. The goal of this study was to construct a computational model for predicting influenza incidence. We built two computational models including an Autoregressive Distributed Lag (ARDL) model and a hybrid model integrating ARDL with a Generalized Regression Neural Network (GRNN), to assess meteorological factors associated with temporal trends in influenza incidence. The modelling and forecasting performance of these two mod ...[more]

PMID: 28775299

Similar Datasets

Project description:Background/purposeThe incidence of medication-related osteonecrosis of the jaw is increasing worldwide, mostly due to the use of antiresorptive agents (ARAs) such as bisphosphonate (BP) and denosumab (Dmab). However, the proportion of BP-related osteonecrosis of the jaw (BRONJ) and Dmab-related osteonecrosis of the jaw (DRONJ) among all ARA-related osteonecrosis of the jaw (ARONJ) cases is not clear; this hinders appropriate treatment, recurrence-prevention planning, and avoidance of unnecessary Dmab withdrawal. Moreover, the causative drug administered at each disease stage remains unknown. Therefore, we conducted a retrospective study of patients with ARONJ who visited oral and maxillofacial surgery departments at hospitals in Hyogo Prefecture, Japan, over 3 years to classify and compare patient characteristics with those having BRONJ and DRONJ. We sought to identify the proportion of DRONJ in ARONJ.Materials and methodsAfter excluding stage 0 patients, 1021 patients were included (471 high-dose; 560 low-dose). ARA treatment for bone metastases of malignant tumors and multiple myeloma was considered high dose, while that for cancer treatment-induced bone loss and osteoporosis was low dose.ResultsLow doses of BP and Dmab accounted for >50% patients; the results differed from those in other countries. DRONJ accounted for 58% and 35% of high-dose and low-dose cases, respectively. Stage 3 ARONJ cases comprised 92 (19.5%) low-dose BRONJ, 39 (20.1%) high-dose BRONJ, 24 (30%) low-dose DRONJ, and 68 (24.5%) high-dose DRONJ. Eighty-nine patients who received switch therapy were divided into BRONJ or DRONJ, but there was no difference in the ratio of each stage compared to the non-switch therapy.ConclusionTo the best of our knowledge, this is the first study to clarify the proportion of BRONJ and DRONJ cases, causative drug, and its doses by disease stages. DRONJ accounted for approximately 30% of the ARONJ, approximately 60% of which was due to high doses.

Dataset Information

Construction and evaluation of two computational models for predicting the incidence of influenza in Nagasaki Prefecture, Japan.

Publications

Construction and evaluation of two computational models for predicting the incidence of influenza in Nagasaki Prefecture, Japan.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets