Control Protocol Research Articles

Developing and testing personalised nutrition feedback for more sustainable healthy diets: the MyPlanetDiet randomised controlled trial protocol.

Agriculture and food production contribute to climate change. There is mounting pressure to transition to diets with less environmental impact while maintaining nutritional adequacy. MyPlanetDiet aimed to reduce diet-related greenhouse gas emissions (GHGE) in a safe, nutritionally adequate, and acceptable manner. This paper describes the trial protocol, development, and testing of personalised nutrition feedback in the MyPlanetDiet randomised controlled trial (RCT). MyPlanetDiet was a 12-week RCT that provided standardised personalised nutrition feedback to participants based on new sustainable healthy eating guidelines (intervention) or existing healthy eating guidelines (control) using decision trees and corresponding feedback messages. To test the personalised nutrition feedback, we modelled a sample of 20 of the MyPlanetDiet participants baseline diets. Diets were modelled to adhere to control and intervention decision trees and feedback messages. Modelled nutrient intakes and environmental metrics were compared using repeated measure one-way analysis of covariance. Intervention diets had significantly lower (p < 0.001) diet-related GHGE per 2500 kilocalories (kcal) (4.7kg CO2-eq) relative to control (6.6kg CO2-eq) and baseline (7.1kg CO2-eq). Modelled control and intervention diets had higher mean daily intakes of macronutrients (carbohydrates, fibre, and protein) and micronutrients (calcium, iron, zinc, and iodine). Modelled control and intervention diets had lower percent energy from fat and saturated fat relative to baseline. Adherence to the MyPlanetDiet personalised nutrition feedback would be expected to lead to better nutrient intakes and reduced diet-related GHGE. The MyPlanetDiet RCT will test the effectiveness and safety of personalised feedback for a more sustainable diet. Clinical trials registration number: NCT05253547, 23 February 2022.

Prevention of postpartum methamphetamine use with micronized progesterone trial (PROMPT): A pilot randomized controlled trial protocol

While most pregnant individuals with methamphetamine use disorder (MUD) achieve abstinence, the postpartum period remains a vulnerable time for return to methamphetamine use (MU). Promising data from human and animal models, including three randomized controlled trials, suggest that micronized progesterone may prevent postpartum return to cocaine and nicotine use by reducing cravings. The primary objective of this study is to assess feasibility of enrollment and randomization of postpartum individuals with MUD to micronized progesterone to prevent return to MU. The secondary objectives are to evaluate safety, establish a preliminary estimate of efficacy, and characterize the association between allopregnanolone levels and methamphetamine cravings. This is a pilot double-blind placebo randomized controlled trial. We plan to enroll 40 postpartum individuals with MUD over 24-months. Individuals, stratified by opioid use disorder (OUD), are randomized 1:1-400mg oral micronized progesterone daily or placebo and attend weekly study sessions for 12 weeks. Feasibility is measured by achieving 80% of enrollment goal. Safety is evaluated by side effect frequency, mental health status changes, lactation and medical complications. Efficacy is assessed by comparing proportion of participants with return to MU and time to return to MU based on self-report or urine testing between treatment and control groups. Salivary allopregnanolone levels and methamphetamine cravings are compared between the groups. Study results will provide a first critical step towards potential intervention for prevention of return to MU among postpartum individuals. Completion of this trial will set the stage for a large-scale efficacy trial.

Mathematical analysis of busy tone in full-duplex optical MAC for hidden node mitigation

This article provides the mathematical analysis of carrier sense multiple access with collision avoidance (CSMA/CA) media access control (MAC) protocol of IEEE 802.15.7 optical wireless communication (OWC). While the prior works have performed the OWC CSMA/CA mathematical analysis using the Markov models, deviation from the simulation results has been observed. We address this by improving the Markov model calculations, which display a mere 0.2% throughput deviation, nearly matching the simulation results. Furthermore, we work on the hidden node problem of the OWC networks. This problem is solved in literature by using various full-duplex communication methods, such as bi-directional data transmission and the busy tone signal; the latter is employed in our previous work on full-duplex optical MAC (FD-OMAC). These techniques increase the coverage area of the nodes by utilizing an access point (AP) as a relay node. However, the AP response is delayed by the processing time, causing an unexpected network behavior. The quantitative effect of this delay remains unexplored, which is critical for optimizing the OWC network. We bridge this gap by extending the proposed Markov analysis to model CSMA/CA and the aforementioned full-duplex techniques. This work equips readers with mathematical insights for future OWC MAC layer enhancements.

ID: 324641 Patient Controller Protocol for Blinded Trials of Neuromodulation

ID: 324641 Patient Controller Protocol for Blinded Trials of Neuromodulation

A Novel Parallel Control Method for Optimal Consensus of Nonlinear Multiagent Systems.

This work concentrates on the initial introduction of parallel control to investigate an optimal consensus control strategy for continuous-time nonlinear multiagent systems (MASs) via adaptive dynamic programming (ADP). First, the control input is integrated into the feedback system for parallel control, facilitating an augmented system's optimal consensus control with an appropriate augmented performance index function to be established, which is identical to the original system's suboptimal control with a conventional performance index. Second, the feasibility of the proposed control scheme is evaluated based on the policy iteration algorithm, and the convergence of the algorithm is demonstrated. Then, an online learning algorithm becomes available to implement the ADP-based optimal parallel consensus control protocol without prior knowledge of the system. The Lyapunov approach is employed to indicate that the signals are convergent. Ultimately, the experimental data support the theoretical results.

Reversing File Access Control Using Disk Forensics on Low-Level Flash Memory

In the history of access control, nearly every system designed has relied on the operating system (OS) to enforce the access control protocols. However, if the OS (and specifically root access) is compromised, there are few if any solutions that can get users back into their system efficiently. In this work, we have proposed a novel approach that allows secure and efficient rollback of file access control after an adversary compromises the OS and corrupts the access control metadata. Our key observation is that the underlying flash memory typically performs out-of-place updates. Taking advantage of this unique feature, we can extract the “stale data” specific for OS access control, by performing low-level disk forensics over the raw flash memory. This allows efficiently rolling back the OS access control to a state pre-dating the compromise. To justify the feasibility of the proposed approach, we have implemented it in a computing device using file system EXT2/EXT3 and open-sourced flash memory firmware OpenNFM. We also evaluated the potential impact of our design on the original system. Experimental results indicate that the performance of the affected drive is not significantly impacted.

Prehospital seizure management protocols need standardized guidelines. A descriptive study from Norway.

BackgroundPatients with convulsive seizures constitute a significant group in acute neurology. No common European clinical practice guidelines on prehospital seizure management exists, and today most patients are brought to hospital for seizure treatment, with great variation in which prehospital treatment is provided. Only 33% of status epilepticus patients receive a benzodiazepine as first anti-seizure medication (ASM). The aim of this study is to assess the prehospital seizure control protocols in the Emergency Medical Services (EMS) in Norway, and compare these with current evidence for acute management. MethodWe performed a descriptive analysis of the 18 regional EMS protocols in Norway and compared the findings with recent evidence on prehospital treatment. We analysed recommended drug and dosage, route of medication administration, number of additional rescue doses permitted, requirements for registration of type of seizures and seizure duration. ResultsThe protocols vary in terms of preferred medication, administration method, dosage and recommendations regarding first- and second-line therapies. 33 % of protocols explicitly define status epilepticus according to contemporary guidelines, and 16.7 % have an operational definition of when to administer benzodiazepines. All protocols showed variations in dosing and administration instructions and only 28% had a clearly stated first line treatment. ConclusionThere are disparities in the prehospital seizure management protocols within the Norwegian healthcare system, a system comparable to other European countries. To improve seizure management there is a need for standardised guidelines for prehospital treatment.

Моделювання систем реального часу з використанням RUDP протоколу передачі даних

The efficiency of real-time systems makes them applicable in various fields by utilizing protocols for data transmission. Well-known transport layer protocols include Transmission Control Protocol (TCP) and User Datagram Protocol (UDP), which facilitate such transmission. However, there are challenges in using these protocols [1] in real-time systems where data rapidly changes during application execution. Exclusively using one of these protocols adversely affects the stable operation of the application and increases the risk of data obsolescence. The objective of this work is to develop and model a data transmission subsystem for real-time systems that utilizes the Reliable UDP (RUDP) protocol [2] for data synchronization. Implementing the RUDP network protocol in the subsystem addresses network issues such as delay, packet loss, and duplication in the most optimal way during real-time data synchronization between sensors and the server, reducing the load on bandwidth. The tasks of the developed subsystem, consisting of a server and a client, include: reading user-specified system data, reliable message transmission between the server and the client using sockets for RUDP protocol operation, ensuring the most optimal message delivery in case of packet loss, subsystem operation modeling compared to well-known UDP and TCP protocols. The simulation results reveal that the maximum time spent by the subsystem is 2.03 seconds for the RUDP protocol and 6.22 seconds for the TCP protocol. Therefore, RUDP is recommended for data transmission in the future. In the event of message loss, retransmission occurs exponentially, calculated using the proposed formula. If the initial transmission occurs immediately, subsequent times exponentially increase but remain collectively less than the transmission time for the TCP protocol.

ROLE OF PERFORMANCE IMPROVEMENT MEASURES TO IMPROVE THE QUALITY OF INFECTION PREVENTION PROGRAMS IN TERTIARY CARE HOSPITAL

Healthcare-associated infections (HAIs) pose a significant risk in hospital settings. Performance improvement measures can enhance the quality of infection prevention programs, leading to better outcomes for patients. Objective: To assess the impact of performance improvement measures on enhancing the quality of infection prevention programs in a tertiary care hospital. Methods: This quasi-experimental study was conducted with healthcare workers (HCWs), including doctors, nurses, infection prevention officers, and support staff, at a tertiary care hospital. The intervention included comprehensive performance improvement measures: rigorous training, educational initiatives, regular audits with feedback, adherence to standard operating procedures (SOPs), checklists, monitoring tools, and hand hygiene promotion. Quantitative data on infection rates, infection control compliance, hand hygiene adherence, and antibiotic usage were collected at baseline and 3, 6, and 12 months post-intervention. Qualitative data were gathered from semi-structured interviews and focus groups to explore barriers and facilitators to infection prevention. Results: The intervention group showed a significant reduction in HAIs per 1,000 patient days compared to the control group (3.06 ± 1.09 vs. 8.23 ± 5.18; p = 0.00). Compliance with infection control practices (71.0% vs. 61.0%; p = 0.13) and hand hygiene adherence (64.0% vs. 48.0%; p = 0.02) were also higher in the intervention group. However, no statistically significant difference in antibiotic usage was observed between the two groups (59.0% vs. 49.0%; p = 0.1). Conclusion: The study demonstrates that performance improvement measures significantly reduce HAIs and improve compliance with infection control protocols. These targeted strategies are essential for enhancing infection prevention in healthcare settings and improving overall patient safety.

Efficient load balancer for local internet service providers based on operation research

Load balancing in internet services acts as a reverse proxy to distribute network bandwidth or application traffic across multiple servers. To decrease the internet route cost and to make the network intermediate devices more intelligent distance, number of hops, bandwidth capacity, equipment maintenance, power consumption ...etc must be considered. .. The aim is for the devices to have self-decision: acting upon data found in the network and transport layer protocols (Internet Protocol IP, Transmission Control Protocol TCP, File Transfer Protocol FTP, User Datagram Protocol UDP), and delivering the services to the secondary internet (wireless or optical fibers) ISPs. To achieve this target, the use of an operation research algorithm, such as linear programming, has been proposed to solve the problem of minimizing transport and distribution costs by developing and overcoming the transmission load cost of the path selection. The proposed EWRRLB (Efficient Weighted Round Robin Load Balancer) will assign different costs to each internet connection based not only on its capacity or priority but also on the cost of transmission paths. This allows load balancers to allocate the best economic path and the share of the bandwidth to certain connections.

Nurses' Adherence to Infection Control Practices in Emergency Departments

Background: Follow-Up on Infection Prevention Measures It is an assortment of techniques intended to keep things free of microbes, Patient protection from diseases necessitates several actions. Preventing and controlling infections is one of the most crucial tasks for nurses. Using hand hygiene with personal protection equipment is a crucial step that can help prevent infections or their repercussions. The safety of patients and maintaining sterility and cleanliness in hospitals are the responsibilities of all nurses working there. Objectives: to evaluate the adherence of emergency department nurses to infection control protocols and recommendations. Methodology: This cross-sectional study selected a nonprobability (purposive) sample of 120 nurses working in emergency departments across three hospitals: Baghdad Teaching Hospital (50%), Al-Kindy Teaching Hospital (35.8%), and Sheik Zaydi Hospital 14.2%. The study was conducted from September 20, 2023, to 30 June 2024. collection tool, which consists of two parts: The first part is the demographic characteristics of the nursing staff (age, gender, level of education, years of experience in the emergency department, and participation in training courses related to infection control measures). Second part: Checklists were utilized for observation. The study instrument's reliability was assessed using the Statistical Package for Social Science Program (IBM SPSS) by applying Cronbach's Alpha. Results: The study finding shows that, based on the data, 66.7% of the respondents reported a fair level of practices about infection control measures. Sociodemographic factors such as qualifications notably impact nurses' practices regarding adherence to infection control practices. CONCLUSIONS: The researcher concluded that the nurses' practices were not at the level required (fair) to fit with the critical and special nature of the emergency department. Recommendations: Standard precautions are the basic level of the infection control process. The participants may possess satisfactory knowledge and compliance levels. However, more training programs and more focus on the standard precautions by educational institutes are needed for nurses to improve their knowledge and compliance with infection-control standard precautions.

Maternal stress during pregnancy alters circulating small extracellular vesicles and enhances their targeting to the placenta and fetus

BackgroundMaternal psychological distress during pregnancy can negatively impact fetal development, resulting in long-lasting consequences for the offspring. These effects show a sex bias. The mechanisms whereby prenatal stress induces functional and/or structural changes in the placental-fetal unit remain poorly understood. Maternal circulating small extracellular vesicles (sEVs) are good candidates to act as “stress signals” in mother-to-fetus communication. Using a repetitive restraint-based rat model of prenatal stress, we examined circulating maternal sEVs under stress conditions and tested whether they could target placental-fetal tissues.ResultsOur mild chronic maternal stress during pregnancy paradigm induced anhedonic-like behavior in pregnant dams and led to intrauterine growth restriction (IUGR), particularly in male fetuses and placentas. The concentration and cargo of maternal circulating sEVs changed under stress conditions. Specifically, there was a significant reduction in neuron-enriched proteins and a significant increase in astrocyte-enriched proteins in blood-borne sEVs from stressed dams. To study the effect of repetitive restraint stress on the biodistribution of maternal circulating sEVs in the fetoplacental unit, sEVs from pregnant dams exposed to stress or control protocol were labeled with DiR fluorescent die and injected into pregnant females previously exposed to control or stress protocol. Remarkably, maternal circulating sEVs target placental/fetal tissues and, under stress conditions, fetal tissues are more receptive to sEVs.ConclusionOur results suggest that maternal circulating sEVs can act as novel mediators/modulators of mother-to-fetus stress communication. Further studies are needed to identify placental/fetal cellular targets of maternal sEVs and characterize their contribution to stress-induced sex-specific placental and fetal changes.

Distributed Adaptive Formation Control for Fractional-Order Multi-Agent Systems with Actuator Failures and Switching Topologies

In this paper, a class of distributed adaptive formation control problems are investigated for second-order nonlinear fractional-order multi-agent systems with actuator failures and switching topologies. To address these challenges, two adaptive coupling gains based on agents’ position and velocity are incorporated into the control protocol. Using the Lyapunov method along with graph theory and matrix analysis, sufficient conditions for system stability are derived in the presence of actuator failures and switching topologies. The effectiveness of the proposed control protocol is demonstrated through numerical simulations, which show its capability to maintain stable formation control under these challenging conditions.

OQuPy: A Python package to efficiently simulate non-Markovian open quantum systems with process tensors.

Non-Markovian dynamics arising from the strong coupling of a system to a structured environment is essential in many applications of quantum mechanics and emerging technologies. Deriving an accurate description of general quantum dynamics including memory effects is, however, a demanding task, prohibitive to standard analytical or direct numerical approaches. We present a major release of our open source software package, OQuPy (Open Quantum System in Python), which provides several recently developed numerical methods that address this challenging task. It utilizes the process tensor approach to open quantum systems (OQS) in which a single map, the process tensor, captures all possible effects of an environment on the system. The representation of the process tensor in a tensor network form allows for an exact yet highly efficient description of non-Markovian OQS (NM-OQS). The OQuPy package provides methods to (1) compute the dynamics and multi-time correlations of quantum systems coupled to single and multiple environments, (2) optimize control protocols for NM-OQS, (3) simulate interacting chains of NM-OQS, and (4) compute the mean-field dynamics of an ensemble of NM-OQS coupled to a common central system. Our aim is to provide an easily accessible and extensible tool for researchers of OQS in fields such as quantum chemistry, quantum sensing, and quantum information.

Asymptotic Synchronization for Caputo Fractional-Order Time-Delayed Cellar Neural Networks with Multiple Fuzzy Operators and Partial Uncertainties via Mixed Impulsive Feedback Control

To construct Caputo fractional-order time-delayed cellar neural networks (FOTDCNNs) that characterize real environments, this article introduces partial uncertainties, fuzzy operators, and nonlinear activation functions into the network models. Specifically, both the fuzzy AND operator and the fuzzy OR operator are contemplated in the master–slave systems. In response to the properties of the considered cellar neural networks (NNs), this article designs a new class of mixed control protocols that utilize both the error feedback information of systems and the sampling information of impulse moments to achieve network synchronization tasks. This approach overcomes the interference of time delays and uncertainties on network stability. By integrating the fractional-order comparison principle, fractional-order stability theory, and hybrid control schemes, readily verifiable asymptotic synchronization conditions for the studied fuzzy cellar NNs are established, and the range of system parameters is determined. Unlike previous results, the impulse gain spectrum considered in this study is no longer confined to a local interval (−2,0) and can be extended to almost the entire real number domain. This spectrum extension relaxes the synchronization conditions, ensuring a broader applicability of the proposed control schemes.

Causal Relationship between Ischemic Stroke and Malignant Brain Tumors: A Two-Sample Mendelian Randomization Analysis

Object: Contemporary observational research has identified associations between cerebrovascular accidents, commonly referred to as strokes, and malignant cerebral neoplasms. However, these studies fall short of elucidating the presence of a direct causal relationship between the two conditions. In our investigation, we employ aggregated data derived from large-scale population-based genome-wide association studies (GWASs), to interrogate the potential causal linkages between these two pathologies. Method: This investigation leverages the two-sample Mendelian randomization (MR) methodology to elucidate the genetic underpinnings of the causal nexus between malignant cerebral neoplasms and ischemic cerebrovascular accidents. Rigorous quality control protocols were enacted to identify SNPs that exhibit a robust association with the exposure variable, namely malignant brain tumors. Analytical strategies, including MR-Egger regression, weighted median, inverse-variance weighted (IVW), simple mode, and weight mode methods, constituted the core of our MR analytical framework. Predominantly, the findings hinge upon the IVW method. To fortify the veracity of our conclusions, an array of sensitivity analyses such as MR-Egger regression, weighted median, MR pleiotropy, MR-PRESSO and radial MR, were deployed to meticulously evaluate heterogeneity and pleiotropy. Result: The findings derived from the IVW model reveal an absence of a significant causal nexus between malignant cerebral neoplasms and any categorization of cerebrovascular accidents, encompassing any strokes (AS) (OR 0.998, 95% CI 0.99-1.01, P=0.741), any ischemic strokes (AIS) (OR 0.999, 95% CI 0.99-1.01, P=0.999), large artery strokes (LAS) (OR 0.993, 95% CI 0.97-1.02, P=0.603), cardioembolic strokes (CES) (OR 1.012, 95% CI 0.99-1.03, P=0.275), and small vessel strokes (SVS) (OR 0.998, 95% CI 0.98-1.02, P=0.880) with respect to either an escalation or reduction in risk. Additionally, the analyses did not unveil any indications of heterogeneity or horizontal pleiotropy within the dataset. On a genome-wide scale, none of the variants associated with malignant brain tumors demonstrated relevance to the investigated outcomes. Conclusion: The outcomes of this MR investigation reveal the absence of a causal linkage between malignant cerebral neoplasms and ischemic cerebrovascular accidents. Nonetheless, the observed correlation between these two pathologies warrants attention, underscoring the necessity for heightened surveillance and care for individuals concurrently afflicted with both conditions.

Research on the comprehensive child life intervention program (CCLIP) for adjusting medical fear in children with central nervous system (CNS) cancers: a randomized controlled trial study protocol

BackgroundMedical fear is a common psychological reaction in hospitalized children, especially during radiotherapy for central nervous system (CNS) cancers. This fear not only causes negative emotions such as anxiety and depression but also affects children’s quality of life and treatment outcomes. It is exacerbated by factors such as unfamiliar environments during radiation therapy and separation from parents. Child Life, as a professional service, offers physical and mental support to children through medical understanding and psychological preparation, addressing their social and psychological needs, among other things. This study aims to construct a comprehensive Child Life intervention program (CCLIP), consisting of four key components: psychological adjustment and preparation, therapeutic play, pain management and coping strategies, and family support. The integration of effective intervention methods aims to reduce medical fear in children undergoing radiotherapy, promote psychological well-being, improve treatment compliance, and enhance quality of life.MethodsThis study is a protocol for a randomized controlled trial. Using a random number table method, we plan to recruit 38 eligible children who meet the inclusion criteria and then randomize them into two distinct groups: the intervention group and the control group. The intervention group will receive the CCLIP, and the control group will receive standardized care. Data will be collected through questionnaires and on-site assessments during the one-month intervention period at four distinct time points: the day of admission (T0), the first radiotherapy positioning (T1), mid-radiotherapy (T2), and postradiotherapy (T3). The primary outcome measure is the effectiveness of the CCLIP in reducing medical fear among children receiving radiation treatment for CNS cancers. Secondary outcomes include anxiety, depression, radiation adherence, quality of life among children, and parental satisfaction.DiscussionThis study aims to alleviate medical fear among children with CNS tumors undergoing radiotherapy through the implementation of the CCLIP while enhancing their mental health and quality of life. The expected outcomes of this research include providing effective intervention strategies for clinical practice, improving the treatment experience and long-term prognosis of children, and having positive impacts on children and their families.Trial registrationThis study is registered at the Chinese Clinical Trial Registry, ChiCTR2400082622. Registered 2 April, 2024.

Implementing a Phase II Quality Control Protocol for a High Precision 137Cs Dosimetry Calibration Irradiator.

In medical physics, rigorous quality assurance and quality control protocols are vital for precise dose delivery applications. In many health physics applications, the allowable uncertainty for various processes is often greater than that of medical physics due to looser safety ties. This results in less demand for quality control and uncertainty analyses, since these may not be needed. However, certain applications can benefit from a comprehensive quality control program, as it may yield important insights, such as air kerma monitoring in dosimetry calibrations for environmental and low-dose applications. By implementing a thorough quality control program tailored to specific contexts and needs, uncertainties associated with dose measurements can be quantified with greater accuracy and reliability. This proactive approach not only ensures the integrity of data collected but also enhances understanding of the measured doses. For these reasons, a comprehensive quality control initiative was implemented following documented failures in a 137Cs dosimetry calibration irradiator. This involved systematic charge collection using NIST-traceable ion chambers to observe long-term changes. A Phase I quality control protocol was previously implemented, which employed Shewhart control charts and Nelson's rules to analyze various datasets subgrouped under different conditions. This study addresses the development of a Phase II protocol, which focuses more on uncertainty quantification of systematic errors and irradiator changes, and air kerma precision for dosimetry calibrations. A designed experiment was performed to identify how much systematic errors influence the air kerma. Emphasis was placed on stricter quality assurance protocols, continuous data collection, and additional control charts to monitor short-term changes, such as exponentially weighted moving average control charts. A pre-irradiation control process was implemented to verify that the total air kerma met the measurement quality objective and to show how various uncertainties were applied before calibration. This study indicates how uncertainty is applied given observed air kerma measurements from the irradiator. Ongoing efforts aim to streamline the quality control procedure, ensure consistent data collection, and assess its impact on dosimetry applications.

Impact of increasing post-filter ionised calcium target on regional citrate anticoagulation efficacy in ICU continuous renal replacement therapy: the non-inferiority randomised controlled Ca-CIBLE protocol

IntroductionContinuous renal replacement therapy (CRRT) is a critical therapeutic intervention for patients with severe acute kidney injury in intensive care. However, premature filter clotting remains a significant challenge during CRRT,...

Comparison of three artificial intelligence methods for predicting 90% quantile interval of future insulin sensitivity of intensive care patients

Insulin dosing of hyperglycemic patients in the intensive care unit (ICU) is a complex and nonlinear clinical control problem. Recent model-based glycemic control protocols predict a patient-specific and time-specific future insulin sensitivity distribution, which defines the future patient state in response to insulin and nutrition inputs. The prediction methods provide a 90% confidence interval for a future insulin sensitivity distribution for a given time horizon, making the prediction problem more specific compared to common prediction problems where the aim is to predict the expected value of the given stochastic parameter. This study proposes three alternative artificial intelligence-based insulin sensitivity prediction methods to improve the prediction accuracy and make prediction parameters better fit the clinical requirements. The proposed prediction methods use different neural network models: a classification deep neural network model, a Mixture Density Network model, and a Quantile Regression-based model. A large patient data set was used to create the neural network models, including 2357 patients and 92646 blood glucose measurements from three clinical sites (Christchurch, New Zealand, Gyula, Hungary, and Liege, Belgium). Prediction accuracy was assessed by statistical metrics expressing clinical requirements, as well as via validated in-silico virtual patient simulations comparing the clinical performance of a proven glycaemic control protocol using the alternative prediction methods to assess impact on glycemic control performance and thus the need for these alternative models.