METHODS: 18 voluntarily participants were recruited from the Canterbury and Otago region of New Zealand to take part in a Dynamic Insulin Sensitivity and Secretion Test (DISST) clinical trial. A total of 46 DISST data were collected. However, due to ambiguous and inconsistency, 4 data had to be removed. Analysis was done using MATLAB 2020a.
RESULTS AND DISCUSSION: Results show that, with 42 gathered dataset, the ANN generates higher gains, ∅P = 20.73 [12.21, 28.57] mU·L·mmol-1·min-1 and ∅D = 60.42 [26.85, 131.38] mU·L·mmol-1 as compared to the linear least square method, ∅P = 19.67 [11.81, 28.02] mU·L·mmol-1 ·min-1 and ∅D = 46.21 [7.25, 116.71] mU·L·mmol-1. The average value of the insulin sensitivity (SI) of ANN is lower with, SI = 16 × 10-4 L·mU-1 ·min-1 than the linear least square, SI = 17 × 10-4 L·mU-1 ·min-1.
CONCLUSION: Although the ANN analysis provided a lower SI value, the results were more dependable than the linear least square model because the ANN approach yielded a better model fitting accuracy than the linear least square method with a lower residual error of less than 5%. With the implementation of this ANN architecture, it shows that ANN able to produce minimal error during optimization process particularly when dealing with outlying data. The findings may provide extra information to clinicians, allowing them to gain a better knowledge of the heterogenous aetiology of diabetes and therapeutic intervention options.
METHODS: A stochastic model was developed using respiratory elastance (Ers) data from two clinical cohorts and averaged over 30-minute time intervals. The stochastic model was used to generate future Ers data based on current Ers values with added normally distributed random noise. Self-validation of the VPs was performed via Monte Carlo simulation and retrospective Ers profile fitting. A stochastic VP cohort of temporal Ers evolution was synthesised and then compared to an independent retrospective patient cohort data in a virtual trial across several measured patient responses, where similarity of profiles validates the realism of stochastic model generated VP profiles.
RESULTS: A total of 120,000 3-hour VPs for pressure control (PC) and volume control (VC) ventilation modes are generated using stochastic simulation. Optimisation of the stochastic simulation process yields an ideal noise percentage of 5-10% and simulation iteration of 200,000 iterations, allowing the simulation of a realistic and diverse set of Ers profiles. Results of self-validation show the retrospective Ers profiles were able to be recreated accurately with a mean squared error of only 0.099 [0.009-0.790]% for the PC cohort and 0.051 [0.030-0.126]% for the VC cohort. A virtual trial demonstrates the ability of the stochastic VP cohort to capture Ers trends within and beyond the retrospective patient cohort providing cohort-level validation.
CONCLUSION: VPs capable of temporal evolution demonstrate feasibility for use in designing, developing, and optimising bedside MV guidance protocols through in-silico simulation and validation. Overall, the temporal VPs developed using stochastic simulation alleviate the need for lengthy, resource intensive, high cost clinical trials, while facilitating statistically robust virtual trials, ultimately leading to improved patient care and outcomes in mechanical ventilation.
METHODS: Hysteresis loop analysis (HLA) which is a rule-based method (RBM) and a tri-input convolutional neural network (TCNN) machine learning model are used to classify 7 different types of PVA, including: 1) flow asynchrony; 2) reverse triggering; 3) premature cycling; 4) double triggering; 5) delayed cycling; 6) ineffective efforts; and 7) auto triggering. Class activation mapping (CAM) heatmaps visualise sections of respiratory waveforms the TCNN model uses for decision making, improving result interpretability. Both PVA classification methods were used to classify incidence in an independent retrospective clinical cohort of 11 mechanically ventilated patients for validation and performance comparison.
RESULTS: Self-validation with the training dataset shows overall better HLA performance (accuracy, sensitivity, specificity: 97.5 %, 96.6 %, 98.1 %) compared to the TCNN model (accuracy, sensitivity, specificity: 89.5 %, 98.3 %, 83.9 %). In this study, the TCNN model demonstrates higher sensitivity in detecting PVA, but HLA was better at identifying non-PVA breathing cycles due to its rule-based nature. While the overall AI identified by both classification methods are very similar, the intra-patient distribution of each PVA type varies between HLA and TCNN.
CONCLUSION: The collective findings underscore the efficacy of both HLA and TCNN in PVA detection, indicating the potential for real-time continuous monitoring of PVA. While ML methods such as TCNN demonstrate good PVA identification performance, it is essential to ensure optimal model architecture and diversity in training data before widespread uptake as standard care. Moving forward, further validation and adoption of RBM methods, such as HLA, offers an effective approach to PVA detection while providing clear distinction into the underlying patterns of PVA, better aligning with clinical needs for transparency, explicability, adaptability and reliability of these emerging tools for clinical care.
Patients and Methods: STAR proposes 1-3 hours treatment based on individual insulin sensitivity variation and history of blood glucose, insulin, and nutrition. A total of 136 patients recorded data from STAR pilot trial in Malaysia (2017-quarter of 2019*) were used in the study to identify the gap between chosen administered insulin and nutrition intervention as recommended by STAR, and the real intervention performed.
Results: The results show the percentage of insulin compliance increased from 2017 to first quarter of 2019* and fluctuated in feed administrations. Overall compliance amounted to 98.8% and 97.7% for administered insulin and feed, respectively. There was higher average of 17 blood glucose measurements per day than in other centres that have been using STAR, but longer intervals were selected when recommended. Control safety and performance were similar for all periods showing no obvious correlation to compliance.
Conclusion: The results indicate that STAR, an automated model-based protocol is positively accepted among the Malaysian ICU clinicians to automate glycemic control and the usage can be extended to other hospitals already. Performance could be improved with several propositions.
METHODS AND DESIGN: The CURE RCT compares two groups of patients requiring invasive MV with a partial pressure of arterial oxygen/fraction of inspired oxygen (PaO2/FiO2) ratio ≤ 200; one criterion of the Berlin consensus definition of moderate (≤ 200) or severe (≤ 100) ARDS. All patients are ventilated using pressure controlled (bi-level) ventilation with tidal volume = 6-8 ml/kg. Patients randomised to the control group will have PEEP selected per standard practice (SPV). Patients randomised to the intervention will have PEEP selected based on a minimal elastance using a model-based computerised method. The CURE RCT is a single-centre trial in the intensive care unit (ICU) of Christchurch hospital, New Zealand, with a target sample size of 320 patients over a maximum of 3 years. The primary outcome is the area under the curve (AUC) ratio of arterial blood oxygenation to the fraction of inspired oxygen over time. Secondary outcomes include length of time of MV, ventilator-free days (VFD) up to 28 days, ICU and hospital length of stay, AUC of oxygen saturation (SpO2)/FiO2 during MV, number of desaturation events (SpO2