A5087186118- Diabetes Management and Research
- Pancreatic function and diabetes
- Diabetes Treatment and Management
- Artificial Intelligence in Healthcare
- Ion Transport and Channel Regulation
- Heart Rate Variability and Autonomic Control
- Hormonal Regulation and Hypertension
- Machine Learning and Data Classification
- Greenhouse Technology and Climate Control
- Renal Diseases and Glomerulopathies
- Hyperglycemia and glycemic control in critically ill and hospitalized patients
- Receptor Mechanisms and Signaling
- Climate change impacts on agriculture
- Irrigation Practices and Water Management
Zhejiang University
2023
University of Bern
2018-2019
China Agricultural University
2018
A deep learning network was used to predict future blood glucose levels, as this can permit diabetes patients take action before imminent hyperglycaemia and hypoglycaemia. sequential model with one long-short-term memory (LSTM) layer, bidirectional LSTM layer several fully connected layers levels for different prediction horizons. The method trained tested on 26 retrospectively analysed datasets from 20 real patients. proposed outperforms the baseline methods in terms of all evaluation criteria.
Self-monitoring of blood glucose (SMBG) and continuous monitoring (CGM) are commonly used by type 1 diabetes (T1D) patients to measure concentrations. The proposed adaptive basal-bolus algorithm (ABBA) supports inputs from either SMBG or CGM devices provide personalised suggestions for the daily basal rate prandial insulin doses on basis patients' level previous day. ABBA is based reinforcement learning (RL), a artificial intelligence, was validated in silico with an FDA-accepted population...
A deep learning network was used to predict future blood glucose levels, as this can permit diabetes patients take action before imminent hyperglycaemia and hypoglycaemia. sequential model with one long-short-term memory (LSTM) layer, bidirectional LSTM layer several fully connected layers levels for different prediction horizons. The method trained tested on 26 datasets from 20 real patients. proposed outperforms the baseline methods in terms of all evaluation criteria.
Nephrotic syndrome is common in children and adults worldwide, steroid-sensitive nephrotic (SSNS) accounts for 80%. Aberrant metabolism involvement early SSNS sparsely studied, its pathogenesis remains unclear. Therefore, the goal of this study was to investigate changes initiated patients-related metabolites through serum urine metabolomics discover novel potential metabolic pathways.Serum samples (27 56 controls) (17 24 were collected. Meanwhile, non-targeted analyses performed by...
The existing adaptive basal-bolus advisor (ABBA) was further developed to benefit patients under insulin therapy with multiple daily injections (MDI). Three different in silico experiments were conducted the DMMS.R simulator validate approach of combined use self-monitoring blood glucose (SMBG) and injection devices, e.g. pen, as are used by majority type 1 diabetes therapy. proposed outperforms conventional method, it increases time spent within target range simultaneously reduces risks...
Fertigation has been proved a good agricultural practice for greenhouse crop production with respect to the efficiency of water and fertilizer use. but frequency irrigation N fertilization, as well their quantity, important effects on crop’s high yield quality. To further save application meanwhile ensuring maximum productivity, rational fertigation management is indispensable. Crop growth model provide useful tool help determine optimal practices. This paper illustrates basic methodological...
This article investigates the impact of carbohydrate (CHO) estimation error on three different algorithms for insulin treatment optimisation. The experiments were conducted using educational version UVa/Padova simulator 11 virtual adult subjects. Under CHO levels, two ways amount announcements investigated: numerical value and categorical (Small, Medium, Large). Results suggest that by low error, way level announcement has algorithm quality. As increases more intelligent algorithmic...
The existing adaptive basal-bolus advisor (ABBA) was further developed to benefit patients under insulin therapy with multiple daily injections (MDI). Three different in silico experiments were conducted the DMMS.R simulator validate approach of combined use self-monitoring blood glucose (SMBG) and injection devices, e.g. pen, as are used by majority type 1 diabetes therapy. proposed outperforms conventional method, it increases time spent within target range simultaneously reduces risks...